/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_cd_7030.py:548: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/xgboost/compat.py:36: FutureWarning: pandas.Int64Index is deprecated and will be removed from pandas in a future version. Use pandas.Index with the appropriate dtype instead.
  from pandas import MultiIndex, Int64Index
1.22.4
1.4.1

aaindex_df contains non-numerical data

Total no. of non-numerial columns: 2

Selecting numerical data only

PASS: successfully selected numerical columns only for aaindex_df

Now checking for NA in the remaining aaindex_cols

Counting aaindex_df cols with NA 
ncols with NA: 4 columns 
Dropping these... 
Original ncols: 127

Revised df ncols: 123

Checking NA in revised df...

PASS: cols with NA successfully dropped from aaindex_df 
Proceeding with combining aa_df with other features_df

PASS: ncols match 
Expected ncols: 123 
Got: 123

Total no. of columns in clean aa_df: 123

Proceeding to merge, expected nrows in merged_df: 531

PASS: my_features_df and aa_df successfully combined 
nrows: 531 
ncols: 286
count of NULL values before imputation

or_mychisq          263
log10_or_mychisq    263
dtype: int64
count of NULL values AFTER imputation

mutationinformation    0
or_rawI                0
logorI                 0
dtype: int64

PASS: OR values imputed, data ready for ML

Total no. of features for aaindex: 123

No. of numerical features: 167 
No. of categorical features: 7

PASS: x_features has no target variable

No. of columns for x_features: 174

------------------------------------------------------------- 
Successfully split data with stratification [COMPLETE data]: 70/30 
Original data size: (531, 174) 
Train data size: (355, 174) 
Test data size: (176, 174) 
y_train numbers: Counter({0: 324, 1: 31}) 
y_train ratio: 10.451612903225806 
 
y_test_numbers: Counter({0: 161, 1: 15}) 
y_test ratio: 10.733333333333333 
-------------------------------------------------------------

index: 0 
ind: 1

Mask count check: True

index: 1 
ind: 2

Mask count check: True
Original Data
 Counter({0: 324, 1: 31}) Data dim: (355, 174)

Simple Random OverSampling
 Counter({0: 324, 1: 324})
(648, 174)

Simple Random UnderSampling
 Counter({0: 31, 1: 31})
(62, 174)

Simple Combined Over and UnderSampling
 Counter({0: 324, 1: 324})
(648, 174)

SMOTE_NC OverSampling
 Counter({0: 324, 1: 324})
(648, 174)

#####################################################################
 
Running ML analysis [COMPLETE DATA]: 70/30 split 
Gene name: gid 
Drug name: streptomycin

Output directory: /home/tanu/git/Data/streptomycin/output/ml/tts_cd_7030/

Sanity checks: 
Total input features: 174 
 
Training data size: (355, 174) 
Test data size: (176, 174) 
 
Target feature numbers (training data): Counter({0: 324, 1: 31}) 
Target features ratio (training data: 10.451612903225806 
 
Target feature numbers (test data): Counter({0: 161, 1: 15}) 
Target features ratio (test data): 10.733333333333333 

#####################################################################


================================================================

Strucutral features (n): 35 
These are: 
Common stablity features: ['ligand_distance', 'ligand_affinity_change', 'duet_stability_change', 'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts', 'mcsm_na_affinity'] 
FoldX columns: ['electro_rr', 'electro_mm', 'electro_sm', 'electro_ss', 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss', 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss', 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss', 'vdwclashes_rr', 'vdwclashes_mm', 'vdwclashes_sm', 'vdwclashes_ss', 'volumetric_rr', 'volumetric_mm', 'volumetric_ss'] 
Other struc columns: ['rsa', 'kd_values', 'rd_values'] 
================================================================

AAindex features (n): 123 
These are:
 ['ALTS910101', 'AZAE970101', 'AZAE970102', 'BASU010101', 'BENS940101', 'BENS940102', 'BENS940103', 'BENS940104', 'BETM990101', 'BLAJ010101', 'BONM030101', 'BONM030102', 'BONM030103', 'BONM030104', 'BONM030105', 'BONM030106', 'BRYS930101', 'CROG050101', 'CSEM940101', 'DAYM780301', 'DAYM780302', 'DOSZ010101', 'DOSZ010102', 'DOSZ010103', 'DOSZ010104', 'FEND850101', 'FITW660101', 'GEOD900101', 'GIAG010101', 'GONG920101', 'GRAR740104', 'HENS920101', 'HENS920102', 'HENS920103', 'HENS920104', 'JOHM930101', 'JOND920103', 'JOND940101', 'KANM000101', 'KAPO950101', 'KESO980101', 'KESO980102', 'KOLA920101', 'KOLA930101', 'KOSJ950100_RSA_SST', 'KOSJ950100_SST', 'KOSJ950110_RSA', 'KOSJ950115', 'LEVJ860101', 'LINK010101', 'LIWA970101', 'LUTR910101', 'LUTR910102', 'LUTR910103', 'LUTR910104', 'LUTR910105', 'LUTR910106', 'LUTR910107', 'LUTR910108', 'LUTR910109', 'MCLA710101', 'MCLA720101', 'MEHP950102', 'MICC010101', 'MIRL960101', 'MIYS850102', 'MIYS850103', 'MIYS930101', 'MIYS960101', 'MIYS960102', 'MIYS960103', 'MIYS990106', 'MIYS990107', 'MIYT790101', 'MOHR870101', 'MOOG990101', 'MUET010101', 'MUET020101', 'MUET020102', 'NAOD960101', 'NGPC000101', 'NIEK910101', 'NIEK910102', 'OGAK980101', 'OVEJ920100_RSA', 'OVEJ920101', 'OVEJ920102', 'OVEJ920103', 'PRLA000101', 'PRLA000102', 'QUIB020101', 'QU_C930101', 'QU_C930102', 'QU_C930103', 'RIER950101', 'RISJ880101', 'RUSR970101', 'RUSR970102', 'RUSR970103', 'SIMK990101', 'SIMK990102', 'SIMK990103', 'SIMK990104', 'SIMK990105', 'SKOJ000101', 'SKOJ000102', 'SKOJ970101', 'TANS760101', 'TANS760102', 'THOP960101', 'TOBD000101', 'TOBD000102', 'TUDE900101', 'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101', 'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'] 
================================================================

Evolutionary features (n): 3 
These are:
 ['consurf_score', 'snap2_score', 'provean_score'] 
================================================================

Genomic features (n): 6 
These are:
 ['maf', 'logorI'] 
 ['lineage_proportion', 'dist_lineage_proportion', 'lineage_count_all', 'lineage_count_unique'] 
================================================================

Categorical features (n): 7 
These are:
 ['ss_class', 'aa_prop_change', 'electrostatics_change', 'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'] 
================================================================


Pass: No. of features match

#####################################################################


Model_name: Logistic Regression 
Model func: LogisticRegression(random_state=42) 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegression(random_state=42))])

key: fit_time 
value: [0.03755164 0.026999   0.04061699 0.0295012  0.04022312 0.03928113
 0.0334549  0.0525279  0.03243518 0.03834724]

mean value: 0.037093830108642575

key: score_time 
value: [0.01234508 0.0125401  0.01212549 0.01237297 0.01236677 0.01239395
 0.01380444 0.01241159 0.01224709 0.01249695]

mean value: 0.012510442733764648

key: test_mcc 
value: [ 0.56061191  0.         -0.05096472  0.          0.          0.
  0.          0.          0.          0.        ]

mean value: 0.05096471914376256

key: train_mcc 
value: [0.25606655 0.40680629 0.40680629 0.44634527 0.41498244 0.446399
 0.446399   0.446399   0.40685732 0.40685732]

mean value: 0.40839184696756237

key: test_accuracy 
value: [0.94444444 0.91666667 0.88888889 0.91666667 0.88888889 0.91428571
 0.91428571 0.91428571 0.91428571 0.91428571]

mean value: 0.9126984126984127

key: train_accuracy 
value: [0.9184953  0.92789969 0.92789969 0.93103448 0.93103448 0.93125
 0.93125    0.93125    0.928125   0.928125  ]

mean value: 0.9286363636363636

key: test_fscore 
value: [0.5 0.  0.  0.  0.  0.  0.  0.  0.  0. ]

mean value: 0.05

key: train_fscore 
value: [0.13333333 0.3030303  0.3030303  0.35294118 0.3125     0.35294118
 0.35294118 0.35294118 0.3030303  0.3030303 ]

mean value: 0.30697192513368987

key: test_precision 
value: [1. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.1

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.33333333 0.         0.         0.         0.         0.
 0.         0.         0.         0.        ]

mean value: 0.03333333333333333

key: train_recall 
value: [0.07142857 0.17857143 0.17857143 0.21428571 0.18518519 0.21428571
 0.21428571 0.21428571 0.17857143 0.17857143]

mean value: 0.1828042328042328

key: test_roc_auc 
value: [0.66666667 0.5        0.48484848 0.5        0.5        0.5
 0.5        0.5        0.5        0.5       ]

mean value: 0.5151515151515151

key: train_roc_auc 
value: [0.53571429 0.58928571 0.58928571 0.60714286 0.59259259 0.60714286
 0.60714286 0.60714286 0.58928571 0.58928571]

mean value: 0.5914021164021164

key: test_jcc 
value: [0.33333333 0.         0.         0.         0.         0.
 0.         0.         0.         0.        ]

mean value: 0.03333333333333333

key: train_jcc 
value: [0.07142857 0.17857143 0.17857143 0.21428571 0.18518519 0.21428571
 0.21428571 0.21428571 0.17857143 0.17857143]

mean value: 0.1828042328042328

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Logistic RegressionCV 
Model func: LogisticRegressionCV(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegressionCV(random_state=42))])

key: fit_time 
value: [1.2483542  0.80813122 1.00250125 0.71726108 0.8024838  0.74083185
 0.76972246 0.91689467 0.77263451 0.81453466]

mean value: 0.8593349695205689

key: score_time 
value: [0.01291823 0.01265597 0.01283002 0.01263189 0.0129478  0.01255131
 0.01294541 0.01267266 0.01263213 0.01274872]

mean value: 0.01275341510772705

key: test_mcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_mcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: test_accuracy 
value: [0.91666667 0.91666667 0.91666667 0.91666667 0.88888889 0.91428571
 0.91428571 0.91428571 0.91428571 0.91428571]

mean value: 0.9126984126984127

key: train_accuracy 
value: [0.91222571 0.91222571 0.91222571 0.91222571 0.9153605  0.9125
 0.9125     0.9125     0.9125     0.9125    ]

mean value: 0.9126763322884013

key: test_fscore 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_fscore 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: test_precision 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_precision 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: test_recall 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_recall 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: test_roc_auc 
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]

mean value: 0.5

key: train_roc_auc 
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]

mean value: 0.5

key: test_jcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_jcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Gaussian NB 
Model func: GaussianNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianNB())])

key: fit_time 
value: [0.0140295  0.01260805 0.00964928 0.00937366 0.00939345 0.00950217
 0.0093832  0.00966716 0.00943232 0.0093925 ]

mean value: 0.01024312973022461

key: score_time 
value: [0.01252508 0.00918508 0.00895333 0.00903797 0.00878906 0.00873327
 0.00877452 0.00886703 0.00889802 0.00885606]

mean value: 0.00926194190979004

key: test_mcc 
value: [ 0.2548236  -0.28520118  0.0838827   0.22667907 -0.1754116   0.00614341
  0.00614341  0.31506302 -0.12878055  0.28097574]

mean value: 0.058431762156129344

key: train_mcc 
value: [0.16087621 0.21642012 0.16454203 0.17937888 0.14648891 0.17424327
 0.19667722 0.16162825 0.19300623 0.15617644]

mean value: 0.17494375773875617

key: test_accuracy 
value: [0.5        0.44444444 0.5        0.44444444 0.27777778 0.37142857
 0.37142857 0.6        0.42857143 0.54285714]

mean value: 0.4480952380952381

key: train_accuracy 
value: [0.49216301 0.52351097 0.4984326  0.52351097 0.47648903 0.4125
 0.521875   0.49375    0.515625   0.484375  ]

mean value: 0.49422315830721003

key: test_fscore 
value: [0.25       0.         0.18181818 0.23076923 0.13333333 0.15384615
 0.15384615 0.3        0.09090909 0.27272727]

mean value: 0.17672494172494171

key: train_fscore 
value: [0.22115385 0.24752475 0.22330097 0.23232323 0.20853081 0.21666667
 0.23880597 0.22115385 0.2364532  0.21800948]

mean value: 0.22639227711265117

key: test_precision 
value: [0.14285714 0.         0.10526316 0.13043478 0.07692308 0.08695652
 0.08695652 0.17647059 0.05263158 0.15789474]

mean value: 0.1016388107786681

key: train_precision 
value: [0.12777778 0.14367816 0.12921348 0.13529412 0.11956522 0.12264151
 0.13872832 0.12777778 0.13714286 0.12568306]

mean value: 0.13075022850450574

key: test_recall 
value: [1.         0.         0.66666667 1.         0.5        0.66666667
 0.66666667 1.         0.33333333 1.        ]

mean value: 0.6833333333333333

key: train_recall 
value: [0.82142857 0.89285714 0.82142857 0.82142857 0.81481481 0.92857143
 0.85714286 0.82142857 0.85714286 0.82142857]

mean value: 0.8457671957671957

key: test_roc_auc 
value: [0.72727273 0.24242424 0.57575758 0.6969697  0.375      0.50520833
 0.50520833 0.78125    0.38541667 0.75      ]

mean value: 0.5544507575757576

key: train_roc_auc 
value: [0.64095484 0.69041483 0.64439126 0.65813697 0.63001015 0.64579256
 0.67343444 0.64187867 0.67000978 0.63674168]

mean value: 0.6531765179043105

key: test_jcc 
value: [0.14285714 0.         0.1        0.13043478 0.07142857 0.08333333
 0.08333333 0.17647059 0.04761905 0.15789474]

mean value: 0.09933715362575236

key: train_jcc 
value: [0.12432432 0.14124294 0.12568306 0.13142857 0.11640212 0.12149533
 0.13559322 0.12432432 0.13407821 0.12234043]

mean value: 0.12769125197059378

MCC on Blind test: 0.04

Accuracy on Blind test: 0.54

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.00990868 0.00959229 0.00968003 0.00970602 0.00970078 0.00976157
 0.00972414 0.00962377 0.00962043 0.00956631]

mean value: 0.009688401222229004

key: score_time 
value: [0.00932574 0.00883555 0.00883079 0.00881195 0.00878096 0.0087657
 0.00874615 0.0087471  0.00887346 0.00881743]

mean value: 0.008853483200073241

key: test_mcc 
value: [-0.07312724 -0.07312724 -0.10660036 -0.07312724  0.11359237 -0.0525105
 -0.0525105  -0.0525105  -0.0525105  -0.0525105 ]

mean value: -0.04749422343217833

key: train_mcc 
value: [0.10917168 0.10917168 0.11334602 0.14827374 0.11381875 0.15618552
 0.1484866  0.15618552 0.14124232 0.15618552]

mean value: 0.13520673464024124

key: test_accuracy 
value: [0.86111111 0.86111111 0.80555556 0.86111111 0.80555556 0.88571429
 0.88571429 0.88571429 0.88571429 0.88571429]

mean value: 0.8623015873015873

key: train_accuracy 
value: [0.87774295 0.87774295 0.89341693 0.88087774 0.88087774 0.884375
 0.88125    0.884375   0.878125   0.884375  ]

mean value: 0.8823158307210032

key: test_fscore 
value: [0.         0.         0.         0.         0.22222222 0.
 0.         0.         0.         0.        ]

mean value: 0.022222222222222223

key: train_fscore 
value: [0.17021277 0.17021277 0.15       0.20833333 0.17391304 0.21276596
 0.20833333 0.21276596 0.20408163 0.21276596]

mean value: 0.19233847470533078

key: test_precision 
value: [0.  0.  0.  0.  0.2 0.  0.  0.  0.  0. ]

mean value: 0.02

key: train_precision 
value: [0.21052632 0.21052632 0.25       0.25       0.21052632 0.26315789
 0.25       0.26315789 0.23809524 0.26315789]

mean value: 0.24091478696741853

key: test_recall 
value: [0.   0.   0.   0.   0.25 0.   0.   0.   0.   0.  ]

mean value: 0.025

key: train_recall 
value: [0.14285714 0.14285714 0.10714286 0.17857143 0.14814815 0.17857143
 0.17857143 0.17857143 0.17857143 0.17857143]

mean value: 0.16124338624338624

key: test_roc_auc 
value: [0.46969697 0.46969697 0.43939394 0.46969697 0.5625     0.484375
 0.484375   0.484375   0.484375   0.484375  ]

mean value: 0.48328598484848484

key: train_roc_auc 
value: [0.54565538 0.54565538 0.53810751 0.56351252 0.54838914 0.56531311
 0.56360078 0.56531311 0.56188845 0.56531311]

mean value: 0.5562748494555443

key: test_jcc 
value: [0.    0.    0.    0.    0.125 0.    0.    0.    0.    0.   ]

mean value: 0.0125

key: train_jcc 
value: [0.09302326 0.09302326 0.08108108 0.11627907 0.0952381  0.11904762
 0.11627907 0.11904762 0.11363636 0.11904762]

mean value: 0.10657030482611878

MCC on Blind test: -0.01

Accuracy on Blind test: 0.85

Model_name: K-Nearest Neighbors 
Model func: KNeighborsClassifier() 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', KNeighborsClassifier())])

key: fit_time 
value: [0.0104382  0.01041794 0.01008844 0.01009679 0.01005197 0.00997472
 0.01043582 0.00987959 0.00933695 0.01001191]

mean value: 0.010073232650756835

key: score_time 
value: [0.05429459 0.01221299 0.01444054 0.01175618 0.01205492 0.01186991
 0.0115397  0.01287484 0.01321888 0.01406431]

mean value: 0.016832685470581053

key: test_mcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_mcc 
value: [0.19933341 0.18039846 0.19933341 0.         0.2336408  0.11577237
 0.31768311 0.16424416 0.22850891 0.22850891]

mean value: 0.18674235320548654

key: test_accuracy 
value: [0.91666667 0.91666667 0.91666667 0.91666667 0.88888889 0.91428571
 0.91428571 0.91428571 0.91428571 0.91428571]

mean value: 0.9126984126984127

key: train_accuracy 
value: [0.9153605  0.90909091 0.9153605  0.91222571 0.9184953  0.9125
 0.921875   0.9125     0.915625   0.915625  ]

mean value: 0.9148657915360502

key: test_fscore 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_fscore 
value: [0.12903226 0.17142857 0.12903226 0.         0.1875     0.06666667
 0.24242424 0.125      0.18181818 0.18181818]

mean value: 0.14147203602848765

key: test_precision 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_precision 
value: [0.66666667 0.42857143 0.66666667 0.         0.6        0.5
 0.8        0.5        0.6        0.6       ]

mean value: 0.5361904761904762

key: test_recall 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_recall 
value: [0.07142857 0.10714286 0.07142857 0.         0.11111111 0.03571429
 0.14285714 0.07142857 0.10714286 0.10714286]

mean value: 0.08253968253968254

key: test_roc_auc 
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]

mean value: 0.5

key: train_roc_auc 
value: [0.53399607 0.54669858 0.53399607 0.5        0.5521309  0.51614481
 0.56971624 0.53228963 0.55014677 0.55014677]

mean value: 0.5385265846676665

key: test_jcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_jcc 
value: [0.06896552 0.09375    0.06896552 0.         0.10344828 0.03448276
 0.13793103 0.06666667 0.1        0.1       ]

mean value: 0.07742097701149425

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: SVM 
Model func: SVC(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SVC(random_state=42))])

key: fit_time 
value: [0.01436853 0.01234698 0.01245475 0.01326418 0.01248026 0.01332474
 0.01294017 0.0134604  0.01365185 0.01456428]

mean value: 0.013285613059997559

key: score_time 
value: [0.01061606 0.00970006 0.00964308 0.01066709 0.00990176 0.01007462
 0.00969577 0.0101335  0.00984168 0.00981879]

mean value: 0.010009241104125977

key: test_mcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_mcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: test_accuracy 
value: [0.91666667 0.91666667 0.91666667 0.91666667 0.88888889 0.91428571
 0.91428571 0.91428571 0.91428571 0.91428571]

mean value: 0.9126984126984127

key: train_accuracy 
value: [0.91222571 0.91222571 0.91222571 0.91222571 0.9153605  0.9125
 0.9125     0.9125     0.9125     0.9125    ]

mean value: 0.9126763322884013

key: test_fscore 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_fscore 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: test_precision 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_precision 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: test_recall 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_recall 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: test_roc_auc 
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]

mean value: 0.5

key: train_roc_auc 
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]

mean value: 0.5

key: test_jcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_jcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: MLP 
Model func: MLPClassifier(max_iter=500, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MLPClassifier(max_iter=500, random_state=42))])

key: fit_time 
value: [1.30631518 1.36791658 1.23426557 0.05097747 1.35838532 1.23258448
 1.33761525 1.30716729 1.21374464 1.34288454]

mean value: 1.1751856327056884

key: score_time 
value: [0.01644564 0.01241517 0.01632237 0.01273298 0.01693249 0.01698637
 0.01220322 0.01648498 0.01693439 0.01239657]

mean value: 0.014985418319702149

key: test_mcc 
value: [ 0.27272727 -0.05096472 -0.07312724  0.          0.          0.
 -0.07537784 -0.0525105   0.          0.80403025]

mean value: 0.08247772240826755

key: train_mcc 
value: [0.98029759 0.98029759 0.96032966 0.         0.9589719  0.94009427
 0.96034089 0.98030334 1.         0.96034089]

mean value: 0.8720976125915196

key: test_accuracy 
value: [0.88888889 0.88888889 0.86111111 0.91666667 0.88888889 0.91428571
 0.85714286 0.88571429 0.91428571 0.97142857]

mean value: 0.8987301587301587

key: train_accuracy 
value: [0.9968652  0.9968652  0.99373041 0.91222571 0.99373041 0.990625
 0.99375    0.996875   1.         0.99375   ]

mean value: 0.9868416927899686

key: test_fscore 
value: [0.33333333 0.         0.         0.         0.         0.
 0.         0.         0.         0.8       ]

mean value: 0.11333333333333334

key: train_fscore 
value: [0.98181818 0.98181818 0.96296296 0.         0.96153846 0.94339623
 0.96296296 0.98181818 1.         0.96296296]

mean value: 0.8739278122296991

key: test_precision 
value: [0.33333333 0.         0.         0.         0.         0.
 0.         0.         0.         1.        ]

mean value: 0.13333333333333333

key: train_precision 
value: [1. 1. 1. 0. 1. 1. 1. 1. 1. 1.]

mean value: 0.9

key: test_recall 
value: [0.33333333 0.         0.         0.         0.         0.
 0.         0.         0.         0.66666667]

mean value: 0.09999999999999999

key: train_recall 
value: [0.96428571 0.96428571 0.92857143 0.         0.92592593 0.89285714
 0.92857143 0.96428571 1.         0.92857143]

mean value: 0.8497354497354498

key: test_roc_auc 
value: [0.63636364 0.48484848 0.46969697 0.5        0.5        0.5
 0.46875    0.484375   0.5        0.83333333]

mean value: 0.5377367424242424

key: train_roc_auc 
value: [0.98214286 0.98214286 0.96428571 0.5        0.96296296 0.94642857
 0.96428571 0.98214286 1.         0.96428571]

mean value: 0.9248677248677248

key: test_jcc 
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
[0.2        0.         0.         0.         0.         0.
 0.         0.         0.         0.66666667]

mean value: 0.08666666666666667

key: train_jcc 
value: [0.96428571 0.96428571 0.92857143 0.         0.92592593 0.89285714
 0.92857143 0.96428571 1.         0.92857143]

mean value: 0.8497354497354498

MCC on Blind test: -0.02

Accuracy on Blind test: 0.91

Model_name: Decision Tree 
Model func: DecisionTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', DecisionTreeClassifier(random_state=42))])

key: fit_time 
value: [0.02365303 0.01858902 0.01577306 0.0176239  0.01741219 0.01743984
 0.01774788 0.01760769 0.01489401 0.01630449]

mean value: 0.01770451068878174

key: score_time 
value: [0.01175332 0.00955725 0.0093677  0.0086236  0.00865078 0.00874329
 0.00871134 0.00880194 0.00865102 0.00864077]

mean value: 0.009150099754333497

key: test_mcc 
value: [0.46014151 0.36563621 0.27272727 0.53300179 0.30012252 0.36432621
 0.36432621 0.75       0.21080523 0.36432621]

mean value: 0.3985413157328502

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.88888889 0.91666667 0.88888889 0.91666667 0.88888889 0.91428571
 0.91428571 0.94285714 0.85714286 0.91428571]

mean value: 0.9042857142857142

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.5        0.4        0.33333333 0.57142857 0.33333333 0.4
 0.4        0.75       0.28571429 0.4       ]

mean value: 0.43738095238095237

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.4        0.5        0.33333333 0.5        0.5        0.5
 0.5        0.6        0.25       0.5       ]

mean value: 0.4583333333333333

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 0.33333333 0.33333333 0.66666667 0.25       0.33333333
 0.33333333 1.         0.33333333 0.33333333]

mean value: 0.4583333333333333

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.78787879 0.65151515 0.63636364 0.8030303  0.609375   0.65104167
 0.65104167 0.96875    0.61979167 0.65104167]

mean value: 0.7029829545454545

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.33333333 0.25       0.2        0.4        0.2        0.25
 0.25       0.6        0.16666667 0.25      ]

mean value: 0.29

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.51

Accuracy on Blind test: 0.93

Model_name: Extra Trees 
Model func: ExtraTreesClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreesClassifier(random_state=42))])

key: fit_time 
value: [0.10164332 0.09875083 0.09840488 0.10061312 0.09945917 0.09909844
 0.09923625 0.10035706 0.10263276 0.10133386]

mean value: 0.10015296936035156

key: score_time 
value: [0.01728988 0.01772642 0.01734233 0.01747251 0.01756477 0.01787114
 0.01776409 0.01777029 0.0185194  0.01758218]

mean value: 0.017690300941467285

key: test_mcc 
value: [ 0.56061191  0.         -0.07312724  0.56061191 -0.08574929  0.
 -0.0525105   0.          0.          0.        ]

mean value: 0.09098367830277584

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.94444444 0.91666667 0.86111111 0.94444444 0.83333333 0.91428571
 0.88571429 0.91428571 0.91428571 0.91428571]

mean value: 0.9042857142857142

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.5 0.  0.  0.5 0.  0.  0.  0.  0.  0. ]

mean value: 0.1

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [1. 0. 0. 1. 0. 0. 0. 0. 0. 0.]

mean value: 0.2

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.33333333 0.         0.         0.33333333 0.         0.
 0.         0.         0.         0.        ]

mean value: 0.06666666666666667

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.66666667 0.5        0.46969697 0.66666667 0.46875    0.5
 0.484375   0.5        0.5        0.5       ]

mean value: 0.5256155303030303

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.33333333 0.         0.         0.33333333 0.         0.
 0.         0.         0.         0.        ]

mean value: 0.06666666666666667

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: -0.03

Accuracy on Blind test: 0.9

Model_name: Extra Tree 
Model func: ExtraTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreeClassifier(random_state=42))])

key: fit_time 
value: [0.00988412 0.00974178 0.01000428 0.00953054 0.0105927  0.00961971
 0.00963712 0.00954556 0.01012039 0.00980616]

mean value: 0.009848237037658691

key: score_time 
value: [0.00898552 0.00953913 0.00913286 0.00856423 0.00947309 0.00917625
 0.00870967 0.00864887 0.00938249 0.00947213]

mean value: 0.009108424186706543

key: test_mcc 
value: [ 0.10580974 -0.10660036 -0.12108987  0.21320072 -0.125      -0.07537784
 -0.10998534  0.1315342  -0.0525105  -0.07537784]

mean value: -0.021539708665422964

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.77777778 0.80555556 0.77777778 0.86111111 0.77777778 0.85714286
 0.8        0.8        0.88571429 0.85714286]

mean value: 0.8200000000000001

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.2        0.         0.         0.28571429 0.         0.
 0.         0.22222222 0.         0.        ]

mean value: 0.0707936507936508

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.14285714 0.         0.         0.25       0.         0.
 0.         0.16666667 0.         0.        ]

mean value: 0.05595238095238095

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.33333333 0.         0.         0.33333333 0.         0.
 0.         0.33333333 0.         0.        ]

mean value: 0.09999999999999999

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.57575758 0.43939394 0.42424242 0.62121212 0.4375     0.46875
 0.4375     0.58854167 0.484375   0.46875   ]

mean value: 0.4946022727272727

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.11111111 0.         0.         0.16666667 0.         0.
 0.         0.125      0.         0.        ]

mean value: 0.04027777777777777

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
0.09

Accuracy on Blind test: 0.84

Model_name: Random Forest 
Model func: RandomForestClassifier(n_estimators=1000, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(n_estimators=1000, random_state=42))])

key: fit_time 
value: [1.38952994 1.3787725  1.38418007 1.50178075 1.5723846  1.41722393
 1.41482353 1.43956017 1.37670922 1.40093136]

mean value: 1.4275896072387695

key: score_time 
value: [0.08936667 0.08898115 0.09113955 0.09574842 0.0888381  0.08929157
 0.08983588 0.08924747 0.08947372 0.08939743]

mean value: 0.09013199806213379

key: test_mcc 
value: [-0.05096472 -0.05096472 -0.05096472  0.36563621 -0.05976143  0.
  0.          0.         -0.0525105   0.        ]

mean value: 0.010047012101450762

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.88888889 0.88888889 0.88888889 0.91666667 0.86111111 0.91428571
 0.91428571 0.91428571 0.88571429 0.91428571]

mean value: 0.8987301587301587

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.  0.  0.  0.4 0.  0.  0.  0.  0.  0. ]

mean value: 0.04

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.  0.  0.  0.5 0.  0.  0.  0.  0.  0. ]

mean value: 0.05

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.         0.         0.         0.33333333 0.         0.
 0.         0.         0.         0.        ]

mean value: 0.03333333333333333

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.48484848 0.48484848 0.48484848 0.65151515 0.484375   0.5
 0.5        0.5        0.484375   0.5       ]

mean value: 0.5074810606060606

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.   0.   0.   0.25 0.   0.   0.   0.   0.   0.  ]

mean value: 0.025

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Random Forest2 
Model func: RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...05', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                                        n_estimators=1000, n_jobs=10,
                                        oob_score=True, random_state=42))])
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

key: fit_time 
value: [1.74896312 0.85947013 0.97088051 0.97154832 0.92093682 0.92401528
 0.98417616 0.92375994 0.88592052 0.92829251]

mean value: 1.0117963314056397

key: score_time 
value: [0.23573852 0.21438527 0.19686961 0.18839693 0.23910666 0.21290851
 0.24078918 0.1919167  0.17325377 0.25020623]

mean value: 0.2143571376800537

key: test_mcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_mcc 
value: [0.         0.         0.         0.         0.18441489 0.
 0.         0.         0.         0.        ]

mean value: 0.018441488990565406

key: test_accuracy 
value: [0.91666667 0.91666667 0.91666667 0.91666667 0.88888889 0.91428571
 0.91428571 0.91428571 0.91428571 0.91428571]

mean value: 0.9126984126984127

key: train_accuracy 
value: [0.91222571 0.91222571 0.91222571 0.91222571 0.9184953  0.9125
 0.9125     0.9125     0.9125     0.9125    ]

mean value: 0.9129898119122257

key: test_fscore 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_fscore 
value: [0.         0.         0.         0.         0.07142857 0.
 0.         0.         0.         0.        ]

mean value: 0.007142857142857143

key: test_precision 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_precision 
value: [0. 0. 0. 0. 1. 0. 0. 0. 0. 0.]

mean value: 0.1

key: test_recall 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_recall 
value: [0.         0.         0.         0.         0.03703704 0.
 0.         0.         0.         0.        ]

mean value: 0.0037037037037037034

key: test_roc_auc 
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]

mean value: 0.5

key: train_roc_auc 
value: [0.5        0.5        0.5        0.5        0.51851852 0.5
 0.5        0.5        0.5        0.5       ]

mean value: 0.5018518518518519

key: test_jcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_jcc 
value: [0.         0.         0.         0.         0.03703704 0.
 0.         0.         0.         0.        ]

mean value: 0.0037037037037037034

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.02200055 0.00942898 0.00953317 0.00945187 0.00941706 0.00946593
 0.01052046 0.00950837 0.01041436 0.01074338]

mean value: 0.011048412322998047

key: score_time 
value: [0.00855827 0.00857615 0.00885057 0.00862408 0.00868845 0.00861311
 0.00898027 0.0089674  0.00867701 0.00942135]

mean value: 0.008795666694641113

key: test_mcc 
value: [-0.07312724 -0.07312724 -0.10660036 -0.07312724  0.11359237 -0.0525105
 -0.0525105  -0.0525105  -0.0525105  -0.0525105 ]

mean value: -0.04749422343217833

key: train_mcc 
value: [0.10917168 0.10917168 0.11334602 0.14827374 0.11381875 0.15618552
 0.1484866  0.15618552 0.14124232 0.15618552]

mean value: 0.13520673464024124

key: test_accuracy 
value: [0.86111111 0.86111111 0.80555556 0.86111111 0.80555556 0.88571429
 0.88571429 0.88571429 0.88571429 0.88571429]

mean value: 0.8623015873015873

key: train_accuracy 
value: [0.87774295 0.87774295 0.89341693 0.88087774 0.88087774 0.884375
 0.88125    0.884375   0.878125   0.884375  ]

mean value: 0.8823158307210032

key: test_fscore 
value: [0.         0.         0.         0.         0.22222222 0.
 0.         0.         0.         0.        ]

mean value: 0.022222222222222223

key: train_fscore 
value: [0.17021277 0.17021277 0.15       0.20833333 0.17391304 0.21276596
 0.20833333 0.21276596 0.20408163 0.21276596]

mean value: 0.19233847470533078

key: test_precision 
value: [0.  0.  0.  0.  0.2 0.  0.  0.  0.  0. ]

mean value: 0.02

key: train_precision 
value: [0.21052632 0.21052632 0.25       0.25       0.21052632 0.26315789
 0.25       0.26315789 0.23809524 0.26315789]

mean value: 0.24091478696741853

key: test_recall 
value: [0.   0.   0.   0.   0.25 0.   0.   0.   0.   0.  ]

mean value: 0.025

key: train_recall 
value: [0.14285714 0.14285714 0.10714286 0.17857143 0.14814815 0.17857143
 0.17857143 0.17857143 0.17857143 0.17857143]

mean value: 0.16124338624338624

key: test_roc_auc 
value: [0.46969697 0.46969697 0.43939394 0.46969697 0.5625     0.484375
 0.484375   0.484375   0.484375   0.484375  ]

mean value: 0.48328598484848484

key: train_roc_auc 
value: [0.54565538 0.54565538 0.53810751 0.56351252 0.54838914 0.56531311
 0.56360078 0.56531311 0.56188845 0.56531311]

mean value: 0.5562748494555443

key: test_jcc 
value: [0.    0.    0.    0.    0.125 0.    0.    0.    0.    0.   ]

mean value: 0.0125

key: train_jcc 
value: [0.09302326 0.09302326 0.08108108 0.11627907 0.0952381  0.11904762
 0.11627907 0.11904762 0.11363636 0.11904762]

mean value: 0.10657030482611878

MCC on Blind test: -0.01

Accuracy on Blind test: 0.85

Model_name: XGBoost 
Model func: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...
                               interaction_constraints=None, learning_rate=None,
                               max_delta_step=None, max_depth=None,
                               min_child_weight=None, missing=nan,
                               monotone_constraints=None, n_estimators=100,
                               n_jobs=None, num_parallel_tree=None,
                               predictor=None, random_state=42, reg_alpha=None,
                               reg_lambda=None, scale_pos_weight=None,
                               subsample=None, tree_method=None,
                               use_label_encoder=False,
                               validate_parameters=None, verbosity=0))])

key: fit_time 
value: [0.10480952 0.06182337 0.06451559 0.06863141 0.06844139 0.12698579
 0.05574274 0.06155849 0.06975102 0.06270981]

mean value: 0.0744969129562378

key: score_time 
value: [0.01106715 0.01057053 0.01095796 0.01068807 0.01159787 0.01094866
 0.01058912 0.01088119 0.01040578 0.01042295]

mean value: 0.010812926292419433

key: test_mcc 
value: [ 0.53300179  0.21320072 -0.07312724  0.36563621  0.          0.56011203
  0.36432621  0.27083333  0.56011203  0.36432621]

mean value: 0.31584212935141587

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.91666667 0.86111111 0.86111111 0.91666667 0.88888889 0.94285714
 0.91428571 0.88571429 0.94285714 0.91428571]

mean value: 0.9044444444444444

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.57142857 0.28571429 0.         0.4        0.         0.5
 0.4        0.33333333 0.5        0.4       ]

mean value: 0.33904761904761904

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.5        0.25       0.         0.5        0.         1.
 0.5        0.33333333 1.         0.5       ]

mean value: 0.4583333333333333

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 0.33333333 0.         0.33333333 0.         0.33333333
 0.33333333 0.33333333 0.33333333 0.33333333]

mean value: 0.3

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.8030303  0.62121212 0.46969697 0.65151515 0.5        0.66666667
 0.65104167 0.63541667 0.66666667 0.65104167]

mean value: 0.6316287878787878

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.4        0.16666667 0.         0.25       0.         0.33333333
 0.25       0.2        0.33333333 0.25      ]

mean value: 0.21833333333333332

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.56

Accuracy on Blind test: 0.94

Model_name: LDA 
Model func: LinearDiscriminantAnalysis() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LinearDiscriminantAnalysis())])

key: fit_time 
value: [0.04993773 0.06716919 0.06001949 0.06319523 0.03165531 0.08965111
 0.08378315 0.0626862  0.06191278 0.03049541]

mean value: 0.060050559043884275

key: score_time 
value: [0.02788305 0.02212262 0.02117324 0.01203609 0.02563787 0.0229702
 0.02336621 0.01960206 0.02250409 0.01243901]

mean value: 0.02097344398498535

key: test_mcc 
value: [ 0.46014151 -0.10660036 -0.10660036  0.21320072 -0.125      -0.07537784
 -0.07537784 -0.09375    -0.07537784  0.45833333]

mean value: 0.04735913306116693

key: train_mcc 
value: [0.5690863  0.74149276 0.69275015 0.68448596 0.68485173 0.58785833
 0.73404621 0.62562534 0.68457014 0.61518887]

mean value: 0.6619955789592123

key: test_accuracy 
value: [0.88888889 0.80555556 0.80555556 0.86111111 0.77777778 0.85714286
 0.85714286 0.82857143 0.85714286 0.88571429]

mean value: 0.8424603174603175

key: train_accuracy 
value: [0.93416928 0.95924765 0.95297806 0.95297806 0.95611285 0.940625
 0.959375   0.94375    0.953125   0.94375   ]

mean value: 0.9496110893416928

key: test_fscore 
value: [0.5        0.         0.         0.28571429 0.         0.
 0.         0.         0.         0.5       ]

mean value: 0.1285714285714286

key: train_fscore 
value: [0.60377358 0.76363636 0.71698113 0.70588235 0.69565217 0.6122449
 0.75471698 0.65384615 0.70588235 0.64      ]

mean value: 0.6852615993350306

key: test_precision 
value: [0.4  0.   0.   0.25 0.   0.   0.   0.   0.   0.4 ]

mean value: 0.10500000000000001

key: train_precision 
value: [0.64       0.77777778 0.76       0.7826087  0.84210526 0.71428571
 0.8        0.70833333 0.7826087  0.72727273]

mean value: 0.7534992207131795

key: test_recall 
value: [0.66666667 0.         0.         0.33333333 0.         0.
 0.         0.         0.         0.66666667]

mean value: 0.16666666666666666

key: train_recall 
value: [0.57142857 0.75       0.67857143 0.64285714 0.59259259 0.53571429
 0.71428571 0.60714286 0.64285714 0.57142857]

mean value: 0.6306878306878307

key: test_roc_auc 
value: [0.78787879 0.43939394 0.43939394 0.62121212 0.4375     0.46875
 0.46875    0.453125   0.46875    0.78645833]

mean value: 0.5371212121212121

key: train_roc_auc 
value: [0.77025037 0.86469072 0.82897644 0.81283751 0.79115931 0.75758317
 0.84858121 0.79158513 0.81286693 0.77544031]

mean value: 0.8053971093372307

key: test_jcc 
value: [0.33333333 0.         0.         0.16666667 0.         0.
 0.         0.         0.         0.33333333]

mean value: 0.08333333333333333

key: train_jcc 
value: [0.43243243 0.61764706 0.55882353 0.54545455 0.53333333 0.44117647
 0.60606061 0.48571429 0.54545455 0.47058824]

mean value: 0.5236685042567395

MCC on Blind test: 0.25

Accuracy on Blind test: 0.91

Model_name: Multinomial 
Model func: MultinomialNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MultinomialNB())])

key: fit_time 
value: [0.02568531 0.01155591 0.01034474 0.01003766 0.01006246 0.00939274
 0.00970602 0.00958538 0.00970125 0.01064706]

mean value: 0.011671853065490723

key: score_time 
value: [0.00945854 0.0092268  0.00892377 0.00949597 0.00894594 0.00876403
 0.00918293 0.0088706  0.00931358 0.00965166]

mean value: 0.009183382987976075

key: test_mcc 
value: [ 0.         -0.05096472  0.         -0.05096472 -0.05976143  0.
 -0.07537784  0.         -0.0525105   0.        ]

mean value: -0.028957920804973607

key: train_mcc 
value: [0.26372174 0.20395116 0.2336496  0.2722537  0.26121307 0.28333087
 0.28815009 0.305787   0.24525918 0.20179681]

mean value: 0.25591132151550705

key: test_accuracy 
value: [0.91666667 0.88888889 0.91666667 0.88888889 0.86111111 0.91428571
 0.85714286 0.91428571 0.88571429 0.91428571]

mean value: 0.8957936507936508

key: train_accuracy 
value: [0.9184953  0.89968652 0.91222571 0.90909091 0.92163009 0.91875
 0.9125     0.915625   0.903125   0.9125    ]

mean value: 0.9123628526645768

key: test_fscore 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_fscore 
value: [0.1875     0.23809524 0.22222222 0.29268293 0.13793103 0.23529412
 0.3        0.30769231 0.27906977 0.17647059]

mean value: 0.23769582026460084

key: test_precision 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_precision 
value: [0.75       0.35714286 0.5        0.46153846 1.         0.66666667
 0.5        0.54545455 0.4        0.5       ]

mean value: 0.5680802530802531

key: test_recall 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_recall 
value: [0.10714286 0.17857143 0.14285714 0.21428571 0.07407407 0.14285714
 0.21428571 0.21428571 0.21428571 0.10714286]

mean value: 0.16097883597883597

key: test_roc_auc 
value: [0.5        0.48484848 0.5        0.48484848 0.484375   0.5
 0.46875    0.5        0.484375   0.5       ]

mean value: 0.490719696969697

key: train_roc_auc 
value: [0.55185322 0.5738218  0.56455572 0.59511537 0.53703704 0.56800391
 0.59686888 0.59858121 0.5917319  0.54843444]

mean value: 0.5726003486489293

key: test_jcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_jcc 
value: [0.10344828 0.13513514 0.125      0.17142857 0.07407407 0.13333333
 0.17647059 0.18181818 0.16216216 0.09677419]

mean value: 0.1359644515597208

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Passive Aggresive 
Model func: PassiveAggressiveClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 PassiveAggressiveClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.01335907 0.01528835 0.01868391 0.01679611 0.01476431 0.01677227
 0.01691008 0.01555681 0.01502848 0.01529408]

mean value: 0.015845346450805663

key: score_time 
value: [0.009094   0.01111984 0.01116633 0.01163173 0.01169109 0.01202536
 0.01198363 0.01208973 0.01166201 0.01181436]

mean value: 0.011427807807922363

key: test_mcc 
value: [-0.05096472 -0.12108987 -0.07312724 -0.05096472  0.36917519  0.
  0.16666667  0.         -0.125       0.56011203]

mean value: 0.06748073419141037

key: train_mcc 
value: [0.36328059 0.60849288 0.72731669 0.51704968 0.52538371 0.66629947
 0.44311063 0.363328   0.50191824 0.48293564]

mean value: 0.519911554466587

key: test_accuracy 
value: [0.88888889 0.77777778 0.86111111 0.88888889 0.86111111 0.91428571
 0.62857143 0.91428571 0.77142857 0.94285714]

mean value: 0.844920634920635

key: train_accuracy 
value: [0.92476489 0.93730408 0.95924765 0.93730408 0.9184953  0.953125
 0.759375   0.925      0.9        0.934375  ]

mean value: 0.9148990987460816

key: test_fscore 
value: [0.         0.         0.         0.         0.44444444 0.
 0.23529412 0.         0.         0.5       ]

mean value: 0.11797385620915032

key: train_fscore 
value: [0.25       0.64285714 0.74509804 0.44444444 0.56666667 0.66666667
 0.42105263 0.25       0.54285714 0.4       ]

mean value: 0.4929642734286698

key: test_precision 
value: [0.         0.         0.         0.         0.4        0.
 0.14285714 0.         0.         1.        ]

mean value: 0.15428571428571428

key: train_precision 
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
[1.         0.64285714 0.82608696 1.         0.51515152 0.88235294
 0.26666667 1.         0.45238095 1.        ]

mean value: 0.7585496174754487

key: test_recall 
value: [0.         0.         0.         0.         0.5        0.
 0.66666667 0.         0.         0.33333333]

mean value: 0.15

key: train_recall 
value: [0.14285714 0.64285714 0.67857143 0.28571429 0.62962963 0.53571429
 1.         0.14285714 0.67857143 0.25      ]

mean value: 0.49867724867724866

key: test_roc_auc 
value: [0.48484848 0.42424242 0.46969697 0.48484848 0.703125   0.5
 0.64583333 0.5        0.421875   0.66666667]

mean value: 0.5301136363636364

key: train_roc_auc 
value: [0.57142857 0.80424644 0.83241286 0.64285714 0.78741755 0.76443249
 0.86815068 0.57142857 0.79990215 0.625     ]

mean value: 0.7267276466047826

key: test_jcc 
value: [0.         0.         0.         0.         0.28571429 0.
 0.13333333 0.         0.         0.33333333]

mean value: 0.07523809523809523

key: train_jcc 
value: [0.14285714 0.47368421 0.59375    0.28571429 0.39534884 0.5
 0.26666667 0.14285714 0.37254902 0.25      ]

mean value: 0.34234273054386993

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Stochastic GDescent 
Model func: SGDClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SGDClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.01842523 0.01609874 0.01722813 0.01848412 0.01800394 0.01625514
 0.01627541 0.01873684 0.01689315 0.01598525]

mean value: 0.017238593101501463

key: score_time 
value: [0.01181364 0.0117054  0.01168561 0.01192164 0.01168036 0.01183629
 0.01207781 0.01193452 0.01175761 0.01219463]

mean value: 0.01186075210571289

key: test_mcc 
value: [ 0.46014151 -0.09090909 -0.09090909 -0.05096472  0.4375      0.56011203
  0.          0.36432621 -0.1392715   0.        ]

mean value: 0.14500253427595935

key: train_mcc 
value: [0.59707499 0.61690665 0.66555656 0.60844312 0.63584475 0.67095427
 0.363328   0.68688845 0.55329017 0.        ]

mean value: 0.5398286947994427

key: test_accuracy 
value: [0.88888889 0.83333333 0.83333333 0.88888889 0.88888889 0.94285714
 0.91428571 0.91428571 0.74285714 0.91428571]

mean value: 0.8761904761904762

key: train_accuracy 
value: [0.93103448 0.94670846 0.93103448 0.94670846 0.94357367 0.953125
 0.925      0.95       0.859375   0.9125    ]

mean value: 0.9299059561128526

key: test_fscore 
value: [0.5 0.  0.  0.  0.5 0.5 0.  0.4 0.  0. ]

mean value: 0.19

key: train_fscore 
value: [0.63333333 0.62222222 0.68571429 0.58536585 0.66666667 0.68085106
 0.25       0.71428571 0.54545455 0.        ]

mean value: 0.5383893685165091

key: test_precision 
value: [0.4 0.  0.  0.  0.5 1.  0.  0.5 0.  0. ]

mean value: 0.24

key: train_precision 
value: [0.59375    0.82352941 0.57142857 0.92307692 0.66666667 0.84210526
 1.         0.71428571 0.38028169 0.        ]

mean value: 0.651512424052132

key: test_recall 
value: [0.66666667 0.         0.         0.         0.5        0.33333333
 0.         0.33333333 0.         0.        ]

mean value: 0.18333333333333332

key: train_recall 
value: [0.67857143 0.5        0.85714286 0.42857143 0.66666667 0.57142857
 0.14285714 0.71428571 0.96428571 0.        ]

mean value: 0.5523809523809524

key: test_roc_auc 
value: [0.78787879 0.45454545 0.45454545 0.48484848 0.71875    0.66666667
 0.5        0.65104167 0.40625    0.5       ]

mean value: 0.5624526515151514

key: train_roc_auc 
value: [0.81694894 0.74484536 0.89764359 0.7125675  0.81792237 0.7805773
 0.57142857 0.84344423 0.90680039 0.5       ]

mean value: 0.7592178263764198

key: test_jcc 
value: [0.33333333 0.         0.         0.         0.33333333 0.33333333
 0.         0.25       0.         0.        ]

mean value: 0.125

key: train_jcc 
value: [0.46341463 0.4516129  0.52173913 0.4137931  0.5        0.51612903
 0.14285714 0.55555556 0.375      0.        ]

mean value: 0.39401015019259694

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: AdaBoost Classifier 
Model func: AdaBoostClassifier(random_state=42) 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', AdaBoostClassifier(random_state=42))])

key: fit_time 
value: [0.15090704 0.13530254 0.14462709 0.13582611 0.13793111 0.13586354
 0.13528109 0.1350677  0.13672662 0.1345737 ]

mean value: 0.13821065425872803

key: score_time 
value: [0.0150373  0.01489091 0.01639485 0.01495051 0.01504731 0.01484656
 0.01496124 0.01503706 0.01494622 0.01486111]

mean value: 0.015097308158874511

key: test_mcc 
value: [ 0.85280287 -0.07312724  0.27272727  0.21320072  0.         -0.07537784
  0.21080523 -0.07537784  0.56011203  0.36432621]

mean value: 0.22500914092895935

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.97222222 0.86111111 0.88888889 0.86111111 0.88888889 0.85714286
 0.85714286 0.85714286 0.94285714 0.91428571]

mean value: 0.890079365079365

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.85714286 0.         0.33333333 0.28571429 0.         0.
 0.28571429 0.         0.5        0.4       ]

mean value: 0.2661904761904762

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.75       0.         0.33333333 0.25       0.         0.
 0.25       0.         1.         0.5       ]

mean value: 0.30833333333333335

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1.         0.         0.33333333 0.33333333 0.         0.
 0.33333333 0.         0.33333333 0.33333333]

mean value: 0.26666666666666666

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.98484848 0.46969697 0.63636364 0.62121212 0.5        0.46875
 0.61979167 0.46875    0.66666667 0.65104167]

mean value: 0.6087121212121211

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.75       0.         0.2        0.16666667 0.         0.
 0.16666667 0.         0.33333333 0.25      ]

mean value: 0.18666666666666668

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.67

Accuracy on Blind test: 0.95

Model_name: Bagging Classifier 
Model func: BaggingClassifier(n_jobs=10, oob_score=True, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 BaggingClassifier(n_jobs=10, oob_score=True,
                                   random_state=42))])

key: fit_time 
value: [0.04788923 0.04903531 0.04620981 0.05060101 0.06126571 0.06680465
 0.04379535 0.04723024 0.04328895 0.06006193]

mean value: 0.051618218421936035

key: score_time 
value: [0.02305627 0.02209425 0.01775551 0.03194594 0.02059269 0.02842784
 0.02079153 0.020015   0.02225471 0.04226279]

mean value: 0.024919652938842775

key: test_mcc 
value: [0.63636364 0.         0.27272727 0.53300179 0.47809144 0.
 0.56011203 0.53159579 0.56011203 0.56011203]

mean value: 0.413211603649971

key: train_mcc 
value: [0.89885656 0.91952193 0.96032966 0.94238154 0.91670079 0.89866557
 0.87743634 0.94009427 0.98030334 0.94009427]

mean value: 0.9274384279664429

key: test_accuracy 
value: [0.94444444 0.91666667 0.88888889 0.91666667 0.91666667 0.91428571
 0.94285714 0.91428571 0.94285714 0.94285714]

mean value: 0.924047619047619

key: train_accuracy 
value: [0.98432602 0.98746082 0.99373041 0.99059561 0.98746082 0.984375
 0.98125    0.990625   0.996875   0.990625  ]

mean value: 0.9887323667711598

key: test_fscore 
value: [0.66666667 0.         0.33333333 0.57142857 0.4        0.
 0.5        0.57142857 0.5        0.5       ]

mean value: 0.4042857142857143

key: train_fscore 
value: [0.90566038 0.92307692 0.96296296 0.94736842 0.92       0.90196078
 0.88       0.94339623 0.98181818 0.94339623]

mean value: 0.9309640103413104

key: test_precision 
value: [0.66666667 0.         0.33333333 0.5        1.         0.
 1.         0.5        1.         1.        ]

mean value: 0.6

key: train_precision 
value: [0.96       1.         1.         0.93103448 1.         1.
 1.         1.         1.         1.        ]

mean value: 0.989103448275862

key: test_recall 
value: [0.66666667 0.         0.33333333 0.66666667 0.25       0.
 0.33333333 0.66666667 0.33333333 0.33333333]

mean value: 0.35833333333333334

key: train_recall 
value: [0.85714286 0.85714286 0.92857143 0.96428571 0.85185185 0.82142857
 0.78571429 0.89285714 0.96428571 0.89285714]

mean value: 0.8816137566137566

key: test_roc_auc 
value: [0.81818182 0.5        0.63636364 0.8030303  0.625      0.5
 0.66666667 0.80208333 0.66666667 0.66666667]

mean value: 0.6684659090909091

key: train_roc_auc 
value: [0.92685322 0.92857143 0.96428571 0.97870643 0.92592593 0.91071429
 0.89285714 0.94642857 0.98214286 0.94642857]

mean value: 0.9402914143893526

key: test_jcc 
value: [0.5        0.         0.2        0.4        0.25       0.
 0.33333333 0.4        0.33333333 0.33333333]

mean value: 0.275

key: train_jcc 
value: [0.82758621 0.85714286 0.92857143 0.9        0.85185185 0.82142857
 0.78571429 0.89285714 0.96428571 0.89285714]

mean value: 0.8722295201605547

MCC on Blind test: 0.39

Accuracy on Blind test: 0.93

Model_name: Gaussian Process 
Model func: GaussianProcessClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianProcessClassifier(random_state=42))])

key: fit_time 
value: [0.07998514 0.10286832 0.09148741 0.09209228 0.09144783 0.07357407
 0.05123305 0.07287621 0.07399321 0.05170155]

mean value: 0.07812590599060058

key: score_time 
value: [0.02458215 0.03045321 0.02859759 0.02494097 0.02559304 0.01381183
 0.02802134 0.02684259 0.01415873 0.02221084]

mean value: 0.02392122745513916

key: test_mcc 
value: [ 0.         -0.05096472  0.          0.56061191 -0.05976143  0.
 -0.0525105  -0.0525105  -0.0525105   0.        ]

mean value: 0.02923542515177548

key: train_mcc 
value: [0.74080884 0.78835256 0.71610436 0.71610436 0.78024417 0.74085908
 0.83380939 0.76491919 0.74085908 0.76491919]

mean value: 0.7586980221859329

key: test_accuracy 
value: [0.91666667 0.88888889 0.91666667 0.94444444 0.86111111 0.91428571
 0.88571429 0.88571429 0.88571429 0.91428571]

mean value: 0.9013492063492063

key: train_accuracy 
value: [0.96238245 0.96865204 0.95924765 0.95924765 0.96865204 0.9625
 0.975      0.965625   0.9625     0.965625  ]

mean value: 0.9649431818181818

key: test_fscore 
value: [0.  0.  0.  0.5 0.  0.  0.  0.  0.  0. ]

mean value: 0.05

key: train_fscore 
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
[0.72727273 0.7826087  0.69767442 0.69767442 0.77272727 0.72727273
 0.83333333 0.75555556 0.72727273 0.75555556]

mean value: 0.7476947431851375

key: test_precision 
value: [0. 0. 0. 1. 0. 0. 0. 0. 0. 0.]

mean value: 0.1

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.         0.         0.         0.33333333 0.         0.
 0.         0.         0.         0.        ]

mean value: 0.03333333333333333

key: train_recall 
value: [0.57142857 0.64285714 0.53571429 0.53571429 0.62962963 0.57142857
 0.71428571 0.60714286 0.57142857 0.60714286]

mean value: 0.5986772486772487

key: test_roc_auc 
value: [0.5        0.48484848 0.5        0.66666667 0.484375   0.5
 0.484375   0.484375   0.484375   0.5       ]

mean value: 0.5089015151515152

key: train_roc_auc 
value: [0.78571429 0.82142857 0.76785714 0.76785714 0.81481481 0.78571429
 0.85714286 0.80357143 0.78571429 0.80357143]

mean value: 0.7993386243386243

key: test_jcc 
value: [0.         0.         0.         0.33333333 0.         0.
 0.         0.         0.         0.        ]

mean value: 0.03333333333333333

key: train_jcc 
value: [0.57142857 0.64285714 0.53571429 0.53571429 0.62962963 0.57142857
 0.71428571 0.60714286 0.57142857 0.60714286]

mean value: 0.5986772486772487

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Gradient Boosting 
Model func: GradientBoostingClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GradientBoostingClassifier(random_state=42))])

key: fit_time 
value: [0.49142981 0.48406339 0.48891139 0.49601245 0.48469663 0.48818421
 0.48846364 0.48314905 0.482656   0.47982621]

mean value: 0.48673927783966064

key: score_time 
value: [0.01021194 0.00918818 0.00930715 0.00910735 0.00968766 0.00931311
 0.00946546 0.00930357 0.00939488 0.0091598 ]

mean value: 0.009413909912109376

key: test_mcc 
value: [ 0.63636364  0.21320072 -0.07312724  0.36563621  0.47809144  0.56011203
 -0.0525105   0.27083333  0.56011203  0.56011203]

mean value: 0.3518823697119751

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.94444444 0.86111111 0.86111111 0.91666667 0.91666667 0.94285714
 0.88571429 0.88571429 0.94285714 0.94285714]

mean value: 0.91

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.66666667 0.28571429 0.         0.4        0.4        0.5
 0.         0.33333333 0.5        0.5       ]

mean value: 0.3585714285714286

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.66666667 0.25       0.         0.5        1.         1.
 0.         0.33333333 1.         1.        ]

mean value: 0.575

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 0.33333333 0.         0.33333333 0.25       0.33333333
 0.         0.33333333 0.33333333 0.33333333]

mean value: 0.29166666666666663

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.81818182 0.62121212 0.46969697 0.65151515 0.625      0.66666667
 0.484375   0.63541667 0.66666667 0.66666667]

mean value: 0.6305397727272727

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.5        0.16666667 0.         0.25       0.25       0.33333333
 0.         0.2        0.33333333 0.33333333]

mean value: 0.23666666666666666

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.56

Accuracy on Blind test: 0.94

Model_name: QDA 
Model func: QuadraticDiscriminantAnalysis() 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', QuadraticDiscriminantAnalysis())])

key: fit_time 
value: [0.02146316 0.02219987 0.02286434 0.02274776 0.0222106  0.02298474
 0.02306271 0.02296424 0.02295995 0.02321172]

mean value: 0.02266690731048584

key: score_time 
value: [0.01231408 0.01265907 0.01238108 0.01508975 0.01465201 0.0185194
 0.01445389 0.0190568  0.0145421  0.01477671]

mean value: 0.014844489097595216

key: test_mcc 
value: [ 0.36563621 -0.05096472 -0.05096472 -0.05096472 -0.125      -0.0525105
 -0.0525105  -0.07537784 -0.0525105  -0.09375   ]

mean value: -0.023891729096531433

key: train_mcc 
value: [0.         0.18078147 0.18078147 0.18078147 0.37058195 0.18080776
 0.18080776 0.18080776 0.31415459 0.18080776]

mean value: 0.19503119990943413

key: test_accuracy 
value: [0.91666667 0.88888889 0.88888889 0.88888889 0.77777778 0.88571429
 0.88571429 0.85714286 0.88571429 0.82857143]

mean value: 0.8703968253968254

key: train_accuracy 
value: [0.91222571 0.9153605  0.9153605  0.9153605  0.92789969 0.915625
 0.915625   0.915625   0.921875   0.915625  ]

mean value: 0.9170581896551724

key: test_fscore 
value: [0.4 0.  0.  0.  0.  0.  0.  0.  0.  0. ]

mean value: 0.04

key: train_fscore 
value: [0.         0.06896552 0.06896552 0.06896552 0.25806452 0.06896552
 0.06896552 0.06896552 0.19354839 0.06896552]

mean value: 0.09343715239154615

key: test_precision 
value: [0.5 0.  0.  0.  0.  0.  0.  0.  0.  0. ]

mean value: 0.05

key: train_precision 
value: [0. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 0.9

key: test_recall 
value: [0.33333333 0.         0.         0.         0.         0.
 0.         0.         0.         0.        ]

mean value: 0.03333333333333333

key: train_recall 
value: [0.         0.03571429 0.03571429 0.03571429 0.14814815 0.03571429
 0.03571429 0.03571429 0.10714286 0.03571429]

mean value: 0.05052910052910053

key: test_roc_auc 
value: [0.65151515 0.48484848 0.48484848 0.48484848 0.4375     0.484375
 0.484375   0.46875    0.484375   0.453125  ]

mean value: 0.49185606060606063

key: train_roc_auc 
value: [0.5        0.51785714 0.51785714 0.51785714 0.57407407 0.51785714
 0.51785714 0.51785714 0.55357143 0.51785714]

mean value: 0.5252645502645503

key: test_jcc 
value: [0.25 0.   0.   0.   0.   0.   0.   0.   0.   0.  ]

mean value: 0.025

key: train_jcc 
value: [0.         0.03571429 0.03571429 0.03571429 0.14814815 0.03571429
 0.03571429 0.03571429 0.10714286 0.03571429]

mean value: 0.05052910052910053

MCC on Blind test: 0.16

Accuracy on Blind test: 0.88

Model_name: Ridge Classifier 
Model func: RidgeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifier(random_state=42))])

key: fit_time 
value: [0.02675796 0.03602767 0.03650331 0.03723526 0.03765059 0.04004049
 0.04653239 0.02796698 0.03070784 0.03603768]

mean value: 0.03554601669311523

key: score_time 
value: [0.02177095 0.02033877 0.02327943 0.0223701  0.02546453 0.02191901
 0.02489305 0.0262723  0.02320623 0.02212548]

mean value: 0.023163986206054688

key: test_mcc 
value: [ 0.56061191 -0.05096472 -0.05096472  0.         -0.05976143  0.
  0.          0.         -0.0525105   0.56011203]

mean value: 0.09065225722872969

key: train_mcc 
value: [0.40680629 0.48287998 0.48287998 0.44634527 0.37241322 0.446399
 0.48293564 0.51710663 0.446399   0.446399  ]

mean value: 0.4530564009171328

key: test_accuracy 
value: [0.94444444 0.88888889 0.88888889 0.91666667 0.86111111 0.91428571
 0.91428571 0.91428571 0.88571429 0.94285714]

mean value: 0.9071428571428571

key: train_accuracy 
value: [0.92789969 0.93416928 0.93416928 0.93103448 0.92789969 0.93125
 0.934375   0.9375     0.93125    0.93125   ]

mean value: 0.9320797413793104

key: test_fscore 
value: [0.5 0.  0.  0.  0.  0.  0.  0.  0.  0.5]

mean value: 0.1

key: train_fscore 
value: [0.3030303  0.4        0.4        0.35294118 0.3030303  0.35294118
 0.4        0.44444444 0.35294118 0.35294118]

mean value: 0.36622697563874035

key: test_precision 
value: [1. 0. 0. 0. 0. 0. 0. 0. 0. 1.]

mean value: 0.2

key: train_precision 
value: [1.         1.         1.         1.         0.83333333 1.
 1.         1.         1.         1.        ]

mean value: 0.9833333333333334

key: test_recall 
value: [0.33333333 0.         0.         0.         0.         0.
 0.         0.         0.         0.33333333]

mean value: 0.06666666666666667

key: train_recall 
value: [0.17857143 0.25       0.25       0.21428571 0.18518519 0.21428571
 0.25       0.28571429 0.21428571 0.21428571]

mean value: 0.22566137566137565

key: test_roc_auc 
value: [0.66666667 0.48484848 0.48484848 0.5        0.484375   0.5
 0.5        0.5        0.484375   0.66666667]

mean value: 0.5271780303030303

key: train_roc_auc 
value: [0.58928571 0.625      0.625      0.60714286 0.59088026 0.60714286
 0.625      0.64285714 0.60714286 0.60714286]

mean value: 0.6126594549539754

key: test_jcc 
value: [0.33333333 0.         0.         0.         0.         0.
 0.         0.         0.         0.33333333]

mean value: 0.06666666666666667

key: train_jcc 
value: [0.17857143 0.25       0.25       0.21428571 0.17857143 0.21428571
 0.25       0.28571429 0.21428571 0.21428571]

mean value: 0.225

MCC on Blind test: -0.02

Accuracy on Blind test: 0.91

Model_name: Ridge ClassifierCV 
Model func: RidgeClassifierCV(cv=10) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifierCV(cv=10))])

key: fit_time 
value: [0.14882421 0.16005588 0.24906087 0.25029731 0.25784326 0.14243555
 0.29462337 0.30070424 0.25544119 0.24099398]

mean value: 0.23002798557281495

key: score_time 
value: [0.02316236 0.01269031 0.0210669  0.02224159 0.02197862 0.01947641
 0.02573705 0.02364016 0.02089238 0.02655578]

mean value: 0.021744155883789064

key: test_mcc 
value: [ 0.          0.         -0.05096472  0.         -0.05976143  0.
  0.          0.         -0.0525105   0.        ]

mean value: -0.01632366527615326

key: train_mcc 
value: [0.         0.25606655 0.48287998 0.         0.37241322 0.18080776
 0.48293564 0.18080776 0.446399   0.18080776]

mean value: 0.2583117674938463

key: test_accuracy 
value: [0.91666667 0.91666667 0.88888889 0.91666667 0.86111111 0.91428571
 0.91428571 0.91428571 0.88571429 0.91428571]

mean value: 0.9042857142857142

key: train_accuracy 
value: [0.91222571 0.9184953  0.93416928 0.91222571 0.92789969 0.915625
 0.934375   0.915625   0.93125    0.915625  ]

mean value: 0.9217515673981191

key: test_fscore 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_fscore 
value: [0.         0.13333333 0.4        0.         0.3030303  0.06896552
 0.4        0.06896552 0.35294118 0.06896552]

mean value: 0.17962013645583624

key: test_precision 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_precision 
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:115: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:118: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
[0.         1.         1.         0.         0.83333333 1.
 1.         1.         1.         1.        ]

mean value: 0.7833333333333333

key: test_recall 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_recall 
value: [0.         0.07142857 0.25       0.         0.18518519 0.03571429
 0.25       0.03571429 0.21428571 0.03571429]

mean value: 0.1078042328042328

key: test_roc_auc 
value: [0.5        0.5        0.48484848 0.5        0.484375   0.5
 0.5        0.5        0.484375   0.5       ]

mean value: 0.4953598484848485

key: train_roc_auc 
value: [0.5        0.53571429 0.625      0.5        0.59088026 0.51785714
 0.625      0.51785714 0.60714286 0.51785714]

mean value: 0.5537308835254041

key: test_jcc 
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

mean value: 0.0

key: train_jcc 
value: [0.         0.07142857 0.25       0.         0.17857143 0.03571429
 0.25       0.03571429 0.21428571 0.03571429]

mean value: 0.10714285714285714

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Logistic Regression 
Model func: LogisticRegression(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegression(random_state=42))])

key: fit_time 
value: [0.03976107 0.03495932 0.03571439 0.03836775 0.0373528  0.03786445
 0.03798771 0.03862476 0.03809953 0.03784561]

mean value: 0.037657737731933594

key: score_time 
value: [0.01219344 0.01211953 0.0121448  0.02239227 0.01213288 0.01559138
 0.01475835 0.01496959 0.01470828 0.01489115]

mean value: 0.014590167999267578

key: test_mcc 
value: [0.84659091 0.78483448 0.87867338 0.81706198 0.81671746 0.78503788
 0.69326017 0.82126124 0.81409158 0.84748251]

mean value: 0.8105011587910188

key: train_mcc 
value: [0.85272655 0.86047557 0.8594701  0.86295632 0.85290108 0.86310986
 0.87725276 0.86662907 0.86374338 0.85999763]

mean value: 0.8619262320868653

key: test_accuracy 
value: [0.92307692 0.89230769 0.93846154 0.90769231 0.90769231 0.89230769
 0.84615385 0.90769231 0.90625    0.921875  ]

mean value: 0.9043509615384615

key: train_accuracy 
value: [0.92624357 0.9296741  0.9296741  0.93138937 0.92624357 0.93138937
 0.93825043 0.93310463 0.93150685 0.92979452]

mean value: 0.9307270495077422

key: test_fscore 
value: [0.92307692 0.88888889 0.93939394 0.90909091 0.91176471 0.89230769
 0.85294118 0.91428571 0.90909091 0.92537313]

mean value: 0.9066213992816275

key: train_fscore 
value: [0.92724196 0.93155259 0.93039049 0.93220339 0.92724196 0.93220339
 0.93939394 0.93401015 0.93288591 0.93086003]

mean value: 0.9317983816662225

key: test_precision 
value: [0.90909091 0.90322581 0.91176471 0.88235294 0.88571429 0.90625
 0.82857143 0.86486486 0.88235294 0.88571429]

mean value: 0.885990216864268

key: train_precision 
value: [0.91638796 0.90879479 0.92255892 0.92281879 0.91333333 0.91973244
 0.92079208 0.92       0.91447368 0.91694352]

mean value: 0.9175835522463105

key: test_recall 
value: [0.9375     0.875      0.96875    0.9375     0.93939394 0.87878788
 0.87878788 0.96969697 0.9375     0.96875   ]

mean value: 0.9291666666666667

key: train_recall 
value: [0.93835616 0.95547945 0.93835616 0.94178082 0.94158076 0.94501718
 0.95876289 0.94845361 0.95205479 0.94520548]

mean value: 0.9465047309702019

key: test_roc_auc 
value: [0.92329545 0.89204545 0.93892045 0.90814394 0.90719697 0.89251894
 0.84564394 0.90672348 0.90625    0.921875  ]

mean value: 0.9042613636363637

key: train_roc_auc 
value: [0.92622276 0.92962976 0.92965918 0.93137151 0.92626983 0.9314127
 0.93828555 0.93313091 0.93150685 0.92979452]

mean value: 0.9307283575766134

key: test_jcc 
value: [0.85714286 0.8        0.88571429 0.83333333 0.83783784 0.80555556
 0.74358974 0.84210526 0.83333333 0.86111111]

mean value: 0.8299723320775952

key: train_jcc 
value: [0.86435331 0.871875   0.86984127 0.87301587 0.86435331 0.87301587
 0.88571429 0.87619048 0.87421384 0.87066246]

mean value: 0.8723235699429267

MCC on Blind test: 0.06

Accuracy on Blind test: 0.86

Model_name: Logistic RegressionCV 
Model func: LogisticRegressionCV(random_state=42) 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegressionCV(random_state=42))])

key: fit_time 
value: [1.04040074 0.88154149 0.96728778 1.03054047 0.88114166 0.8726418
 0.85305929 1.02757621 0.88018322 1.00977778]

mean value: 0.9444150447845459

key: score_time 
value: [0.01467156 0.01519346 0.01523161 0.01524258 0.01261258 0.0123508
 0.01528525 0.0152247  0.01517582 0.01518965]

mean value: 0.01461780071258545

key: test_mcc 
value: [0.85663571 0.78483448 0.82191818 0.87867338 0.87689394 0.84644588
 0.78483448 0.87844611 0.81892302 0.81409158]

mean value: 0.8361696750519234

key: train_mcc 
value: [0.917667   0.92822335 0.95540832 0.96917699 0.91428639 0.91768956
 0.92110342 0.88705256 0.91098027 0.98973183]

mean value: 0.9311319698928137

key: test_accuracy 
value: [0.92307692 0.89230769 0.90769231 0.93846154 0.93846154 0.92307692
 0.89230769 0.93846154 0.90625    0.90625   ]

mean value: 0.9166346153846154

key: train_accuracy 
value: [0.95883362 0.96397942 0.97770154 0.98456261 0.95711835 0.95883362
 0.96054889 0.94339623 0.95547945 0.99486301]

mean value: 0.9655316736765431

key: test_fscore 
value: [0.92753623 0.88888889 0.91176471 0.93939394 0.93939394 0.92537313
 0.89552239 0.94117647 0.91176471 0.90909091]

mean value: 0.9189905313392736

key: train_fscore 
value: [0.95890411 0.96446701 0.97777778 0.98450947 0.95726496 0.95890411
 0.96054889 0.94397284 0.9556314  0.99487179]

mean value: 0.9656852340314617

key: test_precision 
value: [0.86486486 0.90322581 0.86111111 0.91176471 0.93939394 0.91176471
 0.88235294 0.91428571 0.86111111 0.88235294]

mean value: 0.8932227841336001

key: train_precision 
value: [0.95890411 0.95317726 0.97610922 0.98961938 0.95238095 0.9556314
 0.95890411 0.93288591 0.95238095 0.99317406]

mean value: 0.9623167340435886

key: test_recall 
value: [1.         0.875      0.96875    0.96875    0.93939394 0.93939394
 0.90909091 0.96969697 0.96875    0.9375    ]

mean value: 0.9476325757575758

key: train_recall 
value: [0.95890411 0.9760274  0.97945205 0.97945205 0.96219931 0.96219931
 0.96219931 0.95532646 0.95890411 0.99657534]

mean value: 0.969123946711858

key: test_roc_auc 
value: [0.92424242 0.89204545 0.90861742 0.93892045 0.93844697 0.92282197
 0.89204545 0.93797348 0.90625    0.90625   ]

mean value: 0.9167613636363636

key: train_roc_auc 
value: [0.9588335  0.96395872 0.97769854 0.98457139 0.95712705 0.95883938
 0.96055171 0.94341665 0.95547945 0.99486301]

mean value: 0.9655339405921951

key: test_jcc 
value: [0.86486486 0.8        0.83783784 0.88571429 0.88571429 0.86111111
 0.81081081 0.88888889 0.83783784 0.83333333]

mean value: 0.8506113256113256

key: train_jcc 
value: [0.92105263 0.93137255 0.95652174 0.96949153 0.91803279 0.92105263
 0.92409241 0.89389068 0.91503268 0.98979592]

mean value: 0.9340335546204903

MCC on Blind test: 0.2

Accuracy on Blind test: 0.88

Model_name: Gaussian NB 
Model func: GaussianNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianNB())])

key: fit_time 
value: [0.01451039 0.01144934 0.01047444 0.01016974 0.01017523 0.01026917
 0.01046586 0.01044965 0.01014733 0.01011968]

mean value: 0.01082308292388916

key: score_time 
value: [0.01222348 0.00992036 0.00917554 0.00889802 0.00883865 0.00891876
 0.00896478 0.00895166 0.0089066  0.00891304]

mean value: 0.009371089935302734

key: test_mcc 
value: [0.61558566 0.70516447 0.74121539 0.63932742 0.40120547 0.52189378
 0.43834893 0.67632096 0.51639778 0.61872513]

mean value: 0.5874184987591167

key: train_mcc 
value: [0.59320412 0.59090416 0.59915297 0.59800763 0.61438746 0.60192667
 0.62042007 0.59537581 0.59823233 0.59407286]

mean value: 0.6005684089957667

key: test_accuracy 
value: [0.8        0.84615385 0.86153846 0.8        0.69230769 0.75384615
 0.70769231 0.83076923 0.75       0.796875  ]

mean value: 0.7839182692307692

key: train_accuracy 
value: [0.78559177 0.78559177 0.7890223  0.7890223  0.79759863 0.7890223
 0.79759863 0.78730703 0.78767123 0.7859589 ]

mean value: 0.7894384853967433

key: test_fscore 
value: [0.81690141 0.85714286 0.87323944 0.82666667 0.73684211 0.78378378
 0.75324675 0.84931507 0.77777778 0.82191781]

mean value: 0.8096833665663747

key: train_fscore 
value: [0.81146305 0.81031866 0.81391831 0.81335357 0.81957187 0.81447964
 0.82228916 0.81155015 0.81325301 0.81146305]

mean value: 0.814166045386727

key: test_precision 
value: [0.74358974 0.78947368 0.79487179 0.72093023 0.65116279 0.70731707
 0.65909091 0.775      0.7        0.73170732]

mean value: 0.727314354526269

key: train_precision 
value: [0.72506739 0.72752044 0.72899729 0.73024523 0.73829201 0.72580645
 0.73190349 0.72752044 0.72580645 0.72506739]

mean value: 0.7286226563904403

key: test_recall 
value: [0.90625    0.9375     0.96875    0.96875    0.84848485 0.87878788
 0.87878788 0.93939394 0.875      0.9375    ]

mean value: 0.9139204545454546

key: train_recall 
value: [0.92123288 0.91438356 0.92123288 0.91780822 0.9209622  0.92783505
 0.93814433 0.91752577 0.92465753 0.92123288]

mean value: 0.922501529915737

key: test_roc_auc 
value: [0.80160985 0.84753788 0.86316288 0.80255682 0.68986742 0.75189394
 0.70501894 0.82907197 0.75       0.796875  ]

mean value: 0.7837594696969697

key: train_roc_auc 
value: [0.78535871 0.78537047 0.78879513 0.78880102 0.79780987 0.78925999
 0.79783929 0.78753001 0.78767123 0.7859589 ]

mean value: 0.7894394624111472

key: test_jcc 
value: [0.69047619 0.75       0.775      0.70454545 0.58333333 0.64444444
 0.60416667 0.73809524 0.63636364 0.69767442]

mean value: 0.6824099382529615

key: train_jcc 
value: [0.68274112 0.68112245 0.68622449 0.68542199 0.69430052 0.6870229
 0.69820972 0.68286445 0.68527919 0.68274112]

mean value: 0.6865927942676245

MCC on Blind test: -0.04

Accuracy on Blind test: 0.63

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.01066947 0.01049948 0.01047111 0.01053286 0.01064682 0.01042938
 0.01068592 0.01050687 0.0104537  0.01051974]

mean value: 0.010541534423828125

key: score_time 
value: [0.00903535 0.00891495 0.00894284 0.00895119 0.00890207 0.00890875
 0.00898957 0.00916338 0.00888157 0.00895381]

mean value: 0.008964347839355468

key: test_mcc 
value: [0.60304138 0.69383917 0.69383917 0.58027158 0.60191459 0.64071161
 0.67632096 0.7935502  0.77459667 0.5336001 ]

mean value: 0.6591685435526063

key: train_mcc 
value: [0.65898657 0.68990309 0.6839259  0.68014131 0.68094306 0.6947996
 0.69240101 0.67852347 0.66969093 0.68389804]

mean value: 0.6813212997236593

key: test_accuracy 
value: [0.8        0.84615385 0.84615385 0.78461538 0.8        0.81538462
 0.83076923 0.89230769 0.875      0.765625  ]

mean value: 0.8256009615384615

key: train_accuracy 
value: [0.82504288 0.84048027 0.83876501 0.83704974 0.83704974 0.84391081
 0.84219554 0.83533448 0.83047945 0.8390411 ]

mean value: 0.8369349021358585

key: test_fscore 
value: [0.80597015 0.84848485 0.84848485 0.8        0.8115942  0.83333333
 0.84931507 0.90140845 0.88888889 0.7761194 ]

mean value: 0.8363599193526652

key: train_fscore 
value: [0.83860759 0.8526149  0.84935897 0.84751204 0.84751204 0.85393258
 0.85303514 0.84664537 0.84310618 0.8488746 ]

mean value: 0.848119941751926

key: test_precision 
value: [0.77142857 0.82352941 0.82352941 0.73684211 0.77777778 0.76923077
 0.775      0.84210526 0.8        0.74285714]

mean value: 0.7862300453244726

key: train_precision 
value: [0.77941176 0.79351032 0.79819277 0.79758308 0.79518072 0.80120482
 0.79701493 0.79104478 0.78466077 0.8       ]

mean value: 0.7937803952467857

key: test_recall 
value: [0.84375    0.875      0.875      0.875      0.84848485 0.90909091
 0.93939394 0.96969697 1.         0.8125    ]

mean value: 0.8947916666666667

key: train_recall 
value: [0.90753425 0.92123288 0.90753425 0.90410959 0.90721649 0.91408935
 0.91752577 0.91065292 0.9109589  0.90410959]

mean value: 0.9104963988137269

key: test_roc_auc 
value: [0.80066288 0.84659091 0.84659091 0.78598485 0.79924242 0.81392045
 0.82907197 0.89109848 0.875      0.765625  ]

mean value: 0.8253787878787879

key: train_roc_auc 
value: [0.82490114 0.84034152 0.83864685 0.83693452 0.83716989 0.84403097
 0.84232453 0.83546345 0.83047945 0.8390411 ]

mean value: 0.8369333427481994

key: test_jcc 
value: [0.675      0.73684211 0.73684211 0.66666667 0.68292683 0.71428571
 0.73809524 0.82051282 0.8        0.63414634]

mean value: 0.7205317820818463

key: train_jcc 
value: [0.72207084 0.74309392 0.73816156 0.73537604 0.73537604 0.74509804
 0.74373259 0.73407202 0.72876712 0.73743017]

mean value: 0.7363178359154687

MCC on Blind test: -0.1

Accuracy on Blind test: 0.73

Model_name: K-Nearest Neighbors 
Model func: KNeighborsClassifier() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', KNeighborsClassifier())])

key: fit_time 
value: [0.00958514 0.01027513 0.01074672 0.00962615 0.0096271  0.01068401
 0.01093793 0.01086497 0.01082492 0.01069522]

mean value: 0.01038672924041748

key: score_time 
value: [0.01245475 0.01305532 0.01275873 0.01180077 0.0121932  0.019068
 0.02031755 0.01409078 0.01431108 0.01284432]

mean value: 0.014289450645446778

key: test_mcc 
value: [0.68030134 0.70516447 0.76001241 0.68030134 0.51733125 0.739574
 0.75911691 0.82126124 0.80064077 0.73658951]

mean value: 0.7200293236120976

key: train_mcc 
value: [0.80170647 0.80812142 0.80942946 0.81408371 0.82107292 0.8034213
 0.82338373 0.79343943 0.80899632 0.80979039]

mean value: 0.8093445152365274

key: test_accuracy 
value: [0.81538462 0.84615385 0.87692308 0.81538462 0.73846154 0.86153846
 0.87692308 0.90769231 0.890625   0.859375  ]

mean value: 0.8488461538461538

key: train_accuracy 
value: [0.89708405 0.89879931 0.90051458 0.90394511 0.90737564 0.89708405
 0.90737564 0.89193825 0.90068493 0.90068493]

mean value: 0.9005486501092601

key: test_fscore 
value: [0.84210526 0.85714286 0.88235294 0.84210526 0.78481013 0.87671233
 0.88571429 0.91428571 0.90140845 0.87323944]

mean value: 0.8659876667308463

key: train_fscore 
value: [0.90384615 0.90649762 0.90734824 0.90967742 0.91262136 0.90415335
 0.91346154 0.89952153 0.90705128 0.90734824]

mean value: 0.9071526747114103

key: test_precision 
value: [0.72727273 0.78947368 0.83333333 0.72727273 0.67391304 0.8
 0.83783784 0.86486486 0.82051282 0.79487179]

mean value: 0.7869352833654893

key: train_precision 
value: [0.84939759 0.84365782 0.8502994  0.8597561  0.86238532 0.84477612
 0.85585586 0.83928571 0.85240964 0.8502994 ]

mean value: 0.8508122956626465

key: test_recall 
value: [1.         0.9375     0.9375     1.         0.93939394 0.96969697
 0.93939394 0.96969697 1.         0.96875   ]

mean value: 0.9661931818181818

key: train_recall 
value: [0.96575342 0.97945205 0.97260274 0.96575342 0.96907216 0.97250859
 0.97938144 0.96907216 0.96917808 0.97260274]

mean value: 0.9715376830014593

key: test_roc_auc 
value: [0.81818182 0.84753788 0.87784091 0.81818182 0.73532197 0.85984848
 0.87594697 0.90672348 0.890625   0.859375  ]

mean value: 0.8489583333333334

key: train_roc_auc 
value: [0.89696606 0.89866074 0.90039072 0.90383891 0.90748129 0.8972132
 0.90749894 0.89207033 0.90068493 0.90068493]

mean value: 0.9005490043779127

key: test_jcc 
value: [0.72727273 0.75       0.78947368 0.72727273 0.64583333 0.7804878
 0.79487179 0.84210526 0.82051282 0.775     ]

mean value: 0.7652830155509873

key: train_jcc 
value: [0.8245614  0.82898551 0.83040936 0.83431953 0.83928571 0.82507289
 0.84070796 0.8173913  0.82991202 0.83040936]

mean value: 0.8301055043825757

MCC on Blind test: 0.02

Accuracy on Blind test: 0.78

Model_name: SVM 
Model func: SVC(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SVC(random_state=42))])

key: fit_time 
value: [0.02402163 0.02193475 0.02200413 0.02173948 0.02181482 0.02210379
 0.02161193 0.02363348 0.02205205 0.02284265]

mean value: 0.022375869750976562

key: score_time 
value: [0.01336741 0.01201701 0.01211882 0.0124197  0.01214194 0.01216006
 0.01192069 0.01305389 0.01201272 0.01319122]

mean value: 0.012440347671508789

key: test_mcc 
value: [0.91168461 0.81534091 0.90805728 0.84659091 0.81534091 0.90814394
 0.75911691 0.87689394 0.91025899 0.84748251]

mean value: 0.8598910904951684

key: train_mcc 
value: [0.89710607 0.8971658  0.90742179 0.90064387 0.90738126 0.89727746
 0.90738017 0.88692593 0.90419443 0.9041308 ]

mean value: 0.90096275667166

key: test_accuracy 
value: [0.95384615 0.90769231 0.95384615 0.92307692 0.90769231 0.95384615
 0.87692308 0.93846154 0.953125   0.921875  ]

mean value: 0.9290384615384616

key: train_accuracy 
value: [0.94854202 0.94854202 0.95368782 0.95025729 0.95368782 0.94854202
 0.95368782 0.94339623 0.95205479 0.95205479]

mean value: 0.9504452642214338

key: test_fscore 
value: [0.95522388 0.90625    0.95238095 0.92307692 0.90909091 0.95384615
 0.88571429 0.93939394 0.95522388 0.92537313]

mean value: 0.9305574059025552

key: train_fscore 
value: [0.94845361 0.94897959 0.95400341 0.95076401 0.95368782 0.94897959
 0.9535284  0.94378194 0.95238095 0.95189003]

mean value: 0.9506449355614549

key: test_precision 
value: [0.91428571 0.90625    0.96774194 0.90909091 0.90909091 0.96875
 0.83783784 0.93939394 0.91428571 0.88571429]

mean value: 0.915244124518318

key: train_precision 
value: [0.95172414 0.94256757 0.94915254 0.94276094 0.95205479 0.93939394
 0.95517241 0.93581081 0.94594595 0.95517241]

mean value: 0.9469755508889878

key: test_recall 
value: [1.         0.90625    0.9375     0.9375     0.90909091 0.93939394
 0.93939394 0.93939394 1.         0.96875   ]

mean value: 0.9477272727272728

key: train_recall 
value: [0.94520548 0.95547945 0.95890411 0.95890411 0.95532646 0.95876289
 0.95189003 0.95189003 0.95890411 0.94863014]

mean value: 0.9543896813067834

key: test_roc_auc 
value: [0.95454545 0.90767045 0.95359848 0.92329545 0.90767045 0.95407197
 0.87594697 0.93844697 0.953125   0.921875  ]

mean value: 0.9290246212121211

key: train_roc_auc 
value: [0.94854776 0.9485301  0.95367886 0.95024243 0.95369063 0.94855953
 0.95368474 0.94341077 0.95205479 0.95205479]

mean value: 0.9504454408511038

key: test_jcc 
value: [0.91428571 0.82857143 0.90909091 0.85714286 0.83333333 0.91176471
 0.79487179 0.88571429 0.91428571 0.86111111]

mean value: 0.8710171854289501

key: train_jcc 
value: [0.90196078 0.90291262 0.91205212 0.90614887 0.91147541 0.90291262
 0.91118421 0.89354839 0.90909091 0.90819672]

mean value: 0.9059482649471472

MCC on Blind test: 0.01

Accuracy on Blind test: 0.86

Model_name: MLP 
Model func: MLPClassifier(max_iter=500, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MLPClassifier(max_iter=500, random_state=42))])

key: fit_time 
value: [2.08628631 2.09718418 2.11621594 2.1061759  2.162117   2.10625768
 2.08781576 2.14017463 1.73322892 2.10017252]

mean value: 2.0735628843307494

key: score_time 
value: [0.01667047 0.0165205  0.0234046  0.01531911 0.01239681 0.01560879
 0.01541567 0.01365423 0.01246762 0.01549482]

mean value: 0.01569526195526123

key: test_mcc 
value: [0.94028478 0.81671746 0.90814394 0.90814394 0.84659091 0.94028478
 0.84644588 0.87844611 0.91025899 0.90669283]

mean value: 0.890200962485231

key: train_mcc 
value: [0.99316237 1.         1.         1.         0.9965753  1.
 1.         1.         1.         1.        ]

mean value: 0.9989737675344628

key: test_accuracy 
value: [0.96923077 0.90769231 0.95384615 0.95384615 0.92307692 0.96923077
 0.92307692 0.93846154 0.953125   0.953125  ]

mean value: 0.9444711538461539

key: train_accuracy 
value: [0.99656947 1.         1.         1.         0.99828473 1.
 1.         1.         1.         1.        ]

mean value: 0.9994854202401372

key: test_fscore 
value: [0.96969697 0.90322581 0.95384615 0.95384615 0.92307692 0.96875
 0.92537313 0.94117647 0.95522388 0.95384615]

mean value: 0.9448061646277576

key: train_fscore 
value: [0.99656357 1.         1.         1.         0.99827883 1.
 1.         1.         1.         1.        ]

mean value: 0.9994842403487292

key: test_precision 
value: [0.94117647 0.93333333 0.93939394 0.93939394 0.9375     1.
 0.91176471 0.91428571 0.91428571 0.93939394]

mean value: 0.9370527756557169

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1.         0.875      0.96875    0.96875    0.90909091 0.93939394
 0.93939394 0.96969697 1.         0.96875   ]

mean value: 0.9538825757575757

key: train_recall 
value: [0.99315068 1.         1.         1.         0.99656357 1.
 1.         1.         1.         1.        ]

mean value: 0.9989714258814668

key: test_roc_auc 
value: [0.96969697 0.90719697 0.95407197 0.95407197 0.92329545 0.96969697
 0.92282197 0.93797348 0.953125   0.953125  ]

mean value: 0.9445075757575758

key: train_roc_auc 
value: [0.99657534 1.         1.         1.         0.99828179 1.
 1.         1.         1.         1.        ]

mean value: 0.9994857129407334

key: test_jcc 
value: [0.94117647 0.82352941 0.91176471 0.91176471 0.85714286 0.93939394
 0.86111111 0.88888889 0.91428571 0.91176471]

mean value: 0.896082251082251

key: train_jcc 
value: [0.99315068 1.         1.         1.         0.99656357 1.
 1.         1.         1.         1.        ]

mean value: 0.9989714258814668

MCC on Blind test: -0.06

Accuracy on Blind test: 0.88

Model_name: Decision Tree 
Model func: DecisionTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', DecisionTreeClassifier(random_state=42))])

key: fit_time 
value: [0.06062889 0.04593301 0.04395676 0.04463029 0.04500794 0.05236769
 0.03939652 0.04354382 0.05165625 0.05122232]

mean value: 0.047834348678588864

key: score_time 
value: [0.00945187 0.00990057 0.00917029 0.00910878 0.00983834 0.00910401
 0.00904489 0.0093677  0.00912046 0.0090487 ]

mean value: 0.009315562248229981

key: test_mcc 
value: [0.87689394 0.76001241 0.90814394 0.76001241 0.87689394 0.87844611
 0.75911691 0.90805728 0.8125     0.90669283]

mean value: 0.8446769764178679

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.93846154 0.87692308 0.95384615 0.87692308 0.93846154 0.93846154
 0.87692308 0.95384615 0.90625    0.953125  ]

mean value: 0.9213221153846154

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.9375     0.88235294 0.95384615 0.88235294 0.93939394 0.94117647
 0.88571429 0.95522388 0.90625    0.95238095]

mean value: 0.9236191564873523

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.9375     0.83333333 0.93939394 0.83333333 0.93939394 0.91428571
 0.83783784 0.94117647 0.90625    0.96774194]

mean value: 0.9050246503650204

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.9375     0.9375     0.96875    0.9375     0.93939394 0.96969697
 0.93939394 0.96969697 0.90625    0.9375    ]

mean value: 0.9443181818181818

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.93844697 0.87784091 0.95407197 0.87784091 0.93844697 0.93797348
 0.87594697 0.95359848 0.90625    0.953125  ]

mean value: 0.9213541666666667

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.88235294 0.78947368 0.91176471 0.78947368 0.88571429 0.88888889
 0.79487179 0.91428571 0.82857143 0.90909091]

mean value: 0.8594488036902898

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.32

Accuracy on Blind test: 0.9

Model_name: Extra Trees 
Model func: ExtraTreesClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreesClassifier(random_state=42))])

key: fit_time 
value: [0.12709141 0.12748075 0.12779284 0.13085532 0.12777114 0.12760949
 0.12383175 0.12944722 0.13224363 0.13170791]

mean value: 0.12858314514160157

key: score_time 
value: [0.01797247 0.01803613 0.01847935 0.01820111 0.01972103 0.01886845
 0.01881456 0.01977777 0.01946616 0.01882553]

mean value: 0.018816256523132326

key: test_mcc 
value: [0.91168461 0.87844611 0.90814394 0.94017476 0.87867338 0.94028478
 0.87689394 0.94028478 0.93933644 0.91025899]

mean value: 0.9124181728612889

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.95384615 0.93846154 0.95384615 0.96923077 0.93846154 0.96923077
 0.93846154 0.96923077 0.96875    0.953125  ]

mean value: 0.955264423076923

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.95522388 0.93548387 0.95384615 0.96774194 0.9375     0.96875
 0.93939394 0.96875    0.96774194 0.95081967]

mean value: 0.9545251387903739

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.91428571 0.96666667 0.93939394 1.         0.96774194 1.
 0.93939394 1.         1.         1.        ]

mean value: 0.9727482195224131

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1.         0.90625    0.96875    0.9375     0.90909091 0.93939394
 0.93939394 0.93939394 0.9375     0.90625   ]

mean value: 0.9383522727272727

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.95454545 0.93797348 0.95407197 0.96875    0.93892045 0.96969697
 0.93844697 0.96969697 0.96875    0.953125  ]

mean value: 0.9553977272727273

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.91428571 0.87878788 0.91176471 0.9375     0.88235294 0.93939394
 0.88571429 0.93939394 0.9375     0.90625   ]

mean value: 0.9132943404634581

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.12

Accuracy on Blind test: 0.91

Model_name: Extra Tree 
Model func: ExtraTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreeClassifier(random_state=42))])

key: fit_time 
value: [0.01086569 0.01079631 0.01190734 0.0106647  0.0110786  0.01209354
 0.01118755 0.01201916 0.01212025 0.01149154]

mean value: 0.011422467231750489

key: score_time 
value: [0.00885487 0.00906873 0.0097115  0.00940394 0.0099566  0.00943017
 0.00966215 0.00977445 0.00900555 0.00943255]

mean value: 0.00943005084991455

key: test_mcc 
value: [0.60000027 0.63222777 0.72649867 0.78503788 0.60000027 0.75378788
 0.82191818 0.7935502  0.75       0.90669283]

mean value: 0.7369713958456159

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.8        0.81538462 0.86153846 0.89230769 0.8        0.87692308
 0.90769231 0.89230769 0.875      0.953125  ]

mean value: 0.8674278846153847

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.79365079 0.81818182 0.86567164 0.89230769 0.80597015 0.87878788
 0.90322581 0.90140845 0.875      0.95384615]

mean value: 0.8688050384974951

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.80645161 0.79411765 0.82857143 0.87878788 0.79411765 0.87878788
 0.96551724 0.84210526 0.875      0.93939394]

mean value: 0.8602850537099204

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.78125    0.84375    0.90625    0.90625    0.81818182 0.87878788
 0.84848485 0.96969697 0.875      0.96875   ]

mean value: 0.8796401515151515

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.79971591 0.81581439 0.86221591 0.89251894 0.79971591 0.87689394
 0.90861742 0.89109848 0.875      0.953125  ]

mean value: 0.8674715909090909

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.65789474 0.69230769 0.76315789 0.80555556 0.675      0.78378378
 0.82352941 0.82051282 0.77777778 0.91176471]

mean value: 0.7711284379163637

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.02

Accuracy on Blind test: 0.82

Model_name: Random Forest 
Model func: RandomForestClassifier(n_estimators=1000, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(n_estimators=1000, random_state=42))])

key: fit_time 
value: [2.57344103 2.56146312 2.52725482 2.5337038  2.47081637 2.53378224
 2.52254081 2.55472231 2.50992036 2.53707719]

mean value: 2.5324722051620485

key: score_time 
value: [0.10120511 0.09277511 0.0973146  0.09307837 0.09849882 0.09306145
 0.09500909 0.09441996 0.09265494 0.09634829]

mean value: 0.09543657302856445

key: test_mcc 
value: [0.96969697 0.93844697 0.94028478 0.93844697 0.87867338 0.94028478
 0.91168461 0.93844697 0.93933644 0.91025899]

mean value: 0.9305560862611167

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.98461538 0.96923077 0.96923077 0.96923077 0.93846154 0.96923077
 0.95384615 0.96923077 0.96875    0.953125  ]

mean value: 0.9644951923076923

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.98461538 0.96875    0.96969697 0.96875    0.9375     0.96875
 0.95238095 0.96969697 0.96774194 0.95081967]

mean value: 0.9638701884005295

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.96969697 0.96875    0.94117647 0.96875    0.96774194 1.
 1.         0.96969697 1.         1.        ]

mean value: 0.9785812345466046

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1.         0.96875    1.         0.96875    0.90909091 0.93939394
 0.90909091 0.96969697 0.9375     0.90625   ]

mean value: 0.9508522727272727

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.98484848 0.96922348 0.96969697 0.96922348 0.93892045 0.96969697
 0.95454545 0.96922348 0.96875    0.953125  ]

mean value: 0.9647253787878788

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.96969697 0.93939394 0.94117647 0.93939394 0.88235294 0.93939394
 0.90909091 0.94117647 0.9375     0.90625   ]

mean value: 0.9305425579322638

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.25

Accuracy on Blind test: 0.92

Model_name: Random Forest2 
Model func: RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...05', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                                        n_estimators=1000, n_jobs=10,
                                        oob_score=True, random_state=42))])

key: fit_time 
value: [0.99138021 1.107862   1.0639801  1.06102729 1.05139637 1.02275515
 1.0929966  1.04554367 1.02682352 1.01838207]

mean value: 1.0482146978378295

key: score_time 
value: [0.28584266 0.24554586 0.28116274 0.20273829 0.27277923 0.28669381
 0.2614181  0.27412915 0.25570846 0.24849415]

mean value: 0.26145124435424805

key: test_mcc 
value: [0.93844697 0.87844611 0.94028478 0.90814394 0.84995597 0.94028478
 0.91168461 0.93844697 0.81409158 0.8819171 ]

mean value: 0.9001702814048853

key: train_mcc 
value: [0.95253584 0.95217582 0.95940056 0.95568036 0.96254008 0.95585634
 0.97257824 0.95253032 0.95910661 0.96595737]

mean value: 0.9588361532534039

key: test_accuracy 
value: [0.96923077 0.93846154 0.96923077 0.95384615 0.92307692 0.96923077
 0.95384615 0.96923077 0.90625    0.9375    ]

mean value: 0.9489903846153847

key: train_accuracy 
value: [0.97598628 0.97598628 0.97941681 0.97770154 0.98113208 0.97770154
 0.98627787 0.97598628 0.97945205 0.98287671]

mean value: 0.979251744636857

key: test_fscore 
value: [0.96875    0.93548387 0.96969697 0.95384615 0.92063492 0.96875
 0.95238095 0.96969697 0.90322581 0.93333333]

mean value: 0.9475798977008655

key: train_fscore 
value: [0.97560976 0.97577855 0.97909408 0.97746967 0.98086957 0.97731239
 0.9862069  0.97552448 0.97923875 0.98269896]

mean value: 0.9789803094657511

key: test_precision 
value: [0.96875    0.96666667 0.94117647 0.93939394 0.96666667 1.
 1.         0.96969697 0.93333333 1.        ]

mean value: 0.9685684046345812

key: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
train_precision 
value: [0.9929078  0.98601399 0.9964539  0.98947368 0.99295775 0.9929078
 0.98961938 0.99288256 0.98951049 0.99300699]

mean value: 0.9915734342207178

key: test_recall 
value: [0.96875    0.90625    1.         0.96875    0.87878788 0.93939394
 0.90909091 0.96969697 0.875      0.875     ]

mean value: 0.9290719696969697

key: train_recall 
value: [0.95890411 0.96575342 0.96232877 0.96575342 0.96907216 0.96219931
 0.98281787 0.95876289 0.96917808 0.97260274]

mean value: 0.9667372781622181

key: test_roc_auc 
value: [0.96922348 0.93797348 0.96969697 0.95407197 0.92376894 0.96969697
 0.95454545 0.96922348 0.90625    0.9375    ]

mean value: 0.9491950757575758

key: train_roc_auc 
value: [0.97601563 0.97600386 0.97944617 0.97772207 0.98111142 0.977675
 0.98627195 0.97595679 0.97945205 0.98287671]

mean value: 0.9792531657487172

key: test_jcc 
value: [0.93939394 0.87878788 0.94117647 0.91176471 0.85294118 0.93939394
 0.90909091 0.94117647 0.82352941 0.875     ]

mean value: 0.9012254901960784

key: train_jcc 
value: [0.95238095 0.9527027  0.95904437 0.9559322  0.96245734 0.9556314
 0.97278912 0.95221843 0.95932203 0.96598639]

mean value: 0.9588464938412049

MCC on Blind test: 0.35

Accuracy on Blind test: 0.93

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.02427173 0.01190543 0.01070786 0.01075864 0.01079917 0.01071405
 0.01062179 0.01137614 0.01185465 0.01054835]

mean value: 0.012355780601501465

key: score_time 
value: [0.01446009 0.00951314 0.00909829 0.00905752 0.00901055 0.00905895
 0.00915074 0.00982189 0.00982714 0.00908709]

mean value: 0.009808540344238281

key: test_mcc 
value: [0.60304138 0.69383917 0.69383917 0.58027158 0.60191459 0.64071161
 0.67632096 0.7935502  0.77459667 0.5336001 ]

mean value: 0.6591685435526063

key: train_mcc 
value: [0.65898657 0.68990309 0.6839259  0.68014131 0.68094306 0.6947996
 0.69240101 0.67852347 0.66969093 0.68389804]

mean value: 0.6813212997236593

key: test_accuracy 
value: [0.8        0.84615385 0.84615385 0.78461538 0.8        0.81538462
 0.83076923 0.89230769 0.875      0.765625  ]

mean value: 0.8256009615384615

key: train_accuracy 
value: [0.82504288 0.84048027 0.83876501 0.83704974 0.83704974 0.84391081
 0.84219554 0.83533448 0.83047945 0.8390411 ]

mean value: 0.8369349021358585

key: test_fscore 
value: [0.80597015 0.84848485 0.84848485 0.8        0.8115942  0.83333333
 0.84931507 0.90140845 0.88888889 0.7761194 ]

mean value: 0.8363599193526652

key: train_fscore 
value: [0.83860759 0.8526149  0.84935897 0.84751204 0.84751204 0.85393258
 0.85303514 0.84664537 0.84310618 0.8488746 ]

mean value: 0.848119941751926

key: test_precision 
value: [0.77142857 0.82352941 0.82352941 0.73684211 0.77777778 0.76923077
 0.775      0.84210526 0.8        0.74285714]

mean value: 0.7862300453244726

key: train_precision 
value: [0.77941176 0.79351032 0.79819277 0.79758308 0.79518072 0.80120482
 0.79701493 0.79104478 0.78466077 0.8       ]

mean value: 0.7937803952467857

key: test_recall 
value: [0.84375    0.875      0.875      0.875      0.84848485 0.90909091
 0.93939394 0.96969697 1.         0.8125    ]

mean value: 0.8947916666666667

key: train_recall 
value: [0.90753425 0.92123288 0.90753425 0.90410959 0.90721649 0.91408935
 0.91752577 0.91065292 0.9109589  0.90410959]

mean value: 0.9104963988137269

key: test_roc_auc 
value: [0.80066288 0.84659091 0.84659091 0.78598485 0.79924242 0.81392045
 0.82907197 0.89109848 0.875      0.765625  ]

mean value: 0.8253787878787879

key: train_roc_auc 
value: [0.82490114 0.84034152 0.83864685 0.83693452 0.83716989 0.84403097
 0.84232453 0.83546345 0.83047945 0.8390411 ]

mean value: 0.8369333427481994

key: test_jcc 
value: [0.675      0.73684211 0.73684211 0.66666667 0.68292683 0.71428571
 0.73809524 0.82051282 0.8        0.63414634]

mean value: 0.7205317820818463

key: train_jcc 
value: [0.72207084 0.74309392 0.73816156 0.73537604 0.73537604 0.74509804
 0.74373259 0.73407202 0.72876712 0.73743017]

mean value: 0.7363178359154687

MCC on Blind test: -0.1

Accuracy on Blind test: 0.73

Model_name: XGBoost 
Model func: XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...
                               interaction_constraints=None, learning_rate=None,
                               max_delta_step=None, max_depth=None,
                               min_child_weight=None, missing=nan,
                               monotone_constraints=None, n_estimators=100,
                               n_jobs=None, num_parallel_tree=None,
                               predictor=None, random_state=42, reg_alpha=None,
                               reg_lambda=None, scale_pos_weight=None,
                               subsample=None, tree_method=None,
                               use_label_encoder=False,
                               validate_parameters=None, verbosity=0))])

key: fit_time 
value: [0.11458182 0.09472775 0.09744906 0.09983706 0.10677338 0.09806156
 0.09206915 0.09799623 0.1020956  0.10150409]

mean value: 0.10050957202911377

key: score_time 
value: [0.01111531 0.01120782 0.01149702 0.01113391 0.01146054 0.01119089
 0.01112819 0.01126671 0.01145768 0.01106238]

mean value: 0.011252045631408691

key: test_mcc 
value: [0.84659091 0.93844697 0.87867338 0.93844697 0.90814394 0.96966868
 0.84644588 0.91144345 0.9375     0.875     ]

mean value: 0.9050360180565721

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.92307692 0.96923077 0.93846154 0.96923077 0.95384615 0.98461538
 0.92307692 0.95384615 0.96875    0.9375    ]

mean value: 0.9521634615384615

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.92307692 0.96875    0.93939394 0.96875    0.95384615 0.98507463
 0.92537313 0.95652174 0.96875    0.9375    ]

mean value: 0.952703651664148

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.90909091 0.96875    0.91176471 0.96875    0.96875    0.97058824
 0.91176471 0.91666667 0.96875    0.9375    ]

mean value: 0.9432375222816399

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.9375     0.96875    0.96875    0.96875    0.93939394 1.
 0.93939394 1.         0.96875    0.9375    ]

mean value: 0.9628787878787879

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.92329545 0.96922348 0.93892045 0.96922348 0.95407197 0.984375
 0.92282197 0.953125   0.96875    0.9375    ]

mean value: 0.9521306818181818

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.85714286 0.93939394 0.88571429 0.93939394 0.91176471 0.97058824
 0.86111111 0.91666667 0.93939394 0.88235294]

mean value: 0.910352262116968

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.63

Accuracy on Blind test: 0.95

Model_name: LDA 
Model func: LinearDiscriminantAnalysis() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LinearDiscriminantAnalysis())])

key: fit_time 
value: [0.07402301 0.09572005 0.08689284 0.0867219  0.07601881 0.08956218
 0.06421494 0.08183122 0.07881308 0.07907963]

mean value: 0.08128776550292968

key: score_time 
value: [0.01951957 0.01925826 0.01924205 0.01934052 0.01919436 0.01920819
 0.01224995 0.01916742 0.01933527 0.01922226]

mean value: 0.018573784828186037

key: test_mcc 
value: [0.88382395 0.75378788 0.88382395 0.82191818 0.90805728 0.78763191
 0.81671746 0.90805728 0.87671401 0.790965  ]

mean value: 0.8431496902836606

key: train_mcc 
value: [0.92153274 0.9250682  0.92839746 0.92822335 0.9076409  0.91467702
 0.91134752 0.91100205 0.90779513 0.91464642]

mean value: 0.917033079000042

key: test_accuracy 
value: [0.93846154 0.87692308 0.93846154 0.90769231 0.95384615 0.89230769
 0.90769231 0.95384615 0.9375     0.890625  ]

mean value: 0.919735576923077

key: train_accuracy 
value: [0.96054889 0.96226415 0.96397942 0.96397942 0.95368782 0.95711835
 0.95540309 0.95540309 0.95376712 0.95719178]

mean value: 0.958334312366362

key: test_fscore 
value: [0.94117647 0.875      0.94117647 0.91176471 0.95522388 0.89855072
 0.91176471 0.95522388 0.93939394 0.89855072]

mean value: 0.9227825502804509

key: train_fscore 
value: [0.96121417 0.96296296 0.96458685 0.96446701 0.95415959 0.95769882
 0.95608108 0.95578231 0.95431472 0.95769882]

mean value: 0.9588966318325307

key: test_precision 
value: [0.88888889 0.875      0.88888889 0.86111111 0.94117647 0.86111111
 0.88571429 0.94117647 0.91176471 0.83783784]

mean value: 0.8892669770610947

key: train_precision 
value: [0.94684385 0.94701987 0.95016611 0.95317726 0.94295302 0.94333333
 0.94019934 0.94612795 0.94314381 0.94648829]

mean value: 0.9459452834019253

key: test_recall 
value: [1.         0.875      1.         0.96875    0.96969697 0.93939394
 0.93939394 0.96969697 0.96875    0.96875   ]

mean value: 0.9599431818181818

key: train_recall 
value: [0.9760274  0.97945205 0.97945205 0.9760274  0.96563574 0.97250859
 0.97250859 0.96563574 0.96575342 0.96917808]

mean value: 0.9722179070752719

key: test_roc_auc 
value: [0.93939394 0.87689394 0.93939394 0.90861742 0.95359848 0.89157197
 0.90719697 0.95359848 0.9375     0.890625  ]

mean value: 0.9198390151515151

key: train_roc_auc 
value: [0.96052229 0.96223462 0.96395283 0.96395872 0.95370828 0.95714471
 0.95543238 0.95542061 0.95376712 0.95719178]

mean value: 0.9583333333333334

key: test_jcc 
value: [0.88888889 0.77777778 0.88888889 0.83783784 0.91428571 0.81578947
 0.83783784 0.91428571 0.88571429 0.81578947]

mean value: 0.8577095892885367

key: train_jcc 
value: [0.92532468 0.92857143 0.93159609 0.93137255 0.91233766 0.91883117
 0.91585761 0.91530945 0.91262136 0.91883117]

mean value: 0.9210653154776289

MCC on Blind test: 0.24

Accuracy on Blind test: 0.88

Model_name: Multinomial 
Model func: MultinomialNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MultinomialNB())])

key: fit_time 
value: [0.01584506 0.01046205 0.01018    0.00997138 0.00999999 0.0099299
 0.01008153 0.01008105 0.00993848 0.00989532]

mean value: 0.01063847541809082

key: score_time 
value: [0.00984168 0.00909376 0.00891948 0.00863814 0.00863433 0.00864983
 0.00867629 0.0086906  0.00871205 0.0086627 ]

mean value: 0.008851885795593262

key: test_mcc 
value: [0.35948106 0.67020271 0.73234704 0.46223375 0.17227757 0.51508188
 0.47697953 0.585659   0.50902781 0.55359617]

mean value: 0.5036886512811006

key: train_mcc 
value: [0.53813819 0.54044737 0.52861699 0.53120592 0.54784332 0.52736902
 0.55620749 0.53826994 0.4907557  0.51638105]

mean value: 0.5315234997698276

key: test_accuracy 
value: [0.67692308 0.83076923 0.86153846 0.72307692 0.58461538 0.75384615
 0.72307692 0.78461538 0.75       0.765625  ]

mean value: 0.7454086538461538

key: train_accuracy 
value: [0.75986278 0.76329331 0.75814751 0.75814751 0.76672384 0.75814751
 0.77186964 0.76329331 0.7380137  0.75171233]

mean value: 0.7589211447637397

key: test_fscore 
value: [0.69565217 0.84057971 0.86956522 0.75       0.64       0.77777778
 0.76923077 0.81081081 0.77142857 0.79452055]

mean value: 0.771956557864241

key: train_fscore 
value: [0.78787879 0.78769231 0.7820711  0.78407351 0.79012346 0.7800312
 0.79315708 0.78504673 0.76641221 0.77657935]

mean value: 0.7833065729641276

key: test_precision 
value: [0.64864865 0.78378378 0.81081081 0.675      0.57142857 0.71794872
 0.66666667 0.73170732 0.71052632 0.70731707]

mean value: 0.7023837905320576

key: train_precision 
value: [0.70652174 0.7150838  0.71267606 0.70914127 0.71708683 0.71428571
 0.72443182 0.71794872 0.69146006 0.70588235]

mean value: 0.7114518361777111

key: test_recall 
value: [0.75       0.90625    0.9375     0.84375    0.72727273 0.84848485
 0.90909091 0.90909091 0.84375    0.90625   ]

mean value: 0.8581439393939394

key: train_recall 
value: [0.89041096 0.87671233 0.86643836 0.87671233 0.87972509 0.85910653
 0.87628866 0.86597938 0.85958904 0.8630137 ]

mean value: 0.8713976368686155

key: test_roc_auc 
value: [0.6780303  0.83191288 0.86268939 0.7249053  0.58238636 0.75236742
 0.72017045 0.78267045 0.75       0.765625  ]

mean value: 0.7450757575757576

key: train_roc_auc 
value: [0.75963847 0.76309843 0.75796145 0.75794379 0.76691734 0.75832039
 0.77204844 0.76346914 0.7380137  0.75171233]

mean value: 0.7589123475968554

key: test_jcc 
value: [0.53333333 0.725      0.76923077 0.6        0.47058824 0.63636364
 0.625      0.68181818 0.62790698 0.65909091]

mean value: 0.6328332041875133

key: train_jcc 
value: [0.65       0.64974619 0.64213198 0.64483627 0.65306122 0.63938619
 0.65721649 0.64615385 0.62128713 0.63476071]

mean value: 0.6438580033378993

MCC on Blind test: -0.05

Accuracy on Blind test: 0.68

Model_name: Passive Aggresive 
Model func: PassiveAggressiveClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 PassiveAggressiveClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.01804662 0.01985765 0.0240314  0.02479959 0.02373505 0.02630234
 0.02022481 0.02028942 0.02308869 0.02453732]

mean value: 0.02249128818511963

key: score_time 
value: [0.00987554 0.01118493 0.01169372 0.01175666 0.01181984 0.01185131
 0.01175165 0.01173925 0.01166058 0.01175189]

mean value: 0.011508536338806153

key: test_mcc 
value: [0.84995597 0.88340557 0.94028478 0.87689394 0.90814394 0.65264928
 0.63287203 0.82126124 0.81892302 0.84416229]

mean value: 0.822855207063419

key: train_mcc 
value: [0.87993692 0.8971658  0.9108284  0.89455123 0.87651967 0.63782017
 0.73769351 0.8843916  0.88408023 0.89981781]

mean value: 0.8502805341806269

key: test_accuracy 
value: [0.92307692 0.93846154 0.96923077 0.93846154 0.95384615 0.8
 0.78461538 0.90769231 0.90625    0.921875  ]

mean value: 0.9043509615384615

key: train_accuracy 
value: [0.93996569 0.94854202 0.95540309 0.94682676 0.93825043 0.7890223
 0.85248714 0.94168096 0.94178082 0.94863014]

mean value: 0.9202589346554195

key: test_fscore 
value: [0.92537313 0.93333333 0.96969697 0.9375     0.95384615 0.83544304
 0.73076923 0.91428571 0.91176471 0.92307692]

mean value: 0.903508920319372

key: train_fscore 
value: [0.93996569 0.94897959 0.95532646 0.94570928 0.93793103 0.82553191
 0.8266129  0.94295302 0.94276094 0.94661922]

mean value: 0.9212390061541185

key: test_precision 
value: [0.88571429 1.         0.94117647 0.9375     0.96875    0.7173913
 1.         0.86486486 0.86111111 0.90909091]

mean value: 0.9085598945717233

key: train_precision 
value: [0.94158076 0.94256757 0.95862069 0.96774194 0.94117647 0.70289855
 1.         0.92131148 0.92715232 0.98518519]

mean value: 0.9288234948509045

key: test_recall 
value: [0.96875    0.875      1.         0.9375     0.93939394 1.
 0.57575758 0.96969697 0.96875    0.9375    ]

mean value: 0.9172348484848485

key: train_recall 
value: [0.93835616 0.95547945 0.95205479 0.92465753 0.9347079  1.
 0.70446735 0.96563574 0.95890411 0.9109589 ]

mean value: 0.9245221955467684

key: test_roc_auc 
value: [0.92376894 0.9375     0.96969697 0.93844697 0.95407197 0.796875
 0.78787879 0.90672348 0.90625    0.921875  ]

mean value: 0.9043087121212121

key: train_roc_auc 
value: [0.93996846 0.9485301  0.95540884 0.94686485 0.93824436 0.78938356
 0.85223368 0.94172198 0.94178082 0.94863014]

mean value: 0.9202766793767359

key: test_jcc 
value: [0.86111111 0.875      0.94117647 0.88235294 0.91176471 0.7173913
 0.57575758 0.84210526 0.83783784 0.85714286]

mean value: 0.8301640067002162

key: train_jcc 
value: [0.88673139 0.90291262 0.91447368 0.89700997 0.88311688 0.70289855
 0.70446735 0.89206349 0.89171975 0.89864865]

mean value: 0.8574042337661401

MCC on Blind test: 0.16

Accuracy on Blind test: 0.91

Model_name: Stochastic GDescent 
Model func: SGDClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SGDClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.02315521 0.01898193 0.01959205 0.02337122 0.02137542 0.01898146
 0.02197409 0.02109432 0.02077174 0.02239561]

mean value: 0.021169304847717285

key: score_time 
value: [0.01180077 0.0216682  0.01418352 0.01474524 0.0117631  0.01682234
 0.01191783 0.01176167 0.01174808 0.01175189]

mean value: 0.013816261291503906

key: test_mcc 
value: [0.88382395 0.72649867 0.84644588 0.84995597 0.726372   0.78763191
 0.69810664 0.49236596 0.82717019 0.73658951]

mean value: 0.7574960676483226

key: train_mcc 
value: [0.87658012 0.80514005 0.89126004 0.89453522 0.74190307 0.87313838
 0.87112634 0.5153169  0.83026661 0.83231822]

mean value: 0.8131584945550048

key: test_accuracy 
value: [0.93846154 0.86153846 0.92307692 0.92307692 0.84615385 0.89230769
 0.84615385 0.69230769 0.90625    0.859375  ]

mean value: 0.8688701923076924

key: train_accuracy 
value: [0.93825043 0.89536878 0.94511149 0.94682676 0.85591767 0.9348199
 0.93310463 0.71012007 0.90924658 0.90924658]

mean value: 0.8978012876242393

key: test_fscore 
value: [0.94117647 0.86567164 0.92063492 0.92537313 0.86842105 0.89855072
 0.83870968 0.56521739 0.91428571 0.84210526]

mean value: 0.8580145990779131

key: train_fscore 
value: [0.93877551 0.90453834 0.94385965 0.9480737  0.87349398 0.9375
 0.9292196  0.59079903 0.91627172 0.90018832]

mean value: 0.8882719856310122

key: test_precision 
value: [0.88888889 0.82857143 0.93548387 0.88571429 0.76744186 0.86111111
 0.89655172 1.         0.84210526 0.96      ]

mean value: 0.8865868433014398

key: train_precision 
value: [0.93243243 0.83285303 0.9676259  0.92786885 0.77747989 0.89905363
 0.98461538 1.         0.85043988 1.        ]

mean value: 0.9172368997943602

key: test_recall 
value: [1.         0.90625    0.90625    0.96875    1.         0.93939394
 0.78787879 0.39393939 1.         0.75      ]

mean value: 0.8652462121212121

key: train_recall 
value: [0.94520548 0.98972603 0.92123288 0.96917808 0.99656357 0.97938144
 0.87972509 0.41924399 0.99315068 0.81849315]

mean value: 0.8911900390716943

key: test_roc_auc 
value: [0.93939394 0.86221591 0.92282197 0.92376894 0.84375    0.89157197
 0.84706439 0.6969697  0.90625    0.859375  ]

mean value: 0.8693181818181819

key: train_roc_auc 
value: [0.93823848 0.89520666 0.94515252 0.94678835 0.8561585  0.9348962
 0.93301323 0.70962199 0.90924658 0.90924658]

mean value: 0.8977569081579815

key: test_jcc 
value: [0.88888889 0.76315789 0.85294118 0.86111111 0.76744186 0.81578947
 0.72222222 0.39393939 0.84210526 0.72727273]

mean value: 0.7634870011948995

key: train_jcc 
value: [0.88461538 0.82571429 0.89368771 0.90127389 0.77540107 0.88235294
 0.86779661 0.41924399 0.84548105 0.81849315]

mean value: 0.8114060070687773

MCC on Blind test: 0.23

Accuracy on Blind test: 0.87

Model_name: AdaBoost Classifier 
Model func: AdaBoostClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', AdaBoostClassifier(random_state=42))])

key: fit_time 
value: [0.2964623  0.28373861 0.28238082 0.2825644  0.28138447 0.28255749
 0.28149343 0.28534913 0.28425336 0.282763  ]

mean value: 0.28429470062255857

key: score_time 
value: [0.01519012 0.01519156 0.01549268 0.0152359  0.01534128 0.01520538
 0.01530862 0.01543164 0.01527667 0.01528382]

mean value: 0.015295767784118652

key: test_mcc 
value: [0.94028478 0.84659091 0.84995597 0.84659091 0.90814394 0.93844697
 0.81534091 0.87689394 0.84416229 0.90669283]

mean value: 0.8773103442988633

key: train_mcc 
value: [0.99657534 0.99313892 0.99657534 1.         0.9965753  0.99313892
 0.99657534 0.9965753  1.         1.        ]

mean value: 0.9969154464556946

key: test_accuracy 
value: [0.96923077 0.92307692 0.92307692 0.92307692 0.95384615 0.96923077
 0.90769231 0.93846154 0.921875   0.953125  ]

mean value: 0.9382692307692307

key: train_accuracy 
value: [0.99828473 0.99656947 0.99828473 1.         0.99828473 0.99656947
 0.99828473 0.99828473 1.         1.        ]

mean value: 0.9984562607204117

key: test_fscore 
value: [0.96969697 0.92307692 0.92537313 0.92307692 0.95384615 0.96969697
 0.90909091 0.93939394 0.92307692 0.95238095]

mean value: 0.9388709797665021

key: train_fscore 
value: [0.99828473 0.99657534 0.99828473 1.         0.99827883 0.99656357
 0.99828473 0.99827883 1.         1.        ]

mean value: 0.9984550777958549

key: test_precision 
value: [0.94117647 0.90909091 0.88571429 0.90909091 0.96875    0.96969697
 0.90909091 0.93939394 0.90909091 0.96774194]

mean value: 0.9308837237240938

key: train_precision 
value: [1.         0.99657534 1.         1.         1.         0.99656357
 0.99657534 1.         1.         1.        ]

mean value: 0.9989714258814668

key: test_recall 
value: [1.         0.9375     0.96875    0.9375     0.93939394 0.96969697
 0.90909091 0.93939394 0.9375     0.9375    ]

mean value: 0.9476325757575758

key: train_recall 
value: [0.99657534 0.99657534 0.99657534 1.         0.99656357 0.99656357
 1.         0.99656357 1.         1.        ]

mean value: 0.9979416749046744

key: test_roc_auc 
value: [0.96969697 0.92329545 0.92376894 0.92329545 0.95407197 0.96922348
 0.90767045 0.93844697 0.921875   0.953125  ]

mean value: 0.9384469696969697

key: train_roc_auc 
value: [0.99828767 0.99656946 0.99828767 1.         0.99828179 0.99656946
 0.99828767 0.99828179 1.         1.        ]

mean value: 0.9984565503930707

key: test_jcc 
value: [0.94117647 0.85714286 0.86111111 0.85714286 0.91176471 0.94117647
 0.83333333 0.88571429 0.85714286 0.90909091]

mean value: 0.8854795857737034

key: train_jcc 
value: [0.99657534 0.99317406 0.99657534 1.         0.99656357 0.99315068
 0.99657534 0.99656357 1.         1.        ]

mean value: 0.9969177921528537

MCC on Blind test: 0.48

Accuracy on Blind test: 0.93

Model_name: Bagging Classifier 
Model func: BaggingClassifier(n_jobs=10, oob_score=True, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 BaggingClassifier(n_jobs=10, oob_score=True,
                                   random_state=42))])

key: fit_time 
value: [0.10766101 0.08889747 0.12967515 0.11884522 0.10242176 0.13095689
 0.10770798 0.13756514 0.13859272 0.12511349]

mean value: 0.1187436819076538

key: score_time 
value: [0.02559161 0.01886272 0.02924132 0.0291326  0.03726697 0.01806498
 0.04110551 0.04082751 0.03991771 0.02466011]

mean value: 0.0304671049118042

key: test_mcc 
value: [0.87689394 0.81706198 0.87867338 0.87867338 0.84995597 0.87844611
 0.81671746 0.90814394 0.81409158 0.87671401]

mean value: 0.859537174508022

key: train_mcc 
value: [0.98971426 0.99316237 0.9965753  0.99313892 0.99316221 1.
 0.99313892 0.9965753  0.98632451 0.98973183]

mean value: 0.9931523619060675

key: test_accuracy 
value: [0.93846154 0.90769231 0.93846154 0.93846154 0.92307692 0.93846154
 0.90769231 0.95384615 0.90625    0.9375    ]

mean value: 0.9289903846153846

key: train_accuracy 
value: [0.9948542  0.99656947 0.99828473 0.99656947 0.99656947 1.
 0.99656947 0.99828473 0.99315068 0.99486301]

mean value: 0.9965715242369417

key: test_fscore 
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
[0.9375     0.90909091 0.93939394 0.93939394 0.92063492 0.94117647
 0.91176471 0.95384615 0.90322581 0.93548387]

mean value: 0.9291510716249806

key: train_fscore 
value: [0.9948542  0.99656357 0.9982906  0.99657534 0.99655172 1.
 0.99656357 0.99827883 0.99312715 0.9948542 ]

mean value: 0.9965659194833804

key: test_precision 
value: [0.9375     0.88235294 0.91176471 0.91176471 0.96666667 0.91428571
 0.88571429 0.96875    0.93333333 0.96666667]

mean value: 0.9278799019607843

key: train_precision 
value: [0.99656357 1.         0.99658703 0.99657534 1.         1.
 0.99656357 1.         0.99655172 0.99656357]

mean value: 0.9979404818969893

key: test_recall 
value: [0.9375     0.9375     0.96875    0.96875    0.87878788 0.96969697
 0.93939394 0.93939394 0.875      0.90625   ]

mean value: 0.9321022727272728

key: train_recall 
value: [0.99315068 0.99315068 1.         0.99657534 0.99312715 1.
 0.99656357 0.99656357 0.98972603 0.99315068]

mean value: 0.995200772019018

key: test_roc_auc 
value: [0.93844697 0.90814394 0.93892045 0.93892045 0.92376894 0.93797348
 0.90719697 0.95407197 0.90625    0.9375    ]

mean value: 0.9291193181818183

key: train_roc_auc 
value: [0.99485713 0.99657534 0.99828179 0.99656946 0.99656357 1.
 0.99656946 0.99828179 0.99315068 0.99486301]

mean value: 0.9965712234618462

key: test_jcc 
value: [0.88235294 0.83333333 0.88571429 0.88571429 0.85294118 0.88888889
 0.83783784 0.91176471 0.82352941 0.87878788]

mean value: 0.8680864745570628

key: train_jcc 
value: [0.98976109 0.99315068 0.99658703 0.99317406 0.99312715 1.
 0.99315068 0.99656357 0.98634812 0.98976109]

mean value: 0.9931623490829904

MCC on Blind test: 0.5

Accuracy on Blind test: 0.94

Model_name: Gaussian Process 
Model func: GaussianProcessClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianProcessClassifier(random_state=42))])

key: fit_time 
value: [0.25701952 0.40649891 0.32262087 0.22393775 0.23044133 0.18854737
 0.22238064 0.33723783 0.34737706 0.31397367]

mean value: 0.28500349521636964

key: score_time 
value: [0.02734852 0.04947257 0.02745867 0.01618171 0.01620317 0.01635075
 0.03088403 0.03055477 0.02413607 0.02356458]

mean value: 0.026215481758117675

key: test_mcc 
value: [0.80403025 0.78822732 0.82191818 0.79449138 0.585659   0.87844611
 0.73110376 0.87844611 0.82717019 0.81892302]

mean value: 0.7928415327506938

key: train_mcc 
value: [0.96231434 0.96240453 0.96913064 0.96240453 0.96231567 0.96578632
 0.96590041 0.96917699 0.96922924 0.96922924]

mean value: 0.9657891901072067

key: test_accuracy 
value: [0.89230769 0.89230769 0.90769231 0.89230769 0.78461538 0.93846154
 0.86153846 0.93846154 0.90625    0.90625   ]

mean value: 0.8920192307692307

key: train_accuracy 
value: [0.98113208 0.98113208 0.98456261 0.98113208 0.98113208 0.98284734
 0.98284734 0.98456261 0.98458904 0.98458904]

mean value: 0.9828526281162622

key: test_fscore 
value: [0.90140845 0.89552239 0.91176471 0.89855072 0.81081081 0.94117647
 0.87323944 0.94117647 0.91428571 0.91176471]

mean value: 0.8999699878059029

key: train_fscore 
value: [0.98126065 0.98132428 0.98461538 0.98132428 0.98119658 0.98293515
 0.9829932  0.98461538 0.9846678  0.9846678 ]

mean value: 0.9829600510295413

key: test_precision 
value: [0.82051282 0.85714286 0.86111111 0.83783784 0.73170732 0.91428571
 0.81578947 0.91428571 0.84210526 0.86111111]

mean value: 0.8455889220202442

key: train_precision 
value: [0.97627119 0.97306397 0.98293515 0.97306397 0.97619048 0.97627119
 0.97306397 0.97959184 0.97966102 0.97966102]

mean value: 0.9769773792480368

key: test_recall 
value: [1.         0.9375     0.96875    0.96875    0.90909091 0.96969697
 0.93939394 0.96969697 1.         0.96875   ]

mean value: 0.9631628787878788

key: train_recall 
value: [0.98630137 0.98972603 0.98630137 0.98972603 0.9862543  0.98969072
 0.99312715 0.98969072 0.98972603 0.98972603]

mean value: 0.9890269735913007

key: test_roc_auc 
value: [0.89393939 0.89299242 0.90861742 0.89346591 0.78267045 0.93797348
 0.86032197 0.93797348 0.90625    0.90625   ]

mean value: 0.8920454545454546

key: train_roc_auc 
value: [0.98112319 0.98111731 0.98455962 0.98111731 0.98114085 0.98285906
 0.98286494 0.98457139 0.98458904 0.98458904]

mean value: 0.9828531751635833

key: test_jcc 
value: [0.82051282 0.81081081 0.83783784 0.81578947 0.68181818 0.88888889
 0.775      0.88888889 0.84210526 0.83783784]

mean value: 0.8199490003437372

key: train_jcc 
value: [0.9632107  0.96333333 0.96969697 0.96333333 0.96308725 0.96644295
 0.96655518 0.96969697 0.96979866 0.96979866]

mean value: 0.9664954009126755

MCC on Blind test: 0.06

Accuracy on Blind test: 0.81

Model_name: Gradient Boosting 
Model func: GradientBoostingClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GradientBoostingClassifier(random_state=42))])

key: fit_time 
value: [1.19846988 1.2099998  1.20815873 1.20550132 1.1960814  1.19838786
 1.20575476 1.22087693 1.21714902 1.21541381]

mean value: 1.2075793504714967

key: score_time 
value: [0.00960732 0.00946498 0.0092752  0.00957656 0.00936055 0.00928593
 0.01018381 0.00946069 0.00949073 0.00953245]

mean value: 0.009523820877075196

key: test_mcc 
value: [0.81706198 0.76001241 0.87867338 0.90814394 0.87867338 0.94017476
 0.87844611 0.94017476 0.875      0.87671401]

mean value: 0.8753074716604554

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.90769231 0.87692308 0.93846154 0.95384615 0.93846154 0.96923077
 0.93846154 0.96923077 0.9375     0.9375    ]

mean value: 0.9367307692307693

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.90909091 0.88235294 0.93939394 0.95384615 0.9375     0.97058824
 0.94117647 0.97058824 0.9375     0.93548387]

mean value: 0.9377520755651685

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.88235294 0.83333333 0.91176471 0.93939394 0.96774194 0.94285714
 0.91428571 0.94285714 0.9375     0.96666667]

mean value: 0.9238753521936633

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.9375     0.9375     0.96875    0.96875    0.90909091 1.
 0.96969697 1.         0.9375     0.90625   ]

mean value: 0.9535037878787879

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.90814394 0.87784091 0.93892045 0.95407197 0.93892045 0.96875
 0.93797348 0.96875    0.9375     0.9375    ]

mean value: 0.9368371212121213

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.83333333 0.78947368 0.88571429 0.91176471 0.88235294 0.94285714
 0.88888889 0.94285714 0.88235294 0.87878788]

mean value: 0.8838382944884493

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.56

Accuracy on Blind test: 0.94

Model_name: QDA 
Model func: QuadraticDiscriminantAnalysis() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', QuadraticDiscriminantAnalysis())])

key: fit_time 
value: [0.03196478 0.03217864 0.0323441  0.03200746 0.04611158 0.08184719
 0.04776669 0.03345966 0.03114057 0.03112483]

mean value: 0.039994549751281736

key: score_time 
value: [0.01271653 0.01378345 0.01337409 0.01590347 0.02862263 0.01743627
 0.01939297 0.02776408 0.01603842 0.02807379]

mean value: 0.019310569763183592

key: test_mcc 
value: [1.         1.         1.         0.96966868 1.         1.
 0.96969697 1.         1.         1.        ]

mean value: 0.9939365651743151

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [1.         1.         1.         0.98461538 1.         1.
 0.98461538 1.         1.         1.        ]

mean value: 0.9969230769230769

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [1.         1.         1.         0.98412698 1.         1.
 0.98461538 1.         1.         1.        ]

mean value: 0.9968742368742369

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1.         1.         1.         0.96875    1.         1.
 0.96969697 1.         1.         1.        ]

mean value: 0.993844696969697

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [1.         1.         1.         0.984375   1.         1.
 0.98484848 1.         1.         1.        ]

mean value: 0.9969223484848485

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [1.         1.         1.         0.96875    1.         1.
 0.96969697 1.         1.         1.        ]

mean value: 0.993844696969697

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Ridge Classifier 
Model func: RidgeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifier(random_state=42))])

key: fit_time 
value: [0.0287621  0.03958964 0.0396347  0.03341985 0.0348165  0.04529977
 0.0164516  0.01656842 0.01634407 0.03106642]

mean value: 0.03019530773162842

key: score_time 
value: [0.01936316 0.02220511 0.02826476 0.02795935 0.01919365 0.01943302
 0.01244664 0.01234722 0.01225901 0.01916742]

mean value: 0.01926393508911133

key: test_mcc 
value: [0.88382395 0.75378788 0.91168461 0.84995597 0.93844697 0.87844611
 0.72572613 0.90805728 0.84416229 0.84748251]

mean value: 0.8541573701609051

key: train_mcc 
value: [0.90076997 0.91157246 0.89074056 0.89783768 0.89429697 0.90802803
 0.91158485 0.89098559 0.89447052 0.8977869 ]

mean value: 0.8998073542242344

key: test_accuracy 
value: [0.93846154 0.87692308 0.95384615 0.92307692 0.96923077 0.93846154
 0.86153846 0.95384615 0.921875   0.921875  ]

mean value: 0.9259134615384615

key: train_accuracy 
value: [0.95025729 0.95540309 0.94511149 0.94854202 0.94682676 0.95368782
 0.95540309 0.94511149 0.94691781 0.94863014]

mean value: 0.9495890998378721

key: test_fscore 
value: [0.94117647 0.875      0.95522388 0.92537313 0.96969697 0.94117647
 0.86956522 0.95522388 0.92307692 0.92537313]

mean value: 0.9280886081192414

key: train_fscore 
value: [0.95093063 0.95637584 0.94612795 0.94966443 0.94772344 0.9544688
 0.95622896 0.94612795 0.94789916 0.94949495]

mean value: 0.9505042094990621

key: test_precision 
value: [0.88888889 0.875      0.91428571 0.88571429 0.96969697 0.91428571
 0.83333333 0.94117647 0.90909091 0.88571429]

mean value: 0.9017186571598336

key: train_precision 
value: [0.93979933 0.9375     0.93046358 0.93092105 0.93046358 0.93708609
 0.93729373 0.92739274 0.93069307 0.93377483]

mean value: 0.9335388001159252

key: test_recall 
value: [1.         0.875      1.         0.96875    0.96969697 0.96969697
 0.90909091 0.96969697 0.9375     0.96875   ]

mean value: 0.9568181818181818

key: train_recall 
value: [0.96232877 0.9760274  0.96232877 0.96917808 0.96563574 0.97250859
 0.97594502 0.96563574 0.96575342 0.96575342]

mean value: 0.9681094948924351/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:136: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:139: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)


key: test_roc_auc 
value: [0.93939394 0.87689394 0.95454545 0.92376894 0.96922348 0.93797348
 0.86079545 0.95359848 0.921875   0.921875  ]

mean value: 0.9259943181818182

key: train_roc_auc 
value: [0.95023655 0.95536765 0.94508191 0.94850657 0.94685897 0.95372005
 0.95543826 0.94514664 0.94691781 0.94863014]

mean value: 0.9495904533258015

key: test_jcc 
value: [0.88888889 0.77777778 0.91428571 0.86111111 0.94117647 0.88888889
 0.76923077 0.91428571 0.85714286 0.86111111]

mean value: 0.8673899303311068

key: train_jcc 
value: [0.90645161 0.91639871 0.89776358 0.90415335 0.90064103 0.91290323
 0.91612903 0.89776358 0.90095847 0.90384615]

mean value: 0.9057008741917071

MCC on Blind test: 0.2

Accuracy on Blind test: 0.85

Model_name: Ridge ClassifierCV 
Model func: RidgeClassifierCV(cv=10) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifierCV(cv=10))])

key: fit_time 
value: [0.20723772 0.3288908  0.34030318 0.30180621 0.18733144 0.29651952
 0.3267138  0.31015897 0.31902647 0.23160696]

mean value: 0.2849595069885254

key: score_time 
value: [0.01937056 0.02136326 0.01289296 0.02494788 0.01255035 0.02435946
 0.01932001 0.01932645 0.02503896 0.01413894]

mean value: 0.019330883026123048

key: test_mcc 
value: [0.88382395 0.75378788 0.91168461 0.84995597 0.93844697 0.7935502
 0.81671746 0.90805728 0.84416229 0.84748251]

mean value: 0.8547669126005479

key: train_mcc 
value: [0.90076997 0.9250682  0.91133714 0.91449666 0.90428993 0.90781302
 0.91134752 0.89098559 0.89447052 0.91464642]

mean value: 0.9075224983885753

key: test_accuracy 
value: [0.93846154 0.87692308 0.95384615 0.92307692 0.96923077 0.89230769
 0.90769231 0.95384615 0.921875   0.921875  ]

mean value: 0.9259134615384615

key: train_accuracy 
value: [0.95025729 0.96226415 0.95540309 0.95711835 0.95197256 0.95368782
 0.95540309 0.94511149 0.94691781 0.95719178]

mean value: 0.9535327427806104

key: test_fscore 
value: [0.94117647 0.875      0.95522388 0.92537313 0.96969697 0.90140845
 0.91176471 0.95522388 0.92307692 0.92537313]

mean value: 0.9283317549799452

key: train_fscore 
value: [0.95093063 0.96296296 0.95622896 0.95769882 0.95254237 0.95431472
 0.95608108 0.94612795 0.94789916 0.95769882]

mean value: 0.9542485456949552

key: test_precision 
value: [0.88888889 0.875      0.91428571 0.88571429 0.96969697 0.84210526
 0.88571429 0.94117647 0.90909091 0.88571429]

mean value: 0.8997387072851469

key: train_precision 
value: [0.93979933 0.94701987 0.94039735 0.94648829 0.93979933 0.94
 0.94019934 0.92739274 0.93069307 0.94648829]

mean value: 0.9398277613508198

key: test_recall 
value: [1.         0.875      1.         0.96875    0.96969697 0.96969697
 0.93939394 0.96969697 0.9375     0.96875   ]

mean value: 0.9598484848484848

key: train_recall 
value: [0.96232877 0.97945205 0.97260274 0.96917808 0.96563574 0.96907216
 0.97250859 0.96563574 0.96575342 0.96917808]

mean value: 0.9691345384361907

key: test_roc_auc 
value: [0.93939394 0.87689394 0.95454545 0.92376894 0.96922348 0.89109848
 0.90719697 0.95359848 0.921875   0.921875  ]

mean value: 0.9259469696969697

key: train_roc_auc 
value: [0.95023655 0.96223462 0.95537353 0.95709763 0.95199595 0.95371416
 0.95543238 0.94514664 0.94691781 0.95719178]

mean value: 0.9535341053523514

key: test_jcc 
value: [0.88888889 0.77777778 0.91428571 0.86111111 0.94117647 0.82051282
 0.83783784 0.91428571 0.85714286 0.86111111]

mean value: 0.8674130303542068

key: train_jcc 
value: [0.90645161 0.92857143 0.91612903 0.91883117 0.90938511 0.91262136
 0.91585761 0.89776358 0.90095847 0.91883117]

mean value: 0.9125400533793394

MCC on Blind test: 0.2

Accuracy on Blind test: 0.85

Model_name: Logistic Regression 
Model func: LogisticRegression(random_state=42) 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegression(random_state=42))])

key: fit_time 
value: [0.03581429 0.03890061 0.04402566 0.0504868  0.05339575 0.10844016
 0.03914738 0.04084992 0.03889728 0.03860402]

mean value: 0.04885618686676026

key: score_time 
value: [0.01237941 0.01473331 0.02581453 0.01521826 0.01638341 0.01327848
 0.01526642 0.01519799 0.01591086 0.01551175]

mean value: 0.015969443321228027

key: test_mcc 
value: [0.79449138 0.60304138 0.82191818 0.78822732 0.67020271 0.78483448
 0.69326017 0.739574   0.8542422  0.65915306]

mean value: 0.7408944876979084

key: train_mcc 
value: [0.84292018 0.79837701 0.8588135  0.81302839 0.79772134 0.87430331
 0.8300748  0.86848146 0.85539741 0.7913233 ]

mean value: 0.8330440703338137

key: test_accuracy 
value: [0.89230769 0.8        0.90769231 0.89230769 0.83076923 0.89230769
 0.84615385 0.86153846 0.921875   0.828125  ]

mean value: 0.8673076923076923

key: train_accuracy 
value: [0.9193825  0.89879931 0.92795883 0.90566038 0.89879931 0.9348199
 0.91423671 0.93310463 0.92636986 0.89554795]

mean value: 0.9154679386263775

key: test_fscore 
value: [0.89855072 0.80597015 0.91176471 0.89552239 0.81967213 0.89552239
 0.85294118 0.87671233 0.92753623 0.81967213]

mean value: 0.870386435531002

key: train_fscore 
value: [0.9233279  0.90117253 0.93092105 0.90878939 0.89948893 0.9379085
 0.91666667 0.93532338 0.9291598  0.89678511]

mean value: 0.9179543249460512

key: test_precision 
value: [0.83783784 0.77142857 0.86111111 0.85714286 0.89285714 0.88235294
 0.82857143 0.8        0.86486486 0.86206897]

mean value: 0.8458235720507525

key: train_precision 
value: [0.88161994 0.88196721 0.89556962 0.88102894 0.89189189 0.894081
 0.88996764 0.90384615 0.8952381  0.88628763]

mean value: 0.8901498110788765

key: test_recall 
value: [0.96875    0.84375    0.96875    0.9375     0.75757576 0.90909091
 0.87878788 0.96969697 1.         0.78125   ]

mean value: 0.9015151515151515

key: train_recall 
value: [0.96917808 0.92123288 0.96917808 0.93835616 0.90721649 0.9862543
 0.94501718 0.96907216 0.96575342 0.90753425]

mean value: 0.9478793014169373

key: test_roc_auc 
value: [0.89346591 0.80066288 0.90861742 0.89299242 0.83191288 0.89204545
 0.84564394 0.85984848 0.921875   0.828125  ]

mean value: 0.8675189393939394

key: train_roc_auc 
value: [0.91929694 0.89876077 0.92788801 0.9056042  0.89881373 0.93490797
 0.91428941 0.93316622 0.92636986 0.89554795]

mean value: 0.9154645059549028

key: test_jcc 
value: [0.81578947 0.675      0.83783784 0.81081081 0.69444444 0.81081081
 0.74358974 0.7804878  0.86486486 0.69444444]

mean value: 0.7728080235365217

key: train_jcc 
value: [0.85757576 0.82012195 0.87076923 0.83282675 0.81733746 0.88307692
 0.84615385 0.87850467 0.86769231 0.81288344]

mean value: 0.848694233398827

MCC on Blind test: 0.14

Accuracy on Blind test: 0.84

Model_name: Logistic RegressionCV 
Model func: LogisticRegressionCV(random_state=42) 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegressionCV(random_state=42))])

key: fit_time 
value: [0.90877843 1.08433604 0.92330647 1.08300233 0.9151392  1.04889822
 0.93245006 0.86875296 1.00161505 0.90539241]

mean value: 0.9671671152114868

key: score_time 
value: [0.01495171 0.01587248 0.01561594 0.01560974 0.01577425 0.01564336
 0.01552153 0.01565456 0.01567936 0.01603079]

mean value: 0.015635371208190918

key: test_mcc 
value: [0.83005736 0.91168461 0.80403025 0.85663571 0.8291562  0.88340557
 0.91144345 0.80282704 0.91025899 0.91025899]

mean value: 0.864975816523865

key: train_mcc 
value: [0.98637038 0.98299141 0.9965753  0.98299141 0.9829924  0.90501954
 0.98637102 0.9829924  0.98302084 0.96963877]

mean value: 0.9758963474767732

key: test_accuracy 
value: [0.90769231 0.95384615 0.89230769 0.92307692 0.90769231 0.93846154
 0.95384615 0.89230769 0.953125   0.953125  ]

mean value: 0.927548076923077

key: train_accuracy 
value: [0.99313894 0.99142367 0.99828473 0.99142367 0.99142367 0.95025729
 0.99313894 0.99142367 0.99143836 0.98458904]

mean value: 0.9876541977020137

key: test_fscore 
value: [0.91428571 0.95522388 0.90140845 0.92753623 0.91666667 0.94285714
 0.95652174 0.90410959 0.95522388 0.95522388]

mean value: 0.9329057176360382

key: train_fscore 
value: [0.99319728 0.99151104 0.9982906  0.99151104 0.99148211 0.95253682
 0.99317406 0.99148211 0.99151104 0.98482293]

mean value: 0.9879519029578758

key: test_precision 
value: [0.84210526 0.91428571 0.82051282 0.86486486 0.84615385 0.89189189
 0.91666667 0.825      0.91428571 0.91428571]

mean value: 0.8750052496105127

key: train_precision 
value: [0.98648649 0.98316498 0.99658703 0.98316498 0.98310811 0.909375
 0.98644068 0.98310811 0.98316498 0.97009967]

mean value: 0.9764700028654564

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.90909091 0.95454545 0.89393939 0.92424242 0.90625    0.9375
 0.953125   0.890625   0.953125   0.953125  ]

mean value: 0.9275568181818181

key: train_roc_auc 
value: [0.99312715 0.99140893 0.99828179 0.99140893 0.99143836 0.95034247
 0.99315068 0.99143836 0.99143836 0.98458904]

mean value: 0.9876624064397684

key: test_jcc 
value: [0.84210526 0.91428571 0.82051282 0.86486486 0.84615385 0.89189189
 0.91666667 0.825      0.91428571 0.91428571]

mean value: 0.8750052496105127

key: train_jcc 
value: [0.98648649 0.98316498 0.99658703 0.98316498 0.98310811 0.909375
 0.98644068 0.98310811 0.98316498 0.97009967]

mean value: 0.9764700028654564

MCC on Blind test: 0.16

Accuracy on Blind test: 0.85

Model_name: Gaussian NB 
Model func: GaussianNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianNB())])

key: fit_time 
value: [0.01545978 0.01246405 0.01206279 0.01155329 0.01060367 0.01103735
 0.01092315 0.01169395 0.0106163  0.01166654]

mean value: 0.011808085441589355

key: score_time 
value: [0.01749396 0.01039648 0.00999808 0.00901794 0.00929117 0.00975037
 0.00987291 0.00955248 0.00957131 0.00920033]

mean value: 0.010414505004882812

key: test_mcc 
value: [0.25644061 0.2854836  0.37596584 0.36223597 0.15777548 0.39427936
 0.19102329 0.38201322 0.36084392 0.23294541]

mean value: 0.29990066967906026

key: train_mcc 
value: [0.32151626 0.31828836 0.29535681 0.30625707 0.334203   0.28995118
 0.32140204 0.27793285 0.29393809 0.33087981]

mean value: 0.30897254830127135

key: test_accuracy 
value: [0.61538462 0.63076923 0.66153846 0.66153846 0.56923077 0.67692308
 0.58461538 0.67692308 0.65625    0.609375  ]

mean value: 0.6342548076923077

key: train_accuracy 
value: [0.64493997 0.6432247  0.6329331  0.6380789  0.65180103 0.62950257
 0.64493997 0.62264151 0.63184932 0.6489726 ]

mean value: 0.6388883667379402

key: test_fscore 
value: [0.67532468 0.68421053 0.725      0.71794872 0.66666667 0.74074074
 0.6746988  0.73417722 0.725      0.66666667]

mean value: 0.7010434004033853

key: train_fscore 
value: [0.70886076 0.70786517 0.6994382  0.70323488 0.71123755 0.69662921
 0.70721358 0.69359331 0.69845722 0.7116737 ]

mean value: 0.7038203592837032

key: test_precision 
value: [0.57777778 0.59090909 0.60416667 0.60869565 0.54901961 0.625
 0.56       0.63043478 0.60416667 0.58139535]

mean value: 0.5931565593483157

key: train_precision 
value: [0.60143198 0.6        0.59285714 0.59665871 0.60679612 0.58907363
 0.60096154 0.58313817 0.59144893 0.60381862]

mean value: 0.5966184844322203

key: test_recall 
value: [0.8125     0.8125     0.90625    0.875      0.84848485 0.90909091
 0.84848485 0.87878788 0.90625    0.78125   ]

mean value: 0.8578598484848485

key: train_recall 
value: [0.8630137  0.8630137  0.85273973 0.85616438 0.85910653 0.85223368
 0.85910653 0.8556701  0.85273973 0.86643836]

mean value: 0.8580226427529069

key: test_roc_auc 
value: [0.61837121 0.63352273 0.66524621 0.66477273 0.56486742 0.67329545
 0.58049242 0.67376894 0.65625    0.609375  ]

mean value: 0.6339962121212122

key: train_roc_auc 
value: [0.64456527 0.64284706 0.63255543 0.63770418 0.652156   0.62988396
 0.64530669 0.62304053 0.63184932 0.6489726 ]

mean value: 0.638888104316716

key: test_jcc 
value: [0.50980392 0.52       0.56862745 0.56       0.5        0.58823529
 0.50909091 0.58       0.56862745 0.5       ]

mean value: 0.5404385026737968

key: train_jcc 
value: [0.54901961 0.54782609 0.53779698 0.54229935 0.55187638 0.53448276
 0.54704595 0.53091684 0.53663793 0.55240175]

mean value: 0.5430303632562989

MCC on Blind test: 0.17

Accuracy on Blind test: 0.52

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.01223683 0.01116037 0.01235414 0.0117898  0.01232171 0.01229382
 0.01193023 0.01210475 0.01213169 0.0121882 ]

mean value: 0.012051153182983398

key: score_time 
value: [0.01004934 0.00976443 0.01012945 0.00940299 0.01010704 0.01007462
 0.0100646  0.0102427  0.01002789 0.0095613 ]

mean value: 0.009942436218261718

key: test_mcc 
value: [0.48995593 0.48376972 0.58027158 0.45537869 0.26196226 0.47677747
 0.45226702 0.60621087 0.56572458 0.25      ]

mean value: 0.4622318107842896

key: train_mcc 
value: [0.53649056 0.51121673 0.51494469 0.47848196 0.50957754 0.50936987
 0.48520678 0.55458972 0.56624878 0.46021216]

mean value: 0.512633878870168

key: test_accuracy 
value: [0.73846154 0.73846154 0.78461538 0.72307692 0.63076923 0.73846154
 0.72307692 0.8        0.765625   0.625     ]

mean value: 0.7267548076923077

key: train_accuracy 
value: [0.76157804 0.75300172 0.75471698 0.73756432 0.75300172 0.75128645
 0.74099485 0.77186964 0.77910959 0.72945205]

mean value: 0.7532575365962546

key: test_fscore 
value: [0.76056338 0.75362319 0.8        0.74285714 0.65714286 0.74626866
 0.75       0.81690141 0.8        0.625     ]

mean value: 0.745235663385461

key: train_fscore 
value: [0.78582435 0.76996805 0.77192982 0.75282714 0.76623377 0.76947536
 0.75447154 0.79186228 0.79620853 0.73927393]

mean value: 0.7698074773053589

key: test_precision 
value: [0.69230769 0.7027027  0.73684211 0.68421053 0.62162162 0.73529412
 0.69230769 0.76315789 0.69767442 0.625     ]

mean value: 0.6951118771507209

key: train_precision 
value: [0.71428571 0.72155689 0.72238806 0.71253823 0.72615385 0.71597633
 0.71604938 0.72701149 0.73900293 0.7133758 ]

mean value: 0.7208338669727825

key: test_recall 
value: [0.84375    0.8125     0.875      0.8125     0.6969697  0.75757576
 0.81818182 0.87878788 0.9375     0.625     ]

mean value: 0.8057765151515152

key: train_recall 
value: [0.87328767 0.82534247 0.82876712 0.79794521 0.81099656 0.83161512
 0.79725086 0.86941581 0.8630137  0.76712329]

mean value: 0.8264757802570258

key: test_roc_auc 
value: [0.74005682 0.73958333 0.78598485 0.72443182 0.62973485 0.73816288
 0.72159091 0.79876894 0.765625   0.625     ]

mean value: 0.7268939393939394

key: train_roc_auc 
value: [0.7613861  0.75287742 0.75458975 0.73746058 0.75310102 0.751424
 0.74109118 0.77203667 0.77910959 0.72945205]

mean value: 0.7532528362284047

key: test_jcc 
value: [0.61363636 0.60465116 0.66666667 0.59090909 0.4893617  0.5952381
 0.6        0.69047619 0.66666667 0.45454545]

mean value: 0.5972151393056885

key: train_jcc 
value: [0.64720812 0.62597403 0.62857143 0.60362694 0.62105263 0.625323
 0.60574413 0.65544041 0.66141732 0.58638743]

mean value: 0.6260745445596777

MCC on Blind test: -0.02

Accuracy on Blind test: 0.67

Model_name: K-Nearest Neighbors 
Model func: KNeighborsClassifier() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', KNeighborsClassifier())])

key: fit_time 
value: [0.01140833 0.01143813 0.01133871 0.01092339 0.01160717 0.01178408
 0.01134562 0.0110085  0.01134205 0.01141167]

mean value: 0.011360764503479004

key: score_time 
value: [0.01732564 0.01302814 0.01386809 0.0133431  0.01397896 0.01555181
 0.01370358 0.01311135 0.01361513 0.01330614]

mean value: 0.014083194732666015

key: test_mcc 
value: [0.77849894 0.75341057 0.7287143  0.70436073 0.80282704 0.77695466
 0.80282704 0.726372   0.74898305 0.77459667]

mean value: 0.7597544989276062

key: train_mcc 
value: [0.83495806 0.83495806 0.83495806 0.8261068  0.8409798  0.82915171
 0.83801258 0.84395394 0.82937402 0.81475006]

mean value: 0.8327203083142081

key: test_accuracy 
value: [0.87692308 0.86153846 0.84615385 0.83076923 0.89230769 0.87692308
 0.89230769 0.84615385 0.859375   0.875     ]

mean value: 0.8657451923076923

key: train_accuracy 
value: [0.91080617 0.91080617 0.91080617 0.90566038 0.91423671 0.90737564
 0.91252144 0.91595197 0.90753425 0.8989726 ]

mean value: 0.9094671514838224

key: test_fscore 
value: [0.88888889 0.87671233 0.86486486 0.85333333 0.90410959 0.89189189
 0.90410959 0.86842105 0.87671233 0.88888889]

mean value: 0.8817932756115885

key: train_fscore 
value: [0.91823899 0.91823899 0.91823899 0.91392801 0.92088608 0.91509434
 0.91943128 0.92234548 0.9153605  0.90824261]

mean value: 0.9170005286524365

key: test_precision 
value: [0.8        0.7804878  0.76190476 0.74418605 0.825      0.80487805
 0.825      0.76744186 0.7804878  0.8       ]

mean value: 0.7889386327418092

key: train_precision 
value: [0.84883721 0.84883721 0.84883721 0.84149856 0.85337243 0.84347826
 0.85087719 0.85588235 0.84393064 0.83190883]

mean value: 0.8467459895542562

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.87878788 0.86363636 0.84848485 0.83333333 0.890625   0.875
 0.890625   0.84375    0.859375   0.875     ]

mean value: 0.8658617424242424

key: train_roc_auc 
value: [0.91065292 0.91065292 0.91065292 0.90549828 0.91438356 0.90753425
 0.91267123 0.91609589 0.90753425 0.8989726 ]

mean value: 0.9094648825495457

key: test_jcc 
value: [0.8        0.7804878  0.76190476 0.74418605 0.825      0.80487805
 0.825      0.76744186 0.7804878  0.8       ]

mean value: 0.7889386327418092

key: train_jcc 
value: [0.84883721 0.84883721 0.84883721 0.84149856 0.85337243 0.84347826
 0.85087719 0.85588235 0.84393064 0.83190883]

mean value: 0.8467459895542562

MCC on Blind test: 0.13

Accuracy on Blind test: 0.8

Model_name: SVM 
Model func: SVC(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SVC(random_state=42))])

key: fit_time 
value: [0.03128695 0.02532506 0.02574325 0.02931547 0.02702522 0.02704287
 0.02765894 0.02577305 0.02976561 0.02874804]

mean value: 0.027768445014953614

key: score_time 
value: [0.01834273 0.01343679 0.01319671 0.014539   0.01439404 0.01485848
 0.01382279 0.01383924 0.01469851 0.01513839]

mean value: 0.014626669883728027

key: test_mcc 
value: [0.82191818 0.76001241 0.83005736 0.91168461 0.66161167 0.75498882
 0.80282704 0.85599665 0.81892302 0.84748251]

mean value: 0.8065502266365774

key: train_mcc 
value: [0.89453522 0.89482954 0.92078242 0.9112794  0.87065471 0.89008731
 0.92080398 0.91130645 0.90221525 0.88163239]

mean value: 0.8998126672684504

key: test_accuracy 
value: [0.90769231 0.87692308 0.90769231 0.95384615 0.83076923 0.87692308
 0.89230769 0.92307692 0.90625    0.921875  ]

mean value: 0.8997355769230769

key: train_accuracy 
value: [0.94682676 0.94682676 0.95883362 0.95368782 0.9348199  0.94339623
 0.95883362 0.95368782 0.95034247 0.94006849]

mean value: 0.9487323480344932

key: test_fscore 
value: [0.91176471 0.88235294 0.91428571 0.95522388 0.8358209  0.88235294
 0.90410959 0.92957746 0.91176471 0.92537313]

mean value: 0.9052625972680951

key: train_fscore 
value: [0.9480737  0.94824708 0.96052632 0.95581015 0.93624161 0.94563427
 0.96039604 0.95566502 0.95174709 0.94176373]

mean value: 0.9504105000562539

key: test_precision 
value: [0.86111111 0.83333333 0.84210526 0.91428571 0.82352941 0.85714286
 0.825      0.86842105 0.86111111 0.88571429]

mean value: 0.8571754140252592

key: train_precision 
value: [0.92786885 0.92508143 0.92405063 0.9153605  0.9147541  0.90822785
 0.92380952 0.91509434 0.92556634 0.91585761]

mean value: 0.9195671178276714

key: test_recall 
value: [0.96875    0.9375     1.         1.         0.84848485 0.90909091
 1.         1.         0.96875    0.96875   ]

mean value: 0.9601325757575757

key: train_recall 
value: [0.96917808 0.97260274 1.         1.         0.95876289 0.9862543
 1.         1.         0.97945205 0.96917808]

mean value: 0.9835428141034694

key: test_roc_auc 
value: [0.90861742 0.87784091 0.90909091 0.95454545 0.83049242 0.87642045
 0.890625   0.921875   0.90625    0.921875  ]

mean value: 0.8997632575757576

key: train_roc_auc 
value: [0.94678835 0.94678247 0.95876289 0.95360825 0.9348609  0.94346961
 0.95890411 0.95376712 0.95034247 0.94006849]

mean value: 0.948735465800499

key: test_jcc 
value: [0.83783784 0.78947368 0.84210526 0.91428571 0.71794872 0.78947368
 0.825      0.86842105 0.83783784 0.86111111]

mean value: 0.8283494903231745

key: train_jcc 
value: [0.90127389 0.9015873  0.92405063 0.9153605  0.88012618 0.896875
 0.92380952 0.91509434 0.90793651 0.88993711]

mean value: 0.9056050982668623

MCC on Blind test: 0.06

Accuracy on Blind test: 0.86

Model_name: MLP 
Model func: MLPClassifier(max_iter=500, random_state=42) 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MLPClassifier(max_iter=500, random_state=42))])

key: fit_time 
value: [2.18314672 2.28263712 2.65899062 2.28563952 2.27962303 2.25674367
 2.29408383 2.22633529 2.51119161 2.24686193]

mean value: 2.3225253343582155

key: score_time 
value: [0.01327372 0.01348495 0.01395893 0.01341701 0.01356196 0.01372552
 0.01596761 0.01393604 0.01266432 0.0136652 ]

mean value: 0.013765525817871094

key: test_mcc 
value: [0.91168461 0.94028478 0.88382395 0.96969697 1.         0.96966868
 0.94017476 0.88340557 0.91025899 0.93933644]

mean value: 0.9348334754402028

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.95384615 0.96923077 0.93846154 0.98461538 1.         0.98461538
 0.96923077 0.93846154 0.953125   0.96875   ]

mean value: 0.9660336538461538

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.95522388 0.96969697 0.94117647 0.98461538 1.         0.98507463
 0.97058824 0.94285714 0.95522388 0.96969697]

mean value: 0.9674153560808522

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.91428571 0.94117647 0.88888889 0.96969697 1.         0.97058824
 0.94285714 0.89189189 0.91428571 0.94117647]

mean value: 0.937484749837691

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.95454545 0.96969697 0.93939394 0.98484848 1.         0.984375
 0.96875    0.9375     0.953125   0.96875   ]

mean value: 0.9660984848484848

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.91428571 0.94117647 0.88888889 0.96969697 1.         0.97058824
 0.94285714 0.89189189 0.91428571 0.94117647]

mean value: 0.937484749837691

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: -0.03

Accuracy on Blind test: 0.9

Model_name: Decision Tree 
Model func: DecisionTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', DecisionTreeClassifier(random_state=42))])

key: fit_time 
value: [0.03707814 0.02322769 0.02604532 0.02423859 0.02362657 0.02567816
 0.02197337 0.02380657 0.02512789 0.02368164]

mean value: 0.02544839382171631

key: score_time 
value: [0.01360416 0.00929117 0.00906825 0.00917315 0.00909305 0.00901937
 0.00930238 0.00913882 0.00945902 0.00979424]

mean value: 0.009694361686706543

key: test_mcc 
value: [0.94028478 0.88382395 0.91168461 0.91168461 0.96966868 0.96966868
 0.88340557 1.         0.91025899 0.93933644]

mean value: 0.931981632263633

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.96923077 0.93846154 0.95384615 0.95384615 0.98461538 0.98461538
 0.93846154 1.         0.953125   0.96875   ]

mean value: 0.9644951923076923

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.96969697 0.94117647 0.95522388 0.95522388 0.98507463 0.98507463
 0.94285714 1.         0.95522388 0.96969697]

mean value: 0.9659248448361706

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.94117647 0.88888889 0.91428571 0.91428571 0.97058824 0.97058824
 0.89189189 1.         0.91428571 0.94117647]

mean value: 0.934716733540263

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.96969697 0.93939394 0.95454545 0.95454545 0.984375   0.984375
 0.9375     1.         0.953125   0.96875   ]

mean value: 0.9646306818181818

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.94117647 0.88888889 0.91428571 0.91428571 0.97058824 0.97058824
 0.89189189 1.         0.91428571 0.94117647]

mean value: 0.934716733540263

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.48

Accuracy on Blind test: 0.93

Model_name: Extra Trees 
Model func: ExtraTreesClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreesClassifier(random_state=42))])

key: fit_time 
value: [0.13358879 0.12205267 0.1262114  0.11984611 0.12082458 0.12479711
 0.11570835 0.11744642 0.11740303 0.11682224]

mean value: 0.12147006988525391

key: score_time 
value: [0.01942182 0.01986265 0.01864624 0.01847601 0.01829982 0.01757264
 0.01755548 0.01779747 0.0176754  0.01778555]

mean value: 0.018309307098388673

key: test_mcc 
value: [1.         1.         0.96969697 1.         0.96966868 1.
 1.         1.         1.         1.        ]

mean value: 0.9939365651743151

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [1.         1.         0.98461538 1.         0.98461538 1.
 1.         1.         1.         1.        ]

mean value: 0.9969230769230769

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [1.         1.         0.98461538 1.         0.98507463 1.
 1.         1.         1.         1.        ]

mean value: 0.9969690011481056

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [1.         1.         0.96969697 1.         0.97058824 1.
 1.         1.         1.         1.        ]

mean value: 0.9940285204991087

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [1.         1.         0.98484848 1.         0.984375   1.
 1.         1.         1.         1.        ]

mean value: 0.9969223484848485

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [1.         1.         0.96969697 1.         0.97058824 1.
 1.         1.         1.         1.        ]

mean value: 0.9940285204991087

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.25

Accuracy on Blind test: 0.92

Model_name: Extra Tree 
Model func: ExtraTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreeClassifier(random_state=42))])

key: fit_time 
value: [0.01051712 0.01030684 0.01047754 0.01042056 0.01038265 0.01041913
 0.01030159 0.01033568 0.01053667 0.01035261]

mean value: 0.01040503978729248

key: score_time 
value: [0.00892711 0.00874567 0.00871015 0.00876093 0.00874233 0.00880003
 0.00875139 0.00870466 0.00875592 0.00865364]

mean value: 0.008755183219909668

key: test_mcc 
value: [0.88382395 0.85663571 0.91168461 0.94028478 0.88340557 0.96966868
 0.88340557 0.94017476 0.93933644 0.96922337]

mean value: 0.9177643443101774

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.93846154 0.92307692 0.95384615 0.96923077 0.93846154 0.98461538
 0.93846154 0.96923077 0.96875    0.984375  ]

mean value: 0.9568509615384615

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.94117647 0.92753623 0.95522388 0.96969697 0.94285714 0.98507463
 0.94285714 0.97058824 0.96969697 0.98461538]

mean value: 0.9589323054952708

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.88888889 0.86486486 0.91428571 0.94117647 0.89189189 0.97058824
 0.89189189 0.94285714 0.94117647 0.96969697]

mean value: 0.9217318540847953

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.93939394 0.92424242 0.95454545 0.96969697 0.9375     0.984375
 0.9375     0.96875    0.96875    0.984375  ]

mean value: 0.9569128787878788

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.88888889 0.86486486 0.91428571 0.94117647 0.89189189 0.97058824
 0.89189189 0.94285714 0.94117647 0.96969697]

mean value: 0.9217318540847953

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.13

Accuracy on Blind test: 0.89

Model_name: Random Forest 
Model func: RandomForestClassifier(n_estimators=1000, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(n_estimators=1000, random_state=42))])

key: fit_time 
value: [1.63671279 1.65234065 1.64184523 1.65016842 1.63577127 1.64149427
 1.63191724 1.64658523 1.72598886 1.7180469 ]

mean value: 1.6580870866775512

key: score_time 
value: [0.09241462 0.09176898 0.0915277  0.0922246  0.09221959 0.09200907
 0.09190392 0.09223509 0.10036016 0.10014153]

mean value: 0.0936805248260498

key: test_mcc 
value: [0.96969697 0.96969697 0.96969697 0.96969697 1.         1.
 1.         1.         1.         1.        ]

mean value: 0.9878787878787879

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.98461538 0.98461538 0.98461538 0.98461538 1.         1.
 1.         1.         1.         1.        ]

mean value: 0.9938461538461538

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.98461538 0.98461538 0.98461538 0.98461538 1.         1.
 1.         1.         1.         1.        ]

mean value: 0.9938461538461538

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.96969697 0.96969697 0.96969697 0.96969697 1.         1.
 1.         1.         1.         1.        ]

mean value: 0.9878787878787879

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.98484848 0.98484848 0.98484848 0.98484848 1.         1.
 1.         1.         1.         1.        ]

mean value: 0.9939393939393939

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.96969697 0.96969697 0.96969697 0.96969697 1.         1.
 1.         1.         1.         1.        ]

mean value: 0.9878787878787879

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.43

Accuracy on Blind test: 0.93

Model_name: Random Forest2 
Model func: RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...05', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                                        n_estimators=1000, n_jobs=10,
                                        oob_score=True, random_state=42))])

key: fit_time 
value: [0.92967677 0.99532008 0.99862313 0.95890355 0.99375582 0.94548011
 0.98106956 0.95519805 0.98804832 0.99921966]

mean value: 0.974529504776001

key: score_time 
value: [0.27825165 0.27401876 0.27683878 0.27235317 0.2824173  0.26008821
 0.28251076 0.22887921 0.25109577 0.34445214]

mean value: 0.2750905752182007

key: test_mcc 
value: [0.96969697 0.94028478 0.94028478 0.91168461 0.96966868 0.96966868
 0.94017476 1.         1.         1.        ]

mean value: 0.9641463266438918

key: train_mcc 
value: [0.98637038 0.98637038 0.98976061 0.98637038 0.9829924  0.9829924
 0.9829924  0.98637102 0.98302084 0.98639392]

mean value: 0.9853634757822509

key: test_accuracy 
value: [0.98461538 0.96923077 0.96923077 0.95384615 0.98461538 0.98461538
 0.96923077 1.         1.         1.        ]

mean value: 0.9815384615384616

key: train_accuracy 
value: [0.99313894 0.99313894 0.9948542  0.99313894 0.99142367 0.99142367
 0.99142367 0.99313894 0.99143836 0.99315068]

mean value: 0.9926270001644776

key: test_fscore 
value: [0.98461538 0.96969697 0.96969697 0.95522388 0.98507463 0.98507463
 0.97058824 1.         1.         1.        ]

mean value: 0.98199706936318

key: train_fscore 
value: [0.99319728 0.99319728 0.99488927 0.99319728 0.99148211 0.99148211
 0.99148211 0.99317406 0.99151104 0.99319728]

mean value: 0.9926809817503374

key: test_precision 
value: [0.96969697 0.94117647 0.94117647 0.91428571 0.97058824 0.97058824
 0.94285714 1.         1.         1.        ]

mean value: 0.9650369238604533

key: train_precision 
value: [0.98648649 0.98648649 0.98983051 0.98648649 0.98310811 0.98310811
 0.98310811 0.98644068 0.98316498 0.98648649]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(

mean value: 0.9854706439875931

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.98484848 0.96969697 0.96969697 0.95454545 0.984375   0.984375
 0.96875    1.         1.         1.        ]

mean value: 0.9816287878787879

key: train_roc_auc 
value: [0.99312715 0.99312715 0.99484536 0.99312715 0.99143836 0.99143836
 0.99143836 0.99315068 0.99143836 0.99315068]

mean value: 0.992628159864426

key: test_jcc 
value: [0.96969697 0.94117647 0.94117647 0.91428571 0.97058824 0.97058824
 0.94285714 1.         1.         1.        ]

mean value: 0.9650369238604533

key: train_jcc 
value: [0.98648649 0.98648649 0.98983051 0.98648649 0.98310811 0.98310811
 0.98310811 0.98644068 0.98316498 0.98648649]

mean value: 0.9854706439875931

MCC on Blind test: 0.5

Accuracy on Blind test: 0.94

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.02755857 0.01043534 0.01127267 0.01268649 0.01191759 0.01140356
 0.01057506 0.01046157 0.01179338 0.01609325]

mean value: 0.013419747352600098

key: score_time 
value: [0.01041055 0.00958514 0.00997567 0.00907445 0.00976348 0.00894403
 0.00899339 0.00947022 0.00984025 0.01062417]

mean value: 0.00966813564300537

key: test_mcc 
value: [0.48995593 0.48376972 0.58027158 0.45537869 0.26196226 0.47677747
 0.45226702 0.60621087 0.56572458 0.25      ]

mean value: 0.4622318107842896

key: train_mcc 
value: [0.53649056 0.51121673 0.51494469 0.47848196 0.50957754 0.50936987
 0.48520678 0.55458972 0.56624878 0.46021216]

mean value: 0.512633878870168

key: test_accuracy 
value: [0.73846154 0.73846154 0.78461538 0.72307692 0.63076923 0.73846154
 0.72307692 0.8        0.765625   0.625     ]

mean value: 0.7267548076923077

key: train_accuracy 
value: [0.76157804 0.75300172 0.75471698 0.73756432 0.75300172 0.75128645
 0.74099485 0.77186964 0.77910959 0.72945205]

mean value: 0.7532575365962546

key: test_fscore 
value: [0.76056338 0.75362319 0.8        0.74285714 0.65714286 0.74626866
 0.75       0.81690141 0.8        0.625     ]

mean value: 0.745235663385461

key: train_fscore 
value: [0.78582435 0.76996805 0.77192982 0.75282714 0.76623377 0.76947536
 0.75447154 0.79186228 0.79620853 0.73927393]

mean value: 0.7698074773053589

key: test_precision 
value: [0.69230769 0.7027027  0.73684211 0.68421053 0.62162162 0.73529412
 0.69230769 0.76315789 0.69767442 0.625     ]

mean value: 0.6951118771507209

key: train_precision 
value: [0.71428571 0.72155689 0.72238806 0.71253823 0.72615385 0.71597633
 0.71604938 0.72701149 0.73900293 0.7133758 ]

mean value: 0.7208338669727825

key: test_recall 
value: [0.84375    0.8125     0.875      0.8125     0.6969697  0.75757576
 0.81818182 0.87878788 0.9375     0.625     ]

mean value: 0.8057765151515152

key: train_recall 
value: [0.87328767 0.82534247 0.82876712 0.79794521 0.81099656 0.83161512
 0.79725086 0.86941581 0.8630137  0.76712329]

mean value: 0.8264757802570258

key: test_roc_auc 
value: [0.74005682 0.73958333 0.78598485 0.72443182 0.62973485 0.73816288
 0.72159091 0.79876894 0.765625   0.625     ]

mean value: 0.7268939393939394

key: train_roc_auc 
value: [0.7613861  0.75287742 0.75458975 0.73746058 0.75310102 0.751424
 0.74109118 0.77203667 0.77910959 0.72945205]

mean value: 0.7532528362284047

key: test_jcc 
value: [0.61363636 0.60465116 0.66666667 0.59090909 0.4893617  0.5952381
 0.6        0.69047619 0.66666667 0.45454545]

mean value: 0.5972151393056885

key: train_jcc 
value: [0.64720812 0.62597403 0.62857143 0.60362694 0.62105263 0.625323
 0.60574413 0.65544041 0.66141732 0.58638743]

mean value: 0.6260745445596777

MCC on Blind test: -0.02

Accuracy on Blind test: 0.67

Model_name: XGBoost 
Model func: XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...
                               interaction_constraints=None, learning_rate=None,
                               max_delta_step=None, max_depth=None,
                               min_child_weight=None, missing=nan,
                               monotone_constraints=None, n_estimators=100,
                               n_jobs=None, num_parallel_tree=None,
                               predictor=None, random_state=42, reg_alpha=None,
                               reg_lambda=None, scale_pos_weight=None,
                               subsample=None, tree_method=None,
                               use_label_encoder=False,
                               validate_parameters=None, verbosity=0))])

key: fit_time 
value: [0.10844421 0.08503509 0.08846307 0.09150386 0.08986807 0.08964157
 0.08758759 0.08932996 0.08448291 0.08964992]

mean value: 0.09040062427520752

key: score_time 
value: [0.01174879 0.01099372 0.01124406 0.01093197 0.01122189 0.01095152
 0.0110817  0.01111078 0.01102257 0.01106787]

mean value: 0.01113748550415039

key: test_mcc 
value: [0.94028478 0.94028478 0.91168461 0.94028478 1.         0.94017476
 0.94017476 0.94017476 0.93933644 0.93933644]

mean value: 0.9431736100079298

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.96923077 0.96923077 0.95384615 0.96923077 1.         0.96923077
 0.96923077 0.96923077 0.96875    0.96875   ]

mean value: 0.9706730769230769

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.96969697 0.96969697 0.95522388 0.96969697 1.         0.97058824
 0.97058824 0.97058824 0.96969697 0.96969697]

mean value: 0.9715473434964217

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.94117647 0.94117647 0.91428571 0.94117647 1.         0.94285714
 0.94285714 0.94285714 0.94117647 0.94117647]

mean value: 0.944873949579832

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.96969697 0.96969697 0.95454545 0.96969697 1.         0.96875
 0.96875    0.96875    0.96875    0.96875   ]

mean value: 0.9707386363636363

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.94117647 0.94117647 0.91428571 0.94117647 1.         0.94285714
 0.94285714 0.94285714 0.94117647 0.94117647]

mean value: 0.944873949579832

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.59

Accuracy on Blind test: 0.94

Model_name: LDA 
Model func: LinearDiscriminantAnalysis() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LinearDiscriminantAnalysis())])

key: fit_time 
value: [0.04615736 0.05584216 0.08481169 0.07877469 0.07154322 0.07837009
 0.07887888 0.07318735 0.07869864 0.07180595]

mean value: 0.07180700302124024

key: score_time 
value: [0.01233554 0.01888871 0.01950788 0.01950359 0.0196209  0.01934814
 0.01934981 0.02518988 0.01947403 0.01260424]

mean value: 0.01858227252960205

key: test_mcc 
value: [0.77849894 0.80403025 0.80403025 0.80403025 0.85599665 0.77695466
 0.8291562  0.80282704 0.82717019 0.8542422 ]

mean value: 0.8136936627043297

key: train_mcc 
value: [0.90812957 0.89561696 0.89873229 0.89561696 0.89254978 0.88021393
 0.88636547 0.90501954 0.88961286 0.89270548]

mean value: 0.8944562829288452

key: test_accuracy 
value: [0.87692308 0.89230769 0.89230769 0.89230769 0.92307692 0.87692308
 0.90769231 0.89230769 0.90625    0.921875  ]

mean value: 0.8981971153846154

key: train_accuracy 
value: [0.95197256 0.94511149 0.94682676 0.94511149 0.94339623 0.93653516
 0.93996569 0.95025729 0.94178082 0.94349315]

mean value: 0.9444450644986959

key: test_fscore 
value: [0.88888889 0.90140845 0.90140845 0.90140845 0.92957746 0.89189189
 0.91666667 0.90410959 0.91428571 0.92753623]

mean value: 0.9077181799559724

key: train_fscore 
value: [0.95424837 0.94805195 0.9495935  0.94805195 0.94634146 0.94022617
 0.94327391 0.95253682 0.94498382 0.9465154 ]

mean value: 0.9473823339437397

key: test_precision 
value: [0.8        0.82051282 0.82051282 0.82051282 0.86842105 0.80487805
 0.84615385 0.825      0.84210526 0.86486486]

mean value: 0.8312961537127134

key: train_precision 
value: [0.9125     0.90123457 0.90402477 0.90123457 0.89814815 0.88719512
 0.89263804 0.909375   0.89570552 0.89846154]

mean value: 0.9000517270447441

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.87878788 0.89393939 0.89393939 0.89393939 0.921875   0.875
 0.90625    0.890625   0.90625    0.921875  ]

mean value: 0.898248106060606

key: train_roc_auc 
value: [0.95189003 0.94501718 0.9467354  0.94501718 0.94349315 0.93664384
 0.94006849 0.95034247 0.94178082 0.94349315]

mean value: 0.9444481711622652

key: test_jcc 
value: [0.8        0.82051282 0.82051282 0.82051282 0.86842105 0.80487805
 0.84615385 0.825      0.84210526 0.86486486]

mean value: 0.8312961537127134

key: train_jcc 
value: [0.9125     0.90123457 0.90402477 0.90123457 0.89814815 0.88719512
 0.89263804 0.909375   0.89570552 0.89846154]

mean value: 0.9000517270447441

MCC on Blind test: 0.23

Accuracy on Blind test: 0.81

Model_name: Multinomial 
Model func: MultinomialNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MultinomialNB())])

key: fit_time 
value: [0.02369976 0.011307   0.01023698 0.01048636 0.01035714 0.01051974
 0.01058364 0.01071262 0.01042795 0.01046801]

mean value: 0.011879920959472656

key: score_time 
value: [0.00963831 0.00914049 0.00875711 0.00892735 0.00899673 0.00910401
 0.00921798 0.00900078 0.00888038 0.00884247]

mean value: 0.009050559997558594

key: test_mcc 
value: [ 0.14095468  0.20094796  0.29261364  0.08514868 -0.01825358  0.16872045
  0.16908576  0.3844697   0.25197632  0.21971769]

mean value: 0.1895381294153827

key: train_mcc 
value: [0.28874831 0.20459492 0.21469281 0.21802366 0.2118057  0.21506165
 0.2080758  0.20797801 0.2024839  0.18942669]

mean value: 0.21608914605820045

key: test_accuracy 
value: [0.56923077 0.6        0.64615385 0.53846154 0.49230769 0.58461538
 0.58461538 0.69230769 0.625      0.609375  ]

mean value: 0.5942067307692308

key: train_accuracy 
value: [0.64150943 0.60205832 0.60720412 0.60891938 0.60548885 0.60720412
 0.60377358 0.60377358 0.6010274  0.59417808]

mean value: 0.6075136868817407

key: test_fscore 
value: [0.58823529 0.60606061 0.64615385 0.59459459 0.53521127 0.59701493
 0.61971831 0.6969697  0.64705882 0.59016393]

mean value: 0.6121181298689955

key: train_fscore 
value: [0.67496112 0.61716172 0.61896839 0.6187291  0.62046205 0.62023217
 0.6156406  0.61435726 0.61359867 0.61463415]

mean value: 0.6228745218358442

key: test_precision 
value: [0.55555556 0.58823529 0.63636364 0.52380952 0.5        0.58823529
 0.57894737 0.6969697  0.61111111 0.62068966]

mean value: 0.5899917135638284

key: train_precision 
value: [0.61823362 0.5955414  0.60194175 0.60457516 0.5968254  0.59935897
 0.59677419 0.5974026  0.59485531 0.58513932]

mean value: 0.5990647716966054

key: test_recall 
value: [0.625      0.625      0.65625    0.6875     0.57575758 0.60606061
 0.66666667 0.6969697  0.6875     0.5625    ]

mean value: 0.6389204545454545

key: train_recall 
value: [0.74315068 0.64041096 0.6369863  0.63356164 0.64604811 0.64261168
 0.63573883 0.63230241 0.63356164 0.64726027]

mean value: 0.649163253777715

key: test_roc_auc 
value: [0.57007576 0.60037879 0.64630682 0.5407197  0.49100379 0.5842803
 0.58333333 0.69223485 0.625      0.609375  ]

mean value: 0.5942708333333333

key: train_roc_auc 
value: [0.64133479 0.60199242 0.60715294 0.60887704 0.6055583  0.60726475
 0.60382832 0.60382244 0.6010274  0.59417808]

mean value: 0.6075036482606034

key: test_jcc 
value: [0.41666667 0.43478261 0.47727273 0.42307692 0.36538462 0.42553191
 0.44897959 0.53488372 0.47826087 0.41860465]

mean value: 0.44234442894851767

key: train_jcc 
value: [0.50938967 0.44630072 0.44819277 0.44794189 0.44976077 0.44951923
 0.44471154 0.44337349 0.44258373 0.44366197]

mean value: 0.4525435779701462

MCC on Blind test: 0.07

Accuracy on Blind test: 0.64

Model_name: Passive Aggresive 
Model func: PassiveAggressiveClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 PassiveAggressiveClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.01718426 0.02882886 0.0270133  0.02619195 0.02331042 0.02439189
 0.0243485  0.0246799  0.02654791 0.02372336]

mean value: 0.024622035026550294

key: score_time 
value: [0.01066422 0.01161981 0.01200962 0.01207566 0.01204896 0.01204896
 0.01218057 0.01201391 0.01207614 0.01193047]

mean value: 0.01186683177947998

key: test_mcc 
value: [0.88382395 0.82191818 0.51733125 0.81706198 0.87844611 0.87844611
 0.8291562  0.63222777 0.87671401 0.75592895]

mean value: 0.7891054506982248

key: train_mcc 
value: [0.91443809 0.89453522 0.56671126 0.86645324 0.85247595 0.81994483
 0.83801258 0.8126848  0.8772269  0.86309468]

mean value: 0.8305577550283232

key: test_accuracy 
value: [0.93846154 0.90769231 0.73846154 0.90769231 0.93846154 0.93846154
 0.90769231 0.81538462 0.9375     0.875     ]

mean value: 0.8904807692307692

key: train_accuracy 
value: [0.95540309 0.94682676 0.74785592 0.93310463 0.9245283  0.90909091
 0.91252144 0.90566038 0.93835616 0.93150685]

mean value: 0.9104854437369299

key: test_fscore 
value: [0.94117647 0.91176471 0.66666667 0.90909091 0.94117647 0.94117647
 0.91666667 0.8125     0.93939394 0.86666667]

mean value: 0.8846278966131907

key: train_fscore 
value: [0.95737705 0.9480737  0.66817156 0.93401015 0.92763158 0.91181364
 0.91943128 0.90265487 0.93939394 0.93197279]

mean value: 0.9040530559130447

key: test_precision 
value: [0.88888889 0.86111111 0.89473684 0.88235294 0.91428571 0.91428571
 0.84615385 0.83870968 0.91176471 0.92857143]

mean value: 0.8880860869880145

key: train_precision 
value: [0.91823899 0.92786885 0.98013245 0.92307692 0.88958991 0.88387097
 0.85087719 0.93065693 0.92384106 0.92567568]

mean value: 0.9153828955249819

key: test_recall 
value: [1.         0.96875    0.53125    0.9375     0.96969697 0.96969697
 1.         0.78787879 0.96875    0.8125    ]

mean value: 0.8946022727272728

key: train_recall 
value: [1.         0.96917808 0.50684932 0.94520548 0.96907216 0.94158076
 1.         0.87628866 0.95547945 0.93835616]

mean value: 0.9102010073906699

key: test_roc_auc 
value: [0.93939394 0.90861742 0.73532197 0.90814394 0.93797348 0.93797348
 0.90625    0.81581439 0.9375     0.875     ]

mean value: 0.8901988636363637

key: train_roc_auc 
value: [0.95532646 0.94678835 0.74827002 0.93308384 0.92460458 0.90914654
 0.91267123 0.90561008 0.93835616 0.93150685]

mean value: 0.9105364119945394

key: test_jcc 
value: [0.88888889 0.83783784 0.5        0.83333333 0.88888889 0.88888889
 0.84615385 0.68421053 0.88571429 0.76470588]

mean value: 0.80186223783747

key: train_jcc 
value: [0.91823899 0.90127389 0.50169492 0.87619048 0.86503067 0.83792049
 0.85087719 0.82258065 0.88571429 0.87261146]

mean value: 0.8332133023475171

MCC on Blind test: 0.11

Accuracy on Blind test: 0.82

Model_name: Stochastic GDescent 
Model func: SGDClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SGDClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.02363205 0.02447152 0.02191973 0.02641821 0.02313209 0.02325821
 0.0232141  0.02433395 0.02130198 0.02686572]

mean value: 0.023854756355285646

key: score_time 
value: [0.01215982 0.01203179 0.01206779 0.01210499 0.01209164 0.01204705
 0.01207662 0.01209974 0.01202416 0.0123353 ]

mean value: 0.012103891372680664

key: test_mcc 
value: [0.85663571 0.65648795 0.72322307 0.88382395 0.65199287 0.70156076
 0.77695466 0.82126124 0.82717019 0.93933644]

mean value: 0.783844683661808

key: train_mcc 
value: [0.93036774 0.76284909 0.80724786 0.93036774 0.67196474 0.76585916
 0.79715541 0.85624651 0.89580642 0.90829511]

mean value: 0.8326159792673696

key: test_accuracy 
value: [0.92307692 0.8        0.86153846 0.93846154 0.81538462 0.83076923
 0.87692308 0.90769231 0.90625    0.96875   ]

mean value: 0.8828846153846154

key: train_accuracy 
value: [0.96397942 0.86792453 0.90051458 0.96397942 0.82504288 0.86963979
 0.88850772 0.92795883 0.94520548 0.95205479]

mean value: 0.9104807443783923

key: test_fscore 
value: [0.92753623 0.83116883 0.85714286 0.94117647 0.79310345 0.85714286
 0.89189189 0.91428571 0.91428571 0.96969697]

mean value: 0.8897430986362991

key: train_fscore 
value: [0.96528926 0.88350983 0.89416058 0.96528926 0.7992126  0.88449848
 0.89953632 0.92881356 0.94805195 0.95424837]

mean value: 0.912261020346296

key: test_precision 
value: [0.86486486 0.71111111 0.87096774 0.88888889 0.92       0.75
 0.80487805 0.86486486 0.84210526 0.94117647]

mean value: 0.8458857254191832

key: train_precision 
value: [0.93290735 0.79132791 0.95703125 0.93290735 0.93548387 0.79291553
 0.81741573 0.91638796 0.90123457 0.9125    ]

mean value: 0.8890111520172181

key: test_recall 
value: [1.         1.         0.84375    1.         0.6969697  1.
 1.         0.96969697 1.         1.        ]

mean value: 0.9510416666666667

key: train_recall 
value: [1.         1.         0.8390411  1.         0.6975945  1.
 1.         0.94158076 1.         1.        ]

mean value: 0.947821635362237

key: test_roc_auc 
value: [0.92424242 0.8030303  0.86126894 0.93939394 0.81723485 0.828125
 0.875      0.90672348 0.90625    0.96875   ]

mean value: 0.883001893939394

key: train_roc_auc 
value: [0.96391753 0.86769759 0.9006202  0.96391753 0.82482465 0.86986301
 0.88869863 0.92798216 0.94520548 0.95205479]

mean value: 0.9104781575107095

key: test_jcc 
value: [0.86486486 0.71111111 0.75       0.88888889 0.65714286 0.75
 0.80487805 0.84210526 0.84210526 0.94117647]

mean value: 0.8052272767692235

key: train_jcc 
value: [0.93290735 0.79132791 0.80858086 0.93290735 0.66557377 0.79291553
 0.81741573 0.86708861 0.90123457 0.9125    ]

mean value: 0.8422451675510767

MCC on Blind test: 0.15

Accuracy on Blind test: 0.85

Model_name: AdaBoost Classifier 
Model func: AdaBoostClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', AdaBoostClassifier(random_state=42))])

key: fit_time 
value: [0.19397855 0.18181181 0.17552853 0.17718291 0.17545128 0.17430711
 0.17631721 0.17823529 0.17496634 0.17720604]

mean value: 0.1784985065460205

key: score_time 
value: [0.01669073 0.01696658 0.01604557 0.01608968 0.01564956 0.01570296
 0.01739144 0.01585984 0.01708364 0.01639009]

mean value: 0.016387009620666505

key: test_mcc 
value: [0.94028478 0.96969697 0.88382395 0.85663571 1.         1.
 0.85599665 0.91144345 0.93933644 0.93933644]

mean value: 0.9296554387144098

key: train_mcc 
value: [1.         1.         0.99316221 0.9965753  1.         1.
 0.99657534 0.99657534 0.99317398 0.99658119]

mean value: 0.9972643368104748

key: test_accuracy 
value: [0.96923077 0.98461538 0.93846154 0.92307692 1.         1.
 0.92307692 0.95384615 0.96875    0.96875   ]

mean value: 0.9629807692307693

key: train_accuracy 
value: [1.         1.         0.99656947 0.99828473 1.         1.
 0.99828473 0.99828473 0.99657534 0.99828767]

mean value: 0.9986286684367583

key: test_fscore 
value: [0.96969697 0.98461538 0.94117647 0.92753623 1.         1.
 0.92957746 0.95652174 0.96969697 0.96969697]

mean value: 0.9648518200097754

key: train_fscore 
value: [1.         1.         0.99658703 0.9982906  1.         1.
 0.99828473 0.99828473 0.99658703 0.9982906 ]

mean value: 0.9986324726282225

key: test_precision 
value: [0.94117647 0.96969697 0.88888889 0.86486486 1.         1.
 0.86842105 0.91666667 0.94117647 0.94117647]

mean value: 0.9332067854513675

key: train_precision 
value: [1.         1.         0.99319728 0.99658703 1.         1.
 0.99657534 0.99657534 0.99319728 0.99658703]

mean value: 0.9972719304188084

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.96969697 0.98484848 0.93939394 0.92424242 1.         1.
 0.921875   0.953125   0.96875    0.96875   ]

mean value: 0.9630681818181819

key: train_roc_auc 
value: [1.         1.         0.99656357 0.99828179 1.         1.
 0.99828767 0.99828767 0.99657534 0.99828767]

mean value: 0.9986283716989126

key: test_jcc 
value: [0.94117647 0.96969697 0.88888889 0.86486486 1.         1.
 0.86842105 0.91666667 0.94117647 0.94117647]

mean value: 0.9332067854513675

key: train_jcc 
value: [1.         1.         0.99319728 0.99658703 1.         1.
 0.99657534 0.99657534 0.99319728 0.99658703]

mean value: 0.9972719304188084

MCC on Blind test: 0.42

Accuracy on Blind test: 0.91

Model_name: Bagging Classifier 
Model func: BaggingClassifier(n_jobs=10, oob_score=True, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 BaggingClassifier(n_jobs=10, oob_score=True,
                                   random_state=42))])

key: fit_time 
value: [0.07430029 0.09029365 0.07358122 0.0949266  0.07584715 0.09426451
 0.08750987 0.07840252 0.10559344 0.08741522]

mean value: 0.08621344566345215

key: score_time 
value: [0.02481437 0.02719188 0.03059793 0.03311348 0.03278923 0.02787757
 0.04202628 0.0372684  0.04019284 0.03482509]

mean value: 0.033069705963134764

key: test_mcc 
value: [0.94028478 0.88382395 0.94028478 0.85663571 0.96966868 0.96966868
 0.85599665 0.94017476 0.96922337 0.93933644]

mean value: 0.926509780022966

key: train_mcc 
value: [0.9965753  1.         1.         1.         1.         0.99316237
 0.99657534 1.         0.99658119 1.        ]

mean value: 0.9982894204384484

key: test_accuracy 
value: [0.96923077 0.93846154 0.96923077 0.92307692 0.98461538 0.98461538
 0.92307692 0.96923077 0.984375   0.96875   ]

mean value: 0.9614663461538462

key: train_accuracy 
value: [0.99828473 1.         1.         1.         1.         0.99656947
 0.99828473 1.         0.99828767 1.        ]

mean value: 0.9991426607768039

key: test_fscore 
value: [0.96969697 0.94117647 0.96969697 0.92753623 0.98507463 0.98507463
 0.92957746 0.97058824 0.98461538 0.96969697]

mean value: 0.963273394999278

key: train_fscore 
value: [0.9982906  1.         1.         1.         1.         0.99657534
 0.99828473 1.         0.9982906  1.        ]

mean value: 0.9991441273180741

key: test_precision 
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
[0.94117647 0.88888889 0.94117647 0.86486486 0.97058824 0.97058824
 0.86842105 0.94285714 0.96969697 0.94117647]

mean value: 0.9299434801292387

key: train_precision 
value: [0.99658703 1.         1.         1.         1.         0.99317406
 0.99657534 1.         0.99658703 1.        ]

mean value: 0.9982923465332647

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.96969697 0.93939394 0.96969697 0.92424242 0.984375   0.984375
 0.921875   0.96875    0.984375   0.96875   ]

mean value: 0.9615530303030303

key: train_roc_auc 
value: [0.99828179 1.         1.         1.         1.         0.99657534
 0.99828767 1.         0.99828767 1.        ]

mean value: 0.9991432471873087

key: test_jcc 
value: [0.94117647 0.88888889 0.94117647 0.86486486 0.97058824 0.97058824
 0.86842105 0.94285714 0.96969697 0.94117647]

mean value: 0.9299434801292387

key: train_jcc 
value: [0.99658703 1.         1.         1.         1.         0.99317406
 0.99657534 1.         0.99658703 1.        ]

mean value: 0.9982923465332647

MCC on Blind test: 0.61

Accuracy on Blind test: 0.94

Model_name: Gaussian Process 
Model func: GaussianProcessClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianProcessClassifier(random_state=42))])

key: fit_time 
value: [0.27155018 0.25940061 0.25496912 0.26945615 0.24079347 0.24282098
 0.32460666 0.34176469 0.30076313 0.28575492]

mean value: 0.2791879892349243

key: score_time 
value: [0.02793479 0.02761698 0.02729273 0.02815318 0.02801919 0.02736497
 0.03162336 0.02761865 0.02719116 0.02753568]

mean value: 0.028035068511962892

key: test_mcc 
value: [0.91168461 0.85663571 0.85663571 0.88382395 0.85599665 0.91144345
 0.91144345 0.85599665 0.8542422  0.8819171 ]

mean value: 0.8779819481039283

key: train_mcc 
value: [0.97292087 0.97626677 0.96958578 0.96958578 0.96958895 0.97292339
 0.9762687  0.96958895 0.97630797 0.96963877]

mean value: 0.9722675944372162

key: test_accuracy 
value: [0.95384615 0.92307692 0.92307692 0.93846154 0.92307692 0.95384615
 0.95384615 0.92307692 0.921875   0.9375    ]

mean value: 0.9351682692307692

key: train_accuracy 
value: [0.98627787 0.98799314 0.98456261 0.98456261 0.98456261 0.98627787
 0.98799314 0.98456261 0.9880137  0.98458904]

mean value: 0.9859395192556216

key: test_fscore 
value: [0.95522388 0.92753623 0.92753623 0.94117647 0.92957746 0.95652174
 0.95652174 0.92957746 0.92753623 0.94117647]

mean value: 0.9392383925263994

key: train_fscore 
value: [0.98648649 0.98815567 0.98482293 0.98482293 0.98477157 0.98644068
 0.98811545 0.98477157 0.98815567 0.98482293]

mean value: 0.9861365900991393

key: test_precision 
value: [0.91428571 0.86486486 0.86486486 0.88888889 0.86842105 0.91666667
 0.91666667 0.86842105 0.86486486 0.88888889]

mean value: 0.8856833525254578

key: train_precision 
value: [0.97333333 0.97658863 0.97009967 0.97009967 0.97       0.97324415
 0.97651007 0.97       0.97658863 0.97009967]

mean value: 0.9726563808451961

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.95454545 0.92424242 0.92424242 0.93939394 0.921875   0.953125
 0.953125   0.921875   0.921875   0.9375    ]

mean value: 0.9351799242424242

key: train_roc_auc 
value: [0.9862543  0.98797251 0.98453608 0.98453608 0.98458904 0.98630137
 0.9880137  0.98458904 0.9880137  0.98458904]

mean value: 0.9859394859483124

key: test_jcc 
value: [0.91428571 0.86486486 0.86486486 0.88888889 0.86842105 0.91666667
 0.91666667 0.86842105 0.86486486 0.88888889]

mean value: 0.8856833525254578

key: train_jcc 
value: [0.97333333 0.97658863 0.97009967 0.97009967 0.97       0.97324415
 0.97651007 0.97       0.97658863 0.97009967]

mean value: 0.9726563808451961

MCC on Blind test: 0.13

Accuracy on Blind test: 0.86

Model_name: Gradient Boosting 
Model func: GradientBoostingClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GradientBoostingClassifier(random_state=42))])

key: fit_time 
value: [0.66747928 0.66300654 0.66241717 0.66650558 0.66270304 0.66195035
 0.66654229 0.66814399 0.66283178 0.671103  ]

mean value: 0.6652683019638062

key: score_time 
value: [0.00973463 0.00922108 0.00999546 0.00918174 0.00936985 0.00978279
 0.00936556 0.00937557 0.00943875 0.00966763]

mean value: 0.009513306617736816

key: test_mcc 
value: [0.91168461 0.94028478 0.91168461 0.88382395 0.94017476 0.94017476
 0.85599665 0.91144345 0.96922337 0.93933644]

mean value: 0.9203827378351209

key: train_mcc 
value: [1.         1.         1.         1.         1.         1.
 0.99657534 1.         1.         1.        ]

mean value: 0.9996575342465753

key: test_accuracy 
value: [0.95384615 0.96923077 0.95384615 0.93846154 0.96923077 0.96923077
 0.92307692 0.95384615 0.984375   0.96875   ]

mean value: 0.9583894230769231

key: train_accuracy 
value: [1.         1.         1.         1.         1.         1.
 0.99828473 1.         1.         1.        ]

mean value: 0.9998284734133791

key: test_fscore 
value: [0.95522388 0.96969697 0.95522388 0.94117647 0.97058824 0.97058824
 0.92957746 0.95652174 0.98461538 0.96969697]

mean value: 0.9602909230298992

key: train_fscore 
value: [1.         1.         1.         1.         1.         1.
 0.99828473 1.         1.         1.        ]

mean value: 0.9998284734133791

key: test_precision 
value: [0.91428571 0.94117647 0.91428571 0.88888889 0.94285714 0.94285714
 0.86842105 0.91666667 0.96969697 0.94117647]

mean value: 0.9240312233346288

key: train_precision 
value: [1.         1.         1.         1.         1.         1.
 0.99657534 1.         1.         1.        ]

mean value: 0.9996575342465753

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.95454545 0.96969697 0.95454545 0.93939394 0.96875    0.96875
 0.921875   0.953125   0.984375   0.96875   ]

mean value: 0.9583806818181818

key: train_roc_auc 
value: [1.         1.         1.         1.         1.         1.
 0.99828767 1.         1.         1.        ]

mean value: 0.9998287671232877

key: test_jcc 
value: [0.91428571 0.94117647 0.91428571 0.88888889 0.94285714 0.94285714
 0.86842105 0.91666667 0.96969697 0.94117647]

mean value: 0.9240312233346288

key: train_jcc 
value: [1.         1.         1.         1.         1.         1.
 0.99657534 1.         1.         1.        ]

mean value: 0.9996575342465753

MCC on Blind test: 0.68

Accuracy on Blind test: 0.95

Model_name: QDA 
Model func: QuadraticDiscriminantAnalysis() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', QuadraticDiscriminantAnalysis())])

key: fit_time 
value: [0.05285525 0.03185368 0.03243399 0.07518172 0.05158687 0.03198195
 0.03169084 0.03252506 0.03148723 0.03149414]

mean value: 0.04030907154083252

key: score_time 
value: [0.01653838 0.01347303 0.02548623 0.01562452 0.04300427 0.0165596
 0.01636672 0.01792932 0.01616859 0.01604056]

mean value: 0.01971912384033203

key: test_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Ridge Classifier 
Model func: RidgeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifier(random_state=42))])

key: fit_time 
value: [0.02495313 0.03276992 0.03482652 0.03015947 0.03297901 0.03607106
 0.01609159 0.01607418 0.01609254 0.01599169]

mean value: 0.025600910186767578

key: score_time 
value: [0.02951288 0.03466558 0.03318357 0.02238131 0.01504588 0.01208234
 0.01223898 0.01208282 0.01231861 0.01204729]

mean value: 0.01955592632293701

key: test_mcc 
value: [0.80403025 0.83005736 0.80403025 0.83005736 0.88340557 0.88340557
 0.80282704 0.75148662 0.8542422  0.8819171 ]

mean value: 0.8325459320466057

key: train_mcc 
value: [0.89561696 0.89251003 0.89873229 0.88016448 0.89876756 0.87715022
 0.88945349 0.89565444 0.880384   0.89270548]

mean value: 0.8901138939292129

key: test_accuracy 
value: [0.89230769 0.90769231 0.89230769 0.90769231 0.93846154 0.93846154
 0.89230769 0.86153846 0.921875   0.9375    ]

mean value: 0.909014423076923

key: train_accuracy 
value: [0.94511149 0.94339623 0.94682676 0.93653516 0.94682676 0.9348199
 0.94168096 0.94511149 0.93664384 0.94349315]

mean value: 0.9420445734157288

key: test_fscore 
value: [0.90140845 0.91428571 0.90140845 0.91428571 0.94285714 0.94285714
 0.90410959 0.88       0.92753623 0.94117647]

mean value: 0.9169924907207554

key: train_fscore 
value: [0.94805195 0.9465154  0.9495935  0.94041868 0.94942904 0.93870968
 0.94480519 0.94788274 0.94041868 0.9465154 ]

mean value: 0.9452340243151744

key: test_precision 
value: [0.82051282 0.84210526 0.82051282 0.84210526 0.89189189 0.89189189
 0.825      0.78571429 0.86486486 0.88888889]

mean value: 0.8473487990593254

key: train_precision 
value: [0.90123457 0.89846154 0.90402477 0.88753799 0.90372671 0.88449848
 0.89538462 0.90092879 0.88753799 0.89846154]

mean value: 0.8961796996740085

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.89393939 0.90909091 0.89393939 0.90909091 0.9375     0.9375
 0.890625   0.859375   0.921875   0.9375    ]

mean value: 0.9090435606060606

key: train_roc_auc 
value: [0.94501718 0.94329897 0.9467354  0.93642612 0.94691781 0.93493151
 0.94178082 0.94520548 0.93664384 0.94349315]

mean value: 0.9420450265969966

key: test_jcc 
value: [0.82051282 0.84210526 0.82051282 0.84210526 0.89189189 0.89189189
 0.825      0.78571429 0.86486486 0.88888889]

mean value: 0.8473487990593254

key: train_jcc 
value: [0.90123457 0.89846154 0.90402477 0.88753799 0.90372671 0.88449848
 0.89538462 0.90092879 0.88753799 0.89846154]

mean value: 0.8961796996740085

MCC on Blind test: 0.15
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:156: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:159: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)

Accuracy on Blind test: 0.82

Model_name: Ridge ClassifierCV 
Model func: RidgeClassifierCV(cv=10) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifierCV(cv=10))])

key: fit_time 
value: [0.34018302 0.18146539 0.37531209 0.29439926 0.30365586 0.16771746
 0.29330492 0.38020229 0.25970268 0.27999401]

mean value: 0.2875936985015869

key: score_time 
value: [0.01881671 0.0188117  0.01892161 0.0187993  0.01901221 0.02461314
 0.02011442 0.02335548 0.01998448 0.01883245]

mean value: 0.020126152038574218

key: test_mcc 
value: [0.80403025 0.83005736 0.80403025 0.83005736 0.8291562  0.8291562
 0.80282704 0.75148662 0.8542422  0.8819171 ]

mean value: 0.8216960570778064

key: train_mcc 
value: [0.89561696 0.89251003 0.89873229 0.88016448 0.90188922 0.87715022
 0.88945349 0.89565444 0.880384   0.88961286]

mean value: 0.8901167987912053

key: test_accuracy 
value: [0.89230769 0.90769231 0.89230769 0.90769231 0.90769231 0.90769231
 0.89230769 0.86153846 0.921875   0.9375    ]

mean value: 0.902860576923077

key: train_accuracy 
value: [0.94511149 0.94339623 0.94682676 0.93653516 0.94854202 0.9348199
 0.94168096 0.94511149 0.93664384 0.94178082]

mean value: 0.9420448671256374

key: test_fscore 
value: [0.90140845 0.91428571 0.90140845 0.91428571 0.91666667 0.91666667
 0.90410959 0.88       0.92753623 0.94117647]

mean value: 0.9117543954826601

key: train_fscore 
value: [0.94805195 0.9465154  0.9495935  0.94041868 0.95098039 0.93870968
 0.94480519 0.94788274 0.94041868 0.94498382]

mean value: 0.9452360019475785

key: test_precision 
value: [0.82051282 0.84210526 0.82051282 0.84210526 0.84615385 0.84615385
 0.825      0.78571429 0.86486486 0.88888889]

mean value: 0.8382011899117162

key: train_precision 
value: [0.90123457 0.89846154 0.90402477 0.88753799 0.90654206 0.88449848
 0.89538462 0.90092879 0.88753799 0.89570552]

mean value: 0.8961856327751171

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.89393939 0.90909091 0.89393939 0.90909091 0.90625    0.90625
 0.890625   0.859375   0.921875   0.9375    ]

mean value: 0.9027935606060606

key: train_roc_auc 
value: [0.94501718 0.94329897 0.9467354  0.93642612 0.94863014 0.93493151
 0.94178082 0.94520548 0.93664384 0.94178082]

mean value: 0.9420450265969966

key: test_jcc 
value: [0.82051282 0.84210526 0.82051282 0.84210526 0.84615385 0.84615385
 0.825      0.78571429 0.86486486 0.88888889]

mean value: 0.8382011899117162

key: train_jcc 
value: [0.90123457 0.89846154 0.90402477 0.88753799 0.90654206 0.88449848
 0.89538462 0.90092879 0.88753799 0.89570552]

mean value: 0.8961856327751171

MCC on Blind test: 0.15

Accuracy on Blind test: 0.82

Model_name: Logistic Regression 
Model func: LogisticRegression(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegression(random_state=42))])

key: fit_time 
value: [0.02396894 0.0223031  0.02217841 0.03229809 0.02249241 0.02261591
 0.02235079 0.02054095 0.01664996 0.02182865]

mean value: 0.022722721099853516

key: score_time 
value: [0.01181579 0.01145673 0.01170659 0.01176095 0.01151729 0.01139402
 0.01149249 0.01147747 0.01145816 0.01144385]

mean value: 0.01155233383178711

key: test_mcc 
value: [ 0.41666667  1.          0.          0.4472136  -0.33333333  0.33333333
 -0.33333333  0.33333333  0.4472136   0.        ]

mean value: 0.23110938576665827

key: train_mcc 
value: [0.96428571 0.92962225 0.85933785 0.89342711 0.93094934 0.93094934
 0.82618439 0.96490128 0.85714286 0.93094934]

mean value: 0.9087749463776217

key: test_accuracy 
value: [0.71428571 1.         0.5        0.66666667 0.33333333 0.66666667
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.6047619047619047

key: train_accuracy 
value: [0.98181818 0.96363636 0.92857143 0.94642857 0.96428571 0.96428571
 0.91071429 0.98214286 0.92857143 0.96428571]

mean value: 0.953474025974026

key: test_fscore 
value: [0.66666667 1.         0.         0.75       0.33333333 0.66666667
 0.33333333 0.66666667 0.75       0.4       ]

mean value: 0.5566666666666666

key: train_fscore 
value: [0.98181818 0.96153846 0.92592593 0.94545455 0.96296296 0.96296296
 0.90566038 0.98181818 0.92857143 0.96296296]

mean value: 0.9519675991374105

key: test_precision 
value: [0.66666667 1.         0.         0.6        0.33333333 0.66666667
 0.33333333 0.66666667 0.6        0.5       ]

mean value: 0.5366666666666666

key: train_precision 
value: [1.         1.         0.96153846 0.96296296 1.         1.
 0.96       1.         0.92857143 1.        ]

mean value: 0.9813072853072853

key: test_recall 
value: [0.66666667 1.         0.         1.         0.33333333 0.66666667
 0.33333333 0.66666667 1.         0.33333333]

mean value: 0.6

key: train_recall 
value: [0.96428571 0.92592593 0.89285714 0.92857143 0.92857143 0.92857143
 0.85714286 0.96428571 0.92857143 0.92857143]

mean value: 0.9247354497354497

key: test_roc_auc 
value: [0.70833333 1.         0.5        0.66666667 0.33333333 0.66666667
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.6041666666666667

key: train_roc_auc 
value: [0.98214286 0.96296296 0.92857143 0.94642857 0.96428571 0.96428571
 0.91071429 0.98214286 0.92857143 0.96428571]

mean value: 0.9534391534391535

key: test_jcc 
value: [0.5  1.   0.   0.6  0.2  0.5  0.2  0.5  0.6  0.25]

mean value: 0.435

key: train_jcc 
value: [0.96428571 0.92592593 0.86206897 0.89655172 0.92857143 0.92857143
 0.82758621 0.96428571 0.86666667 0.92857143]

mean value: 0.9093085203430031

MCC on Blind test: 0.07

Accuracy on Blind test: 0.64

Model_name: Logistic RegressionCV 
Model func: LogisticRegressionCV(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegressionCV(random_state=42))])

key: fit_time 
value: [0.32889199 0.33602214 0.34544158 0.34122992 0.33867097 0.31434894
 0.33713484 0.35255051 0.32593322 0.31751704]

mean value: 0.33377411365509035

key: score_time 
value: [0.01181865 0.01170731 0.01156902 0.01187563 0.01192331 0.01150537
 0.01207972 0.01224923 0.01184177 0.01186705]

mean value: 0.011843705177307129

key: test_mcc 
value: [ 0.16666667  0.41666667  0.4472136   0.4472136  -0.33333333  0.33333333
  0.          0.33333333  0.          0.        ]

mean value: 0.18110938576665825

key: train_mcc 
value: [1.         0.49137176 0.53881591 0.78571429 0.78772636 0.4645821
 0.75434227 1.         0.71611487 0.67900461]

mean value: 0.7217672161232106

key: test_accuracy 
value: [0.57142857 0.71428571 0.66666667 0.66666667 0.33333333 0.66666667
 0.5        0.66666667 0.5        0.5       ]

mean value: 0.5785714285714285

key: train_accuracy 
value: [1.         0.74545455 0.76785714 0.89285714 0.89285714 0.73214286
 0.875      1.         0.85714286 0.83928571]

mean value: 0.8602597402597403

key: test_fscore 
value: [0.57142857 0.75       0.5        0.75       0.33333333 0.66666667
 0.57142857 0.66666667 0.57142857 0.4       ]

mean value: 0.5780952380952381

key: train_fscore 
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
[1.         0.73076923 0.75471698 0.89285714 0.88888889 0.73684211
 0.86792453 1.         0.85185185 0.83636364]

mean value: 0.8560214365427872

key: test_precision 
value: [0.5        0.75       1.         0.6        0.33333333 0.66666667
 0.5        0.66666667 0.5        0.5       ]

mean value: 0.6016666666666667

key: train_precision 
value: [1.         0.76       0.8        0.89285714 0.92307692 0.72413793
 0.92       1.         0.88461538 0.85185185]

mean value: 0.8756539233435785

key: test_recall 
value: [0.66666667 0.75       0.33333333 1.         0.33333333 0.66666667
 0.66666667 0.66666667 0.66666667 0.33333333]

mean value: 0.6083333333333333

key: train_recall 
value: [1.         0.7037037  0.71428571 0.89285714 0.85714286 0.75
 0.82142857 1.         0.82142857 0.82142857]

mean value: 0.8382275132275132

key: test_roc_auc 
value: [0.58333333 0.70833333 0.66666667 0.66666667 0.33333333 0.66666667
 0.5        0.66666667 0.5        0.5       ]

mean value: 0.5791666666666667

key: train_roc_auc 
value: [1.         0.74470899 0.76785714 0.89285714 0.89285714 0.73214286
 0.875      1.         0.85714286 0.83928571]

mean value: 0.8601851851851852

key: test_jcc 
value: [0.4        0.6        0.33333333 0.6        0.2        0.5
 0.4        0.5        0.4        0.25      ]

mean value: 0.41833333333333333

key: train_jcc 
value: [1.         0.57575758 0.60606061 0.80645161 0.8        0.58333333
 0.76666667 1.         0.74193548 0.71875   ]

mean value: 0.7598955278592375

MCC on Blind test: 0.08

Accuracy on Blind test: 0.61

Model_name: Gaussian NB 
Model func: GaussianNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianNB())])

key: fit_time 
value: [0.01173186 0.01130199 0.00886393 0.00986314 0.00898957 0.00813222
 0.00887823 0.00830531 0.00812173 0.00822043]

mean value: 0.009240841865539551

key: score_time 
value: [0.0114758  0.01065803 0.0090661  0.00906229 0.00914812 0.00877452
 0.00836682 0.00837493 0.00841379 0.00833344]

mean value: 0.00916738510131836

key: test_mcc 
value: [ 0.41666667 -0.35355339  0.          0.70710678  0.          0.33333333
 -0.33333333  0.          0.70710678  0.        ]

mean value: 0.1477326838446488

key: train_mcc 
value: [0.60000053 0.43988592 0.57142857 0.55328334 0.57735027 0.60753044
 0.60753044 0.59628479 0.5728919  0.67900461]

mean value: 0.5805190792911584

key: test_accuracy 
value: [0.71428571 0.42857143 0.5        0.83333333 0.5        0.66666667
 0.33333333 0.5        0.83333333 0.5       ]

mean value: 0.580952380952381

key: train_accuracy 
value: [0.8        0.70909091 0.78571429 0.76785714 0.78571429 0.80357143
 0.80357143 0.78571429 0.78571429 0.83928571]

mean value: 0.7866233766233767

key: test_fscore 
value: [0.66666667 0.6        0.         0.8        0.57142857 0.66666667
 0.33333333 0.4        0.85714286 0.57142857]

mean value: 0.5466666666666666

key: train_fscore 
value: [0.80701754 0.74193548 0.78571429 0.73469388 0.8        0.8
 0.8        0.75       0.77777778 0.83636364]

mean value: 0.7833502605137337

key: test_precision 
value: [0.66666667 0.5        0.         1.         0.5        0.66666667
 0.33333333 0.5        0.75       0.5       ]

mean value: 0.5416666666666666

key: train_precision 
value: [0.79310345 0.65714286 0.78571429 0.85714286 0.75       0.81481481
 0.81481481 0.9        0.80769231 0.85185185]

mean value: 0.8032277237449651

key: test_recall 
value: [0.66666667 0.75       0.         0.66666667 0.66666667 0.66666667
 0.33333333 0.33333333 1.         0.66666667]

mean value: 0.575

key: train_recall 
value: [0.82142857 0.85185185 0.78571429 0.64285714 0.85714286 0.78571429
 0.78571429 0.64285714 0.75       0.82142857]

mean value: 0.7744708994708994

key: test_roc_auc 
value: [0.70833333 0.375      0.5        0.83333333 0.5        0.66666667
 0.33333333 0.5        0.83333333 0.5       ]

mean value: 0.575

key: train_roc_auc 
value: [0.79960317 0.71164021 0.78571429 0.76785714 0.78571429 0.80357143
 0.80357143 0.78571429 0.78571429 0.83928571]

mean value: 0.7868386243386243

key: test_jcc 
value: [0.5        0.42857143 0.         0.66666667 0.4        0.5
 0.2        0.25       0.75       0.4       ]

mean value: 0.4095238095238095

key: train_jcc 
value: [0.67647059 0.58974359 0.64705882 0.58064516 0.66666667 0.66666667
 0.66666667 0.6        0.63636364 0.71875   ]

mean value: 0.6449031799162255

MCC on Blind test: 0.07

Accuracy on Blind test: 0.63

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.00949311 0.00893927 0.0097723  0.00839043 0.00929689 0.00841403
 0.00832248 0.00839972 0.00833035 0.00838971]

mean value: 0.008774828910827637

key: score_time 
value: [0.00858164 0.00839567 0.00912952 0.00850058 0.00905252 0.00845599
 0.00843596 0.00837421 0.00845122 0.00839138]

mean value: 0.00857686996459961

key: test_mcc 
value: [ 0.41666667  0.41666667  0.4472136   0.70710678  0.4472136   0.4472136
 -0.33333333  0.33333333  0.         -0.33333333]

mean value: 0.25487475676864213

key: train_mcc 
value: [0.68300095 0.56441351 0.64285714 0.5728919  0.67900461 0.64450339
 0.68965631 0.71428571 0.71611487 0.71611487]

mean value: 0.6622843266212062

key: test_accuracy 
value: [0.71428571 0.71428571 0.66666667 0.83333333 0.66666667 0.66666667
 0.33333333 0.66666667 0.5        0.33333333]

mean value: 0.6095238095238095

key: train_accuracy 
value: [0.83636364 0.78181818 0.82142857 0.78571429 0.83928571 0.82142857
 0.83928571 0.85714286 0.85714286 0.85714286]

mean value: 0.8296753246753247

key: test_fscore 
value: [0.66666667 0.75       0.5        0.85714286 0.75       0.75
 0.33333333 0.66666667 0.57142857 0.33333333]

mean value: 0.6178571428571429

key: train_fscore 
value: [0.85245902 0.76923077 0.82142857 0.79310345 0.84210526 0.82758621
 0.82352941 0.85714286 0.86206897 0.85185185]

mean value: 0.8300506361659747

key: test_precision 
value: [0.66666667 0.75       1.         0.75       0.6        0.6
 0.33333333 0.66666667 0.5        0.33333333]

mean value: 0.62

key: train_precision 
value: [0.78787879 0.8        0.82142857 0.76666667 0.82758621 0.8
 0.91304348 0.85714286 0.83333333 0.88461538]

mean value: 0.8291695286223022

key: test_recall 
value: [0.66666667 0.75       0.33333333 1.         1.         1.
 0.33333333 0.66666667 0.66666667 0.33333333]

mean value: 0.6749999999999999

key: train_recall 
value: [0.92857143 0.74074074 0.82142857 0.82142857 0.85714286 0.85714286
 0.75       0.85714286 0.89285714 0.82142857]

mean value: 0.8347883597883597

key: test_roc_auc 
value: [0.70833333 0.70833333 0.66666667 0.83333333 0.66666667 0.66666667
 0.33333333 0.66666667 0.5        0.33333333]

mean value: 0.6083333333333334

key: train_roc_auc 
value: [0.83465608 0.78108466 0.82142857 0.78571429 0.83928571 0.82142857
 0.83928571 0.85714286 0.85714286 0.85714286]

mean value: 0.8294312169312169

key: test_jcc 
value: [0.5        0.6        0.33333333 0.75       0.6        0.6
 0.2        0.5        0.4        0.2       ]

mean value: 0.4683333333333333

key: train_jcc 
value: [0.74285714 0.625      0.6969697  0.65714286 0.72727273 0.70588235
 0.7        0.75       0.75757576 0.74193548]

mean value: 0.7104636018630326

MCC on Blind test: 0.04

Accuracy on Blind test: 0.53

Model_name: K-Nearest Neighbors 
Model func: KNeighborsClassifier() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', KNeighborsClassifier())])

key: fit_time 
value: [0.00823832 0.00921917 0.00909948 0.00909138 0.0088973  0.00892854
 0.00888276 0.00916386 0.00911903 0.00909925]

mean value: 0.008973908424377442

key: score_time 
value: [0.01347995 0.0096941  0.00983119 0.01004624 0.00997066 0.00994253
 0.00993466 0.01037478 0.00993657 0.00979114]

mean value: 0.010300183296203613

key: test_mcc 
value: [ 0.41666667  0.41666667  0.4472136   0.70710678  0.          0.33333333
 -0.4472136   0.33333333  0.4472136   0.        ]

mean value: 0.26543203766865053

key: train_mcc 
value: [0.46737879 0.41798942 0.35805744 0.42857143 0.42966892 0.4330127
 0.5728919  0.39310793 0.53605627 0.54446551]

mean value: 0.4581200301811864

key: test_accuracy 
value: [0.71428571 0.71428571 0.66666667 0.83333333 0.5        0.66666667
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.6261904761904762

key: train_accuracy 
value: [0.72727273 0.70909091 0.67857143 0.71428571 0.71428571 0.71428571
 0.78571429 0.69642857 0.76785714 0.76785714]

mean value: 0.7275649350649351

key: test_fscore 
value: [0.66666667 0.75       0.5        0.85714286 0.57142857 0.66666667
 0.5        0.66666667 0.75       0.57142857]

mean value: 0.65

key: train_fscore 
value: [0.76190476 0.7037037  0.68965517 0.71428571 0.72413793 0.73333333
 0.79310345 0.70175439 0.76363636 0.78688525]

mean value: 0.7372400060454567

key: test_precision 
value: [0.66666667 0.75       1.         0.75       0.5        0.66666667
 0.4        0.66666667 0.6        0.5       ]

mean value: 0.65

key: train_precision 
value: [0.68571429 0.7037037  0.66666667 0.71428571 0.7        0.6875
 0.76666667 0.68965517 0.77777778 0.72727273]

mean value: 0.7119242714501335

key: test_recall 
value: [0.66666667 0.75       0.33333333 1.         0.66666667 0.66666667
 0.66666667 0.66666667 1.         0.66666667]

mean value: 0.7083333333333333

key: train_recall 
value: [0.85714286 0.7037037  0.71428571 0.71428571 0.75       0.78571429
 0.82142857 0.71428571 0.75       0.85714286]

mean value: 0.7667989417989418

key: test_roc_auc 
value: [0.70833333 0.70833333 0.66666667 0.83333333 0.5        0.66666667
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.625

key: train_roc_auc 
value: [0.72486772 0.70899471 0.67857143 0.71428571 0.71428571 0.71428571
 0.78571429 0.69642857 0.76785714 0.76785714]

mean value: 0.7273148148148149

key: test_jcc 
value: [0.5        0.6        0.33333333 0.75       0.4        0.5
 0.33333333 0.5        0.6        0.4       ]

mean value: 0.49166666666666664

key: train_jcc 
value: [0.61538462 0.54285714 0.52631579 0.55555556 0.56756757 0.57894737
 0.65714286 0.54054054 0.61764706 0.64864865]

mean value: 0.5850607144415194

MCC on Blind test: -0.06

Accuracy on Blind test: 0.53

Model_name: SVM 
Model func: SVC(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SVC(random_state=42))])

key: fit_time 
value: [0.00954056 0.00941706 0.00971389 0.00993824 0.00958085 0.00846577
 0.00864244 0.00963593 0.00878119 0.00845814]

mean value: 0.009217405319213867

key: score_time 
value: [0.00949955 0.00960994 0.00949001 0.00922036 0.00929332 0.00856066
 0.00873637 0.00920177 0.00861192 0.00859213]

mean value: 0.009081602096557617

key: test_mcc 
value: [ 0.41666667  0.41666667  0.          1.         -0.33333333  0.33333333
 -0.4472136   0.33333333  0.4472136  -0.4472136 ]

mean value: 0.1719453071166709

key: train_mcc 
value: [0.67602163 0.63624339 0.75047877 0.64285714 0.64285714 0.68250015
 0.75047877 0.72168784 0.75047877 0.71611487]

mean value: 0.6969718486383643

key: test_accuracy 
value: [0.71428571 0.71428571 0.5        1.         0.33333333 0.66666667
 0.33333333 0.66666667 0.66666667 0.33333333]

mean value: 0.5928571428571429

key: train_accuracy 
value: [0.83636364 0.81818182 0.875      0.82142857 0.82142857 0.83928571
 0.875      0.85714286 0.875      0.85714286]

mean value: 0.8475974025974026

key: test_fscore 
value: [0.66666667 0.75       0.         1.         0.33333333 0.66666667
 0.5        0.66666667 0.75       0.5       ]

mean value: 0.5833333333333333

key: train_fscore 
value: [0.84745763 0.81481481 0.87272727 0.82142857 0.82142857 0.84745763
 0.87272727 0.86666667 0.87719298 0.86206897]

mean value: 0.850397037200384

key: test_precision 
value: [0.66666667 0.75       0.         1.         0.33333333 0.66666667
 0.4        0.66666667 0.6        0.4       ]

mean value: 0.5483333333333333

key: train_precision 
value: [0.80645161 0.81481481 0.88888889 0.82142857 0.82142857 0.80645161
 0.88888889 0.8125     0.86206897 0.83333333]

mean value: 0.8356255260106762

key: test_recall 
value: [0.66666667 0.75       0.         1.         0.33333333 0.66666667
 0.66666667 0.66666667 1.         0.66666667]

mean value: 0.6416666666666666

key: train_recall 
value: [0.89285714 0.81481481 0.85714286 0.82142857 0.82142857 0.89285714
 0.85714286 0.92857143 0.89285714 0.89285714]

mean value: 0.8671957671957672

key: test_roc_auc 
value: [0.70833333 0.70833333 0.5        1.         0.33333333 0.66666667
 0.33333333 0.66666667 0.66666667 0.33333333]

mean value: 0.5916666666666667

key: train_roc_auc 
value: [0.83531746 0.81812169 0.875      0.82142857 0.82142857 0.83928571
 0.875      0.85714286 0.875      0.85714286]

mean value: 0.8474867724867725

key: test_jcc 
value: [0.5        0.6        0.         1.         0.2        0.5
 0.33333333 0.5        0.6        0.33333333]

mean value: 0.45666666666666667

key: train_jcc 
value: [0.73529412 0.6875     0.77419355 0.6969697  0.6969697  0.73529412
 0.77419355 0.76470588 0.78125    0.75757576]

mean value: 0.7403946365936404

MCC on Blind test: 0.03

Accuracy on Blind test: 0.58

Model_name: MLP 
Model func: MLPClassifier(max_iter=500, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MLPClassifier(max_iter=500, random_state=42))])

key: fit_time 
value: [0.30307984 0.31900239 0.28515434 0.32961416 0.31171894 0.35360336
 0.3566587  0.30262589 0.31346607 0.29689217]

mean value: 0.3171815872192383

key: score_time 
value: [0.01224256 0.01220584 0.01216316 0.01210666 0.01212716 0.01214552
 0.01214147 0.01214099 0.01205206 0.01212144]

mean value: 0.012144684791564941

key: test_mcc 
value: [ 0.41666667  1.          0.          0.          0.          0.70710678
 -0.33333333  0.33333333  0.          0.        ]

mean value: 0.21237734478532141

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.71428571 1.         0.5        0.5        0.5        0.83333333
 0.33333333 0.66666667 0.5        0.5       ]

mean value: 0.6047619047619047

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.66666667 1.         0.57142857 0.57142857 0.57142857 0.85714286
 0.33333333 0.66666667 0.57142857 0.4       ]

mean value: 0.6209523809523809

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.66666667 1.         0.5        0.5        0.5        0.75
 0.33333333 0.66666667 0.5        0.5       ]

mean value: 0.5916666666666667

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 1.         0.66666667 0.66666667 0.66666667 1.
 0.33333333 0.66666667 0.66666667 0.33333333]

mean value: 0.6666666666666666

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.70833333 1.         0.5        0.5        0.5        0.83333333
 0.33333333 0.66666667 0.5        0.5       ]

mean value: 0.6041666666666667

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.5  1.   0.4  0.4  0.4  0.75 0.2  0.5  0.4  0.25]

mean value: 0.48

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.07

Accuracy on Blind test: 0.63

Model_name: Decision Tree 
Model func: DecisionTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', DecisionTreeClassifier(random_state=42))])

key: fit_time 
value: [0.01366615 0.01234555 0.0107317  0.01047468 0.0102725  0.00917101
 0.00930333 0.00933981 0.01039386 0.0104413 ]

mean value: 0.01061398983001709

key: score_time 
value: [0.01174402 0.00966072 0.00954843 0.00907493 0.00855589 0.00836682
 0.00832462 0.00839281 0.00900578 0.00911355]

mean value: 0.009178757667541504

key: test_mcc 
value: [0.75       0.41666667 0.70710678 0.70710678 0.70710678 0.33333333
 0.33333333 0.33333333 0.4472136  0.4472136 ]

mean value: 0.5182414201226225

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.85714286 0.71428571 0.83333333 0.83333333 0.83333333 0.66666667
 0.66666667 0.66666667 0.66666667 0.66666667]

mean value: 0.7404761904761905

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.85714286 0.75       0.8        0.85714286 0.85714286 0.66666667
 0.66666667 0.66666667 0.75       0.5       ]

mean value: 0.7371428571428571

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.75       0.75       1.         0.75       0.75       0.66666667
 0.66666667 0.66666667 0.6        1.        ]

mean value: 0.76

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1.         0.75       0.66666667 1.         1.         0.66666667
 0.66666667 0.66666667 1.         0.33333333]

mean value: 0.775

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.875      0.70833333 0.83333333 0.83333333 0.83333333 0.66666667
 0.66666667 0.66666667 0.66666667 0.66666667]

mean value: 0.7416666666666667

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.75       0.6        0.66666667 0.75       0.75       0.5
 0.5        0.5        0.6        0.33333333]

mean value: 0.595

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.43

Accuracy on Blind test: 0.85

Model_name: Extra Trees 
Model func: ExtraTreesClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreesClassifier(random_state=42))])

key: fit_time 
value: [0.08601737 0.08639932 0.0850184  0.08244681 0.08106399 0.07768703
 0.07779479 0.07703543 0.07883596 0.07706761]

mean value: 0.08093667030334473

key: score_time 
value: [0.01850104 0.01828337 0.01675534 0.01864505 0.01682401 0.01671386
 0.01675773 0.01810884 0.01667213 0.01666355]

mean value: 0.017392492294311522

key: test_mcc 
value: [ 0.41666667  0.73029674 -0.33333333  0.70710678  0.          0.33333333
  0.          0.33333333  0.4472136  -0.33333333]

mean value: 0.23012837866933936

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.71428571 0.85714286 0.33333333 0.83333333 0.5        0.66666667
 0.5        0.66666667 0.66666667 0.33333333]

mean value: 0.6071428571428571

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.66666667 0.88888889 0.33333333 0.85714286 0.57142857 0.66666667
 0.57142857 0.66666667 0.75       0.33333333]

mean value: 0.6305555555555555

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.66666667 0.8        0.33333333 0.75       0.5        0.66666667
 0.5        0.66666667 0.6        0.33333333]

mean value: 0.5816666666666667

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 1.         0.33333333 1.         0.66666667 0.66666667
 0.66666667 0.66666667 1.         0.33333333]

mean value: 0.7

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.70833333 0.83333333 0.33333333 0.83333333 0.5        0.66666667
 0.5        0.66666667 0.66666667 0.33333333]

mean value: 0.6041666666666667

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.5  0.8  0.2  0.75 0.4  0.5  0.4  0.5  0.6  0.2 ]

mean value: 0.485

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.1

Accuracy on Blind test: 0.57

Model_name: Extra Tree 
Model func: ExtraTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreeClassifier(random_state=42))])

key: fit_time 
value: [0.00847769 0.0082128  0.00828052 0.00818801 0.00829625 0.00830555
 0.00822139 0.00828052 0.00835299 0.00829363]

mean value: 0.008290934562683105

key: score_time 
value: [0.00832343 0.00839877 0.00829625 0.00843334 0.00829983 0.00833988
 0.00836444 0.00831199 0.00841045 0.00831652]

mean value: 0.00834949016571045

key: test_mcc 
value: [0.73029674 1.         0.70710678 0.33333333 0.70710678 0.
 0.         0.33333333 0.4472136  0.33333333]

mean value: 0.45917239012132743

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.85714286 1.         0.83333333 0.66666667 0.83333333 0.5
 0.5        0.66666667 0.66666667 0.66666667]

mean value: 0.719047619047619

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.8        1.         0.8        0.66666667 0.85714286 0.4
 0.57142857 0.66666667 0.75       0.66666667]

mean value: 0.7178571428571429

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [1.         1.         1.         0.66666667 0.75       0.5
 0.5        0.66666667 0.6        0.66666667]

mean value: 0.735

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 1.         0.66666667 0.66666667 1.         0.33333333
 0.66666667 0.66666667 1.         0.66666667]

mean value: 0.7333333333333333

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.83333333 1.         0.83333333 0.66666667 0.83333333 0.5
 0.5        0.66666667 0.66666667 0.66666667]

mean value: 0.7166666666666667

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.66666667 1.         0.66666667 0.5        0.75       0.25
 0.4        0.5        0.6        0.5       ]

mean value: 0.5833333333333334

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.04

Accuracy on Blind test: 0.55

Model_name: Random Forest 
Model func: RandomForestClassifier(n_estimators=1000, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(n_estimators=1000, random_state=42))])

key: fit_time 
value: [0.97180128 0.97216392 0.97455215 0.96814251 0.96616793 0.9616642
 0.96398258 0.99810028 1.00037837 0.98141456]

mean value: 0.9758367776870728

key: score_time 
value: [0.0929122  0.09577751 0.08606768 0.09012103 0.086905   0.09162688
 0.08549738 0.09058094 0.08998919 0.09354615]

mean value: 0.09030239582061768

key: test_mcc 
value: [ 0.41666667  0.73029674  0.          0.70710678  0.          0.33333333
 -0.33333333  0.33333333  0.70710678 -0.33333333]

mean value: 0.2561176972379983

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.71428571 0.85714286 0.5        0.83333333 0.5        0.66666667
 0.33333333 0.66666667 0.83333333 0.33333333]

mean value: 0.6238095238095238

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.66666667 0.88888889 0.4        0.85714286 0.57142857 0.66666667
 0.33333333 0.66666667 0.85714286 0.33333333]

mean value: 0.6241269841269841

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.66666667 0.8        0.5        0.75       0.5        0.66666667
 0.33333333 0.66666667 0.75       0.33333333]

mean value: 0.5966666666666667

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 1.         0.33333333 1.         0.66666667 0.66666667
 0.33333333 0.66666667 1.         0.33333333]

mean value: 0.6666666666666666

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.70833333 0.83333333 0.5        0.83333333 0.5        0.66666667
 0.33333333 0.66666667 0.83333333 0.33333333]

mean value: 0.6208333333333333

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.5  0.8  0.25 0.75 0.4  0.5  0.2  0.5  0.75 0.2 ]

mean value: 0.485

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.18

Accuracy on Blind test: 0.64

Model_name: Random Forest2 
Model func: RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...05', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                                        n_estimators=1000, n_jobs=10,
                                        oob_score=True, random_state=42))])

key: fit_time 
value: [0.93364573 0.94478297 0.86035323 0.81261969 0.87720847 0.85843182
 0.83436155 0.82015204 0.80994129 0.9585228 ]

mean value: 0.8710019588470459

key: score_time 
value: [0.23323798 0.18277669 0.22402263 0.23721337 0.18250155 0.22653151
 0.22536087 0.22374034 0.21386456 0.21198082]

mean value: 0.21612303256988524

key: test_mcc 
value: [ 0.41666667  0.73029674  0.4472136   1.         -0.33333333  0.33333333
  0.          0.33333333  0.70710678  0.        ]

mean value: 0.3634617120026727

key: train_mcc 
value: [0.89153439 0.74935731 0.93094934 0.89802651 0.82618439 0.85933785
 0.85933785 0.82195294 0.85933785 0.93094934]

mean value: 0.8626967766562594

key: test_accuracy 
value: [0.71428571 0.85714286 0.66666667 1.         0.33333333 0.66666667
 0.5        0.66666667 0.83333333 0.5       ]

mean value: 0.6738095238095237

key: train_accuracy 
value: [0.94545455 0.87272727 0.96428571 0.94642857 0.91071429 0.92857143
 0.92857143 0.91071429 0.92857143 0.96428571]

mean value: 0.9300324675324675

key: test_fscore 
value: [0.66666667 0.88888889 0.5        1.         0.33333333 0.66666667
 0.57142857 0.66666667 0.85714286 0.4       ]

mean value: 0.655079365079365

key: train_fscore 
value: [0.94545455 0.8627451  0.96296296 0.94339623 0.90566038 0.92592593
 0.92592593 0.90909091 0.92592593 0.96296296]

mean value: 0.9270050860061959

key: test_precision 
value: [0.66666667 0.8        1.         1.         0.33333333 0.66666667
 0.5        0.66666667 0.75       0.5       ]

mean value: 0.6883333333333334

key: train_precision 
value: [0.96296296 0.91666667 1.         1.         0.96       0.96153846
 0.96153846 0.92592593 0.96153846 1.        ]

mean value: 0.965017094017094

key: test_recall 
value: [0.66666667 1.         0.33333333 1.         0.33333333 0.66666667
 0.66666667 0.66666667 1.         0.33333333]

mean value: 0.6666666666666666

key: train_recall 
value: [0.92857143 0.81481481 0.92857143 0.89285714 0.85714286 0.89285714
 0.89285714 0.89285714 0.89285714 0.92857143]

mean value: 0.8921957671957672

key: test_roc_auc 
value: [0.70833333 0.83333333 0.66666667 1.         0.33333333 0.66666667
 0.5        0.66666667 0.83333333 0.5       ]

mean value: 0.6708333333333334

key: train_roc_auc 
value: [0.9457672  0.87169312 0.96428571 0.94642857 0.91071429 0.92857143
 0.92857143 0.91071429 0.92857143 0.96428571]

mean value: 0.9299603174603175

key: test_jcc 
value: [0.5        0.8        0.33333333 1.         0.2        0.5
 0.4        0.5        0.75       0.25      ]

mean value: 0.5233333333333333

key: train_jcc 
value: [0.89655172 0.75862069 0.92857143 0.89285714 0.82758621 0.86206897
 0.86206897 0.83333333 0.86206897 0.92857143]

mean value: 0.8652298850574712

MCC on Blind test: 0.19

Accuracy on Blind test: 0.66

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.02530813 0.00904346 0.00901461 0.00924706 0.00861883 0.00839806
 0.00856972 0.00862861 0.00850034 0.00852227]

mean value: 0.01038510799407959

key: score_time 
value: [0.01197267 0.00865054 0.00873184 0.00858879 0.00849771 0.00855017
 0.00852013 0.00867319 0.00859737 0.00864434]

mean value: 0.008942675590515137

key: test_mcc 
value: [ 0.41666667  0.41666667  0.4472136   0.70710678  0.4472136   0.4472136
 -0.33333333  0.33333333  0.         -0.33333333]

mean value: 0.25487475676864213

key: train_mcc 
value: [0.68300095 0.56441351 0.64285714 0.5728919  0.67900461 0.64450339
 0.68965631 0.71428571 0.71611487 0.71611487]

mean value: 0.6622843266212062

key: test_accuracy 
value: [0.71428571 0.71428571 0.66666667 0.83333333 0.66666667 0.66666667
 0.33333333 0.66666667 0.5        0.33333333]

mean value: 0.6095238095238095

key: train_accuracy 
value: [0.83636364 0.78181818 0.82142857 0.78571429 0.83928571 0.82142857
 0.83928571 0.85714286 0.85714286 0.85714286]

mean value: 0.8296753246753247

key: test_fscore 
value: [0.66666667 0.75       0.5        0.85714286 0.75       0.75
 0.33333333 0.66666667 0.57142857 0.33333333]

mean value: 0.6178571428571429

key: train_fscore 
value: [0.85245902 0.76923077 0.82142857 0.79310345 0.84210526 0.82758621
 0.82352941 0.85714286 0.86206897 0.85185185]

mean value: 0.8300506361659747

key: test_precision 
value: [0.66666667 0.75       1.         0.75       0.6        0.6
 0.33333333 0.66666667 0.5        0.33333333]

mean value: 0.62

key: train_precision 
value: [0.78787879 0.8        0.82142857 0.76666667 0.82758621 0.8
 0.91304348 0.85714286 0.83333333 0.88461538]

mean value: 0.8291695286223022

key: test_recall 
value: [0.66666667 0.75       0.33333333 1.         1.         1.
 0.33333333 0.66666667 0.66666667 0.33333333]

mean value: 0.6749999999999999

key: train_recall 
value: [0.92857143 0.74074074 0.82142857 0.82142857 0.85714286 0.85714286
 0.75       0.85714286 0.89285714 0.82142857]

mean value: 0.8347883597883597

key: test_roc_auc 
value: [0.70833333 0.70833333 0.66666667 0.83333333 0.66666667 0.66666667
 0.33333333 0.66666667 0.5        0.33333333]

mean value: 0.6083333333333334

key: train_roc_auc 
value: [0.83465608 0.78108466 0.82142857 0.78571429 0.83928571 0.82142857
 0.83928571 0.85714286 0.85714286 0.85714286]

mean value: 0.8294312169312169

key: test_jcc 
value: [0.5        0.6        0.33333333 0.75       0.6        0.6
 0.2        0.5        0.4        0.2       ]

mean value: 0.4683333333333333

key: train_jcc 
value: [0.74285714 0.625      0.6969697  0.65714286 0.72727273 0.70588235
 0.7        0.75       0.75757576 0.74193548]

mean value: 0.7104636018630326

MCC on Blind test: 0.04

Accuracy on Blind test: 0.53

Model_name: XGBoost 
Model func: XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...
                               interaction_constraints=None, learning_rate=None,
                               max_delta_step=None, max_depth=None,
                               min_child_weight=None, missing=nan,
                               monotone_constraints=None, n_estimators=100,
                               n_jobs=None, num_parallel_tree=None,
                               predictor=None, random_state=42, reg_alpha=None,
                               reg_lambda=None, scale_pos_weight=None,
                               subsample=None, tree_method=None,
                               use_label_encoder=False,
                               validate_parameters=None, verbosity=0))])

key: fit_time 
value: [0.04599786 0.2149446  0.03394651 0.03558373 0.03934288 0.03849339
 0.04058552 0.03678155 0.03869057 0.03644395]

mean value: 0.05608105659484863

key: score_time 
value: [0.01126957 0.0116303  0.0108521  0.01114607 0.01134968 0.0112679
 0.01098466 0.01067924 0.01040721 0.01074076]

mean value: 0.011032748222351074

key: test_mcc 
value: [ 0.41666667  0.41666667  0.70710678  1.          0.33333333  0.33333333
  0.70710678  0.33333333  1.         -0.33333333]

mean value: 0.49142135623730954

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.71428571 0.71428571 0.83333333 1.         0.66666667 0.66666667
 0.83333333 0.66666667 1.         0.33333333]

mean value: 0.7428571428571429

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.66666667 0.75       0.8        1.         0.66666667 0.66666667
 0.8        0.66666667 1.         0.33333333]

mean value: 0.735

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.66666667 0.75       1.         1.         0.66666667 0.66666667
 1.         0.66666667 1.         0.33333333]

mean value: 0.775

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 0.75       0.66666667 1.         0.66666667 0.66666667
 0.66666667 0.66666667 1.         0.33333333]

mean value: 0.7083333333333333

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.70833333 0.70833333 0.83333333 1.         0.66666667 0.66666667
 0.83333333 0.66666667 1.         0.33333333]

mean value: 0.7416666666666667

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.5        0.6        0.66666667 1.         0.5        0.5
 0.66666667 0.5        1.         0.2       ]

mean value: 0.6133333333333333

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.59

Accuracy on Blind test: 0.89

Model_name: LDA 
Model func: LinearDiscriminantAnalysis() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LinearDiscriminantAnalysis())])

key: fit_time 
value: [0.01369762 0.01518178 0.01506925 0.02844906 0.03665996 0.05949283
 0.0471518  0.03665042 0.03241611 0.03393483]

mean value: 0.031870365142822266

key: score_time 
value: [0.01207423 0.01164985 0.01162529 0.02072716 0.02174664 0.02843571
 0.0151608  0.03072429 0.02236414 0.02126551]

mean value: 0.01957736015319824

key: test_mcc 
value: [ 0.54772256  0.16666667  0.4472136   0.4472136   0.33333333  0.
  0.70710678  0.4472136  -0.33333333  0.4472136 ]

mean value: 0.3210350387358212

key: train_mcc 
value: [0.92724868 0.89139151 0.96490128 0.96490128 0.96490128 0.96490128
 1.         1.         0.92857143 1.        ]

mean value: 0.9606816741601416

key: test_accuracy 
value: [0.71428571 0.57142857 0.66666667 0.66666667 0.66666667 0.5
 0.83333333 0.66666667 0.33333333 0.66666667]

mean value: 0.6285714285714286

key: train_accuracy 
value: [0.96363636 0.94545455 0.98214286 0.98214286 0.98214286 0.98214286
 1.         1.         0.96428571 1.        ]

mean value: 0.9801948051948052

key: test_fscore 
value: [0.75       0.57142857 0.5        0.75       0.66666667 0.4
 0.85714286 0.5        0.33333333 0.5       ]

mean value: 0.5828571428571429

key: train_fscore 
value: [0.96428571 0.94339623 0.98245614 0.98245614 0.98245614 0.98181818
 1.         1.         0.96428571 1.        ]

mean value: 0.9801154257857336

key: test_precision 
value: [0.6        0.66666667 1.         0.6        0.66666667 0.5
 0.75       1.         0.33333333 1.        ]

mean value: 0.7116666666666667

key: train_precision 
value: [0.96428571 0.96153846 0.96551724 0.96551724 0.96551724 1.
 1.         1.         0.96428571 1.        ]

mean value: 0.9786661614247821

key: test_recall 
value: [1.         0.5        0.33333333 1.         0.66666667 0.33333333
 1.         0.33333333 0.33333333 0.33333333]

mean value: 0.5833333333333334

key: train_recall 
value: [0.96428571 0.92592593 1.         1.         1.         0.96428571
 1.         1.         0.96428571 1.        ]

mean value: 0.9818783068783069

key: test_roc_auc 
value: [0.75       0.58333333 0.66666667 0.66666667 0.66666667 0.5
 0.83333333 0.66666667 0.33333333 0.66666667]

mean value: 0.6333333333333333

key: train_roc_auc 
value: [0.96362434 0.94510582 0.98214286 0.98214286 0.98214286 0.98214286
 1.         1.         0.96428571 1.        ]

mean value: 0.9801587301587302

key: test_jcc 
value: [0.6        0.4        0.33333333 0.6        0.5        0.25
 0.75       0.33333333 0.2        0.33333333]

mean value: 0.43

key: train_jcc 
value: [0.93103448 0.89285714 0.96551724 0.96551724 0.96551724 0.96428571
 1.         1.         0.93103448 1.        ]

mean value: 0.961576354679803

MCC on Blind test: 0.16

Accuracy on Blind test: 0.61

Model_name: Multinomial 
Model func: MultinomialNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MultinomialNB())])

key: fit_time 
value: [0.01712322 0.00909805 0.00932932 0.01058125 0.00932312 0.00836778
 0.0089972  0.00945711 0.00867605 0.00840211]

mean value: 0.009935522079467773

key: score_time 
value: [0.01087093 0.00968623 0.00903726 0.009305   0.00837541 0.00848198
 0.0090766  0.00919485 0.00859189 0.008461  ]

mean value: 0.00910811424255371

key: test_mcc 
value: [0.73029674 0.09128709 0.         0.33333333 0.         0.33333333
 0.4472136  0.33333333 0.33333333 0.        ]

mean value: 0.260213076509104

key: train_mcc 
value: [0.41833001 0.41798942 0.39513166 0.35714286 0.35805744 0.35714286
 0.39310793 0.39310793 0.39310793 0.39310793]

mean value: 0.38762259647828906

key: test_accuracy 
value: [0.85714286 0.57142857 0.5        0.66666667 0.5        0.66666667
 0.66666667 0.66666667 0.66666667 0.5       ]

mean value: 0.6261904761904762

key: train_accuracy 
value: [0.70909091 0.70909091 0.69642857 0.67857143 0.67857143 0.67857143
 0.69642857 0.69642857 0.69642857 0.69642857]

mean value: 0.6936038961038961

key: test_fscore 
value: [0.8        0.66666667 0.         0.66666667 0.57142857 0.66666667
 0.75       0.66666667 0.66666667 0.57142857]

mean value: 0.6026190476190476

key: train_fscore 
value: [0.72413793 0.7037037  0.71186441 0.67857143 0.68965517 0.67857143
 0.69090909 0.70175439 0.70175439 0.69090909]

mean value: 0.6971831024822503

key: test_precision 
value: [1.         0.6        0.         0.66666667 0.5        0.66666667
 0.6        0.66666667 0.66666667 0.5       ]

mean value: 0.5866666666666667

key: train_precision 
value: [0.7        0.7037037  0.67741935 0.67857143 0.66666667 0.67857143
 0.7037037  0.68965517 0.68965517 0.7037037 ]

mean value: 0.6891650334586931

key: test_recall 
value: [0.66666667 0.75       0.         0.66666667 0.66666667 0.66666667
 1.         0.66666667 0.66666667 0.66666667]

mean value: 0.6416666666666666

key: train_recall 
value: [0.75       0.7037037  0.75       0.67857143 0.71428571 0.67857143
 0.67857143 0.71428571 0.71428571 0.67857143]

mean value: 0.7060846560846561

key: test_roc_auc 
value: [0.83333333 0.54166667 0.5        0.66666667 0.5        0.66666667
 0.66666667 0.66666667 0.66666667 0.5       ]

mean value: 0.6208333333333333

key: train_roc_auc 
value: [0.70833333 0.70899471 0.69642857 0.67857143 0.67857143 0.67857143
 0.69642857 0.69642857 0.69642857 0.69642857]

mean value: 0.6935185185185185

key: test_jcc 
value: [0.66666667 0.5        0.         0.5        0.4        0.5
 0.6        0.5        0.5        0.4       ]

mean value: 0.45666666666666667

key: train_jcc 
value: [0.56756757 0.54285714 0.55263158 0.51351351 0.52631579 0.51351351
 0.52777778 0.54054054 0.54054054 0.52777778]

mean value: 0.5353035742509427

MCC on Blind test: 0.03

Accuracy on Blind test: 0.57

Model_name: Passive Aggresive 
Model func: PassiveAggressiveClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 PassiveAggressiveClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.01032519 0.0134182  0.01277184 0.0125854  0.01247573 0.01274657
 0.01297832 0.01324177 0.01268935 0.01285481]

mean value: 0.012608718872070313

key: score_time 
value: [0.009408   0.0115633  0.01149321 0.01148438 0.01144481 0.01154017
 0.01205564 0.01176572 0.0118618  0.01181412]

mean value: 0.011443114280700684

key: test_mcc 
value: [-0.09128709  0.73029674 -0.70710678  0.33333333 -0.33333333  0.70710678
 -0.33333333  0.33333333  0.4472136   0.        ]

mean value: 0.10862232459226517

key: train_mcc 
value: [0.5950716  1.         0.96490128 0.83484711 0.89802651 0.96490128
 0.80439967 1.         0.89802651 0.96490128]

mean value: 0.8925075239665476

key: test_accuracy 
value: [0.42857143 0.85714286 0.16666667 0.66666667 0.33333333 0.83333333
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.5452380952380952

key: train_accuracy 
value: [0.76363636 1.         0.98214286 0.91071429 0.94642857 0.98214286
 0.89285714 1.         0.94642857 0.98214286]

mean value: 0.9406493506493506

key: test_fscore 
value: [0.5        0.88888889 0.         0.66666667 0.33333333 0.85714286
 0.33333333 0.66666667 0.75       0.4       ]

mean value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
0.5396031746031746

key: train_fscore 
value: [0.8115942  1.         0.98245614 0.90196078 0.94339623 0.98181818
 0.88       1.         0.94339623 0.98181818]

mean value: 0.9426439944029705

key: test_precision 
value: [0.4        0.8        0.         0.66666667 0.33333333 0.75
 0.33333333 0.66666667 0.6        0.5       ]

mean value: 0.505

key: train_precision 
value: [0.68292683 1.         0.96551724 1.         1.         1.
 1.         1.         1.         1.        ]

mean value: 0.9648444070647603

key: test_recall 
value: [0.66666667 1.         0.         0.66666667 0.33333333 1.
 0.33333333 0.66666667 1.         0.33333333]

mean value: 0.6

key: train_recall 
value: [1.         1.         1.         0.82142857 0.89285714 0.96428571
 0.78571429 1.         0.89285714 0.96428571]

mean value: 0.9321428571428572

key: test_roc_auc 
value: [0.45833333 0.83333333 0.16666667 0.66666667 0.33333333 0.83333333
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.5458333333333334

key: train_roc_auc 
value: [0.75925926 1.         0.98214286 0.91071429 0.94642857 0.98214286
 0.89285714 1.         0.94642857 0.98214286]

mean value: 0.9402116402116403

key: test_jcc 
value: [0.33333333 0.8        0.         0.5        0.2        0.75
 0.2        0.5        0.6        0.25      ]

mean value: 0.41333333333333333

key: train_jcc 
value: [0.68292683 1.         0.96551724 0.82142857 0.89285714 0.96428571
 0.78571429 1.         0.89285714 0.96428571]

mean value: 0.8969872642076174

MCC on Blind test: 0.22

Accuracy on Blind test: 0.81

Model_name: Stochastic GDescent 
Model func: SGDClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SGDClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.01248312 0.01205182 0.01259065 0.01246166 0.01225281 0.01191282
 0.01285648 0.01354647 0.01264191 0.01220679]

mean value: 0.012500452995300292

key: score_time 
value: [0.01174188 0.01167893 0.01177812 0.01229596 0.01187444 0.01173162
 0.01186562 0.01188636 0.0117352  0.0117588 ]

mean value: 0.01183469295501709

key: test_mcc 
value: [ 0.41666667  0.75        0.          0.          0.          0.70710678
 -0.33333333  0.33333333  0.4472136   0.        ]

mean value: 0.2320987043353172

key: train_mcc 
value: [0.78961518 0.73981424 1.         1.         0.23791548 0.96490128
 0.89802651 0.8660254  1.         0.93094934]

mean value: 0.8427247424458356

key: test_accuracy 
value: [0.71428571 0.85714286 0.5        0.5        0.5        0.83333333
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.6071428571428571

key: train_accuracy 
value: [0.89090909 0.85454545 1.         1.         0.55357143 0.98214286
 0.94642857 0.92857143 1.         0.96428571]

mean value: 0.9120454545454545

key: test_fscore 
value: [0.66666667 0.85714286 0.         0.57142857 0.         0.85714286
 0.33333333 0.66666667 0.75       0.4       ]

mean value: 0.5102380952380953

key: train_fscore 
value: [0.9        0.82608696 1.         1.         0.19354839 0.98181818
 0.94339623 0.92307692 1.         0.96296296]

mean value: 0.8730889637891676

key: test_precision 
value: [0.66666667 1.         0.         0.5        0.         0.75
 0.33333333 0.66666667 0.6        0.5       ]

mean value: 0.5016666666666667

key: train_precision 
value: [0.84375 1.      1.      1.      1.      1.      1.      1.      1.
 1.     ]

mean value: 0.984375

key: test_recall 
value: [0.66666667 0.75       0.         0.66666667 0.         1.
 0.33333333 0.66666667 1.         0.33333333]

mean value: 0.5416666666666666

key: train_recall 
value: [0.96428571 0.7037037  1.         1.         0.10714286 0.96428571
 0.89285714 0.85714286 1.         0.92857143]

mean value: 0.8417989417989418

key: test_roc_auc 
value: [0.70833333 0.875      0.5        0.5        0.5        0.83333333
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.6083333333333334

key: train_roc_auc 
value: [0.88955026 0.85185185 1.         1.         0.55357143 0.98214286
 0.94642857 0.92857143 1.         0.96428571]

mean value: 0.9116402116402117

key: test_jcc 
value: [0.5  0.75 0.   0.4  0.   0.75 0.2  0.5  0.6  0.25]

mean value: 0.395

key: train_jcc 
value: [0.81818182 0.7037037  1.         1.         0.10714286 0.96428571
 0.89285714 0.85714286 1.         0.92857143]

mean value: 0.8271885521885523

MCC on Blind test: 0.08

Accuracy on Blind test: 0.61

Model_name: AdaBoost Classifier 
Model func: AdaBoostClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', AdaBoostClassifier(random_state=42))])

key: fit_time 
value: [0.09026432 0.07359457 0.07355642 0.07545662 0.07713127 0.07464409
 0.07500982 0.07337379 0.073946   0.07459235]

mean value: 0.07615692615509033

key: score_time 
value: [0.01471281 0.01447606 0.01474142 0.01583719 0.01568365 0.01509976
 0.01465964 0.01486158 0.01541591 0.01487398]

mean value: 0.015036201477050782

key: test_mcc 
value: [0.41666667 0.75       0.4472136  0.70710678 0.4472136  0.4472136
 0.33333333 0.4472136  1.         0.4472136 ]

mean value: 0.5443174758686338

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.71428571 0.85714286 0.66666667 0.83333333 0.66666667 0.66666667
 0.66666667 0.66666667 1.         0.66666667]

mean value: 0.7404761904761905

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.66666667 0.85714286 0.5        0.85714286 0.75       0.75
 0.66666667 0.75       1.         0.5       ]

mean value: 0.7297619047619047

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.66666667 1.         1.         0.75       0.6        0.6
 0.66666667 0.6        1.         1.        ]

mean value: 0.7883333333333333

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 0.75       0.33333333 1.         1.         1.
 0.66666667 1.         1.         0.33333333]

mean value: 0.775

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.70833333 0.875      0.66666667 0.83333333 0.66666667 0.66666667
 0.66666667 0.66666667 1.         0.66666667]

mean value: 0.7416666666666667

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.5        0.75       0.33333333 0.75       0.6        0.6
 0.5        0.6        1.         0.33333333]

mean value: 0.5966666666666667

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.24

Accuracy on Blind test: 0.64

Model_name: Bagging Classifier 
Model func: BaggingClassifier(n_jobs=10, oob_score=True, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 BaggingClassifier(n_jobs=10, oob_score=True,
                                   random_state=42))])

key: fit_time 
value: [0.02606773 0.02928543 0.03392863 0.04728842 0.04110289 0.02960777
 0.02888727 0.02760363 0.02849007 0.02523732]

mean value: 0.031749916076660153

key: score_time 
value: [0.02186918 0.02333927 0.03487301 0.03544354 0.02109313 0.02897167
 0.01872945 0.02299023 0.01631522 0.02588534]

mean value: 0.02495100498199463

key: test_mcc 
value: [0.41666667 0.41666667 0.70710678 1.         0.70710678 0.33333333
 0.70710678 0.33333333 0.70710678 0.4472136 ]

mean value: 0.5775640720246148

key: train_mcc 
value: [0.96428571 0.96423926 1.         0.96490128 1.         0.96490128
 0.89802651 0.93094934 1.         0.93094934]

mean value: 0.9618252716013356

key: test_accuracy 
value: [0.71428571 0.71428571 0.83333333 1.         0.83333333 0.66666667
 0.83333333 0.66666667 0.83333333 0.66666667]

mean value: 0.7761904761904762

key: train_accuracy 
value: [0.98181818 0.98181818 1.         0.98214286 1.         0.98214286
 0.94642857 0.96428571 1.         0.96428571]

mean value: 0.9802922077922078

key: test_fscore 
value: [0.66666667 0.75       0.8        1.         0.85714286 0.66666667
 0.8        0.66666667 0.85714286 0.5       ]

mean value: 0.7564285714285715

key: train_fscore 
value: [0.98181818 0.98113208 1.         0.98181818 1.         0.98181818
 0.94339623 0.96296296 1.         0.96296296]

mean value: 0.9795908773267265

key: test_precision 
value: [0.66666667 0.75       1.         1.         0.75       0.66666667
 1.         0.66666667 0.75       1.        ]

mean value: 0.825

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 0.75       0.66666667 1.         1.         0.66666667
 0.66666667 0.66666667 1.         0.33333333]

mean value: 0.7416666666666667

key: train_recall 
value: [0.96428571 0.96296296 1.         0.96428571 1.         0.96428571
 0.89285714 0.92857143 1.         0.92857143]

mean value: 0.9605820105820106

key: test_roc_auc 
value: [0.70833333 0.70833333 0.83333333 1.         0.83333333 0.66666667
 0.83333333 0.66666667 0.83333333 0.66666667]

mean value: 0.775

key: train_roc_auc 
value: [0.98214286 0.98148148 1.         0.98214286 1.         0.98214286
 0.94642857 0.96428571 1.         0.96428571]

mean value: 0.9802910052910053

key: test_jcc 
value: [0.5        0.6        0.66666667 1.         0.75       0.5
 0.66666667 0.5        0.75       0.33333333]

mean value: 0.6266666666666667

key: train_jcc 
value: [0.96428571 0.96296296 1.         0.96428571 1.         0.96428571
 0.89285714 0.92857143 1.         0.92857143]

mean value: 0.9605820105820106

MCC on Blind test: 0.58

Accuracy on Blind test: 0.9

Model_name: Gaussian Process 
Model func: GaussianProcessClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianProcessClassifier(random_state=42))])

key: fit_time 
value: [0.01239824 0.0106442  0.01139164 0.01033688 0.01141787 0.01138425
 0.01022696 0.01127267 0.0115602  0.01133299]

mean value: 0.011196589469909668

key: score_time 
value: [0.00994658 0.00929451 0.00900078 0.00866699 0.00945234 0.00949311
 0.00942707 0.00952792 0.00963473 0.00945282]

mean value: 0.009389686584472656

key: test_mcc 
value: [ 0.16666667  1.         -0.33333333  1.         -0.33333333  0.70710678
 -0.70710678  0.          0.4472136  -0.33333333]

mean value: 0.16138802621666246

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.57142857 1.         0.33333333 1.         0.33333333 0.83333333
 0.16666667 0.5        0.66666667 0.33333333]

mean value: 0.5738095238095238

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.57142857 1.         0.33333333 1.         0.33333333 0.85714286
 0.28571429 0.4        0.75       0.33333333]

mean value: 0.5864285714285714

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.5        1.         0.33333333 1.         0.33333333 0.75
 0.25       0.5        0.6        0.33333333]

mean value: 0.5599999999999999

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 1.         0.33333333 1.         0.33333333 1.
 0.33333333 0.33333333 1.         0.33333333]

mean value: 0.6333333333333333

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.58333333 1.         0.33333333 1.         0.33333333 0.83333333
 0.16666667 0.5        0.66666667 0.33333333]

mean value: 0.5750000000000001

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.4        1.         0.2        1.         0.2        0.75
 0.16666667 0.25       0.6        0.2       ]

mean value: 0.4766666666666667

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.03

Accuracy on Blind test: 0.52

Model_name: Gradient Boosting 
Model func: GradientBoostingClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GradientBoostingClassifier(random_state=42))])

key: fit_time 
value: [0.1559341  0.14096451 0.14865351 0.1459341  0.14436388 0.14416242
 0.14324951 0.14705586 0.14461684 0.14689589]

mean value: 0.14618306159973143

key: score_time 
value: [0.00923705 0.00975156 0.00922012 0.00910306 0.00928426 0.00917768
 0.00920558 0.00925708 0.00913954 0.00912595]

mean value: 0.009250187873840332

key: test_mcc 
value: [0.75       0.41666667 0.4472136  1.         0.70710678 0.33333333
 0.70710678 0.33333333 0.70710678 0.4472136 ]

mean value: 0.5849080867892892

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.85714286 0.71428571 0.66666667 1.         0.83333333 0.66666667
 0.83333333 0.66666667 0.83333333 0.66666667]

mean value: 0.7738095238095238

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.85714286 0.75       0.5        1.         0.85714286 0.66666667
 0.8        0.66666667 0.85714286 0.5       ]

mean value: 0.7454761904761904

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.75       0.75       1.         1.         0.75       0.66666667
 1.         0.66666667 0.75       1.        ]

mean value: 0.8333333333333334

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1.         0.75       0.33333333 1.         1.         0.66666667
 0.66666667 0.66666667 1.         0.33333333]

mean value: 0.7416666666666667

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.875      0.70833333 0.66666667 1.         0.83333333 0.66666667
 0.83333333 0.66666667 0.83333333 0.66666667]

mean value: 0.775

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.75       0.6        0.33333333 1.         0.75       0.5
 0.66666667 0.5        0.75       0.33333333]

mean value: 0.6183333333333333

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.48

Accuracy on Blind test: 0.86

Model_name: QDA 
Model func: QuadraticDiscriminantAnalysis() 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', QuadraticDiscriminantAnalysis())])

key: fit_time 
value: [0.00967383 0.01260471 0.01283741 0.01275611 0.01264787 0.01265216
 0.01271796 0.01298189 0.01507378 0.01323509]

mean value: 0.0127180814743042

key: score_time 
value: [0.00898314 0.01174188 0.01165843 0.01176929 0.01176214 0.01175547
 0.01430345 0.01174092 0.01242518 0.0140512 ]

mean value: 0.012019109725952149

key: test_mcc 
value: [ 0.41666667  0.41666667  0.          1.          0.          1.
 -0.33333333  0.          0.         -0.33333333]

mean value: 0.21666666666666667

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.71428571 0.71428571 0.5        1.         0.5        1.
 0.33333333 0.5        0.5        0.33333333]

mean value: 0.6095238095238096

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.66666667 0.75       0.4        1.         0.         1.
 0.33333333 0.57142857 0.4        0.33333333]

mean value: 0.5454761904761904

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.66666667 0.75       0.5        1.         0.         1.
 0.33333333 0.5        0.5        0.33333333]

mean value: 0.5583333333333333

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 0.75       0.33333333 1.         0.         1.
 0.33333333 0.66666667 0.33333333 0.33333333]

mean value: 0.5416666666666666

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.70833333 0.70833333 0.5        1.         0.5        1.
 0.33333333 0.5        0.5        0.33333333]

mean value: 0.6083333333333334

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.5  0.6  0.25 1.   0.   1.   0.2  0.4  0.25 0.2 ]

mean value: 0.44

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.11

Accuracy on Blind test: 0.55

Model_name: Ridge Classifier 
Model func: RidgeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifier(random_state=42))])

key: fit_time 
value: [0.02282548 0.01265121 0.01275706 0.01262021 0.01270914 0.0125742
 0.0126338  0.01251626 0.0127449  0.01251292]

mean value: 0.013654518127441406

key: score_time 
value: [0.01168394 0.01157737 0.01159072 0.01156926 0.01153255 0.01165366
 0.01156425 0.01157522 0.01158023 0.01167011]

mean value: 0.0115997314453125

key: test_mcc 
value: [ 0.16666667  1.         -0.33333333  0.          0.33333333  0.70710678
 -0.33333333  0.33333333  0.4472136   0.        ]

mean value: 0.2320987043353172

key: train_mcc 
value: [0.96428571 0.96423926 1.         1.         0.96490128 0.96490128
 0.96490128 1.         0.96490128 0.96490128]

mean value: 0.9753031377439002

key: test_accuracy 
value: [0.57142857 1.         0.33333333 0.5        0.66666667 0.83333333
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.6071428571428571

key: train_accuracy 
value: [0.98181818 0.98181818 1.         1.         0.98214286 0.98214286
 0.98214286 1.         0.98214286 0.98214286]

mean value: 0.9874350649350649

key: test_fscore 
value: [0.57142857 1.         0.33333333 0.57142857 0.66666667 0.85714286
 0.33333333 0.66666667 0.75       0.4       ]

mean value: 0.615

key: train_fscore 
value: [0.98181818 0.98113208 1.         1.         0.98181818 0.98181818
 0.98181818 1.         0.98181818 0.98181818]

mean value: 0.9872041166380789

key: test_precision 
value: [0.5        1.         0.33333333 0.5        0.66666667 0.75
 0.33333333 0.66666667 0.6        0.5       ]

mean value: 0.585

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [0.66666667 1.         0.33333333 0.66666667 0.66666667 1.
 0.33333333 0.66666667 1.         0.33333333]

mean value: 0.6666666666666666

key: train_recall 
value: [0.96428571 0.96296296 1.         1.         0.96428571 0.96428571
 0.96428571 1.         0.96428571 0.96428571]

mean value: 0.9748677248677249

key: test_roc_auc 
value: [0.58333333 1.         0.33333333 0.5        0.66666667 0.83333333
 0.33333333 0.66666667 0.66666667 0.5       ]

mean value: 0.6083333333333334

key: train_roc_auc 
value: [0.98214286 0.98148148 1.         1.         0.98214286 0.98214286
 0.98214286 1.         0.98214286 0.98214286]

mean value: 0.9874338624338624

key: test_jcc 
value: [0.4  1.   0.2  0.4  0.5  0.75 0.2  0.5  0.6  0.25]

mean value: 0.48

key: train_jcc 
value: [0.96428571 0.96296296 1.         1.         0.96428571 0.96428571
 0.96428571 1.         0.96428571 0.96428571]

mean value: 0.9748677248677249

MCC on Blind test: 0.08

Accuracy on Blind test: 0.65

Model_name: Ridge ClassifierCV 
Model func: RidgeClassifierCV(cv=10) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifierCV(cv=10))])

key: fit_time 
value: [0.08206749 0.08403969 0.08206391 0.08247185 0.08237004 0.09134841
 0.08206105 0.08144999 0.10941315 0.12250161]

mean value: 0.08997871875762939

key: score_time 
value: [0.01189399 0.01179409 0.01217628 0.0118084  0.0117743  0.01175857
 0.0117414  0.01176047 0.0117588  0.01199698]

mean value: 0.011846327781677246

key: test_mcc 
value: [0.16666667 1.         0.         0.         0.33333333 0.70710678
 0.         0.33333333 0.         0.        ]

mean value: 0.25404401145198807

key: train_mcc 
value: [1.         0.74603175 0.71428571 1.         1.         0.96490128
 0.78772636 1.         0.71611487 0.78772636]

mean value: 0.8716786338597661

key: test_accuracy 
value: [0.57142857 1.         0.5        0.5        0.66666667 0.83333333
 0.5        0.66666667 0.5        0.5       ]

mean value: 0.6238095238095238

key: train_accuracy 
value: [1.         0.87272727 0.85714286 1.         1.         0.98214286
 0.89285714 1.         0.85714286 0.89285714]

mean value: 0.935487012987013

key: test_fscore 
value: [0.57142857 1.         0.         0.57142857 0.66666667 0.85714286
 0.57142857 0.66666667 0.57142857 0.4       ]

mean value: 0.5876190476190476

key: train_fscore 
value: [1.         0.87272727 0.85714286 1.         1.         0.98181818
 0.88888889 1.         0.85185185 0.88888889]

mean value: 0.9341317941317941

key: test_precision 
value: /home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:176: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:179: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
[0.5        1.         0.         0.5        0.66666667 0.75
 0.5        0.66666667 0.5        0.5       ]

mean value: 0.5583333333333333

key: train_precision 
value: [1.         0.85714286 0.85714286 1.         1.         1.
 0.92307692 1.         0.88461538 0.92307692]

mean value: 0.9445054945054945

key: test_recall 
value: [0.66666667 1.         0.         0.66666667 0.66666667 1.
 0.66666667 0.66666667 0.66666667 0.33333333]

mean value: 0.6333333333333333

key: train_recall 
value: [1.         0.88888889 0.85714286 1.         1.         0.96428571
 0.85714286 1.         0.82142857 0.85714286]

mean value: 0.9246031746031745

key: test_roc_auc 
value: [0.58333333 1.         0.5        0.5        0.66666667 0.83333333
 0.5        0.66666667 0.5        0.5       ]

mean value: 0.625

key: train_roc_auc 
value: [1.         0.87301587 0.85714286 1.         1.         0.98214286
 0.89285714 1.         0.85714286 0.89285714]

mean value: 0.935515873015873

key: test_jcc 
value: [0.4  1.   0.   0.4  0.5  0.75 0.4  0.5  0.4  0.25]

mean value: 0.46

key: train_jcc 
value: [1.         0.77419355 0.75       1.         1.         0.96428571
 0.8        1.         0.74193548 0.8       ]

mean value: 0.8830414746543779

MCC on Blind test: 0.07

Accuracy on Blind test: 0.64

Model_name: Logistic Regression 
Model func: LogisticRegression(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegression(random_state=42))])

key: fit_time 
value: [0.04051828 0.03856063 0.03865337 0.03771973 0.0377152  0.03819609
 0.03756094 0.03836608 0.03767562 0.03748059]

mean value: 0.03824465274810791

key: score_time 
value: [0.01504564 0.01525474 0.01512647 0.01525068 0.0148778  0.01584601
 0.01504493 0.01530743 0.01584649 0.01210523]

mean value: 0.014970541000366211

key: test_mcc 
value: [0.87867338 0.70516447 0.7152459  0.73234704 0.78503788 0.69697258
 0.75378788 0.78763191 0.91025899 0.62622429]

mean value: 0.7591344320361865

key: train_mcc 
value: [0.85243167 0.85932127 0.82585078 0.81955827 0.82681976 0.87744312
 0.83333833 0.81632786 0.85539741 0.79806221]

mean value: 0.8364550698994235

key: test_accuracy 
value: [0.93846154 0.84615385 0.84615385 0.86153846 0.89230769 0.84615385
 0.87692308 0.89230769 0.953125   0.8125    ]

mean value: 0.8765625

key: train_accuracy 
value: [0.9245283  0.92795883 0.91252144 0.90909091 0.91252144 0.93653516
 0.91595197 0.90737564 0.92636986 0.8989726 ]

mean value: 0.9171826170727696

key: test_fscore 
value: [0.93939394 0.85714286 0.86111111 0.86956522 0.89230769 0.85714286
 0.87878788 0.89855072 0.95522388 0.80645161]

mean value: 0.8815677771415562

key: train_fscore 
value: [0.92786885 0.93114754 0.91457286 0.91181364 0.91514143 0.93944354
 0.91819699 0.91       0.9291598  0.89983022]

mean value: 0.9197174885838806

key: test_precision 
value: [0.91176471 0.78947368 0.775      0.81081081 0.90625    0.81081081
 0.87878788 0.86111111 0.91428571 0.83333333]

mean value: 0.8491628049232538

key: train_precision 
value: [0.88993711 0.89308176 0.89508197 0.88673139 0.88709677 0.896875
 0.89285714 0.88349515 0.8952381  0.89225589]

mean value: 0.891265027689915

key: test_recall 
value: [0.96875    0.9375     0.96875    0.9375     0.87878788 0.90909091
 0.87878788 0.93939394 1.         0.78125   ]

mean value: 0.9199810606060606

key: train_recall 
value: [0.96917808 0.97260274 0.93493151 0.93835616 0.94501718 0.9862543
 0.94501718 0.93814433 0.96575342 0.90753425]

mean value: 0.9502789154074283

key: test_roc_auc 
value: [0.93892045 0.84753788 0.84801136 0.86268939 0.89251894 0.84517045
 0.87689394 0.89157197 0.953125   0.8125    ]

mean value: 0.8768939393939394

key: train_roc_auc 
value: [0.92445158 0.92788213 0.91248294 0.90904063 0.91257708 0.9366203
 0.91600174 0.90742833 0.92636986 0.8989726 ]

mean value: 0.917182719013322

key: test_jcc 
value: [0.88571429 0.75       0.75609756 0.76923077 0.80555556 0.75
 0.78378378 0.81578947 0.91428571 0.67567568]

mean value: 0.7906132818905605

key: train_jcc 
value: [0.86544343 0.87116564 0.84259259 0.83792049 0.84355828 0.88580247
 0.84876543 0.83486239 0.86769231 0.81790123]

mean value: 0.8515704262161927

MCC on Blind test: 0.14

Accuracy on Blind test: 0.84

Model_name: Logistic RegressionCV 
Model func: LogisticRegressionCV(random_state=42) 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LogisticRegressionCV(random_state=42))])

key: fit_time 
value: [0.84224105 1.0396843  0.87281895 1.00940371 0.9135735  0.95874333
 0.91852117 0.91843176 1.03515816 0.90810609]

mean value: 0.9416682004928589

key: score_time 
value: [0.01493192 0.01542521 0.01544452 0.01656914 0.01555705 0.01606178
 0.01575232 0.01536036 0.01991749 0.02013874]

mean value: 0.01651585102081299

key: test_mcc 
value: [0.80403025 0.83005736 0.91168461 0.83005736 0.88340557 0.8291562
 0.91144345 0.94017476 0.8819171  0.8819171 ]

mean value: 0.8703843762612629

key: train_mcc 
value: [0.98976061 0.96626138 0.99316221 0.9965753  0.98976097 0.96626528
 0.98637102 0.979625   0.94014412 0.98302084]

mean value: 0.9790946737555735

key: test_accuracy 
value: [0.89230769 0.90769231 0.95384615 0.90769231 0.93846154 0.90769231
 0.95384615 0.96923077 0.9375     0.9375    ]

mean value: 0.9305769230769231

key: train_accuracy 
value: [0.9948542  0.98284734 0.99656947 0.99828473 0.9948542  0.98284734
 0.99313894 0.9897084  0.96917808 0.99143836]

mean value: 0.9893721069574003

key: test_fscore 
value: [0.90140845 0.91428571 0.95522388 0.91428571 0.94285714 0.91666667
 0.95652174 0.97058824 0.94117647 0.94117647]

mean value: 0.9354190484997501

key: train_fscore 
value: [0.99488927 0.98316498 0.99658703 0.9982906  0.99487179 0.98310811
 0.99317406 0.98979592 0.97009967 0.99151104]

mean value: 0.9895492465842408

key: test_precision 
value: [0.82051282 0.84210526 0.91428571 0.84210526 0.89189189 0.84615385
 0.91666667 0.94285714 0.88888889 0.88888889]

mean value: 0.8794356386461649

key: train_precision 
value: [0.98983051 0.96688742 0.99319728 0.99658703 0.98979592 0.96677741
 0.98644068 0.97979798 0.94193548 0.98316498]

mean value: 0.979441468712666

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.89393939 0.90909091 0.95454545 0.90909091 0.9375     0.90625
 0.953125   0.96875    0.9375     0.9375    ]

mean value: 0.9307291666666666

key: train_roc_auc 
value: [0.99484536 0.98281787 0.99656357 0.99828179 0.99486301 0.98287671
 0.99315068 0.98972603 0.96917808 0.99143836]

mean value: 0.9893741467777621

key: test_jcc 
value: [0.82051282 0.84210526 0.91428571 0.84210526 0.89189189 0.84615385
 0.91666667 0.94285714 0.88888889 0.88888889]

mean value: 0.8794356386461649

key: train_jcc 
value: [0.98983051 0.96688742 0.99319728 0.99658703 0.98979592 0.96677741
 0.98644068 0.97979798 0.94193548 0.98316498]

mean value: 0.979441468712666

MCC on Blind test: 0.19

Accuracy on Blind test: 0.87

Model_name: Gaussian NB 
Model func: GaussianNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianNB())])

key: fit_time 
value: [0.01498199 0.01215243 0.01155519 0.01152968 0.0115912  0.01105309
 0.0116272  0.01176739 0.01058292 0.0118258 ]

mean value: 0.01186668872833252

key: score_time 
value: [0.02086377 0.01020646 0.00974274 0.00977182 0.00932312 0.00979376
 0.00979137 0.00901008 0.00971365 0.00989032]

mean value: 0.01081070899963379

key: test_mcc 
value: [0.19678673 0.22691793 0.42989498 0.30594355 0.25423478 0.30748943
 0.34363041 0.35336971 0.38915203 0.10613237]

mean value: 0.29135519305532803

key: train_mcc 
value: [0.33756651 0.3279537  0.33061195 0.30625707 0.31818758 0.29648123
 0.31818758 0.28123139 0.29393809 0.33725915]

mean value: 0.3147674269174375

key: test_accuracy 
value: [0.58461538 0.6        0.69230769 0.63076923 0.61538462 0.63076923
 0.66153846 0.66153846 0.671875   0.546875  ]

mean value: 0.6295673076923077

key: train_accuracy 
value: [0.6535163  0.6483705  0.64493997 0.6380789  0.6432247  0.6329331
 0.6432247  0.62435678 0.63184932 0.65239726]

mean value: 0.641289151530816

key: test_fscore 
value: [0.65822785 0.66666667 0.74358974 0.7        0.69135802 0.71428571
 0.71794872 0.725      0.73417722 0.63291139]

mean value: 0.6984165322878403

key: train_fscore 
value: [0.71388102 0.71086037 0.71448276 0.70323488 0.70621469 0.69859155
 0.70621469 0.69456067 0.69845722 0.71368124]

mean value: 0.7060179087083555

key: test_precision 
value: [0.55319149 0.56521739 0.63043478 0.58333333 0.58333333 0.58823529
 0.62222222 0.61702128 0.61702128 0.53191489]

mean value: 0.5891925293089793

key: train_precision 
value: [0.60869565 0.60431655 0.59815242 0.59665871 0.59952038 0.59188544
 0.59952038 0.58450704 0.59144893 0.60671463]

mean value: 0.598142014567676

key: test_recall 
value: [0.8125     0.8125     0.90625    0.875      0.84848485 0.90909091
 0.84848485 0.87878788 0.90625    0.78125   ]

mean value: 0.8578598484848485

key: train_recall 
value: [0.8630137  0.8630137  0.8869863  0.85616438 0.85910653 0.85223368
 0.85910653 0.8556701  0.85273973 0.86643836]

mean value: 0.8614473002871534

key: test_roc_auc 
value: [0.58806818 0.6032197  0.69554924 0.6344697  0.61174242 0.62642045
 0.65861742 0.65814394 0.671875   0.546875  ]

mean value: 0.6294981060606061

key: train_roc_auc 
value: [0.65315633 0.64800169 0.64452408 0.63770418 0.64359436 0.63330862
 0.64359436 0.62475286 0.63184932 0.65239726]

mean value: 0.6412883067363366

key: test_jcc 
value: [0.49056604 0.5        0.59183673 0.53846154 0.52830189 0.55555556
 0.56       0.56862745 0.58       0.46296296]

mean value: 0.5376312167182629

key: train_jcc 
value: [0.55506608 0.55142232 0.55579399 0.54229935 0.54585153 0.53679654
 0.54585153 0.53205128 0.53663793 0.55482456]

mean value: 0.545659510748145

MCC on Blind test: 0.17

Accuracy on Blind test: 0.52

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.01223803 0.01213884 0.01214671 0.01096129 0.01079917 0.01217866
 0.01092148 0.01078749 0.01121664 0.01081061]

mean value: 0.011419892311096191

key: score_time 
value: [0.00960898 0.00971127 0.00994253 0.00925398 0.00981116 0.01001668
 0.0091517  0.00931573 0.00952816 0.0095005 ]

mean value: 0.00958406925201416

key: test_mcc 
value: [0.54591405 0.42714107 0.45048355 0.51238932 0.51782513 0.51053958
 0.42970381 0.54981488 0.51639778 0.35228194]

mean value: 0.4812491111861127

key: train_mcc 
value: [0.54577313 0.50800592 0.44151736 0.48500674 0.54779323 0.56548054
 0.50452644 0.55769881 0.42529648 0.58854301]

mean value: 0.5169641656226446

key: test_accuracy 
value: [0.76923077 0.70769231 0.72307692 0.75384615 0.75384615 0.75384615
 0.70769231 0.76923077 0.75       0.671875  ]

mean value: 0.7360336538461538

key: train_accuracy 
value: [0.76672384 0.75128645 0.72041166 0.74099485 0.77186964 0.77701544
 0.74957118 0.77358491 0.71232877 0.78938356]

mean value: 0.7553170304753402

key: test_fscore 
value: [0.7826087  0.73239437 0.73529412 0.76470588 0.73333333 0.77142857
 0.74666667 0.79452055 0.77777778 0.70422535]

mean value: 0.7542955311113587

key: train_fscore 
value: [0.78947368 0.76874003 0.72878536 0.75526742 0.78444084 0.796875
 0.76602564 0.79310345 0.72       0.80690738]

mean value: 0.7709618807285279

key: test_precision 
value: [0.72972973 0.66666667 0.69444444 0.72222222 0.81481481 0.72972973
 0.66666667 0.725      0.7        0.64102564]

mean value: 0.7090299915299915

key: train_precision 
value: [0.72033898 0.71940299 0.70873786 0.71692308 0.74233129 0.73065903
 0.71771772 0.72910663 0.7012987  0.74492754]

mean value: 0.7231443806748123

key: test_recall 
value: [0.84375    0.8125     0.78125    0.8125     0.66666667 0.81818182
 0.84848485 0.87878788 0.875      0.78125   ]

mean value: 0.8118371212121213

key: train_recall 
value: [0.87328767 0.82534247 0.75       0.79794521 0.83161512 0.87628866
 0.82130584 0.86941581 0.73972603 0.88013699]

mean value: 0.8265063785717648

key: test_roc_auc 
value: [0.77035985 0.7092803  0.72395833 0.75473485 0.75520833 0.75284091
 0.70549242 0.76751894 0.75       0.671875  ]

mean value: 0.736126893939394

key: train_roc_auc 
value: [0.76654074 0.75115921 0.72036082 0.740897   0.77197194 0.77718543
 0.74969402 0.773749   0.71232877 0.78938356]

mean value: 0.7553270489102293

key: test_jcc 
value: [0.64285714 0.57777778 0.58139535 0.61904762 0.57894737 0.62790698
 0.59574468 0.65909091 0.63636364 0.54347826]

mean value: 0.6062609720860163

key: train_jcc 
value: [0.65217391 0.62435233 0.57329843 0.60677083 0.64533333 0.66233766
 0.62077922 0.65714286 0.5625     0.67631579]

mean value: 0.6281004370369159

MCC on Blind test: -0.02

Accuracy on Blind test: 0.67

Model_name: K-Nearest Neighbors 
Model func: KNeighborsClassifier() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', KNeighborsClassifier())])

key: fit_time 
value: [0.01161218 0.01073384 0.01169538 0.011518   0.01158452 0.01138449
 0.01132417 0.01091003 0.01119661 0.01145172]

mean value: 0.011341094970703125

key: score_time 
value: [0.01320648 0.01457477 0.0145638  0.01410818 0.01411867 0.01438308
 0.01363206 0.01349115 0.01319051 0.01353502]

mean value: 0.013880372047424316

key: test_mcc 
value: [0.77849894 0.7287143  0.85663571 0.77849894 0.8291562  0.75148662
 0.75148662 0.77695466 0.72374686 0.74898305]

mean value: 0.7724161906523206

key: train_mcc 
value: [0.8261068  0.8379218  0.83200103 0.83495806 0.84395394 0.83505221
 0.83209861 0.83209861 0.82350526 0.82350526]

mean value: 0.8321201593327054

key: test_accuracy 
value: [0.87692308 0.84615385 0.92307692 0.87692308 0.90769231 0.86153846
 0.86153846 0.87692308 0.84375    0.859375  ]

mean value: 0.8733894230769231

key: train_accuracy 
value: [0.90566038 0.91252144 0.90909091 0.91080617 0.91595197 0.91080617
 0.90909091 0.90909091 0.90410959 0.90410959]

mean value: 0.909123804600672

key: test_fscore 
value: [0.88888889 0.86486486 0.92753623 0.88888889 0.91666667 0.88
 0.88       0.89189189 0.86486486 0.87671233]

mean value: 0.8880314626717247

key: train_fscore 
value: [0.91392801 0.91968504 0.91679749 0.91823899 0.92234548 0.91798107
 0.91653543 0.91653543 0.9125     0.9125    ]

mean value: 0.9167046955883076

key: test_precision 
value: [0.8        0.76190476 0.86486486 0.8        0.84615385 0.78571429
 0.78571429 0.80487805 0.76190476 0.7804878 ]

mean value: 0.7991622659915343

key: train_precision 
value: [0.84149856 0.85131195 0.84637681 0.84883721 0.85588235 0.8483965
 0.84593023 0.84593023 0.83908046 0.83908046]

mean value: 0.8462324772382519

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.87878788 0.84848485 0.92424242 0.87878788 0.90625    0.859375
 0.859375   0.875      0.84375    0.859375  ]

mean value: 0.873342803030303

key: train_roc_auc 
value: [0.90549828 0.91237113 0.90893471 0.91065292 0.91609589 0.9109589
 0.90924658 0.90924658 0.90410959 0.90410959]

mean value: 0.909122416796121

key: test_jcc 
value: [0.8        0.76190476 0.86486486 0.8        0.84615385 0.78571429
 0.78571429 0.80487805 0.76190476 0.7804878 ]

mean value: 0.7991622659915343

key: train_jcc 
value: [0.84149856 0.85131195 0.84637681 0.84883721 0.85588235 0.8483965
 0.84593023 0.84593023 0.83908046 0.83908046]

mean value: 0.8462324772382519

MCC on Blind test: 0.13

Accuracy on Blind test: 0.8

Model_name: SVM 
Model func: SVC(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SVC(random_state=42))])

key: fit_time 
value: [0.03182697 0.0288589  0.02790952 0.0295608  0.02778172 0.02629852
 0.02606511 0.02575874 0.02627993 0.02554488]

mean value: 0.027588510513305665

key: score_time 
value: [0.0145452  0.01467657 0.01521754 0.01494265 0.01376438 0.01334858
 0.01403713 0.0147779  0.01372337 0.01399994]

mean value: 0.014303326606750488

key: test_mcc 
value: [0.90814394 0.76001241 0.88382395 0.82191818 0.75545058 0.72572613
 0.8291562  0.7935502  0.78163175 0.82717019]

mean value: 0.8086583536577907

key: train_mcc 
value: [0.89453522 0.89811185 0.87454604 0.88468453 0.88056591 0.8996623
 0.92398811 0.88797834 0.86729831 0.91775339]

mean value: 0.8929124006698493

key: test_accuracy 
value: [0.95384615 0.87692308 0.93846154 0.90769231 0.87692308 0.86153846
 0.90769231 0.89230769 0.890625   0.90625   ]

mean value: 0.9012259615384616

key: train_accuracy 
value: [0.94682676 0.94854202 0.93653516 0.94168096 0.93996569 0.94854202
 0.96054889 0.94339623 0.93321918 0.95719178]

mean value: 0.9456448694753166

key: test_fscore 
value: [0.95384615 0.88235294 0.94117647 0.91176471 0.875      0.86956522
 0.91666667 0.90140845 0.88888889 0.91428571]

mean value: 0.9054955209430012

key: train_fscore 
value: [0.9480737  0.94983278 0.93843594 0.94333333 0.94097808 0.95033113
 0.96198347 0.94472362 0.93467337 0.9589491 ]

mean value: 0.9471314507474065

key: test_precision 
value: [0.93939394 0.83333333 0.88888889 0.86111111 0.90322581 0.83333333
 0.84615385 0.84210526 0.90322581 0.84210526]

mean value: 0.8692876591433467

key: train_precision 
value: [0.92786885 0.92810458 0.91262136 0.91883117 0.92384106 0.91693291
 0.92675159 0.92156863 0.9147541  0.92113565]

mean value: 0.9212409887483798

key: test_recall 
value: [0.96875    0.9375     1.         0.96875    0.84848485 0.90909091
 1.         0.96969697 0.875      1.        ]

mean value: 0.9477272727272728

key: train_recall 
value: [0.96917808 0.97260274 0.96575342 0.96917808 0.95876289 0.9862543
 1.         0.96907216 0.95547945 1.        ]

mean value: 0.9746281127900955

key: test_roc_auc 
value: [0.95407197 0.87784091 0.93939394 0.90861742 0.87736742 0.86079545
 0.90625    0.89109848 0.890625   0.90625   ]

mean value: 0.9012310606060606

key: train_roc_auc 
value: [0.94678835 0.94850068 0.93648496 0.94163371 0.93999788 0.9486066
 0.96061644 0.94344019 0.93321918 0.95719178]

mean value: 0.9456479781575107

key: test_jcc 
value: [0.91176471 0.78947368 0.88888889 0.83783784 0.77777778 0.76923077
 0.84615385 0.82051282 0.8        0.84210526]

mean value: 0.8283745593652714

key: train_jcc 
value: [0.90127389 0.9044586  0.88401254 0.89274448 0.88853503 0.90536278
 0.92675159 0.8952381  0.87735849 0.92113565]

mean value: 0.8996871135477543

MCC on Blind test: 0.06

Accuracy on Blind test: 0.86

Model_name: MLP 
Model func: MLPClassifier(max_iter=500, random_state=42) 
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  warnings.warn(
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MLPClassifier(max_iter=500, random_state=42))])

key: fit_time 
value: [2.29923701 2.24889135 2.20340872 2.39515138 2.21263361 2.2729845
 2.20828414 2.19532013 2.1394341  2.22791529]

mean value: 2.2403260231018067

key: score_time 
value: [0.0132978  0.01880932 0.01257491 0.01510024 0.01275301 0.01275826
 0.0150218  0.01252794 0.01292801 0.01483226]

mean value: 0.014060354232788086

key: test_mcc 
value: [0.96969697 0.85663571 1.         0.91168461 0.96966868 0.85599665
 0.91144345 0.91144345 0.91025899 0.93933644]

mean value: 0.9236164950035539

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.98461538 0.92307692 1.         0.95384615 0.98461538 0.92307692
 0.95384615 0.95384615 0.953125   0.96875   ]

mean value: 0.9598798076923077

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.98461538 0.92753623 1.         0.95522388 0.98507463 0.92957746
 0.95652174 0.95652174 0.95522388 0.96969697]

mean value: 0.9619991917305716

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.96969697 0.86486486 1.         0.91428571 0.97058824 0.86842105
 0.91666667 0.91666667 0.91428571 0.94117647]

mean value: 0.9276652354980528

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.98484848 0.92424242 1.         0.95454545 0.984375   0.921875
 0.953125   0.953125   0.953125   0.96875   ]

mean value: 0.9598011363636364

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.96969697 0.86486486 1.         0.91428571 0.97058824 0.86842105
 0.91666667 0.91666667 0.91428571 0.94117647]

mean value: 0.9276652354980528

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: -0.03

Accuracy on Blind test: 0.9

Model_name: Decision Tree 
Model func: DecisionTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', DecisionTreeClassifier(random_state=42))])

key: fit_time 
value: [0.03853536 0.02843142 0.02515435 0.02727842 0.02360392 0.02490282
 0.02359962 0.02525878 0.02376103 0.02358556]

mean value: 0.02641112804412842

key: score_time 
value: [0.01263428 0.01008964 0.00967503 0.00938606 0.00941706 0.00909281
 0.00908589 0.00929618 0.0090282  0.00904346]

mean value: 0.009674859046936036

key: test_mcc 
value: [0.96969697 0.94028478 0.91168461 0.94028478 0.94017476 0.91144345
 1.         0.94017476 0.91025899 0.91025899]

mean value: 0.9374262090063642

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.98461538 0.96923077 0.95384615 0.96923077 0.96923077 0.95384615
 1.         0.96923077 0.953125   0.953125  ]

mean value: 0.967548076923077

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.98461538 0.96969697 0.95522388 0.96969697 0.97058824 0.95652174
 1.         0.97058824 0.95522388 0.95522388]

mean value: 0.968737917551904

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.96969697 0.94117647 0.91428571 0.94117647 0.94285714 0.91666667
 1.         0.94285714 0.91428571 0.91428571]

mean value: 0.9397288006111535

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.98484848 0.96969697 0.95454545 0.96969697 0.96875    0.953125
 1.         0.96875    0.953125   0.953125  ]

mean value: 0.9675662878787878

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.96969697 0.94117647 0.91428571 0.94117647 0.94285714 0.91666667
 1.         0.94285714 0.91428571 0.91428571]

mean value: 0.9397288006111535

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.48

Accuracy on Blind test: 0.93

Model_name: Extra Trees 
Model func: ExtraTreesClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreesClassifier(random_state=42))])

key: fit_time 
value: [0.11725593 0.11946774 0.12943268 0.13295674 0.1286943  0.11638618
 0.1168642  0.1186254  0.11677861 0.11604857]

mean value: 0.1212510347366333

key: score_time 
value: [0.01795173 0.01999903 0.01983118 0.01986241 0.01773834 0.01775241
 0.01779103 0.01778221 0.01765633 0.0175786 ]

mean value: 0.018394327163696288

key: test_mcc 
value: [1.         0.94028478 1.         1.         0.96966868 1.
 1.         1.         0.93933644 1.        ]

mean value: 0.984928990126414

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [1.         0.96923077 1.         1.         0.98461538 1.
 1.         1.         0.96875    1.        ]

mean value: 0.9922596153846154

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [1.         0.96969697 1.         1.         0.98507463 1.
 1.         1.         0.96969697 1.        ]

mean value: 0.9924468566259611

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [1.         0.94117647 1.         1.         0.97058824 1.
 1.         1.         0.94117647 1.        ]

mean value: 0.9852941176470589

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [1.         0.96969697 1.         1.         0.984375   1.
 1.         1.         0.96875    1.        ]

mean value: 0.992282196969697

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [1.         0.94117647 1.         1.         0.97058824 1.
 1.         1.         0.94117647 1.        ]

mean value: 0.9852941176470589

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.25

Accuracy on Blind test: 0.92

Model_name: Extra Tree 
Model func: ExtraTreeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', ExtraTreeClassifier(random_state=42))])

key: fit_time 
value: [0.01046395 0.01063585 0.01049542 0.01052618 0.01028848 0.0104053
 0.0105176  0.01052761 0.01046443 0.01030326]

mean value: 0.010462808609008788

key: score_time 
value: [0.00906444 0.00880194 0.00879192 0.00883579 0.00878119 0.00875998
 0.0088048  0.00871205 0.00875258 0.00871849]

mean value: 0.008802318572998047

key: test_mcc 
value: [0.88382395 0.7287143  0.96969697 0.91168461 0.88340557 0.88340557
 0.91144345 0.96966868 0.8819171  0.93933644]

mean value: 0.8963096654567525

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.93846154 0.84615385 0.98461538 0.95384615 0.93846154 0.93846154
 0.95384615 0.98461538 0.9375     0.96875   ]

mean value: 0.9444711538461539

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.94117647 0.86486486 0.98461538 0.95522388 0.94285714 0.94285714
 0.95652174 0.98507463 0.94117647 0.96969697]

mean value: 0.9484064692661097

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.88888889 0.76190476 0.96969697 0.91428571 0.89189189 0.89189189
 0.91666667 0.97058824 0.88888889 0.94117647]

mean value: 0.9035880379998027

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.93939394 0.84848485 0.98484848 0.95454545 0.9375     0.9375
 0.953125   0.984375   0.9375     0.96875   ]

mean value: 0.9446022727272727

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.88888889 0.76190476 0.96969697 0.91428571 0.89189189 0.89189189
 0.91666667 0.97058824 0.88888889 0.94117647]

mean value: 0.9035880379998027

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.13

Accuracy on Blind test: 0.89

Model_name: Random Forest 
Model func: RandomForestClassifier(n_estimators=1000, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(n_estimators=1000, random_state=42))])

key: fit_time 
value: [1.63480306 1.6422596  1.63659716 1.64672923 1.64224148 1.64532304
 1.63788843 1.64187598 1.6310873  1.62848496]

mean value: 1.6387290239334107

key: score_time 
value: [0.09194922 0.09221864 0.09211254 0.09215569 0.09183455 0.09223676
 0.09230447 0.09206653 0.09145308 0.09079313]

mean value: 0.09191246032714843

key: test_mcc 
value: [1.         0.96969697 0.96969697 0.96969697 0.96966868 1.
 1.         1.         0.96922337 1.        ]

mean value: 0.9847982960332209

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [1.         0.98461538 0.98461538 0.98461538 0.98461538 1.
 1.         1.         0.984375   1.        ]

mean value: 0.9922836538461539

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [1.         0.98461538 0.98461538 0.98461538 0.98507463 1.
 1.         1.         0.98461538 1.        ]

mean value: 0.992353616532721

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [1.         0.96969697 0.96969697 0.96969697 0.97058824 1.
 1.         1.         0.96969697 1.        ]

mean value: 0.9849376114081997

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [1.         0.98484848 0.98484848 0.98484848 0.984375   1.
 1.         1.         0.984375   1.        ]

mean value: 0.9923295454545454

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [1.         0.96969697 0.96969697 0.96969697 0.97058824 1.
 1.         1.         0.96969697 1.        ]

mean value: 0.9849376114081997

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.36

Accuracy on Blind test: 0.93

Model_name: Random Forest2 
Model func: RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...05', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                                        n_estimators=1000, n_jobs=10,
                                        oob_score=True, random_state=42))])

key: fit_time 
value: [0.90825748 1.03018761 0.991642   1.00335169 0.97958708 0.99142098
 0.96074009 1.00840521 1.03518343 0.96110916]

mean value: 0.9869884729385376

key: score_time 
value: [0.26518273 0.21562219 0.25169134 0.28403592 0.19426227 0.17347264
 0.24130011 0.22081041 0.19871473 0.25657582]

mean value: 0.23016681671142578

key: test_mcc 
value: [1.         0.94028478 0.91168461 0.94028478 0.96966868 0.96966868
 1.         0.96966868 0.93933644 0.93933644]

mean value: 0.9579933096251564

key: train_mcc 
value: [0.98299141 0.98637038 0.98637038 0.98637038 0.98637102 0.9829924
 0.9829924  0.98637102 0.98639392 0.98302084]

mean value: 0.9850244174242655

key: test_accuracy 
value: [1.         0.96923077 0.95384615 0.96923077 0.98461538 0.98461538
 1.         0.98461538 0.96875    0.96875   ]

mean value: 0.9783653846153846

key: train_accuracy 
value: [0.99142367 0.99313894 0.99313894 0.99313894 0.99313894 0.99142367
 0.99142367 0.99313894 0.99315068 0.99143836]

mean value: 0.9924554735778566

key: test_fscore 
value: [1.         0.96969697 0.95522388 0.96969697 0.98507463 0.98507463
 1.         0.98507463 0.96969697 0.96969697]

mean value: 0.9789235639981909

key: train_fscore 
value: [0.99151104 0.99319728 0.99319728 0.99319728 0.99317406 0.99148211
 0.99148211 0.99317406 0.99319728 0.99151104]

mean value: 0.9925123534692686

key: test_precision 
value: [1.         0.94117647 0.91428571 0.94117647 0.97058824 0.97058824
 1.         0.97058824 0.94117647 0.94117647]

mean value: 0.9590756302521009

key: train_precision 
value: [0.98316498 0.98648649 0.98648649 0.98648649 0.98644068 0.98310811
 0.98310811 0.98644068 0.98648649 0.98316498]/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
  warn(


mean value: 0.9851373484424332

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [1.         0.96969697 0.95454545 0.96969697 0.984375   0.984375
 1.         0.984375   0.96875    0.96875   ]

mean value: 0.9784564393939394

key: train_roc_auc 
value: [0.99140893 0.99312715 0.99312715 0.99312715 0.99315068 0.99143836
 0.99143836 0.99315068 0.99315068 0.99143836]

mean value: 0.9924557501294544

key: test_jcc 
value: [1.         0.94117647 0.91428571 0.94117647 0.97058824 0.97058824
 1.         0.97058824 0.94117647 0.94117647]

mean value: 0.9590756302521009

key: train_jcc 
value: [0.98316498 0.98648649 0.98648649 0.98648649 0.98644068 0.98310811
 0.98310811 0.98644068 0.98648649 0.98316498]

mean value: 0.9851373484424332

MCC on Blind test: 0.5

Accuracy on Blind test: 0.94

Model_name: Naive Bayes 
Model func: BernoulliNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', BernoulliNB())])

key: fit_time 
value: [0.01217985 0.01177597 0.01277018 0.01172662 0.01123691 0.01213551
 0.01210856 0.01089239 0.010638   0.01056147]

mean value: 0.011602544784545898

key: score_time 
value: [0.00999904 0.00990224 0.00991368 0.00980997 0.00969315 0.00975943
 0.00983715 0.00897145 0.00892138 0.00886154]

mean value: 0.009566903114318848

key: test_mcc 
value: [0.54591405 0.42714107 0.45048355 0.51238932 0.51782513 0.51053958
 0.42970381 0.54981488 0.51639778 0.35228194]

mean value: 0.4812491111861127

key: train_mcc 
value: [0.54577313 0.50800592 0.44151736 0.48500674 0.54779323 0.56548054
 0.50452644 0.55769881 0.42529648 0.58854301]

mean value: 0.5169641656226446

key: test_accuracy 
value: [0.76923077 0.70769231 0.72307692 0.75384615 0.75384615 0.75384615
 0.70769231 0.76923077 0.75       0.671875  ]

mean value: 0.7360336538461538

key: train_accuracy 
value: [0.76672384 0.75128645 0.72041166 0.74099485 0.77186964 0.77701544
 0.74957118 0.77358491 0.71232877 0.78938356]

mean value: 0.7553170304753402

key: test_fscore 
value: [0.7826087  0.73239437 0.73529412 0.76470588 0.73333333 0.77142857
 0.74666667 0.79452055 0.77777778 0.70422535]

mean value: 0.7542955311113587

key: train_fscore 
value: [0.78947368 0.76874003 0.72878536 0.75526742 0.78444084 0.796875
 0.76602564 0.79310345 0.72       0.80690738]

mean value: 0.7709618807285279

key: test_precision 
value: [0.72972973 0.66666667 0.69444444 0.72222222 0.81481481 0.72972973
 0.66666667 0.725      0.7        0.64102564]

mean value: 0.7090299915299915

key: train_precision 
value: [0.72033898 0.71940299 0.70873786 0.71692308 0.74233129 0.73065903
 0.71771772 0.72910663 0.7012987  0.74492754]

mean value: 0.7231443806748123

key: test_recall 
value: [0.84375    0.8125     0.78125    0.8125     0.66666667 0.81818182
 0.84848485 0.87878788 0.875      0.78125   ]

mean value: 0.8118371212121213

key: train_recall 
value: [0.87328767 0.82534247 0.75       0.79794521 0.83161512 0.87628866
 0.82130584 0.86941581 0.73972603 0.88013699]

mean value: 0.8265063785717648

key: test_roc_auc 
value: [0.77035985 0.7092803  0.72395833 0.75473485 0.75520833 0.75284091
 0.70549242 0.76751894 0.75       0.671875  ]

mean value: 0.736126893939394

key: train_roc_auc 
value: [0.76654074 0.75115921 0.72036082 0.740897   0.77197194 0.77718543
 0.74969402 0.773749   0.71232877 0.78938356]

mean value: 0.7553270489102293

key: test_jcc 
value: [0.64285714 0.57777778 0.58139535 0.61904762 0.57894737 0.62790698
 0.59574468 0.65909091 0.63636364 0.54347826]

mean value: 0.6062609720860163

key: train_jcc 
value: [0.65217391 0.62435233 0.57329843 0.60677083 0.64533333 0.66233766
 0.62077922 0.65714286 0.5625     0.67631579]

mean value: 0.6281004370369159

MCC on Blind test: -0.02

Accuracy on Blind test: 0.67

Model_name: XGBoost 
Model func: XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
              colsample_bynode=None, colsample_bytree=None,
              enable_categorical=False, gamma=None, gpu_id=None,
              importance_type=None, interaction_constraints=None,
              learning_rate=None, max_delta_step=None, max_depth=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
              scale_pos_weight=None, subsample=None, tree_method=None,
              use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000...
                               interaction_constraints=None, learning_rate=None,
                               max_delta_step=None, max_depth=None,
                               min_child_weight=None, missing=nan,
                               monotone_constraints=None, n_estimators=100,
                               n_jobs=None, num_parallel_tree=None,
                               predictor=None, random_state=42, reg_alpha=None,
                               reg_lambda=None, scale_pos_weight=None,
                               subsample=None, tree_method=None,
                               use_label_encoder=False,
                               validate_parameters=None, verbosity=0))])

key: fit_time 
value: [0.10760784 0.08884239 0.09322405 0.09264636 0.08951044 0.0939033
 0.09080219 0.09187436 0.0901165  0.08882475]

mean value: 0.09273521900177002

key: score_time 
value: [0.0112102  0.01109529 0.01115131 0.01122785 0.01118112 0.01140642
 0.011096   0.0109508  0.01109266 0.01138234]

mean value: 0.011179399490356446

key: test_mcc 
value: [0.96969697 0.94028478 0.91168461 0.88382395 0.96966868 0.96966868
 0.94017476 0.94017476 0.91025899 0.93933644]

mean value: 0.9374772619807376

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.98461538 0.96923077 0.95384615 0.93846154 0.98461538 0.98461538
 0.96923077 0.96923077 0.953125   0.96875   ]

mean value: 0.9675721153846154

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.98461538 0.96969697 0.95522388 0.94117647 0.98507463 0.98507463
 0.97058824 0.97058824 0.95522388 0.96969697]

mean value: 0.9686959280111168

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.96969697 0.94117647 0.91428571 0.88888889 0.97058824 0.97058824
 0.94285714 0.94285714 0.91428571 0.94117647]

mean value: 0.9396400984636278

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.98484848 0.96969697 0.95454545 0.93939394 0.984375   0.984375
 0.96875    0.96875    0.953125   0.96875   ]

mean value: 0.9676609848484848

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.96969697 0.94117647 0.91428571 0.88888889 0.97058824 0.97058824
 0.94285714 0.94285714 0.91428571 0.94117647]

mean value: 0.9396400984636278

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.59

Accuracy on Blind test: 0.94

Model_name: LDA 
Model func: LinearDiscriminantAnalysis() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', LinearDiscriminantAnalysis())])

key: fit_time 
value: [0.05063415 0.04425192 0.07656264 0.09184074 0.06914711 0.04449272
 0.0849452  0.06077504 0.0754478  0.04349518]

mean value: 0.06415925025939942

key: score_time 
value: [0.012187   0.0123415  0.01836634 0.01906538 0.01233792 0.02319288
 0.03892374 0.01880527 0.01228619 0.01224875]

mean value: 0.017975497245788574

key: test_mcc 
value: [0.75341057 0.70436073 0.83005736 0.83005736 0.80282704 0.77695466
 0.8291562  0.80282704 0.8819171  0.82717019]

mean value: 0.8038738234198813

key: train_mcc 
value: [0.9018561  0.90812957 0.90812957 0.89873229 0.88945349 0.88945349
 0.88636547 0.90501954 0.88961286 0.89270548]

mean value: 0.8969457849586407

key: test_accuracy 
value: [0.86153846 0.83076923 0.90769231 0.90769231 0.89230769 0.87692308
 0.90769231 0.89230769 0.9375     0.90625   ]

mean value: 0.8920673076923077

key: train_accuracy 
value: [0.94854202 0.95197256 0.95197256 0.94682676 0.94168096 0.94168096
 0.93996569 0.95025729 0.94178082 0.94349315]

mean value: 0.9458172771916633

key: test_fscore 
value: [0.87671233 0.85333333 0.91428571 0.91428571 0.90410959 0.89189189
 0.91666667 0.90410959 0.94117647 0.91428571]

mean value: 0.9030857012186585

key: train_fscore 
value: [0.95114007 0.95424837 0.95424837 0.9495935  0.94480519 0.94480519
 0.94327391 0.95253682 0.94498382 0.9465154 ]

mean value: 0.9486150629444966

key: test_precision 
value: [0.7804878  0.74418605 0.84210526 0.84210526 0.825      0.80487805
 0.84615385 0.825      0.88888889 0.84210526]

mean value: 0.8240910424686584

key: train_precision 
value: [0.9068323  0.9125     0.9125     0.90402477 0.89538462 0.89538462
 0.89263804 0.909375   0.89570552 0.89846154]

mean value: 0.9022806393451481

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.86363636 0.83333333 0.90909091 0.90909091 0.890625   0.875
 0.90625    0.890625   0.9375     0.90625   ]

mean value: 0.8921401515151515

key: train_roc_auc 
value: [0.94845361 0.95189003 0.95189003 0.9467354  0.94178082 0.94178082
 0.94006849 0.95034247 0.94178082 0.94349315]

mean value: 0.9458215647507414

key: test_jcc 
value: [0.7804878  0.74418605 0.84210526 0.84210526 0.825      0.80487805
 0.84615385 0.825      0.88888889 0.84210526]

mean value: 0.8240910424686584

key: train_jcc 
value: [0.9068323  0.9125     0.9125     0.90402477 0.89538462 0.89538462
 0.89263804 0.909375   0.89570552 0.89846154]

mean value: 0.9022806393451481

MCC on Blind test: 0.23

Accuracy on Blind test: 0.81

Model_name: Multinomial 
Model func: MultinomialNB() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', MultinomialNB())])

key: fit_time 
value: [0.01436424 0.01114702 0.01046348 0.01003289 0.01020837 0.01039195
 0.01198506 0.01129222 0.01113153 0.01129103]

mean value: 0.011230778694152833

key: score_time 
value: [0.01192999 0.00940728 0.00917029 0.00874305 0.00866723 0.00872612
 0.00957513 0.00902653 0.00877285 0.00914168]

mean value: 0.009316015243530273

key: test_mcc 
value: [0.08070002 0.14095468 0.17304806 0.29439816 0.26476623 0.23106061
 0.2315322  0.4157197  0.12909944 0.        ]

mean value: 0.19612790980806505

key: train_mcc 
value: [0.26964669 0.19442061 0.24192545 0.22142777 0.24223804 0.20154369
 0.22571551 0.18088738 0.20587098 0.25583644]

mean value: 0.2239512556529534

key: test_accuracy 
value: [0.53846154 0.56923077 0.58461538 0.64615385 0.63076923 0.61538462
 0.61538462 0.70769231 0.5625     0.5       ]

mean value: 0.5970192307692308

key: train_accuracy 
value: [0.6329331  0.59691252 0.62092624 0.61063465 0.62092624 0.60034305
 0.61234991 0.59005146 0.60273973 0.62671233]

mean value: 0.61145292417585

key: test_fscore 
value: [0.57142857 0.58823529 0.60869565 0.65671642 0.61290323 0.61538462
 0.64788732 0.70769231 0.61111111 0.54285714]

mean value: 0.616291166242587

key: train_fscore 
value: [0.66246057 0.61412151 0.62731872 0.61976549 0.62981575 0.61614498
 0.62828947 0.6062603  0.61461794 0.65064103]

mean value: 0.6269435747761918

key: test_precision 
value: [0.52631579 0.55555556 0.56756757 0.62857143 0.65517241 0.625
 0.60526316 0.71875    0.55       0.5       ]

mean value: 0.5932195912856076

key: train_precision 
value: [0.61403509 0.58990536 0.6179402  0.60655738 0.61437908 0.59177215
 0.60252366 0.58227848 0.59677419 0.61144578]

mean value: 0.6027611380745675

key: test_recall 
value: [0.625      0.625      0.65625    0.6875     0.57575758 0.60606061
 0.6969697  0.6969697  0.6875     0.59375   ]

mean value: 0.6450757575757576

key: train_recall 
value: [0.71917808 0.64041096 0.6369863  0.63356164 0.64604811 0.64261168
 0.65635739 0.63230241 0.63356164 0.69520548]

mean value: 0.6536223697217907

key: test_roc_auc 
value: [0.53977273 0.57007576 0.58570076 0.6467803  0.63162879 0.6155303
 0.61410985 0.70785985 0.5625     0.5       ]

mean value: 0.5973958333333333

key: train_roc_auc 
value: [0.63278492 0.59683778 0.62089865 0.61059525 0.62096926 0.60041543
 0.61242527 0.59012381 0.60273973 0.62671233]

mean value: 0.6114502424328014

key: test_jcc 
value: [0.4        0.41666667 0.4375     0.48888889 0.44186047 0.44444444
 0.47916667 0.54761905 0.44       0.37254902]

mean value: 0.44686951990098367

key: train_jcc 
value: [0.49528302 0.44312796 0.45700246 0.44902913 0.4596577  0.4452381
 0.45803357 0.43498818 0.44364508 0.48218527]

mean value: 0.4568190471021385

MCC on Blind test: 0.07

Accuracy on Blind test: 0.64

Model_name: Passive Aggresive 
Model func: PassiveAggressiveClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 PassiveAggressiveClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.02348709 0.02451515 0.02574182 0.02574849 0.0234983  0.02286196
 0.02288342 0.02032018 0.0363512  0.02619815]

mean value: 0.025160574913024904

key: score_time 
value: [0.00988913 0.0113039  0.01181936 0.01191044 0.01187229 0.01182842
 0.01186371 0.01792216 0.01783681 0.02013397]

mean value: 0.013638019561767578

key: test_mcc 
value: [0.83005736 0.75545058 0.77849894 0.83005736 0.87844611 0.60805838
 0.69383917 0.46632157 0.81409158 0.8542422 ]

mean value: 0.7509063245385188

key: train_mcc 
value: [0.8649109  0.88005698 0.87098916 0.9018561  0.83667708 0.72942978
 0.8126848  0.46487515 0.86988342 0.85311819]

mean value: 0.8084481578198187

key: test_accuracy 
value: [0.90769231 0.87692308 0.87692308 0.90769231 0.93846154 0.8
 0.84615385 0.69230769 0.90625    0.921875  ]

mean value: 0.8674278846153847

key: train_accuracy 
value: [0.92795883 0.93996569 0.93138937 0.94854202 0.91595197 0.8593482
 0.90566038 0.68610635 0.93493151 0.92123288]

mean value: 0.8971087196597665

key: test_fscore 
value: [0.91428571 0.87878788 0.88888889 0.91428571 0.94117647 0.78688525
 0.84375    0.58333333 0.90909091 0.92753623]

mean value: 0.8588020387046371

key: train_fscore 
value: [0.93290735 0.94057725 0.93589744 0.95114007 0.92006525 0.84586466
 0.90265487 0.55036855 0.9347079  0.92698413]

mean value: 0.8841167461760711

key: test_precision 
value: [0.84210526 0.85294118 0.8        0.84210526 0.91428571 0.85714286
 0.87096774 0.93333333 0.88235294 0.86486486]

mean value: 0.8660099155525102

key: train_precision 
value: [0.8742515  0.93265993 0.87951807 0.9068323  0.8757764  0.93360996
 0.93065693 0.96551724 0.93793103 0.86390533]

mean value: 0.91006586917259

key: test_recall 
value: [1.         0.90625    1.         1.         0.96969697 0.72727273
 0.81818182 0.42424242 0.9375     1.        ]

mean value: 0.8783143939393939

key: train_recall 
value: [1.         0.94863014 1.         1.         0.96907216 0.77319588
 0.87628866 0.38487973 0.93150685 1.        ]

mean value: 0.8883573412418209

key: test_roc_auc 
value: [0.90909091 0.87736742 0.87878788 0.90909091 0.93797348 0.80113636
 0.84659091 0.69649621 0.90625    0.921875  ]

mean value: 0.8684659090909091

key: train_roc_auc 
value: [0.92783505 0.93995081 0.93127148 0.94845361 0.91604293 0.85920068
 0.90561008 0.68559055 0.93493151 0.92123288]

mean value: 0.8970119568799134

key: test_jcc 
value: [0.84210526 0.78378378 0.8        0.84210526 0.88888889 0.64864865
 0.72972973 0.41176471 0.83333333 0.86486486]

mean value: 0.7645224481447391

key: train_jcc 
value: [0.8742515  0.88782051 0.87951807 0.9068323  0.85196375 0.73289902
 0.82258065 0.37966102 0.87741935 0.86390533]

mean value: 0.8076851491670111

MCC on Blind test: 0.35

Accuracy on Blind test: 0.93

Model_name: Stochastic GDescent 
Model func: SGDClassifier(n_jobs=10, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', SGDClassifier(n_jobs=10, random_state=42))])

key: fit_time 
value: [0.02317524 0.05044103 0.02148104 0.03122425 0.02698755 0.01972318
 0.02172518 0.0217917  0.02196026 0.02300739]

mean value: 0.0261516809463501

key: score_time 
value: [0.01553392 0.02089071 0.01182866 0.01298642 0.0189147  0.01208305
 0.012326   0.01187444 0.01187134 0.01183939]

mean value: 0.014014863967895507

key: test_mcc 
value: [0.85663571 0.72322307 0.7287143  0.75545058 0.85599665 0.57429509
 0.726372   0.80282704 0.32025631 0.84416229]

mean value: 0.7187933027079934

key: train_mcc 
value: [0.89561696 0.88768384 0.79126456 0.85976508 0.85291877 0.72310774
 0.70226564 0.87409444 0.46145488 0.88849334]

mean value: 0.7936665251590732

key: test_accuracy 
value: [0.92307692 0.86153846 0.84615385 0.87692308 0.92307692 0.78461538
 0.84615385 0.89230769 0.625      0.921875  ]

mean value: 0.8500721153846154

key: train_accuracy 
value: [0.94511149 0.94339623 0.88507719 0.9296741  0.92109777 0.85763293
 0.83018868 0.93310463 0.67979452 0.94349315]

mean value: 0.8868570690100801

key: test_fscore 
value: [0.92753623 0.85714286 0.86486486 0.87878788 0.92957746 0.77419355
 0.86842105 0.90410959 0.45454545 0.92307692]

mean value: 0.838225586515054

key: train_fscore 
value: [0.94805195 0.94220665 0.89708141 0.92869565 0.92675159 0.84601113
 0.85462555 0.93719807 0.53366584 0.94509151]

mean value: 0.8759379360357865

key: test_precision 
value: [0.86486486 0.87096774 0.76190476 0.85294118 0.86842105 0.82758621
 0.76744186 0.825      0.83333333 0.90909091]

mean value: 0.8381551907593188

key: train_precision 
value: [0.90123457 0.96415771 0.81337047 0.9434629  0.86350148 0.91935484
 0.74615385 0.88181818 0.98165138 0.91909385]

mean value: 0.8933799222699237

key: test_recall 
value: [1.         0.84375    1.         0.90625    1.         0.72727273
 1.         1.         0.3125     0.9375    ]

mean value: 0.8727272727272727

key: train_recall 
value: [1.         0.92123288 1.         0.91438356 1.         0.78350515
 1.         1.         0.36643836 0.97260274]

mean value: 0.895816268888575

key: test_roc_auc 
value: [0.92424242 0.86126894 0.84848485 0.87736742 0.921875   0.78551136
 0.84375    0.890625   0.625      0.921875  ]

mean value: 0.8500000000000001

key: train_roc_auc 
value: [0.94501718 0.94343431 0.88487973 0.92970037 0.92123288 0.857506
 0.83047945 0.93321918 0.67979452 0.94349315]

mean value: 0.886875676693499

key: test_jcc 
value: [0.86486486 0.75       0.76190476 0.78378378 0.86842105 0.63157895
 0.76744186 0.825      0.29411765 0.85714286]

mean value: 0.7404255775220208

key: train_jcc 
value: [0.90123457 0.89072848 0.81337047 0.86688312 0.86350148 0.73311897
 0.74615385 0.88181818 0.36394558 0.89589905]

mean value: 0.7956653749714847

MCC on Blind test: 0.35

Accuracy on Blind test: 0.93

Model_name: AdaBoost Classifier 
Model func: AdaBoostClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', AdaBoostClassifier(random_state=42))])

key: fit_time 
value: [0.18650293 0.17165112 0.17229891 0.17193842 0.17386103 0.17276812
 0.17192197 0.17404485 0.1718421  0.17594957]

mean value: 0.1742779016494751

key: score_time 
value: [0.01533413 0.01535606 0.01543331 0.01528668 0.01527905 0.01545119
 0.01554418 0.01539397 0.01541591 0.01535726]

mean value: 0.015385174751281738

key: test_mcc 
value: [0.96969697 0.85663571 0.85663571 0.83005736 0.94017476 0.94017476
 0.96966868 0.94017476 0.93933644 0.93933644]

mean value: 0.9181891562217024

key: train_mcc 
value: [0.9965753  0.9965753  1.         0.99316221 1.         0.98976097
 0.99657534 0.99657534 0.99317398 0.98639392]

mean value: 0.994879237985911

key: test_accuracy 
value: [0.98461538 0.92307692 0.92307692 0.90769231 0.96923077 0.96923077
 0.98461538 0.96923077 0.96875    0.96875   ]

mean value: 0.9568269230769231

key: train_accuracy 
value: [0.99828473 0.99828473 1.         0.99656947 1.         0.9948542
 0.99828473 0.99828473 0.99657534 0.99315068]

mean value: 0.9974288634601377

key: test_fscore 
value: [0.98461538 0.92753623 0.92753623 0.91428571 0.97058824 0.97058824
 0.98507463 0.97058824 0.96969697 0.96969697]

mean value: 0.9590206834811179

key: train_fscore 
value: [0.9982906  0.9982906  1.         0.99658703 1.         0.99487179
 0.99828473 0.99828473 0.99658703 0.99319728]

mean value: 0.9974393800065584

key: test_precision 
value: [0.96969697 0.86486486 0.86486486 0.84210526 0.94285714 0.94285714
 0.97058824 0.94285714 0.94117647 0.94117647]

mean value: 0.922304456762661

key: train_precision 
value: [0.99658703 0.99658703 1.         0.99319728 1.         0.98979592
 0.99657534 0.99657534 0.99319728 0.98648649]

mean value: 0.9949001709041917

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.98484848 0.92424242 0.92424242 0.90909091 0.96875    0.96875
 0.984375   0.96875    0.96875    0.96875   ]

mean value: 0.9570549242424242

key: train_roc_auc 
value: [0.99828179 0.99828179 1.         0.99656357 1.         0.99486301
 0.99828767 0.99828767 0.99657534 0.99315068]

mean value: 0.9974291531327967

key: test_jcc 
value: [0.96969697 0.86486486 0.86486486 0.84210526 0.94285714 0.94285714
 0.97058824 0.94285714 0.94117647 0.94117647]

mean value: 0.922304456762661

key: train_jcc 
value: [0.99658703 0.99658703 1.         0.99319728 1.         0.98979592
 0.99657534 0.99657534 0.99319728 0.98648649]

mean value: 0.9949001709041917

MCC on Blind test: 0.42

Accuracy on Blind test: 0.91

Model_name: Bagging Classifier 
Model func: BaggingClassifier(n_jobs=10, oob_score=True, random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model',
                 BaggingClassifier(n_jobs=10, oob_score=True,
                                   random_state=42))])

key: fit_time 
value: [0.07659578 0.07157373 0.08280945 0.08775377 0.10871935 0.09558105
 0.10084009 0.10113811 0.10687089 0.09861875]

mean value: 0.09305009841918946

key: score_time 
value: [0.02109408 0.02704668 0.04142761 0.03079677 0.0253861  0.03030872
 0.02791905 0.02809644 0.02971673 0.03240538]

mean value: 0.029419755935668944

key: test_mcc 
value: [0.94028478 0.91168461 0.91168461 0.91168461 0.94017476 0.91144345
 1.         0.94017476 0.91025899 0.93933644]

mean value: 0.9316727007925569

key: train_mcc 
value: [0.9965753  0.99316221 1.         0.9965753  1.         0.99316237
 0.99657534 0.98976097 0.99658119 1.        ]

mean value: 0.9962392691600719

key: test_accuracy 
value: [0.96923077 0.95384615 0.95384615 0.95384615 0.96923077 0.95384615
 1.         0.96923077 0.953125   0.96875   ]

mean value: 0.9644951923076923

key: train_accuracy 
value: [0.99828473 0.99656947 1.         0.99828473 1.         0.99656947
 0.99828473 0.9948542  0.99828767 1.        ]

mean value: 0.9981135012570784

key: test_fscore 
value: [0.96969697 0.95522388 0.95522388 0.95522388 0.97058824 0.95652174
 1.         0.97058824 0.95522388 0.96969697]

mean value: 0.965798767150067

key: train_fscore 
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
  warn(
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
  oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
[0.9982906  0.99658703 1.         0.9982906  1.         0.99657534
 0.99828473 0.99487179 0.9982906  1.        ]

mean value: 0.9981190697059857

key: test_precision 
value: [0.94117647 0.91428571 0.91428571 0.91428571 0.94285714 0.91666667
 1.         0.94285714 0.91428571 0.94117647]

mean value: 0.934187675070028

key: train_precision 
value: [0.99658703 0.99319728 1.         0.99658703 1.         0.99317406
 0.99657534 0.98979592 0.99658703 1.        ]

mean value: 0.9962503693328283

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.96969697 0.95454545 0.95454545 0.95454545 0.96875    0.953125
 1.         0.96875    0.953125   0.96875   ]

mean value: 0.9645833333333333

key: train_roc_auc 
value: [0.99828179 0.99656357 1.         0.99828179 1.         0.99657534
 0.99828767 0.99486301 0.99828767 1.        ]

mean value: 0.998114084639646

key: test_jcc 
value: [0.94117647 0.91428571 0.91428571 0.91428571 0.94285714 0.91666667
 1.         0.94285714 0.91428571 0.94117647]

mean value: 0.934187675070028

key: train_jcc 
value: [0.99658703 0.99319728 1.         0.99658703 1.         0.99317406
 0.99657534 0.98979592 0.99658703 1.        ]

mean value: 0.9962503693328283

MCC on Blind test: 0.72

Accuracy on Blind test: 0.96

Model_name: Gaussian Process 
Model func: GaussianProcessClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GaussianProcessClassifier(random_state=42))])

key: fit_time 
value: [0.26787758 0.2549746  0.24863625 0.24087739 0.24055767 0.24235177
 0.27194905 0.2524724  0.24572325 0.25500298]

mean value: 0.252042293548584

key: score_time 
value: [0.02748966 0.02720499 0.02736878 0.02728605 0.02737689 0.02730894
 0.02735734 0.02733779 0.02703261 0.02718282]

mean value: 0.02729458808898926

key: test_mcc 
value: [0.91168461 0.80403025 0.91168461 0.91168461 0.91144345 0.80282704
 0.85599665 0.88340557 0.8819171  0.8542422 ]

mean value: 0.8728916096997283

key: train_mcc 
value: [0.97292087 0.97626677 0.96958578 0.96958578 0.96958895 0.9762687
 0.97292339 0.97292339 0.97630797 0.96963877]

mean value: 0.9726010380953438

key: test_accuracy 
value: [0.95384615 0.89230769 0.95384615 0.95384615 0.95384615 0.89230769
 0.92307692 0.93846154 0.9375     0.921875  ]

mean value: 0.9320913461538461

key: train_accuracy 
value: [0.98627787 0.98799314 0.98456261 0.98456261 0.98456261 0.98799314
 0.98627787 0.98627787 0.9880137  0.98458904]

mean value: 0.9861110458422425

key: test_fscore 
value: [0.95522388 0.90140845 0.95522388 0.95522388 0.95652174 0.90410959
 0.92957746 0.94285714 0.94117647 0.92753623]

mean value: 0.9368858730784969

key: train_fscore 
value: [0.98648649 0.98815567 0.98482293 0.98482293 0.98477157 0.98811545
 0.98644068 0.98644068 0.98815567 0.98482293]

mean value: 0.9863035005353434

key: test_precision 
value: [0.91428571 0.82051282 0.91428571 0.91428571 0.91666667 0.825
 0.86842105 0.89189189 0.88888889 0.86486486]

mean value: 0.8819103328313854

key: train_precision 
value: [0.97333333 0.97658863 0.97009967 0.97009967 0.97       0.97651007
 0.97324415 0.97324415 0.97658863 0.97009967]

mean value: 0.9729807955609151

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.95454545 0.89393939 0.95454545 0.95454545 0.953125   0.890625
 0.921875   0.9375     0.9375     0.921875  ]

mean value: 0.9320075757575758

key: train_roc_auc 
value: [0.9862543  0.98797251 0.98453608 0.98453608 0.98458904 0.9880137
 0.98630137 0.98630137 0.9880137  0.98458904]

mean value: 0.9861107188250247

key: test_jcc 
value: [0.91428571 0.82051282 0.91428571 0.91428571 0.91666667 0.825
 0.86842105 0.89189189 0.88888889 0.86486486]

mean value: 0.8819103328313854

key: train_jcc 
value: [0.97333333 0.97658863 0.97009967 0.97009967 0.97       0.97651007
 0.97324415 0.97324415 0.97658863 0.97009967]

mean value: 0.9729807955609151

MCC on Blind test: 0.13

Accuracy on Blind test: 0.86

Model_name: Gradient Boosting 
Model func: GradientBoostingClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', GradientBoostingClassifier(random_state=42))])

key: fit_time 
value: [0.66391373 0.65884423 0.65857482 0.6570735  0.65652871 0.66290188
 0.66021538 0.66108704 0.66082072 0.65878868]

mean value: 0.6598748683929443

key: score_time 
value: [0.00941205 0.00931334 0.00932384 0.00943518 0.00943756 0.00926757
 0.00938845 0.00943446 0.00942087 0.00933051]

mean value: 0.00937638282775879

key: test_mcc 
value: [0.94028478 0.88382395 0.85663571 0.91168461 0.94017476 0.96966868
 0.94017476 0.94017476 0.91025899 0.93933644]

mean value: 0.9232217430457786

key: train_mcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_accuracy 
value: [0.96923077 0.93846154 0.92307692 0.95384615 0.96923077 0.98461538
 0.96923077 0.96923077 0.953125   0.96875   ]

mean value: 0.9598798076923077

key: train_accuracy 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_fscore 
value: [0.96969697 0.94117647 0.92753623 0.95522388 0.97058824 0.98507463
 0.97058824 0.97058824 0.95522388 0.96969697]

mean value: 0.9615393735808287

key: train_fscore 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_precision 
value: [0.94117647 0.88888889 0.86486486 0.91428571 0.94285714 0.97058824
 0.94285714 0.94285714 0.91428571 0.94117647]

mean value: 0.92638377873672

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.96969697 0.93939394 0.92424242 0.95454545 0.96875    0.984375
 0.96875    0.96875    0.953125   0.96875   ]

mean value: 0.9600378787878788

key: train_roc_auc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_jcc 
value: [0.94117647 0.88888889 0.86486486 0.91428571 0.94285714 0.97058824
 0.94285714 0.94285714 0.91428571 0.94117647]

mean value: 0.92638377873672

key: train_jcc 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

MCC on Blind test: 0.68

Accuracy on Blind test: 0.95

Model_name: QDA 
Model func: QuadraticDiscriminantAnalysis() 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
  warnings.warn("Variables are collinear")
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', QuadraticDiscriminantAnalysis())])

key: fit_time 
value: [0.0450356  0.03151059 0.03181267 0.03158712 0.03178883 0.03114939
 0.03153753 0.03193092 0.03179383 0.0317831 ]

mean value: 0.03299295902252197

key: score_time 
value: [0.01232505 0.01475477 0.01303792 0.01809192 0.01550174 0.01585913
 0.01549196 0.01559973 0.01550555 0.0192318 ]

mean value: 0.015539956092834473

key: test_mcc 
value: [1.         1.         1.         1.         1.         1.
 1.         1.         1.         0.96922337]

mean value: 0.9969223369195119

key: train_mcc 
value: [1.         1.         1.         1.         1.         1.
 1.         1.         1.         0.95315095]

mean value: 0.9953150949234246

key: test_accuracy 
value: [1.       1.       1.       1.       1.       1.       1.       1.
 1.       0.984375]

mean value: 0.9984375

key: train_accuracy 
value: [1.        1.        1.        1.        1.        1.        1.
 1.        1.        0.9760274]

mean value: 0.9976027397260274

key: test_fscore 
value: [1.         1.         1.         1.         1.         1.
 1.         1.         1.         0.98412698]

mean value: 0.9984126984126984

key: train_fscore 
value: [1.        1.        1.        1.        1.        1.        1.
 1.        1.        0.9754386]

mean value: 0.9975438596491228

key: test_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_precision 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_recall 
value: [1.      1.      1.      1.      1.      1.      1.      1.      1.
 0.96875]

mean value: 0.996875

key: train_recall 
value: [1.         1.         1.         1.         1.         1.
 1.         1.         1.         0.95205479]

mean value: 0.9952054794520548

key: test_roc_auc 
value: [1.       1.       1.       1.       1.       1.       1.       1.
 1.       0.984375]

mean value: 0.9984375

key: train_roc_auc 
value: [1.        1.        1.        1.        1.        1.        1.
 1.        1.        0.9760274]

mean value: 0.9976027397260274

key: test_jcc 
value: [1.      1.      1.      1.      1.      1.      1.      1.      1.
 0.96875]

mean value: 0.996875

key: train_jcc 
value: [1.         1.         1.         1.         1.         1.
 1.         1.         1.         0.95205479]

mean value: 0.9952054794520548

MCC on Blind test: 0.0

Accuracy on Blind test: 0.91

Model_name: Ridge Classifier 
Model func: RidgeClassifier(random_state=42) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifier(random_state=42))])

key: fit_time 
value: [0.03726959 0.03467846 0.04118037 0.05077076 0.03332877 0.03175402
 0.02880526 0.04015493 0.03343964 0.02534652]

mean value: 0.03567283153533936

key: score_time 
value: [0.03105974 0.01898766 0.02504396 0.02593851 0.03050971 0.03763342
 0.0190258  0.01969433 0.01897311 0.01728129]

mean value: 0.024414753913879393

key: test_mcc 
value: [0.80403025 0.77849894 0.77849894 0.83005736 0.88340557 0.8291562
 0.88340557 0.85599665 0.91025899 0.8542422 ]

mean value: 0.8407550674668564

key: train_mcc 
value: [0.8894114  0.9112794  0.89251003 0.89561696 0.88021393 0.88636547
 0.88021393 0.89565444 0.89270548 0.88652847]

mean value: 0.8910499504571014

key: test_accuracy 
value: [0.89230769 0.87692308 0.87692308 0.90769231 0.93846154 0.90769231
 0.93846154 0.92307692 0.953125   0.921875  ]

mean value: 0.9136538461538461

key: train_accuracy 
value: [0.94168096 0.95368782 0.94339623 0.94511149 0.93653516 0.93996569
 0.93653516 0.94511149 0.94349315 0.94006849]

mean value: 0.9425585657557743

key: test_fscore 
value: [0.90140845 0.88888889 0.88888889 0.91428571 0.94285714 0.91666667
 0.94285714 0.92957746 0.95522388 0.92753623]

mean value: 0.9208190472418475

key: train_fscore 
value: [0.94498382 0.95581015 0.9465154  0.94805195 0.94022617 0.94327391
 0.94022617 0.94788274 0.9465154  0.94345719]

mean value: 0.9456942881942533

key: test_precision 
value: [0.82051282 0.8        0.8        0.84210526 0.89189189 0.84615385
 0.89189189 0.86842105 0.91428571 0.86486486]

mean value: 0.8540127345390504

key: train_precision 
value: [0.89570552 0.9153605  0.89846154 0.90123457 0.88719512 0.89263804
 0.88719512 0.90092879 0.89846154 0.89296636]/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:196: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_cd_7030.py:199: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)


mean value: 0.8970147102002286

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.89393939 0.87878788 0.87878788 0.90909091 0.9375     0.90625
 0.9375     0.921875   0.953125   0.921875  ]

mean value: 0.913873106060606

key: train_roc_auc 
value: [0.94158076 0.95360825 0.94329897 0.94501718 0.93664384 0.94006849
 0.93664384 0.94520548 0.94349315 0.94006849]

mean value: 0.9425628442310408

key: test_jcc 
value: [0.82051282 0.8        0.8        0.84210526 0.89189189 0.84615385
 0.89189189 0.86842105 0.91428571 0.86486486]

mean value: 0.8540127345390504

key: train_jcc 
value: [0.89570552 0.9153605  0.89846154 0.90123457 0.88719512 0.89263804
 0.88719512 0.90092879 0.89846154 0.89296636]

mean value: 0.8970147102002286

MCC on Blind test: 0.15

Accuracy on Blind test: 0.82

Model_name: Ridge ClassifierCV 
Model func: RidgeClassifierCV(cv=10) 
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
                       n_estimators=1000, n_jobs=10, oob_score=True,
                       random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=12,
              num_parallel_tree=1, predictor='auto', random_state=42,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
Running model pipeline: Pipeline(steps=[('prep',
                 ColumnTransformer(remainder='passthrough',
                                   transformers=[('num', MinMaxScaler(),
                                                  Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
       'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
       'mcsm_na_affinity', 'rsa',
       ...
       'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
       'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
      dtype='object', length=167)),
                                                 ('cat', OneHotEncoder(),
                                                  Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
       'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
      dtype='object'))])),
                ('model', RidgeClassifierCV(cv=10))])

key: fit_time 
value: [0.30489087 0.29502535 0.34359074 0.29409862 0.24557519 0.30722618
 0.3390739  0.31296277 0.3027482  0.22724485]

mean value: 0.29724366664886476

key: score_time 
value: [0.01903176 0.01896119 0.01887846 0.01890588 0.01899719 0.01896191
 0.01884484 0.02046967 0.01896167 0.01885223]

mean value: 0.019086480140686035

key: test_mcc 
value: [0.77849894 0.75341057 0.77849894 0.85663571 0.85599665 0.8291562
 0.8291562  0.85599665 0.91025899 0.8542422 ]

mean value: 0.8301851049137695

key: train_mcc 
value: [0.886321   0.9049885  0.89251003 0.89561696 0.89565444 0.88636547
 0.88636547 0.89565444 0.88652847 0.88652847]

mean value: 0.8916533233509137

key: test_accuracy 
value: [0.87692308 0.86153846 0.87692308 0.92307692 0.92307692 0.90769231
 0.90769231 0.92307692 0.953125   0.921875  ]

mean value: 0.9075

key: train_accuracy 
value: [0.93996569 0.95025729 0.94339623 0.94511149 0.94511149 0.93996569
 0.93996569 0.94511149 0.94006849 0.94006849]

mean value: 0.9429022063488334

key: test_fscore 
value: [0.88888889 0.87671233 0.88888889 0.92753623 0.92957746 0.91666667
 0.91666667 0.92957746 0.95522388 0.92753623]

mean value: 0.915727471382083

key: train_fscore 
value: [0.94345719 0.95269168 0.9465154  0.94805195 0.94788274 0.94327391
 0.94327391 0.94788274 0.94345719 0.94345719]

mean value: 0.9459943876745457

key: test_precision 
value: [0.8        0.7804878  0.8        0.86486486 0.86842105 0.84615385
 0.84615385 0.86842105 0.91428571 0.86486486]

mean value: 0.8453653046464343

key: train_precision 
value: [0.89296636 0.90965732 0.89846154 0.90123457 0.90092879 0.89263804
 0.89263804 0.90092879 0.89296636 0.89296636]

mean value: 0.8975386168562806

key: test_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: train_recall 
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

mean value: 1.0

key: test_roc_auc 
value: [0.87878788 0.86363636 0.87878788 0.92424242 0.921875   0.90625
 0.90625    0.921875   0.953125   0.921875  ]

mean value: 0.9076704545454546

key: train_roc_auc 
value: [0.93986254 0.95017182 0.94329897 0.94501718 0.94520548 0.94006849
 0.94006849 0.94520548 0.94006849 0.94006849]

mean value: 0.9429035446970766

key: test_jcc 
value: [0.8        0.7804878  0.8        0.86486486 0.86842105 0.84615385
 0.84615385 0.86842105 0.91428571 0.86486486]

mean value: 0.8453653046464343

key: train_jcc 
value: [0.89296636 0.90965732 0.89846154 0.90123457 0.90092879 0.89263804
 0.89263804 0.90092879 0.89296636 0.89296636]

mean value: 0.8975386168562806

MCC on Blind test: 0.15

Accuracy on Blind test: 0.82