19598 lines
965 KiB
Text
19598 lines
965 KiB
Text
/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_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: 858
|
|
|
|
PASS: my_features_df and aa_df successfully combined
|
|
nrows: 858
|
|
ncols: 269
|
|
count of NULL values before imputation
|
|
|
|
or_mychisq 244
|
|
log10_or_mychisq 244
|
|
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: 168
|
|
No. of categorical features: 7
|
|
|
|
PASS: x_features has no target variable
|
|
|
|
No. of columns for x_features: 175
|
|
|
|
-------------------------------------------------------------
|
|
Successfully split data with stratification: 70/30
|
|
Input features data size: (448, 175)
|
|
Train data size: (300, 175)
|
|
Test data size: (148, 175)
|
|
y_train numbers: Counter({0: 236, 1: 64})
|
|
y_train ratio: 3.6875
|
|
|
|
y_test_numbers: Counter({0: 117, 1: 31})
|
|
y_test ratio: 3.774193548387097
|
|
-------------------------------------------------------------
|
|
|
|
index: 0
|
|
ind: 1
|
|
|
|
Mask count check: True
|
|
|
|
index: 1
|
|
ind: 2
|
|
|
|
Mask count check: False
|
|
Original Data
|
|
Counter({0: 236, 1: 64}) Data dim: (300, 175)
|
|
|
|
Simple Random OverSampling
|
|
Counter({1: 236, 0: 236})
|
|
(472, 175)
|
|
|
|
Simple Random UnderSampling
|
|
Counter({0: 64, 1: 64})
|
|
(128, 175)
|
|
|
|
Simple Combined Over and UnderSampling
|
|
Counter({0: 236, 1: 236})
|
|
(472, 175)
|
|
|
|
SMOTE_NC OverSampling
|
|
Counter({1: 236, 0: 236})
|
|
(472, 175)
|
|
|
|
#####################################################################
|
|
|
|
Running ML analysis: 70/30 split
|
|
Gene name: embB
|
|
Drug name: ethambutol
|
|
|
|
Output directory: /home/tanu/git/Data/ethambutol/output/ml/tts_7030/
|
|
|
|
Sanity checks:
|
|
Total input features: 175
|
|
|
|
Training data size: (300, 175)
|
|
Test data size: (148, 175)
|
|
|
|
Target feature numbers (training data): Counter({0: 236, 1: 64})
|
|
Target features ratio (training data: 3.6875
|
|
|
|
Target feature numbers (test data): Counter({0: 117, 1: 31})
|
|
Target features ratio (test data): 3.774193548387097
|
|
|
|
#####################################################################
|
|
|
|
|
|
================================================================
|
|
|
|
Strucutral features (n): 36
|
|
These are:
|
|
Common stablity features: ['ligand_distance', 'ligand_affinity_change', 'duet_stability_change', 'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts', 'mcsm_ppi2_affinity', 'interface_dist']
|
|
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/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer 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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03264999 0.03559327 0.03803825 0.0327158 0.04181242 0.04413223
|
|
0.036062 0.03810501 0.03271389 0.03382134]
|
|
|
|
mean value: 0.036564421653747556
|
|
|
|
key: score_time
|
|
value: [0.01232839 0.0119369 0.0119381 0.01187754 0.01489878 0.01481462
|
|
0.01502156 0.01490927 0.01197386 0.01511574]
|
|
|
|
mean value: 0.013481473922729493
|
|
|
|
key: test_mcc
|
|
value: [0.71098137 0.73663511 0.34151451 0.33660139 0.78446454 0.53931937
|
|
0.78446454 0.67082039 0.31524416 0.38888889]
|
|
|
|
mean value: 0.5608934267581484
|
|
|
|
key: train_mcc
|
|
value: [0.81565488 0.85186661 0.86314183 0.85139373 0.83014124 0.86500718
|
|
0.83003944 0.84179128 0.86500718 0.80664096]
|
|
|
|
mean value: 0.8420684316933071
|
|
|
|
key: test_accuracy
|
|
value: [0.9 0.9 0.8 0.8 0.93333333 0.86666667
|
|
0.93333333 0.9 0.76666667 0.83333333]
|
|
|
|
mean value: 0.8633333333333334
|
|
|
|
key: train_accuracy
|
|
value: [0.94074074 0.95185185 0.95555556 0.95185185 0.94444444 0.95555556
|
|
0.94444444 0.94814815 0.95555556 0.93703704]
|
|
|
|
mean value: 0.9485185185185185
|
|
|
|
key: test_fscore
|
|
value: [0.72727273 0.8 0.4 0.25 0.8 0.6
|
|
0.8 0.72727273 0.46153846 0.44444444]
|
|
|
|
mean value: 0.601052836052836
|
|
|
|
key: train_fscore
|
|
value: [0.84615385 0.87378641 0.88679245 0.87619048 0.85714286 0.88888889
|
|
0.85981308 0.87037037 0.88888889 0.8411215 ]
|
|
|
|
mean value: 0.8689148767671759
|
|
|
|
key: test_precision
|
|
value: [1. 0.75 0.66666667 1. 1. 0.75
|
|
1. 0.8 0.42857143 0.66666667]
|
|
|
|
mean value: 0.8061904761904762
|
|
|
|
key: train_precision
|
|
value: [0.93617021 0.97826087 0.95918367 0.95833333 0.95744681 0.96
|
|
0.93877551 0.94 0.96 0.91836735]
|
|
|
|
mean value: 0.9506537754787392
|
|
|
|
key: test_recall
|
|
value: [0.57142857 0.85714286 0.28571429 0.14285714 0.66666667 0.5
|
|
0.66666667 0.66666667 0.5 0.33333333]
|
|
|
|
mean value: 0.519047619047619
|
|
|
|
key: train_recall
|
|
value: [0.77192982 0.78947368 0.8245614 0.80701754 0.77586207 0.82758621
|
|
0.79310345 0.81034483 0.82758621 0.77586207]
|
|
|
|
mean value: 0.8003327283726558
|
|
|
|
key: test_roc_auc
|
|
value: [0.78571429 0.88509317 0.62111801 0.57142857 0.83333333 0.72916667
|
|
0.83333333 0.8125 0.66666667 0.64583333]
|
|
|
|
mean value: 0.7384187370600414
|
|
|
|
key: train_roc_auc
|
|
value: [0.87892266 0.89238942 0.90758587 0.89881394 0.88321405 0.90907612
|
|
0.88947625 0.89809694 0.90907612 0.87849707]
|
|
|
|
mean value: 0.894514845008367
|
|
|
|
key: test_jcc
|
|
value: [0.57142857 0.66666667 0.25 0.14285714 0.66666667 0.42857143
|
|
0.66666667 0.57142857 0.3 0.28571429]
|
|
|
|
mean value: 0.45499999999999996
|
|
|
|
key: train_jcc
|
|
value: [0.73333333 0.77586207 0.79661017 0.77966102 0.75 0.8
|
|
0.75409836 0.7704918 0.8 0.72580645]
|
|
|
|
mean value: 0.7685863204286858
|
|
|
|
MCC on Blind test: 0.7
|
|
|
|
Accuracy on Blind test: 0.91
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.77536702 0.78346443 1.00830078 0.89629722 0.74466634 0.78407001
|
|
0.89625335 0.76911545 0.81942534 0.89245582]
|
|
|
|
mean value: 0.8369415760040283
|
|
|
|
key: score_time
|
|
value: [0.01453424 0.0150764 0.01225781 0.01779866 0.01522613 0.01509738
|
|
0.01189756 0.01507449 0.01512694 0.01515436]
|
|
|
|
mean value: 0.014724397659301757
|
|
|
|
key: test_mcc
|
|
value: [0.90632697 0.84270097 0.34151451 0.48445214 0.78446454 0.79166667
|
|
0.89442719 0.51227176 0.45226702 0.53931937]
|
|
|
|
mean value: 0.6549411140568817
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 0.90964729 1. 1.
|
|
0.98914802 1. 1. 0.8880045 ]
|
|
|
|
mean value: 0.9786799817863074
|
|
|
|
key: test_accuracy
|
|
value: [0.96666667 0.93333333 0.8 0.83333333 0.93333333 0.93333333
|
|
0.96666667 0.83333333 0.8 0.86666667]
|
|
|
|
mean value: 0.8866666666666667
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 0.97037037 1. 1.
|
|
0.9962963 1. 1. 0.96296296]
|
|
|
|
mean value: 0.9929629629629629
|
|
|
|
key: test_fscore
|
|
value: [0.92307692 0.875 0.4 0.44444444 0.8 0.83333333
|
|
0.90909091 0.61538462 0.57142857 0.6 ]
|
|
|
|
mean value: 0.6971758796758797
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 0.92727273 1. 1.
|
|
0.99145299 1. 1. 0.90909091]
|
|
|
|
mean value: 0.9827816627816628
|
|
|
|
key: test_precision
|
|
value: [1. 0.77777778 0.66666667 1. 1. 0.83333333
|
|
1. 0.57142857 0.5 0.75 ]
|
|
|
|
mean value: 0.8099206349206349
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 0.96226415 1. 1.
|
|
0.98305085 1. 1. 0.96153846]
|
|
|
|
mean value: 0.9906853459939485
|
|
|
|
key: test_recall
|
|
value: [0.85714286 1. 0.28571429 0.28571429 0.66666667 0.83333333
|
|
0.83333333 0.66666667 0.66666667 0.5 ]
|
|
|
|
mean value: 0.6595238095238095
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 0.89473684 1. 1.
|
|
1. 1. 1. 0.86206897]
|
|
|
|
mean value: 0.9756805807622504
|
|
|
|
key: test_roc_auc
|
|
value: [0.92857143 0.95652174 0.62111801 0.64285714 0.83333333 0.89583333
|
|
0.91666667 0.77083333 0.75 0.72916667]
|
|
|
|
mean value: 0.80449016563147
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 0.94267359 1. 1.
|
|
0.99764151 1. 1. 0.9263175 ]
|
|
|
|
mean value: 0.9866632596432388
|
|
|
|
key: test_jcc
|
|
value: [0.85714286 0.77777778 0.25 0.28571429 0.66666667 0.71428571
|
|
0.83333333 0.44444444 0.4 0.42857143]
|
|
|
|
mean value: 0.5657936507936507
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 0.86440678 1. 1.
|
|
0.98305085 1. 1. 0.83333333]
|
|
|
|
mean value: 0.9680790960451977
|
|
|
|
MCC on Blind test: 0.81
|
|
|
|
Accuracy on Blind test: 0.94
|
|
|
|
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: /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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01480556 0.01099253 0.00942039 0.00947356 0.00929809 0.00928307
|
|
0.00915933 0.00926924 0.00907397 0.0091536 ]
|
|
|
|
mean value: 0.00999293327331543
|
|
|
|
key: score_time
|
|
value: [0.01331377 0.00910592 0.0089035 0.00885582 0.00884891 0.00876856
|
|
0.00862026 0.00861478 0.00865769 0.00866747]
|
|
|
|
mean value: 0.009235668182373046
|
|
|
|
key: test_mcc
|
|
value: [ 0.84270097 0.35807332 0.67072118 -0.07086916 0.40360368 0.53452248
|
|
0.40006613 0.36748421 0.27216553 0.16666667]
|
|
|
|
mean value: 0.3945135011037356
|
|
|
|
key: train_mcc
|
|
value: [0.52075356 0.57758177 0.71098031 0.35275618 0.56173686 0.59360688
|
|
0.52717377 0.54801406 0.63407402 0.51748655]
|
|
|
|
mean value: 0.554416397250037
|
|
|
|
key: test_accuracy
|
|
value: [0.93333333 0.63333333 0.86666667 0.4 0.7 0.73333333
|
|
0.76666667 0.66666667 0.66666667 0.56666667]
|
|
|
|
mean value: 0.6933333333333334
|
|
|
|
key: train_accuracy
|
|
value: [0.73333333 0.78148148 0.88148148 0.54444444 0.76666667 0.78518519
|
|
0.73703704 0.76296296 0.82222222 0.73703704]
|
|
|
|
mean value: 0.7551851851851852
|
|
|
|
key: test_fscore
|
|
value: [0.875 0.52173913 0.75 0.30769231 0.52631579 0.6
|
|
0.53333333 0.5 0.44444444 0.38095238]
|
|
|
|
mean value: 0.5439477386330933
|
|
|
|
key: train_fscore
|
|
value: [0.6043956 0.65088757 0.76811594 0.47659574 0.64 0.6627907
|
|
0.61202186 0.63218391 0.7 0.60773481]
|
|
|
|
mean value: 0.6354726135343666
|
|
|
|
key: test_precision
|
|
value: [0.77777778 0.375 0.66666667 0.21052632 0.38461538 0.42857143
|
|
0.44444444 0.35714286 0.33333333 0.26666667]
|
|
|
|
mean value: 0.4244744875008033
|
|
|
|
key: train_precision
|
|
value: [0.44 0.49107143 0.65432099 0.31460674 0.47863248 0.5
|
|
0.448 0.47413793 0.54901961 0.44715447]
|
|
|
|
mean value: 0.47969436468535975
|
|
|
|
key: test_recall
|
|
value: [1. 0.85714286 0.85714286 0.57142857 0.83333333 1.
|
|
0.66666667 0.83333333 0.66666667 0.66666667]
|
|
|
|
mean value: 0.7952380952380952
|
|
|
|
key: train_recall
|
|
value: [0.96491228 0.96491228 0.92982456 0.98245614 0.96551724 0.98275862
|
|
0.96551724 0.94827586 0.96551724 0.94827586]
|
|
|
|
mean value: 0.9617967332123412
|
|
|
|
key: test_roc_auc
|
|
value: [0.95652174 0.71118012 0.86335404 0.45962733 0.75 0.83333333
|
|
0.72916667 0.72916667 0.66666667 0.60416667]
|
|
|
|
mean value: 0.7303183229813665
|
|
|
|
key: train_roc_auc
|
|
value: [0.81813689 0.84865332 0.89918458 0.70484309 0.8388907 0.85694535
|
|
0.82002277 0.83027001 0.87426805 0.81376057]
|
|
|
|
mean value: 0.8304975339372008
|
|
|
|
key: test_jcc
|
|
value: [0.77777778 0.35294118 0.6 0.18181818 0.35714286 0.42857143
|
|
0.36363636 0.33333333 0.28571429 0.23529412]
|
|
|
|
mean value: 0.3916229522111875
|
|
|
|
key: train_jcc
|
|
value: [0.43307087 0.48245614 0.62352941 0.31284916 0.47058824 0.49565217
|
|
0.44094488 0.46218487 0.53846154 0.43650794]
|
|
|
|
mean value: 0.46962452202844684
|
|
|
|
MCC on Blind test: 0.43
|
|
|
|
Accuracy on Blind test: 0.73
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.00931048 0.00948501 0.00927162 0.00942969 0.00924516 0.00918984
|
|
0.01029277 0.00940418 0.009233 0.00919557]
|
|
|
|
mean value: 0.009405732154846191
|
|
|
|
key: score_time
|
|
value: [0.00904727 0.00860882 0.00865102 0.00859952 0.00858021 0.00849819
|
|
0.00908542 0.00855827 0.00855184 0.00850987]
|
|
|
|
mean value: 0.008669042587280273
|
|
|
|
key: test_mcc
|
|
value: [0. 0.44099379 0. 0.07881104 0.53452248 0.26382243
|
|
0. 0.20044593 0.26382243 0.20044593]
|
|
|
|
mean value: 0.19828640291483576
|
|
|
|
key: train_mcc
|
|
value: [0.42902868 0.4133301 0.4133301 0.46917704 0.41651235 0.48849333
|
|
0.39472347 0.45206847 0.49962045 0.44189798]
|
|
|
|
mean value: 0.4418181972240108
|
|
|
|
key: test_accuracy
|
|
value: [0.76666667 0.8 0.76666667 0.73333333 0.86666667 0.73333333
|
|
0.8 0.8 0.73333333 0.8 ]
|
|
|
|
mean value: 0.78
|
|
|
|
key: train_accuracy
|
|
value: [0.82592593 0.82222222 0.82222222 0.84074074 0.82222222 0.84444444
|
|
0.81851852 0.83333333 0.84814815 0.82962963]
|
|
|
|
mean value: 0.8307407407407408
|
|
|
|
key: test_fscore
|
|
value: [0. 0.57142857 0. 0.2 0.5 0.42857143
|
|
0. 0.25 0.42857143 0.25 ]
|
|
|
|
mean value: 0.26285714285714284
|
|
|
|
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))
|
|
/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))
|
|
[0.52525253 0.51020408 0.51020408 0.54736842 0.51020408 0.5625
|
|
0.48421053 0.53608247 0.56842105 0.53061224]
|
|
|
|
mean value: 0.5285059489275248
|
|
|
|
key: test_precision
|
|
value: [0. 0.57142857 0. 0.33333333 1. 0.375
|
|
0. 0.5 0.375 0.5 ]
|
|
|
|
mean value: 0.36547619047619045
|
|
|
|
key: train_precision
|
|
value: [0.61904762 0.6097561 0.6097561 0.68421053 0.625 0.71052632
|
|
0.62162162 0.66666667 0.72972973 0.65 ]
|
|
|
|
mean value: 0.6526314674292851
|
|
|
|
key: test_recall
|
|
value: [0. 0.57142857 0. 0.14285714 0.33333333 0.5
|
|
0. 0.16666667 0.5 0.16666667]
|
|
|
|
mean value: 0.23809523809523808
|
|
|
|
key: train_recall
|
|
value: [0.45614035 0.43859649 0.43859649 0.45614035 0.43103448 0.46551724
|
|
0.39655172 0.44827586 0.46551724 0.44827586]
|
|
|
|
mean value: 0.44446460980036295
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.72049689 0.5 0.52795031 0.66666667 0.64583333
|
|
0.5 0.5625 0.64583333 0.5625 ]
|
|
|
|
mean value: 0.5831780538302277
|
|
|
|
key: train_roc_auc
|
|
value: [0.69051149 0.68173956 0.68173956 0.69990116 0.68013988 0.70681522
|
|
0.66525699 0.69347755 0.70917372 0.69111906]
|
|
|
|
mean value: 0.6899874204994374
|
|
|
|
key: test_jcc
|
|
value: [0. 0.4 0. 0.11111111 0.33333333 0.27272727
|
|
0. 0.14285714 0.27272727 0.14285714]
|
|
|
|
mean value: 0.16756132756132755
|
|
|
|
key: train_jcc
|
|
value: [0.35616438 0.34246575 0.34246575 0.37681159 0.34246575 0.39130435
|
|
0.31944444 0.36619718 0.39705882 0.36111111]
|
|
|
|
mean value: 0.3595489148048161
|
|
|
|
MCC on Blind test: 0.28
|
|
|
|
Accuracy on Blind test: 0.78
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.00980783 0.00940561 0.01034379 0.00929999 0.00875139 0.00973439
|
|
0.00933743 0.00967407 0.00983763 0.0097034 ]
|
|
|
|
mean value: 0.009589552879333496
|
|
|
|
key: score_time
|
|
value: [0.08368659 0.01248932 0.0128026 0.01100183 0.01079488 0.01175022
|
|
0.0110364 0.01237178 0.01116776 0.01164651]
|
|
|
|
mean value: 0.01887478828430176
|
|
|
|
key: test_mcc
|
|
value: [ 0. -0.14744196 0. -0.1024439 0. -0.13363062
|
|
0. 0.37139068 -0.16666667 0.04902903]
|
|
|
|
mean value: -0.012976343352432269
|
|
|
|
key: train_mcc
|
|
value: [0.37349153 0.33142014 0.40988463 0.42733294 0.37952509 0.43871673
|
|
0.3531848 0.41768067 0.45420164 0.42685971]
|
|
|
|
mean value: 0.40122978730274855
|
|
|
|
key: test_accuracy
|
|
value: [0.76666667 0.7 0.76666667 0.73333333 0.8 0.73333333
|
|
0.8 0.83333333 0.7 0.73333333]
|
|
|
|
mean value: 0.7566666666666667
|
|
|
|
key: train_accuracy
|
|
value: [0.82592593 0.81851852 0.83333333 0.83703704 0.82222222 0.83703704
|
|
0.81851852 0.82962963 0.84074074 0.83333333]
|
|
|
|
mean value: 0.8296296296296296
|
|
|
|
key: test_fscore
|
|
value: [0. 0. 0. 0. 0. 0.
|
|
0. 0.28571429 0. 0.2 ]
|
|
|
|
mean value: 0.04857142857142857
|
|
|
|
key: train_fscore
|
|
value: [0.38961039 0.32876712 0.43037975 0.45 0.42857143 0.46341463
|
|
0.37974684 0.47727273 0.4556962 0.47058824]
|
|
|
|
mean value: 0.4274047322992803
|
|
|
|
key: test_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 1. 0. 0.25]
|
|
|
|
mean value: 0.125
|
|
|
|
key: train_precision
|
|
value: [0.75 0.75 0.77272727 0.7826087 0.69230769 0.79166667
|
|
0.71428571 0.7 0.85714286 0.74074074]
|
|
|
|
mean value: 0.7551479639523118
|
|
|
|
key: test_recall
|
|
value: [0. 0. 0. 0. 0. 0.
|
|
0. 0.16666667 0. 0.16666667]
|
|
|
|
mean value: 0.03333333333333333
|
|
|
|
key: train_recall
|
|
value: [0.26315789 0.21052632 0.29824561 0.31578947 0.31034483 0.32758621
|
|
0.25862069 0.36206897 0.31034483 0.34482759]
|
|
|
|
mean value: 0.300151240169389
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.45652174 0.5 0.47826087 0.5 0.45833333
|
|
0.5 0.58333333 0.4375 0.52083333]
|
|
|
|
mean value: 0.49347826086956526
|
|
|
|
key: train_roc_auc
|
|
value: [0.61984186 0.59587349 0.63738572 0.64615765 0.63630449 0.65200065
|
|
0.6151594 0.65980807 0.64809694 0.65590436]
|
|
|
|
mean value: 0.6366532620370374
|
|
|
|
key: test_jcc
|
|
value: [0. 0. 0. 0. 0. 0.
|
|
0. 0.16666667 0. 0.11111111]
|
|
|
|
mean value: 0.027777777777777776
|
|
|
|
key: train_jcc
|
|
value: [0.24193548 0.19672131 0.27419355 0.29032258 0.27272727 0.3015873
|
|
0.234375 0.31343284 0.29508197 0.30769231]
|
|
|
|
mean value: 0.2728069609419528
|
|
|
|
MCC on Blind test: 0.32
|
|
|
|
Accuracy on Blind test: 0.82
|
|
|
|
Model_name: SVM
|
|
Model func: SVC(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))
|
|
[('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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01334167 0.01223922 0.01212859 0.01231408 0.01217222 0.01251698
|
|
0.01237893 0.01231146 0.01210451 0.01245141]
|
|
|
|
mean value: 0.012395906448364257
|
|
|
|
key: score_time
|
|
value: [0.00952339 0.00940394 0.00948238 0.00928617 0.00946164 0.00948071
|
|
0.00941992 0.00945282 0.00937486 0.0094099 ]
|
|
|
|
mean value: 0.009429574012756348
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0.34151451 0.48445214 0.33660139 0. 0.37139068
|
|
0. 0.53452248 0.11111111 -0.09284767]
|
|
|
|
mean value: 0.20867446385606936
|
|
|
|
key: train_mcc
|
|
value: [0.50109097 0.53185386 0.57575521 0.65266788 0.56942881 0.63728351
|
|
0.49558498 0.58340396 0.65031724 0.61071825]
|
|
|
|
mean value: 0.580810464747048
|
|
|
|
key: test_accuracy
|
|
value: [0.76666667 0.8 0.83333333 0.8 0.8 0.83333333
|
|
0.8 0.86666667 0.76666667 0.76666667]
|
|
|
|
mean value: 0.8033333333333333
|
|
|
|
key: train_accuracy
|
|
value: [0.85185185 0.85925926 0.87037037 0.89259259 0.86666667 0.88518519
|
|
0.84814815 0.87037037 0.88888889 0.87777778]
|
|
|
|
mean value: 0.8711111111111111
|
|
|
|
key: test_fscore
|
|
value: [0. 0.4 0.44444444 0.25 0. 0.28571429
|
|
0. 0.5 0.22222222 0. ]
|
|
|
|
mean value: 0.21023809523809525
|
|
|
|
key: train_fscore
|
|
value: [0.45945946 0.5 0.55696203 0.6741573 0.55 0.63529412
|
|
0.45333333 0.56790123 0.65116279 0.60240964]
|
|
|
|
mean value: 0.5650679902946886
|
|
|
|
key: test_precision
|
|
value: [0. 0.66666667 1. 1. 0. 1.
|
|
0. 1. 0.33333333 0. ]
|
|
|
|
mean value: 0.5
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 0.9375 1. 1. 1. 1. 1. 1. ]
|
|
|
|
mean value: 0.99375
|
|
|
|
key: test_recall
|
|
value: [0. 0.28571429 0.28571429 0.14285714 0. 0.16666667
|
|
0. 0.33333333 0.16666667 0. ]
|
|
|
|
mean value: 0.13809523809523808
|
|
|
|
key: train_recall
|
|
value: [0.29824561 0.33333333 0.38596491 0.52631579 0.37931034 0.46551724
|
|
0.29310345 0.39655172 0.48275862 0.43103448]
|
|
|
|
mean value: 0.3992135511191772
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.62111801 0.64285714 0.57142857 0.5 0.58333333
|
|
0.5 0.66666667 0.54166667 0.47916667]
|
|
|
|
mean value: 0.5606237060041408
|
|
|
|
key: train_roc_auc
|
|
value: [0.64912281 0.66666667 0.69298246 0.75846306 0.68965517 0.73275862
|
|
0.64655172 0.69827586 0.74137931 0.71551724]
|
|
|
|
mean value: 0.6991372919915135
|
|
|
|
key: test_jcc
|
|
value: [0. 0.25 0.28571429 0.14285714 0. 0.16666667
|
|
0. 0.33333333 0.125 0. ]
|
|
|
|
mean value: 0.13035714285714284
|
|
|
|
key: train_jcc
|
|
value: [0.29824561 0.33333333 0.38596491 0.50847458 0.37931034 0.46551724
|
|
0.29310345 0.39655172 0.48275862 0.43103448]
|
|
|
|
mean value: 0.3974294297989275
|
|
|
|
MCC on Blind test: 0.32
|
|
|
|
Accuracy on Blind test: 0.82
|
|
|
|
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: /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(
|
|
/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(
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.25646901 1.12328196 1.27120352 1.15447664 1.33698177 1.14706755
|
|
1.27492309 1.18750501 1.11980724 1.30215621]
|
|
|
|
mean value: 1.2173871994018555
|
|
|
|
key: score_time
|
|
value: [0.01514077 0.0149231 0.02296877 0.01224971 0.02547908 0.02322793
|
|
0.01571989 0.01894879 0.01560116 0.01249456]
|
|
|
|
mean value: 0.017675375938415526
|
|
|
|
key: test_mcc
|
|
value: [0.59917127 0.62732919 0.47913962 0.16850509 0.53931937 0.67082039
|
|
0.78446454 0.45226702 0.31524416 0.53931937]
|
|
|
|
mean value: 0.5175580029537483
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.86666667 0.86666667 0.83333333 0.76666667 0.86666667 0.9
|
|
0.93333333 0.8 0.76666667 0.86666667]
|
|
|
|
mean value: 0.8466666666666667
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.66666667 0.71428571 0.54545455 0.22222222 0.6 0.72727273
|
|
0.8 0.57142857 0.46153846 0.6 ]
|
|
|
|
mean value: 0.5908868908868908
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.8 0.71428571 0.75 0.5 0.75 0.8
|
|
1. 0.5 0.42857143 0.75 ]
|
|
|
|
mean value: 0.6992857142857143
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.57142857 0.71428571 0.42857143 0.14285714 0.5 0.66666667
|
|
0.66666667 0.66666667 0.5 0.5 ]
|
|
|
|
mean value: 0.5357142857142857
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.76397516 0.8136646 0.69254658 0.54968944 0.72916667 0.8125
|
|
0.83333333 0.75 0.66666667 0.72916667]
|
|
|
|
mean value: 0.7340709109730849
|
|
|
|
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 0.55555556 0.375 0.125 0.42857143 0.57142857
|
|
0.66666667 0.4 0.3 0.42857143]
|
|
|
|
mean value: 0.43507936507936507
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.7
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03823161 0.01571989 0.01405907 0.01503277 0.01399803 0.01317
|
|
0.01383829 0.01496935 0.0134964 0.01523948]
|
|
|
|
mean value: 0.01677548885345459
|
|
|
|
key: score_time
|
|
value: [0.01093936 0.00863934 0.00841665 0.00836897 0.00841331 0.00858045
|
|
0.008533 0.00854969 0.00864458 0.00866604]
|
|
|
|
mean value: 0.008775138854980468
|
|
|
|
key: test_mcc
|
|
value: [1. 0.84270097 0.90632697 0.90632697 0.79166667 0.70929937
|
|
0.66666667 0.8291562 0.79166667 1. ]
|
|
|
|
mean value: 0.8443810469154356
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.93333333 0.96666667 0.96666667 0.93333333 0.9
|
|
0.9 0.93333333 0.93333333 1. ]
|
|
|
|
mean value: 0.9466666666666667
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 0.875 0.92307692 0.92307692 0.83333333 0.76923077
|
|
0.66666667 0.85714286 0.83333333 1. ]
|
|
|
|
mean value: 0.8680860805860806
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 0.77777778 1. 1. 0.83333333 0.71428571
|
|
1. 0.75 0.83333333 1. ]
|
|
|
|
mean value: 0.8908730158730159
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.85714286 0.85714286 0.83333333 0.83333333
|
|
0.5 1. 0.83333333 1. ]
|
|
|
|
mean value: 0.8714285714285714
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.95652174 0.92857143 0.92857143 0.89583333 0.875
|
|
0.75 0.95833333 0.89583333 1. ]
|
|
|
|
mean value: 0.9188664596273293
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 0.77777778 0.85714286 0.85714286 0.71428571 0.625
|
|
0.5 0.75 0.71428571 1. ]
|
|
|
|
mean value: 0.7795634920634921
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.76
|
|
|
|
Accuracy on Blind test: 0.92
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.09980416 0.0996089 0.09998441 0.09808803 0.0998466 0.09872079
|
|
0.09878469 0.09888625 0.09762359 0.09940338]
|
|
|
|
mean value: 0.0990750789642334
|
|
|
|
key: score_time
|
|
value: [0.01704431 0.01702619 0.01736307 0.01698923 0.01705313 0.01703215
|
|
0.01708555 0.016958 0.01702142 0.01715088]
|
|
|
|
mean value: 0.017072391510009766
|
|
|
|
key: test_mcc
|
|
value: [0.48445214 0.62732919 0.60421798 0.33660139 0.38888889 0.37139068
|
|
0.66666667 0.53931937 0.4472136 0.20044593]
|
|
|
|
mean value: 0.46665258281260485
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.83333333 0.86666667 0.86666667 0.8 0.83333333 0.83333333
|
|
0.9 0.86666667 0.83333333 0.8 ]
|
|
|
|
mean value: 0.8433333333333334
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.44444444 0.71428571 0.6 0.25 0.44444444 0.28571429
|
|
0.66666667 0.6 0.54545455 0.25 ]
|
|
|
|
mean value: 0.4801010101010101
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 0.71428571 1. 1. 0.66666667 1.
|
|
1. 0.75 0.6 0.5 ]
|
|
|
|
mean value: 0.8230952380952381
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.28571429 0.71428571 0.42857143 0.14285714 0.33333333 0.16666667
|
|
0.5 0.5 0.5 0.16666667]
|
|
|
|
mean value: 0.3738095238095238
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.64285714 0.8136646 0.71428571 0.57142857 0.64583333 0.58333333
|
|
0.75 0.72916667 0.70833333 0.5625 ]
|
|
|
|
mean value: 0.6721402691511387
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.28571429 0.55555556 0.42857143 0.14285714 0.28571429 0.16666667
|
|
0.5 0.42857143 0.375 0.14285714]
|
|
|
|
mean value: 0.33115079365079364
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.62
|
|
|
|
Accuracy on Blind test: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01024365 0.00978684 0.00923109 0.0093596 0.00926661 0.009166
|
|
0.00933385 0.00929308 0.00936723 0.00929832]
|
|
|
|
mean value: 0.0094346284866333
|
|
|
|
key: score_time
|
|
value: [0.00897551 0.00858545 0.00856066 0.00853968 0.00846982 0.00852656
|
|
0.00848079 0.00846124 0.00850558 0.00851321]
|
|
|
|
mean value: 0.008561849594116211
|
|
|
|
key: test_mcc
|
|
value: [ 0.17622684 0.47913962 -0.11801242 0.25465839 0.04902903 0.13834289
|
|
0.38888889 0.375 -0.04166667 0.26382243]
|
|
|
|
mean value: 0.19654289997257754
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.73333333 0.83333333 0.6 0.73333333 0.73333333 0.63333333
|
|
0.83333333 0.8 0.66666667 0.73333333]
|
|
|
|
mean value: 0.73
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.33333333 0.54545455 0.14285714 0.42857143 0.2 0.35294118
|
|
0.44444444 0.5 0.16666667 0.42857143]
|
|
|
|
mean value: 0.3542840166369578
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.4 0.75 0.14285714 0.42857143 0.25 0.27272727
|
|
0.66666667 0.5 0.16666667 0.375 ]
|
|
|
|
mean value: 0.39524891774891774
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.28571429 0.42857143 0.14285714 0.42857143 0.16666667 0.5
|
|
0.33333333 0.5 0.16666667 0.5 ]
|
|
|
|
mean value: 0.34523809523809523
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.57763975 0.69254658 0.44099379 0.62732919 0.52083333 0.58333333
|
|
0.64583333 0.6875 0.47916667 0.64583333]
|
|
|
|
mean value: 0.5901009316770186
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.2 0.375 0.07692308 0.27272727 0.11111111 0.21428571
|
|
0.28571429 0.33333333 0.09090909 0.27272727]
|
|
|
|
mean value: 0.22327311577311576
|
|
|
|
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: 0.7
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.37597132 1.36085105 1.36928844 1.36414075 1.38993359 1.36109924
|
|
1.39832282 1.4257853 1.4313221 1.44128251]
|
|
|
|
mean value: 1.3917997121810912
|
|
|
|
key: score_time
|
|
value: [0.08814955 0.08808422 0.14979434 0.08908105 0.08810949 0.08824229
|
|
0.09622312 0.09655809 0.09692621 0.09693909]
|
|
|
|
mean value: 0.09781074523925781
|
|
|
|
key: test_mcc
|
|
value: [0.81064348 0.62732919 0.71098137 0.60421798 0.66666667 0.53931937
|
|
0.66666667 0.67082039 0.4472136 0.79166667]
|
|
|
|
mean value: 0.6535525382316371
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.93333333 0.86666667 0.9 0.86666667 0.9 0.86666667
|
|
0.9 0.9 0.83333333 0.93333333]
|
|
|
|
mean value: 0.89
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 0.71428571 0.72727273 0.6 0.66666667 0.6
|
|
0.66666667 0.72727273 0.54545455 0.83333333]
|
|
|
|
mean value: 0.6914285714285714
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 0.71428571 1. 1. 1. 0.75
|
|
1. 0.8 0.6 0.83333333]
|
|
|
|
mean value: 0.8697619047619047
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.71428571 0.71428571 0.57142857 0.42857143 0.5 0.5
|
|
0.5 0.66666667 0.5 0.83333333]
|
|
|
|
mean value: 0.5928571428571429
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.85714286 0.8136646 0.78571429 0.71428571 0.75 0.72916667
|
|
0.75 0.8125 0.70833333 0.89583333]
|
|
|
|
mean value: 0.7816640786749482
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
/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(
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 0.55555556 0.57142857 0.42857143 0.5 0.42857143
|
|
0.5 0.57142857 0.375 0.71428571]
|
|
|
|
mean value: 0.5359126984126984
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.81
|
|
|
|
Accuracy on Blind test: 0.94
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000...05', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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/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/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))
|
|
|
|
key: fit_time
|
|
value: [1.80116463 0.95938873 0.91688776 0.97945976 0.93260837 0.88188934
|
|
0.86905456 0.94177294 0.92283177 0.92724848]
|
|
|
|
mean value: 1.0132306337356567
|
|
|
|
key: score_time
|
|
value: [0.25280952 0.23567629 0.16636014 0.25092673 0.20835114 0.16313744
|
|
0.18864083 0.24807954 0.24673986 0.28317308]
|
|
|
|
mean value: 0.2243894577026367
|
|
|
|
key: test_mcc
|
|
value: [0. 0.51227176 0.71098137 0.48445214 0.53452248 0.37139068
|
|
0.66666667 0.38888889 0.53931937 0.37139068]
|
|
|
|
mean value: 0.45798840373213023
|
|
|
|
key: train_mcc
|
|
value: [0.92156513 0.92110219 0.91023656 0.8866892 0.91143897 0.93337985
|
|
0.91143897 0.92260747 0.933743 0.88822308]
|
|
|
|
mean value: 0.9140424426331186
|
|
|
|
key: test_accuracy
|
|
value: [0.76666667 0.83333333 0.9 0.83333333 0.86666667 0.83333333
|
|
0.9 0.83333333 0.86666667 0.83333333]
|
|
|
|
mean value: 0.8466666666666667
|
|
|
|
key: train_accuracy
|
|
value: [0.97407407 0.97407407 0.97037037 0.96296296 0.97037037 0.97777778
|
|
0.97037037 0.97407407 0.97777778 0.96296296]
|
|
|
|
mean value: 0.9714814814814815
|
|
|
|
key: test_fscore
|
|
value: [0. 0.61538462 0.72727273 0.44444444 0.5 0.28571429
|
|
0.66666667 0.44444444 0.6 0.28571429]
|
|
|
|
mean value: 0.45696414696414694
|
|
|
|
key: train_fscore
|
|
value: [0.93457944 0.93577982 0.9245283 0.90566038 0.92592593 0.94642857
|
|
0.92592593 0.93577982 0.94545455 0.90740741]
|
|
|
|
mean value: 0.9287470127667519
|
|
|
|
key: test_precision
|
|
value: [0. 0.66666667 1. 1. 1. 1.
|
|
1. 0.66666667 0.75 1. ]
|
|
|
|
mean value: 0.8083333333333333
|
|
|
|
key: train_precision
|
|
value: [1. 0.98076923 1. 0.97959184 1. 0.98148148
|
|
1. 1. 1. 0.98 ]
|
|
|
|
mean value: 0.9921842548985406
|
|
|
|
key: test_recall
|
|
value: [0. 0.57142857 0.57142857 0.28571429 0.33333333 0.16666667
|
|
0.5 0.33333333 0.5 0.16666667]
|
|
|
|
mean value: 0.34285714285714286
|
|
|
|
key: train_recall
|
|
value: [0.87719298 0.89473684 0.85964912 0.84210526 0.86206897 0.9137931
|
|
0.86206897 0.87931034 0.89655172 0.84482759]
|
|
|
|
mean value: 0.8732304900181488
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.74223602 0.78571429 0.64285714 0.66666667 0.58333333
|
|
0.75 0.64583333 0.72916667 0.58333333]
|
|
|
|
mean value: 0.6629140786749482
|
|
|
|
key: train_roc_auc
|
|
value: [0.93859649 0.945021 0.92982456 0.91870521 0.93103448 0.95453806
|
|
0.93103448 0.93965517 0.94827586 0.9200553 ]
|
|
|
|
mean value: 0.9356740633277918
|
|
|
|
key: test_jcc
|
|
value: [0. 0.44444444 0.57142857 0.28571429 0.33333333 0.16666667
|
|
0.5 0.28571429 0.42857143 0.16666667]
|
|
|
|
mean value: 0.31825396825396823
|
|
|
|
key: train_jcc
|
|
value: [0.87719298 0.87931034 0.85964912 0.82758621 0.86206897 0.89830508
|
|
0.86206897 0.87931034 0.89655172 0.83050847]
|
|
|
|
mean value: 0.8672552216309329
|
|
|
|
MCC on Blind test: 0.63
|
|
|
|
Accuracy on Blind test: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03207803 0.01167703 0.01085591 0.01018047 0.01019716 0.01056027
|
|
0.01075149 0.00945878 0.00968695 0.01019764]
|
|
|
|
mean value: 0.012564373016357423
|
|
|
|
key: score_time
|
|
value: [0.010077 0.00994515 0.0098238 0.00955153 0.0092864 0.00951719
|
|
0.00963402 0.00893927 0.00962639 0.00949931]
|
|
|
|
mean value: 0.00959000587463379
|
|
|
|
key: test_mcc
|
|
value: [0. 0.44099379 0. 0.07881104 0.53452248 0.26382243
|
|
0. 0.20044593 0.26382243 0.20044593]
|
|
|
|
mean value: 0.19828640291483576
|
|
|
|
key: train_mcc
|
|
value: [0.42902868 0.4133301 0.4133301 0.46917704 0.41651235 0.48849333
|
|
0.39472347 0.45206847 0.49962045 0.44189798]
|
|
|
|
mean value: 0.4418181972240108
|
|
|
|
key: test_accuracy
|
|
value: [0.76666667 0.8 0.76666667 0.73333333 0.86666667 0.73333333
|
|
0.8 0.8 0.73333333 0.8 ]
|
|
|
|
mean value: 0.78
|
|
|
|
key: train_accuracy
|
|
value: [0.82592593 0.82222222 0.82222222 0.84074074 0.82222222 0.84444444
|
|
0.81851852 0.83333333 0.84814815 0.82962963]
|
|
|
|
mean value: 0.8307407407407408
|
|
|
|
key: test_fscore
|
|
value: [0. 0.57142857 0. 0.2 0.5 0.42857143
|
|
0. 0.25 0.42857143 0.25 ]
|
|
|
|
mean value: 0.26285714285714284
|
|
|
|
key: train_fscore
|
|
value: [0.52525253 0.51020408 0.51020408 0.54736842 0.51020408 0.5625
|
|
0.48421053 0.53608247 0.56842105 0.53061224]
|
|
|
|
mean value: 0.5285059489275248
|
|
|
|
key: test_precision
|
|
value: [0. 0.57142857 0. 0.33333333 1. 0.375
|
|
0. 0.5 0.375 0.5 ]
|
|
|
|
mean value: 0.36547619047619045
|
|
|
|
key: train_precision
|
|
value: [0.61904762 0.6097561 0.6097561 0.68421053 0.625 0.71052632
|
|
0.62162162 0.66666667 0.72972973 0.65 ]
|
|
|
|
mean value: 0.6526314674292851
|
|
|
|
key: test_recall
|
|
value: [0. 0.57142857 0. 0.14285714 0.33333333 0.5
|
|
0. 0.16666667 0.5 0.16666667]
|
|
|
|
mean value: 0.23809523809523808
|
|
|
|
key: train_recall
|
|
value: [0.45614035 0.43859649 0.43859649 0.45614035 0.43103448 0.46551724
|
|
0.39655172 0.44827586 0.46551724 0.44827586]
|
|
|
|
mean value: 0.44446460980036295
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.72049689 0.5 0.52795031 0.66666667 0.64583333
|
|
0.5 0.5625 0.64583333 0.5625 ]
|
|
|
|
mean value: 0.5831780538302277
|
|
|
|
key: train_roc_auc
|
|
value: [0.69051149 0.68173956 0.68173956 0.69990116 0.68013988 0.70681522
|
|
0.66525699 0.69347755 0.70917372 0.69111906]
|
|
|
|
mean value: 0.6899874204994374
|
|
|
|
key: test_jcc
|
|
value: [0. 0.4 0. 0.11111111 0.33333333 0.27272727
|
|
0. 0.14285714 0.27272727 0.14285714]
|
|
|
|
mean value: 0.16756132756132755
|
|
|
|
key: train_jcc
|
|
value: [0.35616438 0.34246575 0.34246575 0.37681159 0.34246575 0.39130435
|
|
0.31944444 0.36619718 0.39705882 0.36111111]
|
|
|
|
mean value: 0.3595489148048161
|
|
|
|
MCC on Blind test: 0.28
|
|
|
|
Accuracy on Blind test: 0.78
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'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: [0.10339999 0.05094528 0.053684 0.06175375 0.06219912 0.06532979
|
|
0.06505036 0.06244802 0.06267715 0.07398534]
|
|
|
|
mean value: 0.06614727973937988
|
|
|
|
key: score_time
|
|
value: [0.01137733 0.01059747 0.01104617 0.01055908 0.01211071 0.01153946
|
|
0.01059914 0.01165128 0.01161838 0.01142693]
|
|
|
|
mean value: 0.011252593994140626
|
|
|
|
key: test_mcc
|
|
value: [1. 0.91485328 1. 1. 1. 0.70929937
|
|
0.66666667 0.90632697 0.70929937 1. ]
|
|
|
|
mean value: 0.8906445643876397
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.96666667 1. 1. 1. 0.9
|
|
0.9 0.96666667 0.9 1. ]
|
|
|
|
mean value: 0.9633333333333334
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 0.93333333 1. 1. 1. 0.76923077
|
|
0.66666667 0.92307692 0.76923077 1. ]
|
|
|
|
mean value: 0.9061538461538461
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 0.875 1. 1. 1. 0.71428571
|
|
1. 0.85714286 0.71428571 1. ]
|
|
|
|
mean value: 0.9160714285714285
|
|
|
|
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. 0.83333333
|
|
0.5 1. 0.83333333 1. ]
|
|
|
|
mean value: 0.9166666666666666
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.97826087 1. 1. 1. 0.875
|
|
0.75 0.97916667 0.875 1. ]
|
|
|
|
mean value: 0.9457427536231884
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 0.875 1. 1. 1. 0.625
|
|
0.5 0.85714286 0.625 1. ]
|
|
|
|
mean value: 0.8482142857142857
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.85
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.04709005 0.0325582 0.05858684 0.0306325 0.05300045 0.0640173
|
|
0.06457448 0.06448078 0.06892991 0.064569 ]
|
|
|
|
mean value: 0.05484395027160645
|
|
|
|
key: score_time
|
|
value: [0.01224017 0.02271295 0.01214767 0.01212764 0.01570773 0.02162123
|
|
0.02348661 0.02088094 0.02161551 0.0236485 ]
|
|
|
|
mean value: 0.01861889362335205
|
|
|
|
key: test_mcc
|
|
value: [0.59917127 0.55841694 0.47913962 0.34151451 0.79166667 0.4472136
|
|
0.67082039 0.76376262 0.64071161 0.4472136 ]
|
|
|
|
mean value: 0.5739630807571057
|
|
|
|
key: train_mcc
|
|
value: [0.94481583 0.95552261 0.95631739 0.97827926 0.95685154 0.97804164
|
|
0.94661124 0.96732502 0.96732502 0.96817595]
|
|
|
|
mean value: 0.9619265504315446
|
|
|
|
key: test_accuracy
|
|
value: [0.86666667 0.83333333 0.83333333 0.8 0.93333333 0.83333333
|
|
0.9 0.9 0.86666667 0.83333333]
|
|
|
|
mean value: 0.86
|
|
|
|
key: train_accuracy
|
|
value: [0.98148148 0.98518519 0.98518519 0.99259259 0.98518519 0.99259259
|
|
0.98148148 0.98888889 0.98888889 0.98888889]
|
|
|
|
mean value: 0.987037037037037
|
|
|
|
key: test_fscore
|
|
value: [0.66666667 0.66666667 0.54545455 0.4 0.83333333 0.54545455
|
|
0.72727273 0.8 0.71428571 0.54545455]
|
|
|
|
mean value: 0.6444588744588744
|
|
|
|
key: train_fscore
|
|
value: [0.95652174 0.96491228 0.96551724 0.98275862 0.96610169 0.98275862
|
|
0.95798319 0.97435897 0.97435897 0.97478992]
|
|
|
|
mean value: 0.970006125546771
|
|
|
|
key: test_precision
|
|
value: [0.8 0.625 0.75 0.66666667 0.83333333 0.6
|
|
0.8 0.66666667 0.625 0.6 ]
|
|
|
|
mean value: 0.6966666666666667
|
|
|
|
key: train_precision
|
|
value: [0.94827586 0.96491228 0.94915254 0.96610169 0.95 0.98275862
|
|
0.93442623 0.96610169 0.96610169 0.95081967]
|
|
|
|
mean value: 0.9578650292218364
|
|
|
|
key: test_recall
|
|
value: [0.57142857 0.71428571 0.42857143 0.28571429 0.83333333 0.5
|
|
0.66666667 1. 0.83333333 0.5 ]
|
|
|
|
mean value: 0.6333333333333333
|
|
|
|
key: train_recall
|
|
value: [0.96491228 0.96491228 0.98245614 1. 0.98275862 0.98275862
|
|
0.98275862 0.98275862 0.98275862 1. ]
|
|
|
|
mean value: 0.9826073805202662
|
|
|
|
key: test_roc_auc
|
|
value: [0.76397516 0.79192547 0.69254658 0.62111801 0.89583333 0.70833333
|
|
0.8125 0.9375 0.85416667 0.70833333]
|
|
|
|
mean value: 0.7786231884057971
|
|
|
|
key: train_roc_auc
|
|
value: [0.97541389 0.9777613 0.98418582 0.99530516 0.98430384 0.98902082
|
|
0.98194535 0.98666233 0.98666233 0.99292453]
|
|
|
|
mean value: 0.9854185365707009
|
|
|
|
key: test_jcc
|
|
value: [0.5 0.5 0.375 0.25 0.71428571 0.375
|
|
0.57142857 0.66666667 0.55555556 0.375 ]
|
|
|
|
mean value: 0.4882936507936508
|
|
|
|
key: train_jcc
|
|
value: [0.91666667 0.93220339 0.93333333 0.96610169 0.93442623 0.96610169
|
|
0.91935484 0.95 0.95 0.95081967]
|
|
|
|
mean value: 0.9419007520010039
|
|
|
|
MCC on Blind test: 0.66
|
|
|
|
Accuracy on Blind test: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01754761 0.01052833 0.01029849 0.009619 0.01030421 0.01053333
|
|
0.00946617 0.01075244 0.01050544 0.01063013]
|
|
|
|
mean value: 0.011018514633178711
|
|
|
|
key: score_time
|
|
value: [0.01000285 0.00963688 0.00934887 0.00879693 0.00936627 0.00951409
|
|
0.00916576 0.00953078 0.0096128 0.00958228]
|
|
|
|
mean value: 0.0094557523727417
|
|
|
|
key: test_mcc
|
|
value: [0.60421798 0.51227176 0.47913962 0.24729787 0.38888889 0.
|
|
0.53452248 0.67082039 0.35355339 0.20044593]
|
|
|
|
mean value: 0.399115831475217
|
|
|
|
key: train_mcc
|
|
value: [0.52919102 0.56194029 0.51030718 0.53350443 0.54685671 0.54685671
|
|
0.5376566 0.55767376 0.59421175 0.53635546]
|
|
|
|
mean value: 0.5454553905972329
|
|
|
|
key: test_accuracy
|
|
value: [0.86666667 0.83333333 0.83333333 0.76666667 0.83333333 0.8
|
|
0.86666667 0.9 0.73333333 0.8 ]
|
|
|
|
mean value: 0.8233333333333334
|
|
|
|
key: train_accuracy
|
|
value: [0.85555556 0.86666667 0.85185185 0.85555556 0.85925926 0.85925926
|
|
0.85925926 0.86296296 0.87407407 0.85555556]
|
|
|
|
mean value: 0.86
|
|
|
|
key: test_fscore
|
|
value: [0.6 0.61538462 0.54545455 0.36363636 0.44444444 0.
|
|
0.5 0.72727273 0.5 0.25 ]
|
|
|
|
mean value: 0.4546192696192696
|
|
|
|
key: train_fscore
|
|
value: [0.60606061 0.625 0.58333333 0.61386139 0.62 0.62
|
|
0.59574468 0.62626263 0.65306122 0.61386139]
|
|
|
|
mean value: 0.6157185243274653
|
|
|
|
key: test_precision
|
|
value: [1. 0.66666667 0.75 0.5 0.66666667 0.
|
|
1. 0.8 0.4 0.5 ]
|
|
|
|
mean value: 0.6283333333333333
|
|
|
|
key: train_precision
|
|
value: [0.71428571 0.76923077 0.71794872 0.70454545 0.73809524 0.73809524
|
|
0.77777778 0.75609756 0.8 0.72093023]
|
|
|
|
mean value: 0.743700670351266
|
|
|
|
key: test_recall
|
|
value: [0.42857143 0.57142857 0.42857143 0.28571429 0.33333333 0.
|
|
0.33333333 0.66666667 0.66666667 0.16666667]
|
|
|
|
mean value: 0.38809523809523805
|
|
|
|
key: train_recall
|
|
value: [0.52631579 0.52631579 0.49122807 0.54385965 0.53448276 0.53448276
|
|
0.48275862 0.53448276 0.55172414 0.53448276]
|
|
|
|
mean value: 0.5260133091349062
|
|
|
|
key: test_roc_auc
|
|
value: [0.71428571 0.74223602 0.69254658 0.59937888 0.64583333 0.5
|
|
0.66666667 0.8125 0.70833333 0.5625 ]
|
|
|
|
mean value: 0.6644280538302277
|
|
|
|
key: train_roc_auc
|
|
value: [0.73498888 0.74203113 0.71979244 0.74141339 0.74129798 0.74129798
|
|
0.72251139 0.74365647 0.75699414 0.73893949]
|
|
|
|
mean value: 0.7382923308895365
|
|
|
|
key: test_jcc
|
|
value: [0.42857143 0.44444444 0.375 0.22222222 0.28571429 0.
|
|
0.33333333 0.57142857 0.33333333 0.14285714]
|
|
|
|
mean value: 0.3136904761904762
|
|
|
|
key: train_jcc
|
|
value: [0.43478261 0.45454545 0.41176471 0.44285714 0.44927536 0.44927536
|
|
0.42424242 0.45588235 0.48484848 0.44285714]
|
|
|
|
mean value: 0.4450331041507512
|
|
|
|
MCC on Blind test: 0.53
|
|
|
|
Accuracy on Blind test: 0.86
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01443243 0.01724362 0.01736236 0.01823735 0.02097249 0.01814556
|
|
0.01761293 0.0170033 0.0196116 0.01855135]
|
|
|
|
mean value: 0.017917299270629884
|
|
|
|
key: score_time
|
|
value: [0.00955415 0.01115894 0.01130891 0.01184487 0.01181889 0.01177907
|
|
0.01168704 0.01180267 0.01164842 0.01211548]
|
|
|
|
mean value: 0.011471843719482422
|
|
|
|
key: test_mcc
|
|
value: [0.71098137 0.73663511 0.34151451 0.33660139 0.78446454 0.38888889
|
|
0.78446454 0.53931937 0.31127151 0.65712874]
|
|
|
|
mean value: 0.5591269961248411
|
|
|
|
key: train_mcc
|
|
value: [0.6962004 0.8529518 0.84134414 0.87483789 0.96817595 0.86500718
|
|
0.94661124 0.68855055 0.95803613 0.83568024]
|
|
|
|
mean value: 0.8527395527552342
|
|
|
|
key: test_accuracy
|
|
value: [0.9 0.9 0.8 0.8 0.93333333 0.83333333
|
|
0.93333333 0.86666667 0.7 0.83333333]
|
|
|
|
mean value: 0.85
|
|
|
|
key: train_accuracy
|
|
value: [0.9037037 0.95185185 0.94814815 0.95925926 0.98888889 0.95555556
|
|
0.98148148 0.9 0.98518519 0.93333333]
|
|
|
|
mean value: 0.9507407407407408
|
|
|
|
key: test_fscore
|
|
value: [0.72727273 0.8 0.4 0.25 0.8 0.44444444
|
|
0.8 0.6 0.47058824 0.70588235]
|
|
|
|
mean value: 0.5998187759952466
|
|
|
|
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))
|
|
[0.70454545 0.87128713 0.86 0.89719626 0.97478992 0.88888889
|
|
0.95798319 0.69662921 0.96666667 0.86567164]
|
|
|
|
mean value: 0.8683658365014013
|
|
|
|
key: test_precision
|
|
value: [1. 0.75 0.66666667 1. 1. 0.66666667
|
|
1. 0.75 0.36363636 0.54545455]
|
|
|
|
mean value: 0.7742424242424242
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 0.96 0.95081967 0.96
|
|
0.93442623 1. 0.93548387 0.76315789]
|
|
|
|
mean value: 0.9503887667343929
|
|
|
|
key: test_recall
|
|
value: [0.57142857 0.85714286 0.28571429 0.14285714 0.66666667 0.33333333
|
|
0.66666667 0.5 0.66666667 1. ]
|
|
|
|
mean value: 0.569047619047619
|
|
|
|
key: train_recall
|
|
value: [0.54385965 0.77192982 0.75438596 0.84210526 1. 0.82758621
|
|
0.98275862 0.53448276 1. 1. ]
|
|
|
|
mean value: 0.8257108287961282
|
|
|
|
key: test_roc_auc
|
|
value: [0.78571429 0.88509317 0.62111801 0.57142857 0.83333333 0.64583333
|
|
0.83333333 0.72916667 0.6875 0.89583333]
|
|
|
|
mean value: 0.748835403726708
|
|
|
|
key: train_roc_auc
|
|
value: [0.77192982 0.88596491 0.87719298 0.9163578 0.99292453 0.90907612
|
|
0.98194535 0.76724138 0.99056604 0.95754717]
|
|
|
|
mean value: 0.905074610075272
|
|
|
|
key: test_jcc
|
|
value: [0.57142857 0.66666667 0.25 0.14285714 0.66666667 0.28571429
|
|
0.66666667 0.42857143 0.30769231 0.54545455]
|
|
|
|
mean value: 0.45317182817182816
|
|
|
|
key: train_jcc
|
|
value: [0.54385965 0.77192982 0.75438596 0.81355932 0.95081967 0.8
|
|
0.91935484 0.53448276 0.93548387 0.76315789]
|
|
|
|
mean value: 0.7787033795796489
|
|
|
|
MCC on Blind test: 0.75
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01676464 0.01634693 0.01514077 0.0154686 0.01485229 0.01604962
|
|
0.01415801 0.01640582 0.01465034 0.01683164]
|
|
|
|
mean value: 0.015666866302490236
|
|
|
|
key: score_time
|
|
value: [0.01178169 0.01173091 0.01171231 0.01167488 0.01170492 0.01171422
|
|
0.01158881 0.01167893 0.01168942 0.01159167]
|
|
|
|
mean value: 0.01168677806854248
|
|
|
|
key: test_mcc
|
|
value: [0.71098137 0.55841694 0.34151451 0. 0.37139068 0.53452248
|
|
0.78446454 0.51227176 0.40006613 0.53931937]
|
|
|
|
mean value: 0.4752947782195236
|
|
|
|
key: train_mcc
|
|
value: [0.70882477 0.9438568 0.78234837 0.58988563 0.35502173 0.83209945
|
|
0.84452043 0.93515969 0.88670738 0.88822308]
|
|
|
|
mean value: 0.7766647319290388
|
|
|
|
key: test_accuracy
|
|
value: [0.9 0.83333333 0.8 0.76666667 0.83333333 0.86666667
|
|
0.93333333 0.83333333 0.76666667 0.86666667]
|
|
|
|
mean value: 0.8400000000000001
|
|
|
|
key: train_accuracy
|
|
value: [0.90740741 0.98148148 0.92962963 0.87407407 0.81851852 0.94444444
|
|
0.94444444 0.97777778 0.95925926 0.96296296]
|
|
|
|
mean value: 0.9299999999999999
|
|
|
|
key: test_fscore
|
|
value: [0.72727273 0.66666667 0.4 0. 0.28571429 0.5
|
|
0.8 0.61538462 0.53333333 0.6 ]
|
|
|
|
mean value: 0.5128371628371629
|
|
|
|
key: train_fscore
|
|
value: [0.71910112 0.95495495 0.8 0.575 0.26865672 0.85148515
|
|
0.87804878 0.94915254 0.91056911 0.90740741]
|
|
|
|
mean value: 0.7814375779442373
|
|
|
|
key: test_precision
|
|
value: [1. 0.625 0.66666667 0. 1. 1.
|
|
1. 0.57142857 0.44444444 0.75 ]
|
|
|
|
mean value: 0.7057539682539682
|
|
|
|
key: train_precision
|
|
value: [1. 0.98148148 1. 1. 1. 1.
|
|
0.83076923 0.93333333 0.86153846 0.98 ]
|
|
|
|
mean value: 0.9587122507122507
|
|
|
|
key: test_recall
|
|
value: [0.57142857 0.71428571 0.28571429 0. 0.16666667 0.33333333
|
|
0.66666667 0.66666667 0.66666667 0.5 ]
|
|
|
|
mean value: 0.45714285714285713
|
|
|
|
key: train_recall
|
|
value: [0.56140351 0.92982456 0.66666667 0.40350877 0.15517241 0.74137931
|
|
0.93103448 0.96551724 0.96551724 0.84482759]
|
|
|
|
mean value: 0.7164851784633999
|
|
|
|
key: test_roc_auc
|
|
value: [0.78571429 0.79192547 0.62111801 0.5 0.58333333 0.66666667
|
|
0.83333333 0.77083333 0.72916667 0.72916667]
|
|
|
|
mean value: 0.7011257763975155
|
|
|
|
key: train_roc_auc
|
|
value: [0.78070175 0.96256486 0.83333333 0.70175439 0.57758621 0.87068966
|
|
0.93957385 0.97332466 0.96153221 0.9200553 ]
|
|
|
|
mean value: 0.852111621032568
|
|
|
|
key: test_jcc
|
|
value: [0.57142857 0.5 0.25 0. 0.16666667 0.33333333
|
|
0.66666667 0.44444444 0.36363636 0.42857143]
|
|
|
|
mean value: 0.37247474747474746
|
|
|
|
key: train_jcc
|
|
value: [0.56140351 0.9137931 0.66666667 0.40350877 0.15517241 0.74137931
|
|
0.7826087 0.90322581 0.8358209 0.83050847]
|
|
|
|
mean value: 0.6794087647157074
|
|
|
|
MCC on Blind test: 0.51
|
|
|
|
Accuracy on Blind test: 0.75
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.14580512 0.13405323 0.13631344 0.14046717 0.14530969 0.13987613
|
|
0.13885093 0.12599254 0.12484145 0.12611699]
|
|
|
|
mean value: 0.13576266765594483
|
|
|
|
key: score_time
|
|
value: [0.01614213 0.01601243 0.01695514 0.01937366 0.01671982 0.01692653
|
|
0.01483989 0.01472139 0.01459241 0.01634359]
|
|
|
|
mean value: 0.01626269817352295
|
|
|
|
key: test_mcc
|
|
value: [0.90632697 0.84270097 0.90632697 0.90632697 1. 0.70929937
|
|
0.37139068 0.90632697 0.79166667 1. ]
|
|
|
|
mean value: 0.8340365548936208
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.96666667 0.93333333 0.96666667 0.96666667 1. 0.9
|
|
0.83333333 0.96666667 0.93333333 1. ]
|
|
|
|
mean value: 0.9466666666666667
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.92307692 0.875 0.92307692 0.92307692 1. 0.76923077
|
|
0.28571429 0.92307692 0.83333333 1. ]
|
|
|
|
mean value: 0.845558608058608
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 0.77777778 1. 1. 1. 0.71428571
|
|
1. 0.85714286 0.83333333 1. ]
|
|
|
|
mean value: 0.9182539682539682
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.85714286 1. 0.85714286 0.85714286 1. 0.83333333
|
|
0.16666667 1. 0.83333333 1. ]
|
|
|
|
mean value: 0.8404761904761905
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.92857143 0.95652174 0.92857143 0.92857143 1. 0.875
|
|
0.58333333 0.97916667 0.89583333 1. ]
|
|
|
|
mean value: 0.9075569358178054
|
|
|
|
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 0.77777778 0.85714286 0.85714286 1. 0.625
|
|
0.16666667 0.85714286 0.71428571 1. ]
|
|
|
|
mean value: 0.7712301587301588
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.83
|
|
|
|
Accuracy on Blind test: 0.94
|
|
|
|
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))
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.04065537 0.0388546 0.06377196 0.04338026 0.03827286 0.04347134
|
|
0.05566072 0.0426755 0.04525566 0.05041337]
|
|
|
|
mean value: 0.046241164207458496
|
|
|
|
key: score_time
|
|
value: [0.02124453 0.02442527 0.02890682 0.01769495 0.01785421 0.03107214
|
|
0.02257037 0.0270083 0.02530599 0.02508759]
|
|
|
|
mean value: 0.024117016792297365
|
|
|
|
key: test_mcc
|
|
value: [0.90632697 0.91485328 0.91485328 1. 0.89442719 0.70929937
|
|
0.89442719 0.90632697 0.79166667 1. ]
|
|
|
|
mean value: 0.8932180906240387
|
|
|
|
key: train_mcc
|
|
value: [0.96691391 0.9777613 0.9777613 0.9777613 0.97804164 0.97800497
|
|
0.96691391 0.96691391 0.97804164 0.97804164]
|
|
|
|
mean value: 0.9746155541138715
|
|
|
|
key: test_accuracy
|
|
value: [0.96666667 0.96666667 0.96666667 1. 0.96666667 0.9
|
|
0.96666667 0.96666667 0.93333333 1. ]
|
|
|
|
mean value: 0.9633333333333334
|
|
|
|
key: train_accuracy
|
|
value: [0.98888889 0.99259259 0.99259259 0.99259259 0.99259259 0.99259259
|
|
0.98888889 0.98888889 0.99259259 0.99259259]
|
|
|
|
mean value: 0.9914814814814815
|
|
|
|
key: test_fscore
|
|
value: [0.92307692 0.93333333 0.93333333 1. 0.90909091 0.76923077
|
|
0.90909091 0.92307692 0.83333333 1. ]
|
|
|
|
mean value: 0.9133566433566433
|
|
|
|
key: train_fscore
|
|
value: [0.97391304 0.98245614 0.98245614 0.98245614 0.98275862 0.98245614
|
|
0.97391304 0.97391304 0.98275862 0.98275862]
|
|
|
|
mean value: 0.9799839553907257
|
|
|
|
key: test_precision
|
|
value: [1. 0.875 0.875 1. 1. 0.71428571
|
|
1. 0.85714286 0.83333333 1. ]
|
|
|
|
mean value: 0.9154761904761904
|
|
|
|
key: train_precision
|
|
value: [0.96551724 0.98245614 0.98245614 0.98245614 0.98275862 1.
|
|
0.98245614 0.98245614 0.98275862 0.98275862]
|
|
|
|
mean value: 0.9826073805202662
|
|
|
|
key: test_recall
|
|
value: [0.85714286 1. 1. 1. 0.83333333 0.83333333
|
|
0.83333333 1. 0.83333333 1. ]
|
|
|
|
mean value: 0.9190476190476191
|
|
|
|
key: train_recall
|
|
value: [0.98245614 0.98245614 0.98245614 0.98245614 0.98275862 0.96551724
|
|
0.96551724 0.96551724 0.98275862 0.98275862]
|
|
|
|
mean value: 0.9774652147610405
|
|
|
|
key: test_roc_auc
|
|
value: [0.92857143 0.97826087 0.97826087 1. 0.91666667 0.875
|
|
0.91666667 0.97916667 0.89583333 1. ]
|
|
|
|
mean value: 0.9468426501035198
|
|
|
|
key: train_roc_auc
|
|
value: [0.98653323 0.98888065 0.98888065 0.98888065 0.98902082 0.98275862
|
|
0.98040013 0.98040013 0.98902082 0.98902082]
|
|
|
|
mean value: 0.9863796531773136
|
|
|
|
key: test_jcc
|
|
value: [0.85714286 0.875 0.875 1. 0.83333333 0.625
|
|
0.83333333 0.85714286 0.71428571 1. ]
|
|
|
|
mean value: 0.8470238095238095
|
|
|
|
key: train_jcc
|
|
value: [0.94915254 0.96551724 0.96551724 0.96551724 0.96610169 0.96551724
|
|
0.94915254 0.94915254 0.96610169 0.96610169]
|
|
|
|
mean value: 0.9607831677381649
|
|
|
|
MCC on Blind test: 0.84
|
|
|
|
Accuracy on Blind test: 0.95
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.06801105 0.08086944 0.08217549 0.08551049 0.08354163 0.08338308
|
|
0.08468556 0.08343172 0.08823562 0.09278727]
|
|
|
|
mean value: 0.08326313495635987
|
|
|
|
key: score_time
|
|
value: [0.02195382 0.02120185 0.02089286 0.02659488 0.02669311 0.02682614
|
|
0.02669072 0.02567911 0.02662802 0.01908517]
|
|
|
|
mean value: 0.024224567413330077
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0.24729787 -0.1024439 0. 0. 0.20044593
|
|
0. 0.20044593 -0.13363062 0.11111111]
|
|
|
|
mean value: 0.052322632023241354
|
|
|
|
key: train_mcc
|
|
value: [0.94411696 0.94411696 0.95534545 0.95534545 0.94484812 0.95592526
|
|
0.94484812 0.95592526 0.94484812 0.96697679]
|
|
|
|
mean value: 0.9512296484136088
|
|
|
|
key: test_accuracy
|
|
value: [0.76666667 0.76666667 0.73333333 0.76666667 0.8 0.8
|
|
0.8 0.8 0.73333333 0.76666667]
|
|
|
|
mean value: 0.7733333333333333
|
|
|
|
key: train_accuracy
|
|
value: [0.98148148 0.98148148 0.98518519 0.98518519 0.98148148 0.98518519
|
|
0.98148148 0.98518519 0.98148148 0.98888889]
|
|
|
|
mean value: 0.9837037037037037
|
|
|
|
key: test_fscore
|
|
value: [0. 0.36363636 0. 0. 0. 0.25
|
|
0. 0.25 0. 0.22222222]
|
|
|
|
mean value: 0.10858585858585859
|
|
|
|
key: train_fscore
|
|
value: [0.95412844 0.95412844 0.96363636 0.96363636 0.95495495 0.96428571
|
|
0.95495495 0.96428571 0.95495495 0.97345133]
|
|
|
|
mean value: 0.9602417228876594
|
|
|
|
key: test_precision
|
|
value: [0. 0.5 0. 0. 0. 0.5
|
|
0. 0.5 0. 0.33333333]
|
|
|
|
mean value: 0.18333333333333332
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0. 0.28571429 0. 0. 0. 0.16666667
|
|
0. 0.16666667 0. 0.16666667]
|
|
|
|
mean value: 0.07857142857142857
|
|
|
|
key: train_recall
|
|
value: [0.9122807 0.9122807 0.92982456 0.92982456 0.9137931 0.93103448
|
|
0.9137931 0.93103448 0.9137931 0.94827586]
|
|
|
|
mean value: 0.9235934664246824
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.59937888 0.47826087 0.5 0.5 0.5625
|
|
0.5 0.5625 0.45833333 0.54166667]
|
|
|
|
mean value: 0.5202639751552794
|
|
|
|
key: train_roc_auc
|
|
value: [0.95614035 0.95614035 0.96491228 0.96491228 0.95689655 0.96551724
|
|
0.95689655 0.96551724 0.95689655 0.97413793]
|
|
|
|
mean value: 0.9617967332123412
|
|
|
|
key: test_jcc
|
|
value: [0. 0.22222222 0. 0. 0. 0.14285714
|
|
0. 0.14285714 0. 0.125 ]
|
|
|
|
mean value: 0.06329365079365079
|
|
|
|
key: train_jcc
|
|
value: [0.9122807 0.9122807 0.92982456 0.92982456 0.9137931 0.93103448
|
|
0.9137931 0.93103448 0.9137931 0.94827586]
|
|
|
|
mean value: 0.9235934664246824
|
|
|
|
MCC on Blind test: 0.29
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.44241452 0.42846489 0.43671846 0.438236 0.43929386 0.45626354
|
|
0.44174147 0.43929839 0.43570423 0.43489265]
|
|
|
|
mean value: 0.43930280208587646
|
|
|
|
key: score_time
|
|
value: [0.00924778 0.00906825 0.00963926 0.00940657 0.00979161 0.00987196
|
|
0.00929642 0.00997448 0.00935817 0.00917006]
|
|
|
|
mean value: 0.009482455253601075
|
|
|
|
key: test_mcc
|
|
value: [1. 0.84270097 0.8136646 1. 0.79166667 0.70929937
|
|
0.89442719 0.8291562 0.79166667 1. ]
|
|
|
|
mean value: 0.8672581655410966
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.93333333 0.93333333 1. 0.93333333 0.9
|
|
0.96666667 0.93333333 0.93333333 1. ]
|
|
|
|
mean value: 0.9533333333333334
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 0.875 0.85714286 1. 0.83333333 0.76923077
|
|
0.90909091 0.85714286 0.83333333 1. ]
|
|
|
|
mean value: 0.8934274059274059
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 0.77777778 0.85714286 1. 0.83333333 0.71428571
|
|
1. 0.75 0.83333333 1. ]
|
|
|
|
mean value: 0.8765873015873016
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.85714286 1. 0.83333333 0.83333333
|
|
0.83333333 1. 0.83333333 1. ]
|
|
|
|
mean value: 0.9190476190476191
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.95652174 0.9068323 1. 0.89583333 0.875
|
|
0.91666667 0.95833333 0.89583333 1. ]
|
|
|
|
mean value: 0.9405020703933747
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 0.77777778 0.75 1. 0.71428571 0.625
|
|
0.83333333 0.75 0.71428571 1. ]
|
|
|
|
mean value: 0.816468253968254
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.85
|
|
|
|
Accuracy on Blind test: 0.95
|
|
|
|
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/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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02217054 0.02345276 0.02494359 0.02240586 0.02307248 0.02586699
|
|
0.02208257 0.03030801 0.02230382 0.02258754]
|
|
|
|
mean value: 0.02391941547393799
|
|
|
|
key: score_time
|
|
value: [0.01234412 0.01350999 0.01206422 0.01223588 0.01225114 0.0121696
|
|
0.01426482 0.01219535 0.01425266 0.01464319]
|
|
|
|
mean value: 0.012993097305297852
|
|
|
|
key: test_mcc
|
|
value: [ 0.01545612 -0.03524537 0.16850509 0.01545612 -0.13363062 0.
|
|
0.20044593 0.11111111 -0.16666667 -0.13363062]
|
|
|
|
mean value: 0.004180109125903944
|
|
|
|
key: train_mcc
|
|
value: [0.29142448 0.26553052 0.31537228 0.31537228 0.28822231 0.33407831
|
|
0.28822231 0.31190697 0.33407831 0.28822231]
|
|
|
|
mean value: 0.303243008578363
|
|
|
|
key: test_accuracy
|
|
value: [0.7 0.66666667 0.76666667 0.7 0.73333333 0.7
|
|
0.8 0.76666667 0.7 0.73333333]
|
|
|
|
mean value: 0.7266666666666667
|
|
|
|
key: train_accuracy
|
|
value: [0.81111111 0.80740741 0.81481481 0.81481481 0.80740741 0.81481481
|
|
0.80740741 0.81111111 0.81481481 0.80740741]
|
|
|
|
mean value: 0.8111111111111111
|
|
|
|
key: test_fscore
|
|
value: [0.18181818 0.16666667 0.22222222 0.18181818 0. 0.18181818
|
|
0.25 0.22222222 0. 0. ]
|
|
|
|
mean value: 0.14065656565656565
|
|
|
|
key: train_fscore
|
|
value: [0.19047619 0.16129032 0.21875 0.21875 0.1875 0.24242424
|
|
0.1875 0.21538462 0.24242424 0.1875 ]
|
|
|
|
mean value: 0.2051999613289936
|
|
|
|
key: test_precision
|
|
value: [0.25 0.2 0.5 0.25 0. 0.2
|
|
0.5 0.33333333 0. 0. ]
|
|
|
|
mean value: 0.22333333333333333
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.14285714 0.14285714 0.14285714 0.14285714 0. 0.16666667
|
|
0.16666667 0.16666667 0. 0. ]
|
|
|
|
mean value: 0.10714285714285714
|
|
|
|
key: train_recall
|
|
value: [0.10526316 0.0877193 0.12280702 0.12280702 0.10344828 0.13793103
|
|
0.10344828 0.12068966 0.13793103 0.10344828]
|
|
|
|
mean value: 0.11454930429522081
|
|
|
|
key: test_roc_auc
|
|
value: [0.50621118 0.48447205 0.54968944 0.50621118 0.45833333 0.5
|
|
0.5625 0.54166667 0.4375 0.45833333]
|
|
|
|
mean value: 0.500491718426501
|
|
|
|
key: train_roc_auc
|
|
value: [0.55263158 0.54385965 0.56140351 0.56140351 0.55172414 0.56896552
|
|
0.55172414 0.56034483 0.56896552 0.55172414]
|
|
|
|
mean value: 0.5572746521476104
|
|
|
|
key: test_jcc
|
|
value: [0.1 0.09090909 0.125 0.1 0. 0.1
|
|
0.14285714 0.125 0. 0. ]
|
|
|
|
mean value: 0.07837662337662338
|
|
|
|
key: train_jcc
|
|
value: [0.10526316 0.0877193 0.12280702 0.12280702 0.10344828 0.13793103
|
|
0.10344828 0.12068966 0.13793103 0.10344828]
|
|
|
|
mean value: 0.11454930429522081
|
|
|
|
MCC on Blind test: -0.08
|
|
|
|
Accuracy on Blind test: 0.73
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02915764 0.03015637 0.03976631 0.03463793 0.03463483 0.03489685
|
|
0.03476095 0.03470182 0.0349226 0.03496695]
|
|
|
|
mean value: 0.034260225296020505
|
|
|
|
key: score_time
|
|
value: [0.02342033 0.02312112 0.02306843 0.02017307 0.02206421 0.022578
|
|
0.01998425 0.021523 0.02265787 0.01175332]
|
|
|
|
mean value: 0.0210343599319458
|
|
|
|
key: test_mcc
|
|
value: [0.90632697 0.73663511 0.59917127 0.33660139 0.67082039 0.79166667
|
|
0.78446454 0.8291562 0.45226702 0.53931937]
|
|
|
|
mean value: 0.664642891699831
|
|
|
|
key: train_mcc
|
|
value: [0.93328391 0.93328391 0.95631739 0.94481583 0.91216656 0.94550201
|
|
0.93412492 0.93352024 0.94481583 0.94550201]
|
|
|
|
mean value: 0.9383332619443605
|
|
|
|
key: test_accuracy
|
|
value: [0.96666667 0.9 0.86666667 0.8 0.9 0.93333333
|
|
0.93333333 0.93333333 0.8 0.86666667]
|
|
|
|
mean value: 0.89
|
|
|
|
key: train_accuracy
|
|
value: [0.97777778 0.97777778 0.98518519 0.98148148 0.97037037 0.98148148
|
|
0.97777778 0.97777778 0.98148148 0.98148148]
|
|
|
|
mean value: 0.9792592592592593
|
|
|
|
key: test_fscore
|
|
value: [0.92307692 0.8 0.66666667 0.25 0.72727273 0.83333333
|
|
0.8 0.85714286 0.57142857 0.6 ]
|
|
|
|
mean value: 0.7028921078921079
|
|
|
|
key: train_fscore
|
|
value: [0.94736842 0.94736842 0.96551724 0.95652174 0.93103448 0.95726496
|
|
0.94827586 0.94736842 0.95652174 0.95726496]
|
|
|
|
mean value: 0.9514506242155575
|
|
|
|
key: test_precision
|
|
value: [1. 0.75 0.8 1. 0.8 0.83333333
|
|
1. 0.75 0.5 0.75 ]
|
|
|
|
mean value: 0.8183333333333334
|
|
|
|
key: train_precision
|
|
value: [0.94736842 0.94736842 0.94915254 0.94827586 0.93103448 0.94915254
|
|
0.94827586 0.96428571 0.96491228 0.94915254]
|
|
|
|
mean value: 0.9498978671107927
|
|
|
|
key: test_recall
|
|
value: [0.85714286 0.85714286 0.57142857 0.14285714 0.66666667 0.83333333
|
|
0.66666667 1. 0.66666667 0.5 ]
|
|
|
|
mean value: 0.6761904761904761
|
|
|
|
key: train_recall
|
|
value: [0.94736842 0.94736842 0.98245614 0.96491228 0.93103448 0.96551724
|
|
0.94827586 0.93103448 0.94827586 0.96551724]
|
|
|
|
mean value: 0.9531760435571688
|
|
|
|
key: test_roc_auc
|
|
value: [0.92857143 0.88509317 0.76397516 0.57142857 0.8125 0.89583333
|
|
0.83333333 0.95833333 0.75 0.72916667]
|
|
|
|
mean value: 0.8128234989648033
|
|
|
|
key: train_roc_auc
|
|
value: [0.96664196 0.96664196 0.98418582 0.97541389 0.95608328 0.97568315
|
|
0.96706246 0.96080026 0.96942095 0.97568315]
|
|
|
|
mean value: 0.9697616864078695
|
|
|
|
key: test_jcc
|
|
value: [0.85714286 0.66666667 0.5 0.14285714 0.57142857 0.71428571
|
|
0.66666667 0.75 0.4 0.42857143]
|
|
|
|
mean value: 0.5697619047619047
|
|
|
|
key: train_jcc
|
|
value: [0.9 0.9 0.93333333 0.91666667 0.87096774 0.91803279
|
|
0.90163934 0.9 0.91666667 0.91803279]
|
|
|
|
mean value: 0.9075339326634937
|
|
|
|
MCC on Blind test: 0.77
|
|
|
|
Accuracy on Blind test: 0.93
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.23716664 0.33816957 0.2779398 0.23869252 0.2659688 0.24666333
|
|
0.25041795 0.24919891 0.27069283 0.36590862]
|
|
|
|
mean value: 0.2740818977355957
|
|
|
|
key: score_time
|
|
value: [0.02124047 0.02292156 0.02382946 0.02101827 0.02291059 0.02023649
|
|
0.02161932 0.01984978 0.02158308 0.02380562]
|
|
|
|
mean value: 0.021901464462280272
|
|
|
|
key: test_mcc
|
|
value: [0.90632697 0.67072118 0.70929937 0.33660139 0.67082039 0.79166667
|
|
0.78446454 0.76376262 0.45226702 0.53931937]
|
|
|
|
mean value: 0.6625249504397052
|
|
|
|
key: train_mcc
|
|
value: [0.93328391 0.95552261 0.94481583 0.94481583 0.91216656 0.94550201
|
|
0.93412492 0.96732502 0.94481583 0.94550201]
|
|
|
|
mean value: 0.9427874528318679
|
|
|
|
key: test_accuracy
|
|
value: [0.96666667 0.86666667 0.9 0.8 0.9 0.93333333
|
|
0.93333333 0.9 0.8 0.86666667]
|
|
|
|
mean value: 0.8866666666666667
|
|
|
|
key: train_accuracy
|
|
value: [0.97777778 0.98518519 0.98148148 0.98148148 0.97037037 0.98148148
|
|
0.97777778 0.98888889 0.98148148 0.98148148]
|
|
|
|
mean value: 0.9807407407407407
|
|
|
|
key: test_fscore
|
|
value: [0.92307692 0.75 0.76923077 0.25 0.72727273 0.83333333
|
|
0.8 0.8 0.57142857 0.6 ]
|
|
|
|
mean value: 0.7024342324342324
|
|
|
|
key: train_fscore
|
|
value: /home/tanu/git/LSHTM_analysis/scripts/ml/./embb_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/./embb_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(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
[0.94736842 0.96491228 0.95652174 0.95652174 0.93103448 0.95726496
|
|
0.94827586 0.97435897 0.95652174 0.95726496]
|
|
|
|
mean value: 0.9550045152862165
|
|
|
|
key: test_precision
|
|
value: [1. 0.66666667 0.83333333 1. 0.8 0.83333333
|
|
1. 0.66666667 0.5 0.75 ]
|
|
|
|
mean value: 0.805
|
|
|
|
key: train_precision
|
|
value: [0.94736842 0.96491228 0.94827586 0.94827586 0.93103448 0.94915254
|
|
0.94827586 0.96610169 0.96491228 0.94915254]
|
|
|
|
mean value: 0.9517461831082674
|
|
|
|
key: test_recall
|
|
value: [0.85714286 0.85714286 0.71428571 0.14285714 0.66666667 0.83333333
|
|
0.66666667 1. 0.66666667 0.5 ]
|
|
|
|
mean value: 0.6904761904761905
|
|
|
|
key: train_recall
|
|
value: [0.94736842 0.96491228 0.96491228 0.96491228 0.93103448 0.96551724
|
|
0.94827586 0.98275862 0.94827586 0.96551724]
|
|
|
|
mean value: 0.9583484573502722
|
|
|
|
key: test_roc_auc
|
|
value: [0.92857143 0.86335404 0.83540373 0.57142857 0.8125 0.89583333
|
|
0.83333333 0.9375 0.75 0.72916667]
|
|
|
|
mean value: 0.8157091097308489
|
|
|
|
key: train_roc_auc
|
|
value: [0.96664196 0.9777613 0.97541389 0.97541389 0.95608328 0.97568315
|
|
0.96706246 0.98666233 0.96942095 0.97568315]
|
|
|
|
mean value: 0.9725826350884588
|
|
|
|
key: test_jcc
|
|
value: [0.85714286 0.6 0.625 0.14285714 0.57142857 0.71428571
|
|
0.66666667 0.66666667 0.4 0.42857143]
|
|
|
|
mean value: 0.5672619047619047
|
|
|
|
key: train_jcc
|
|
value: [0.9 0.93220339 0.91666667 0.91666667 0.87096774 0.91803279
|
|
0.90163934 0.95 0.91666667 0.91803279]
|
|
|
|
mean value: 0.914087604979878
|
|
|
|
MCC on Blind test: 0.77
|
|
|
|
Accuracy on Blind test: 0.93
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03449607 0.03762531 0.0351913 0.09771824 0.03410959 0.03479981
|
|
0.03532839 0.0349102 0.03884578 0.03600955]
|
|
|
|
mean value: 0.04190342426300049
|
|
|
|
key: score_time
|
|
value: [0.0118041 0.01457787 0.01448703 0.01188588 0.01445436 0.01444316
|
|
0.01442671 0.01455832 0.01463914 0.01466894]
|
|
|
|
mean value: 0.013994550704956055
|
|
|
|
key: test_mcc
|
|
value: [0.91986621 0.9591663 0.79308818 0.8729597 0.8729597 0.91804649
|
|
0.83303222 0.84254172 0.66243303 0.70289855]
|
|
|
|
mean value: 0.8376992105156902
|
|
|
|
key: train_mcc
|
|
value: [0.92555856 0.921052 0.9351604 0.93449419 0.93933764 0.93908654
|
|
0.92572296 0.920493 0.93907982 0.91674568]
|
|
|
|
mean value: 0.9296730800912981
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 0.97916667 0.89361702 0.93617021 0.93617021 0.95744681
|
|
0.91489362 0.91489362 0.82978723 0.85106383]
|
|
|
|
mean value: 0.917154255319149
|
|
|
|
key: train_accuracy
|
|
value: [0.96226415 0.95990566 0.96705882 0.96705882 0.96941176 0.96941176
|
|
0.96235294 0.96 0.96941176 0.95764706]
|
|
|
|
mean value: 0.9644522752497225
|
|
|
|
key: test_fscore
|
|
value: [0.96 0.97959184 0.90196078 0.93877551 0.93877551 0.96
|
|
0.91666667 0.92 0.83333333 0.85106383]
|
|
|
|
mean value: 0.9200167471243816
|
|
|
|
key: train_fscore
|
|
value: [0.96313364 0.96091954 0.96774194 0.96744186 0.96983759 0.96969697
|
|
0.96330275 0.96073903 0.96983759 0.95890411]
|
|
|
|
mean value: 0.9651555012348473
|
|
|
|
key: test_precision
|
|
value: [0.92307692 0.96 0.85185185 0.92 0.92 0.92307692
|
|
0.88 0.85185185 0.8 0.83333333]
|
|
|
|
mean value: 0.8863190883190883
|
|
|
|
key: train_precision
|
|
value: [0.94144144 0.93721973 0.94594595 0.95412844 0.9543379 0.95852535
|
|
0.94170404 0.94545455 0.9587156 0.93333333]
|
|
|
|
mean value: 0.9470806314854157
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 0.95833333 0.95833333 1.
|
|
0.95652174 1. 0.86956522 0.86956522]
|
|
|
|
mean value: 0.9570652173913043
|
|
|
|
key: train_recall
|
|
value: [0.98584906 0.98584906 0.99056604 0.98113208 0.98584906 0.98113208
|
|
0.98591549 0.97652582 0.98122066 0.98591549]
|
|
|
|
mean value: 0.9839954823279298
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 0.97916667 0.89221014 0.93568841 0.93568841 0.95652174
|
|
0.91576087 0.91666667 0.83061594 0.85144928]
|
|
|
|
mean value: 0.9172101449275363
|
|
|
|
key: train_roc_auc
|
|
value: [0.96226415 0.95990566 0.967114 0.96709186 0.96945035 0.96943928
|
|
0.96229737 0.95996102 0.96938391 0.95758039]
|
|
|
|
mean value: 0.9644487997165382
|
|
|
|
key: test_jcc
|
|
value: [0.92307692 0.96 0.82142857 0.88461538 0.88461538 0.92307692
|
|
0.84615385 0.85185185 0.71428571 0.74074074]
|
|
|
|
mean value: 0.854984533984534
|
|
|
|
key: train_jcc
|
|
value: [0.92888889 0.92477876 0.9375 0.93693694 0.94144144 0.94117647
|
|
0.92920354 0.92444444 0.94144144 0.92105263]
|
|
|
|
mean value: 0.9326864556205292
|
|
|
|
MCC on Blind test: 0.67
|
|
|
|
Accuracy on Blind test: 0.88
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.80999112 0.9104569 0.8289113 0.93962145 1.00176835 1.24311352
|
|
1.10284805 1.38999534 1.28155708 1.17678881]
|
|
|
|
mean value: 1.0685051918029784
|
|
|
|
key: score_time
|
|
value: [0.01203275 0.01517606 0.01585746 0.0150466 0.01516366 0.01499987
|
|
0.01499581 0.01560545 0.01517367 0.02332377]
|
|
|
|
mean value: 0.015737509727478026
|
|
|
|
key: test_mcc
|
|
value: [0.91986621 1. 0.91485507 0.91804649 0.91485507 0.91804649
|
|
0.95833333 0.95833333 0.87979456 0.91804649]
|
|
|
|
mean value: 0.9300177060064538
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 1. 0.95744681 0.95744681 0.95744681 0.95744681
|
|
0.9787234 0.9787234 0.93617021 0.95744681]
|
|
|
|
mean value: 0.9639184397163121
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.96 1. 0.95833333 0.96 0.95833333 0.96
|
|
0.9787234 0.9787234 0.93877551 0.95454545]
|
|
|
|
mean value: 0.9647434439926841
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.92307692 1. 0.95833333 0.92307692 0.95833333 0.92307692
|
|
0.95833333 0.95833333 0.88461538 1. ]
|
|
|
|
mean value: 0.9487179487179488
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 1. 0.95833333 1.
|
|
1. 1. 1. 0.91304348]
|
|
|
|
mean value: 0.9829710144927536
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 1. 0.95742754 0.95652174 0.95742754 0.95652174
|
|
0.97916667 0.97916667 0.9375 0.95652174]
|
|
|
|
mean value: 0.963858695652174
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.92307692 1. 0.92 0.92307692 0.92 0.92307692
|
|
0.95833333 0.95833333 0.88461538 0.91304348]
|
|
|
|
mean value: 0.932355629877369
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
Accuracy on Blind test: 0.93
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01922727 0.01160359 0.01650715 0.01204014 0.01291585 0.01280642
|
|
0.01133561 0.01488614 0.01162529 0.01477838]
|
|
|
|
mean value: 0.0137725830078125
|
|
|
|
key: score_time
|
|
value: [0.01338983 0.01031947 0.01032329 0.01044989 0.01429105 0.01019621
|
|
0.00990605 0.01226544 0.01027727 0.01262355]
|
|
|
|
mean value: 0.011404204368591308
|
|
|
|
key: test_mcc
|
|
value: [0.76063883 0.6761234 0.79308818 0.7876601 0.53483083 0.84147165
|
|
0.58428436 0.87318841 0.61775362 0.53734864]
|
|
|
|
mean value: 0.7006388024243406
|
|
|
|
key: train_mcc
|
|
value: [0.74930754 0.76461432 0.77600635 0.76537738 0.77674705 0.74617408
|
|
0.76285707 0.72270631 0.7575994 0.77765656]
|
|
|
|
mean value: 0.759904607645008
|
|
|
|
key: test_accuracy
|
|
value: [0.875 0.83333333 0.89361702 0.89361702 0.76595745 0.91489362
|
|
0.78723404 0.93617021 0.80851064 0.76595745]
|
|
|
|
mean value: 0.8474290780141844
|
|
|
|
key: train_accuracy
|
|
value: [0.86792453 0.87735849 0.88235294 0.88 0.88470588 0.86823529
|
|
0.87764706 0.85647059 0.87529412 0.88470588]
|
|
|
|
mean value: 0.8754694783573806
|
|
|
|
key: test_fscore
|
|
value: [0.88461538 0.84615385 0.90196078 0.89795918 0.78431373 0.92307692
|
|
0.8 0.93617021 0.80851064 0.7755102 ]
|
|
|
|
mean value: 0.8558270902469007
|
|
|
|
key: train_fscore
|
|
value: [0.87931034 0.88646288 0.89130435 0.88641425 0.89183223 0.87772926
|
|
0.88596491 0.86767896 0.88351648 0.89277899]
|
|
|
|
mean value: 0.8842992663887672
|
|
|
|
key: test_precision
|
|
value: [0.82142857 0.78571429 0.85185185 0.88 0.74074074 0.85714286
|
|
0.74074074 0.91666667 0.79166667 0.73076923]
|
|
|
|
mean value: 0.8116721611721611
|
|
|
|
key: train_precision
|
|
value: [0.80952381 0.82520325 0.8266129 0.83966245 0.83817427 0.81707317
|
|
0.83127572 0.80645161 0.83057851 0.83606557]
|
|
|
|
mean value: 0.826062127586517
|
|
|
|
key: test_recall
|
|
value: [0.95833333 0.91666667 0.95833333 0.91666667 0.83333333 1.
|
|
0.86956522 0.95652174 0.82608696 0.82608696]
|
|
|
|
mean value: 0.9061594202898551
|
|
|
|
key: train_recall
|
|
value: [0.96226415 0.95754717 0.96698113 0.93867925 0.95283019 0.94811321
|
|
0.94835681 0.93896714 0.94366197 0.95774648]
|
|
|
|
mean value: 0.951514748870582
|
|
|
|
key: test_roc_auc
|
|
value: [0.875 0.83333333 0.89221014 0.89311594 0.76449275 0.91304348
|
|
0.78894928 0.9365942 0.80887681 0.76721014]
|
|
|
|
mean value: 0.8472826086956522
|
|
|
|
key: train_roc_auc
|
|
value: [0.86792453 0.87735849 0.8825516 0.88013774 0.8848658 0.8684228
|
|
0.87748029 0.85627602 0.87513287 0.88453362]
|
|
|
|
mean value: 0.8754683762955089
|
|
|
|
key: test_jcc
|
|
value: [0.79310345 0.73333333 0.82142857 0.81481481 0.64516129 0.85714286
|
|
0.66666667 0.88 0.67857143 0.63333333]
|
|
|
|
mean value: 0.7523555743889447
|
|
|
|
key: train_jcc
|
|
value: [0.78461538 0.79607843 0.80392157 0.796 0.80478088 0.78210117
|
|
0.79527559 0.76628352 0.79133858 0.80632411]
|
|
|
|
mean value: 0.7926719237229082
|
|
|
|
MCC on Blind test: 0.38
|
|
|
|
Accuracy on Blind test: 0.78
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01507783 0.01659036 0.01731706 0.01430321 0.01484537 0.01193476
|
|
0.01758504 0.01128435 0.01131129 0.01800013]
|
|
|
|
mean value: 0.014824938774108887
|
|
|
|
key: score_time
|
|
value: [0.01349115 0.01515126 0.01466036 0.01118159 0.01542044 0.01087761
|
|
0.01128101 0.00956059 0.01173615 0.01214504]
|
|
|
|
mean value: 0.01255052089691162
|
|
|
|
key: test_mcc
|
|
value: [0.66899361 0.83624201 0.54211097 0.79308818 0.4121128 0.57427536
|
|
0.62296012 0.74456522 0.53734864 0.31876614]
|
|
|
|
mean value: 0.6050463054309297
|
|
|
|
key: train_mcc
|
|
value: [0.64196668 0.68170693 0.68199016 0.67307013 0.67623828 0.66194531
|
|
0.69131813 0.65244722 0.66673391 0.69629094]
|
|
|
|
mean value: 0.6723707683420355
|
|
|
|
key: test_accuracy
|
|
value: [0.83333333 0.91666667 0.76595745 0.89361702 0.70212766 0.78723404
|
|
0.80851064 0.87234043 0.76595745 0.65957447]
|
|
|
|
mean value: 0.800531914893617
|
|
|
|
key: train_accuracy
|
|
value: [0.82075472 0.83962264 0.84 0.83529412 0.83764706 0.83058824
|
|
0.84470588 0.82588235 0.83294118 0.84705882]
|
|
|
|
mean value: 0.8354495005549389
|
|
|
|
key: test_fscore
|
|
value: [0.82608696 0.92 0.79245283 0.90196078 0.68181818 0.79166667
|
|
0.81632653 0.86956522 0.7755102 0.63636364]
|
|
|
|
mean value: 0.801175100795781
|
|
|
|
key: train_fscore
|
|
value: [0.82407407 0.84615385 0.84545455 0.84162896 0.84137931 0.83410138
|
|
0.85067873 0.83027523 0.8375286 0.85327314]
|
|
|
|
mean value: 0.8404547821997773
|
|
|
|
key: test_precision
|
|
value: [0.86363636 0.88461538 0.72413793 0.85185185 0.75 0.79166667
|
|
0.76923077 0.86956522 0.73076923 0.66666667]
|
|
|
|
mean value: 0.7902140081862721
|
|
|
|
key: train_precision
|
|
value: [0.80909091 0.81304348 0.81578947 0.80869565 0.8206278 0.81531532
|
|
0.8209607 0.81165919 0.81696429 0.82173913]
|
|
|
|
mean value: 0.8153885938879937
|
|
|
|
key: test_recall
|
|
value: [0.79166667 0.95833333 0.875 0.95833333 0.625 0.79166667
|
|
0.86956522 0.86956522 0.82608696 0.60869565]
|
|
|
|
mean value: 0.817391304347826
|
|
|
|
key: train_recall
|
|
value: [0.83962264 0.88207547 0.87735849 0.87735849 0.86320755 0.85377358
|
|
0.88262911 0.84976526 0.85915493 0.88732394]
|
|
|
|
mean value: 0.8672269465851714
|
|
|
|
key: test_roc_auc
|
|
value: [0.83333333 0.91666667 0.76358696 0.89221014 0.70380435 0.78713768
|
|
0.80978261 0.87228261 0.76721014 0.65851449]
|
|
|
|
mean value: 0.8004528985507247
|
|
|
|
key: train_roc_auc
|
|
value: [0.82075472 0.83962264 0.8400877 0.83539286 0.83770706 0.83064266
|
|
0.84461644 0.82582603 0.83287935 0.84696386]
|
|
|
|
mean value: 0.83544933120737
|
|
|
|
key: test_jcc
|
|
value: [0.7037037 0.85185185 0.65625 0.82142857 0.51724138 0.65517241
|
|
0.68965517 0.76923077 0.63333333 0.46666667]
|
|
|
|
mean value: 0.6764533861732138
|
|
|
|
key: train_jcc
|
|
value: [0.7007874 0.73333333 0.73228346 0.7265625 0.72619048 0.71541502
|
|
0.74015748 0.70980392 0.72047244 0.74409449]
|
|
|
|
mean value: 0.7249100526445834
|
|
|
|
MCC on Blind test: 0.36
|
|
|
|
Accuracy on Blind test: 0.75
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01082373 0.01179671 0.0157249 0.01087689 0.01807046 0.0132463
|
|
0.01136136 0.01074243 0.01187515 0.01685405]
|
|
|
|
mean value: 0.013137197494506836
|
|
|
|
key: score_time
|
|
value: [0.01867104 0.01932931 0.0286932 0.01813102 0.03446174 0.02312946
|
|
0.0197289 0.03949952 0.01898313 0.01972079]
|
|
|
|
mean value: 0.024034810066223145
|
|
|
|
key: test_mcc
|
|
value: [0.6761234 0.79235477 0.83243502 0.79308818 0.62091661 0.79308818
|
|
0.44646172 0.7085716 0.77125066 0.57427536]
|
|
|
|
mean value: 0.7008565506331991
|
|
|
|
key: train_mcc
|
|
value: [0.80920967 0.81364131 0.77695269 0.79023988 0.81355985 0.77137232
|
|
0.83735531 0.79643107 0.81098457 0.79717543]
|
|
|
|
mean value: 0.8016922089842818
|
|
|
|
key: test_accuracy
|
|
value: [0.83333333 0.89583333 0.91489362 0.89361702 0.80851064 0.89361702
|
|
0.72340426 0.85106383 0.87234043 0.78723404]
|
|
|
|
mean value: 0.8473847517730496
|
|
|
|
key: train_accuracy
|
|
value: [0.90330189 0.90566038 0.88705882 0.89411765 0.90588235 0.88470588
|
|
0.91764706 0.89647059 0.90352941 0.89647059]
|
|
|
|
mean value: 0.899484461709212
|
|
|
|
key: test_fscore
|
|
value: [0.84615385 0.89795918 0.92 0.90196078 0.82352941 0.90196078
|
|
0.71111111 0.85714286 0.88461538 0.7826087 ]
|
|
|
|
mean value: 0.8527042058740999
|
|
|
|
key: train_fscore
|
|
value: [0.90702948 0.90909091 0.89140271 0.89749431 0.9086758 0.88838269
|
|
0.92063492 0.90134529 0.9082774 0.90178571]
|
|
|
|
mean value: 0.9034119226056286
|
|
|
|
key: test_precision
|
|
value: [0.78571429 0.88 0.88461538 0.85185185 0.77777778 0.85185185
|
|
0.72727273 0.80769231 0.79310345 0.7826087 ]
|
|
|
|
mean value: 0.8142488330704223
|
|
|
|
key: train_precision
|
|
value: [0.87336245 0.87719298 0.85652174 0.86784141 0.88053097 0.85903084
|
|
0.89035088 0.86266094 0.86752137 0.85957447]
|
|
|
|
mean value: 0.869458804415425
|
|
|
|
key: test_recall
|
|
value: [0.91666667 0.91666667 0.95833333 0.95833333 0.875 0.95833333
|
|
0.69565217 0.91304348 1. 0.7826087 ]
|
|
|
|
mean value: 0.8974637681159421
|
|
|
|
key: train_recall
|
|
value: [0.94339623 0.94339623 0.92924528 0.92924528 0.93867925 0.91981132
|
|
0.95305164 0.94366197 0.95305164 0.94835681]
|
|
|
|
mean value: 0.940189565063336
|
|
|
|
key: test_roc_auc
|
|
value: [0.83333333 0.89583333 0.91394928 0.89221014 0.80706522 0.89221014
|
|
0.72282609 0.85235507 0.875 0.78713768]
|
|
|
|
mean value: 0.8471920289855073
|
|
|
|
key: train_roc_auc
|
|
value: [0.90330189 0.90566038 0.88715785 0.89420011 0.90595934 0.88478829
|
|
0.91756356 0.89635929 0.90341261 0.89634822]
|
|
|
|
mean value: 0.8994751528036141
|
|
|
|
key: test_jcc
|
|
value: [0.73333333 0.81481481 0.85185185 0.82142857 0.7 0.82142857
|
|
0.55172414 0.75 0.79310345 0.64285714]
|
|
|
|
mean value: 0.7480541871921182
|
|
|
|
key: train_jcc
|
|
value: [0.82987552 0.83333333 0.80408163 0.81404959 0.83263598 0.79918033
|
|
0.85294118 0.82040816 0.83196721 0.82113821]
|
|
|
|
mean value: 0.8239611146800666
|
|
|
|
MCC on Blind test: 0.28
|
|
|
|
Accuracy on Blind test: 0.76
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02992916 0.02378225 0.02392197 0.02256894 0.02189469 0.01958084
|
|
0.0212667 0.02193141 0.02358747 0.02965021]
|
|
|
|
mean value: 0.02381136417388916
|
|
|
|
key: score_time
|
|
value: [0.01384568 0.01313853 0.0136919 0.01628327 0.01233101 0.0129168
|
|
0.01212525 0.01937962 0.01301479 0.01562142]
|
|
|
|
mean value: 0.014234828948974609
|
|
|
|
key: test_mcc
|
|
value: [0.84515425 0.72422435 0.75474102 0.91804649 0.74682354 0.83243502
|
|
0.70289855 0.84254172 0.7196797 0.67037015]
|
|
|
|
mean value: 0.7756914779862731
|
|
|
|
key: train_mcc
|
|
value: [0.84418042 0.8653764 0.86268172 0.86633003 0.88083526 0.85758094
|
|
0.87068367 0.86189352 0.85828625 0.86774659]
|
|
|
|
mean value: 0.8635594798431147
|
|
|
|
key: test_accuracy
|
|
value: [0.91666667 0.85416667 0.87234043 0.95744681 0.87234043 0.91489362
|
|
0.85106383 0.91489362 0.85106383 0.82978723]
|
|
|
|
mean value: 0.8834663120567376
|
|
|
|
key: train_accuracy
|
|
value: [0.91981132 0.93160377 0.92941176 0.93176471 0.93882353 0.92705882
|
|
0.93411765 0.92941176 0.92705882 0.93176471]
|
|
|
|
mean value: 0.9300826859045505
|
|
|
|
key: test_fscore
|
|
value: [0.92307692 0.86792453 0.88461538 0.96 0.88 0.92
|
|
0.85106383 0.92 0.8627451 0.84 ]
|
|
|
|
mean value: 0.8909425763820644
|
|
|
|
key: train_fscore
|
|
value: [0.92376682 0.93394077 0.93243243 0.93424036 0.94117647 0.93002257
|
|
0.93665158 0.93243243 0.93064877 0.93512304]
|
|
|
|
mean value: 0.9330435258050236
|
|
|
|
key: test_precision
|
|
value: [0.85714286 0.79310345 0.82142857 0.92307692 0.84615385 0.88461538
|
|
0.83333333 0.85185185 0.78571429 0.77777778]
|
|
|
|
mean value: 0.8374198279370693
|
|
|
|
key: train_precision
|
|
value: [0.88034188 0.9030837 0.89224138 0.89956332 0.90434783 0.89177489
|
|
0.90393013 0.8961039 0.88888889 0.89316239]
|
|
|
|
mean value: 0.8953438305891439
|
|
|
|
key: test_recall
|
|
value: [1. 0.95833333 0.95833333 1. 0.91666667 0.95833333
|
|
0.86956522 1. 0.95652174 0.91304348]
|
|
|
|
mean value: 0.9530797101449275
|
|
|
|
key: train_recall
|
|
value: [0.97169811 0.96698113 0.97641509 0.97169811 0.98113208 0.97169811
|
|
0.97183099 0.97183099 0.97652582 0.98122066]
|
|
|
|
mean value: 0.9741031092213659
|
|
|
|
key: test_roc_auc
|
|
value: [0.91666667 0.85416667 0.87047101 0.95652174 0.87137681 0.91394928
|
|
0.85144928 0.91666667 0.85326087 0.83152174]
|
|
|
|
mean value: 0.8836050724637682
|
|
|
|
key: train_roc_auc
|
|
value: [0.91981132 0.93160377 0.9295221 0.93185845 0.93892285 0.92716361
|
|
0.9340287 0.92931172 0.92694216 0.93164806]
|
|
|
|
mean value: 0.9300812738063602
|
|
|
|
key: test_jcc
|
|
value: [0.85714286 0.76666667 0.79310345 0.92307692 0.78571429 0.85185185
|
|
0.74074074 0.85185185 0.75862069 0.72413793]
|
|
|
|
mean value: 0.8052907246010694
|
|
|
|
key: train_jcc
|
|
value: [0.85833333 0.87606838 0.87341772 0.87659574 0.88888889 0.86919831
|
|
0.88085106 0.87341772 0.87029289 0.87815126]
|
|
|
|
mean value: 0.8745215309608989
|
|
|
|
MCC on Blind test: 0.66
|
|
|
|
Accuracy on Blind test: 0.88
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [2.25122118 1.58495998 2.26852441 2.66025066 1.31172609 0.68474889
|
|
2.69817162 2.55282569 1.77935028 2.8502481 ]
|
|
|
|
mean value: 2.0642026901245116
|
|
|
|
key: score_time
|
|
value: [0.01252627 0.01248145 0.01890683 0.02309513 0.01239014 0.02043343
|
|
0.04827285 0.01596212 0.01292706 0.01241565]
|
|
|
|
mean value: 0.0189410924911499
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.83243502 0.91804649 0.87318841 0.83243502
|
|
0.83303222 0.87979456 0.77125066 0.65942029]
|
|
|
|
mean value: 0.8558768969205821
|
|
|
|
key: train_mcc
|
|
value: [1. 0.98130676 1. 1. 0.99530516 0.864388
|
|
1. 1. 0.94057664 1. ]
|
|
|
|
mean value: 0.9781576573433062
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.91489362 0.95744681 0.93617021 0.91489362
|
|
0.91489362 0.93617021 0.87234043 0.82978723]
|
|
|
|
mean value: 0.9255762411347518
|
|
|
|
key: train_accuracy
|
|
value: [1. 0.99056604 1. 1. 0.99764706 0.92941176
|
|
1. 1. 0.96941176 1. ]
|
|
|
|
mean value: 0.9887036625971143
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.92 0.96 0.93617021 0.92
|
|
0.91666667 0.93877551 0.88461538 0.82608696]
|
|
|
|
mean value: 0.9281906567508523
|
|
|
|
key: train_fscore
|
|
value: [1. 0.99065421 1. 1. 0.99764706 0.93303571
|
|
1. 1. 0.97038724 1. ]
|
|
|
|
mean value: 0.9891724222452484
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.88461538 0.92307692 0.95652174 0.88461538
|
|
0.88 0.88461538 0.79310345 0.82608696]
|
|
|
|
mean value: 0.8992635220851113
|
|
|
|
key: train_precision
|
|
value: [1. 0.98148148 1. 1. 0.99530516 0.88559322
|
|
1. 1. 0.94247788 1. ]
|
|
|
|
mean value: 0.9804857742245908
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 1. 0.91666667 0.95833333
|
|
0.95652174 1. 1. 0.82608696]
|
|
|
|
mean value: 0.9615942028985507
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 0.98584906
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9985849056603774
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.91394928 0.95652174 0.9365942 0.91394928
|
|
0.91576087 0.9375 0.875 0.82971014]
|
|
|
|
mean value: 0.9258152173913043
|
|
|
|
key: train_roc_auc
|
|
value: [1. 0.99056604 1. 1. 0.99765258 0.92954425
|
|
1. 1. 0.96933962 1. ]
|
|
|
|
mean value: 0.9887102489148729
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.85185185 0.92307692 0.88 0.85185185
|
|
0.84615385 0.88461538 0.79310345 0.7037037 ]
|
|
|
|
mean value: 0.8694357009529423
|
|
|
|
key: train_jcc
|
|
value: [1. 0.98148148 1. 1. 0.99530516 0.87447699
|
|
1. 1. 0.94247788 1. ]
|
|
|
|
mean value: 0.9793741509354624
|
|
|
|
MCC on Blind test: 0.65
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03052568 0.02842188 0.02449274 0.0236342 0.03348374 0.02171397
|
|
0.02360129 0.02903414 0.02557063 0.02380848]
|
|
|
|
mean value: 0.02642867565155029
|
|
|
|
key: score_time
|
|
value: [0.01216698 0.01339197 0.00984573 0.00962591 0.01047254 0.00887585
|
|
0.00871325 0.01319289 0.00919366 0.00850916]
|
|
|
|
mean value: 0.010398793220520019
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.91485507 0.8729597 0.95833333 0.91804649
|
|
0.95833333 1. 0.91833182 0.91804649]
|
|
|
|
mean value: 0.9458906242800675
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.95744681 0.93617021 0.9787234 0.95744681
|
|
0.9787234 1. 0.95744681 0.95744681]
|
|
|
|
mean value: 0.9723404255319149
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.95833333 0.93877551 0.9787234 0.96
|
|
0.9787234 1. 0.95833333 0.95454545]
|
|
|
|
mean value: 0.9727434439926841
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.95833333 0.92 1. 0.92307692
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.967974358974359
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 0.95833333 0.95833333 1.
|
|
1. 1. 1. 0.91304348]
|
|
|
|
mean value: 0.9788043478260869
|
|
|
|
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. 0.95742754 0.93568841 0.97916667 0.95652174
|
|
0.97916667 1. 0.95833333 0.95652174]
|
|
|
|
mean value: 0.9722826086956522
|
|
|
|
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. 0.92 0.88461538 0.95833333 0.92307692
|
|
0.95833333 1. 0.92 0.91304348]
|
|
|
|
mean value: 0.9477402452619844
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.85
|
|
|
|
Accuracy on Blind test: 0.95
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.11498809 0.1160183 0.1233232 0.12288165 0.12551832 0.12082362
|
|
0.12370038 0.12545753 0.12705469 0.11694169]
|
|
|
|
mean value: 0.12167074680328369
|
|
|
|
key: score_time
|
|
value: [0.0211978 0.01757097 0.01934648 0.01911211 0.01925993 0.01820016
|
|
0.01906133 0.01928306 0.0183382 0.01907492]
|
|
|
|
mean value: 0.01904449462890625
|
|
|
|
key: test_mcc
|
|
value: [0.91666667 0.9591663 0.91833182 0.91485507 0.91833182 0.91804649
|
|
0.7876601 0.95833333 0.79418308 0.79308818]
|
|
|
|
mean value: 0.8878662870399457
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 0.97916667 0.95744681 0.95744681 0.95744681 0.95744681
|
|
0.89361702 0.9787234 0.89361702 0.89361702]
|
|
|
|
mean value: 0.942686170212766
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.95833333 0.9787234 0.95652174 0.95833333 0.95652174 0.96
|
|
0.88888889 0.9787234 0.89795918 0.88372093]
|
|
|
|
mean value: 0.9417725956233092
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.95833333 1. 1. 0.95833333 1. 0.92307692
|
|
0.90909091 0.95833333 0.84615385 0.95 ]
|
|
|
|
mean value: 0.9503321678321679
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.95833333 0.95833333 0.91666667 0.95833333 0.91666667 1.
|
|
0.86956522 1. 0.95652174 0.82608696]
|
|
|
|
mean value: 0.9360507246376811
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 0.97916667 0.95833333 0.95742754 0.95833333 0.95652174
|
|
0.89311594 0.97916667 0.89492754 0.89221014]
|
|
|
|
mean value: 0.9427536231884058
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.92 0.95833333 0.91666667 0.92 0.91666667 0.92307692
|
|
0.8 0.95833333 0.81481481 0.79166667]
|
|
|
|
mean value: 0.8919558404558404
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.7
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01029873 0.01048374 0.01039195 0.01048231 0.01037955 0.01036739
|
|
0.0103364 0.0102787 0.01070547 0.01053286]
|
|
|
|
mean value: 0.010425710678100586
|
|
|
|
key: score_time
|
|
value: [0.00883007 0.00876021 0.00898576 0.00892329 0.00889826 0.00889611
|
|
0.00895333 0.0088973 0.00893116 0.00891089]
|
|
|
|
mean value: 0.008898639678955078
|
|
|
|
key: test_mcc
|
|
value: [0.41666667 0.59160798 0.61706091 0.65942029 0.71722586 0.48913043
|
|
0.44874504 0.74773263 0.49454913 0.61706091]
|
|
|
|
mean value: 0.5799199842698882
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.70833333 0.79166667 0.80851064 0.82978723 0.85106383 0.74468085
|
|
0.72340426 0.87234043 0.74468085 0.80851064]
|
|
|
|
mean value: 0.7882978723404255
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.70833333 0.80769231 0.81632653 0.83333333 0.86792453 0.75
|
|
0.69767442 0.875 0.71428571 0.8 ]
|
|
|
|
mean value: 0.7870570166163472
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.70833333 0.75 0.8 0.83333333 0.79310345 0.75
|
|
0.75 0.84 0.78947368 0.81818182]
|
|
|
|
mean value: 0.7832425617334874
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.70833333 0.875 0.83333333 0.83333333 0.95833333 0.75
|
|
0.65217391 0.91304348 0.65217391 0.7826087 ]
|
|
|
|
mean value: 0.7958333333333334
|
|
|
|
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 0.79166667 0.80797101 0.82971014 0.84873188 0.74456522
|
|
0.72192029 0.87318841 0.74275362 0.80797101]
|
|
|
|
mean value: 0.7876811594202898
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.5483871 0.67741935 0.68965517 0.71428571 0.76666667 0.6
|
|
0.53571429 0.77777778 0.55555556 0.66666667]
|
|
|
|
mean value: 0.6532128290693363
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.15
|
|
|
|
Accuracy on Blind test: 0.68
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.82471442 1.82844329 1.79011774 1.83105421 1.8452208 1.84841108
|
|
1.82388473 1.83219314 1.75959945 1.92894244]
|
|
|
|
mean value: 1.8312581300735473
|
|
|
|
key: score_time
|
|
value: [0.09624219 0.0992229 0.09345317 0.09789276 0.09796286 0.09920692
|
|
0.098032 0.09076977 0.09462881 0.09905481]
|
|
|
|
mean value: 0.09664661884307861
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.95833333 0.95825929 1. 0.95825929
|
|
0.8729597 1. 0.91833182 0.87917396]
|
|
|
|
mean value: 0.9545317396993056
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.9787234 0.9787234 1. 0.9787234
|
|
0.93617021 1. 0.95744681 0.93617021]
|
|
|
|
mean value: 0.9765957446808511
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.9787234 0.97959184 1. 0.97959184
|
|
0.93333333 1. 0.95833333 0.93023256]
|
|
|
|
mean value: 0.9759806302530908
|
|
|
|
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. 0.96 1. 0.96
|
|
0.95454545 1. 0.92 1. ]
|
|
|
|
mean value: 0.9794545454545455
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 1. 1. 1.
|
|
0.91304348 1. 1. 0.86956522]
|
|
|
|
mean value: 0.9740942028985508
|
|
|
|
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. 0.97916667 0.97826087 1. 0.97826087
|
|
0.93568841 1. 0.95833333 0.93478261]
|
|
|
|
mean value: 0.9764492753623188
|
|
|
|
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. 0.95833333 0.96 1. 0.96
|
|
0.875 1. 0.92 0.86956522]
|
|
|
|
mean value: 0.9542898550724638
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.77
|
|
|
|
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: /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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000...05', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.01496148 0.95214868 0.95732546 0.95987844 0.96722293 0.96256638
|
|
0.9632771 0.98704982 0.96414256 1.08190107]
|
|
|
|
mean value: 0.9810473918914795
|
|
|
|
key: score_time
|
|
value: [0.22425747 0.21750998 0.29014921 0.2865181 0.2636435 0.26358747
|
|
0.22439122 0.19054675 0.24048018 0.20813012]
|
|
|
|
mean value: 0.24092140197753906
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.95833333 0.91485507 0.95833333 0.95825929
|
|
0.91485507 1. 0.87318841 0.91804649]
|
|
|
|
mean value: 0.9455037307134223
|
|
|
|
key: train_mcc
|
|
value: [0.97174136 0.97651287 0.98135106 0.98122024 0.97180822 0.98122024
|
|
0.97180697 0.97180697 0.98589304 0.97656701]
|
|
|
|
mean value: 0.9769927971034004
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.9787234 0.95744681 0.9787234 0.9787234
|
|
0.95744681 1. 0.93617021 0.95744681]
|
|
|
|
mean value: 0.9723847517730496
|
|
|
|
key: train_accuracy
|
|
value: [0.98584906 0.98820755 0.99058824 0.99058824 0.98588235 0.99058824
|
|
0.98588235 0.98588235 0.99294118 0.98823529]
|
|
|
|
mean value: 0.9884644839067702
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.9787234 0.95833333 0.9787234 0.97959184
|
|
0.95652174 1. 0.93617021 0.95454545]
|
|
|
|
mean value: 0.9722201221755206
|
|
|
|
key: train_fscore
|
|
value: [0.98591549 0.9882904 0.99065421 0.99061033 0.98591549 0.99061033
|
|
0.98598131 0.98598131 0.99297424 0.98834499]
|
|
|
|
mean value: 0.9885278090969725
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 1. 0.95833333 1. 0.96
|
|
0.95652174 1. 0.91666667 1. ]
|
|
|
|
mean value: 0.9751521739130434
|
|
|
|
key: train_precision
|
|
value: [0.98130841 0.98139535 0.98148148 0.98598131 0.98130841 0.98598131
|
|
0.98139535 0.98139535 0.99065421 0.98148148]
|
|
|
|
mean value: 0.9832382654334404
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 0.95833333 0.95833333 1.
|
|
0.95652174 1. 0.95652174 0.91304348]
|
|
|
|
mean value: 0.970108695652174
|
|
|
|
key: train_recall
|
|
value: [0.99056604 0.99528302 1. 0.99528302 0.99056604 0.99528302
|
|
0.99061033 0.99061033 0.99530516 0.99530516]
|
|
|
|
mean value: 0.9938812117990965
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.97916667 0.95742754 0.97916667 0.97826087
|
|
0.95742754 1. 0.9365942 0.95652174]
|
|
|
|
mean value: 0.9723731884057971
|
|
|
|
key: train_roc_auc
|
|
value: [0.98584906 0.98820755 0.99061033 0.99059926 0.98589335 0.99059926
|
|
0.9858712 0.9858712 0.9929356 0.98821862]
|
|
|
|
mean value: 0.9884655416777394
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.95833333 0.92 0.95833333 0.96
|
|
0.91666667 1. 0.88 0.91304348]
|
|
|
|
mean value: 0.9466376811594203
|
|
|
|
key: train_jcc
|
|
value: [0.97222222 0.97685185 0.98148148 0.98139535 0.97222222 0.98139535
|
|
0.97235023 0.97235023 0.98604651 0.97695853]
|
|
|
|
mean value: 0.9773273973255219
|
|
|
|
MCC on Blind test: 0.77
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02566028 0.01113081 0.01062346 0.0112977 0.01124787 0.01040483
|
|
0.01082873 0.01027322 0.01099563 0.01097655]
|
|
|
|
mean value: 0.012343907356262207
|
|
|
|
key: score_time
|
|
value: [0.01252389 0.00886297 0.00960898 0.00960708 0.00915885 0.00957012
|
|
0.00895715 0.0090785 0.01065207 0.00960851]
|
|
|
|
mean value: 0.009762811660766601
|
|
|
|
key: test_mcc
|
|
value: [0.66899361 0.83624201 0.54211097 0.79308818 0.4121128 0.57427536
|
|
0.62296012 0.74456522 0.53734864 0.31876614]
|
|
|
|
mean value: 0.6050463054309297
|
|
|
|
key: train_mcc
|
|
value: [0.64196668 0.68170693 0.68199016 0.67307013 0.67623828 0.66194531
|
|
0.69131813 0.65244722 0.66673391 0.69629094]
|
|
|
|
mean value: 0.6723707683420355
|
|
|
|
key: test_accuracy
|
|
value: [0.83333333 0.91666667 0.76595745 0.89361702 0.70212766 0.78723404
|
|
0.80851064 0.87234043 0.76595745 0.65957447]
|
|
|
|
mean value: 0.800531914893617
|
|
|
|
key: train_accuracy
|
|
value: [0.82075472 0.83962264 0.84 0.83529412 0.83764706 0.83058824
|
|
0.84470588 0.82588235 0.83294118 0.84705882]
|
|
|
|
mean value: 0.8354495005549389
|
|
|
|
key: test_fscore
|
|
value: [0.82608696 0.92 0.79245283 0.90196078 0.68181818 0.79166667
|
|
0.81632653 0.86956522 0.7755102 0.63636364]
|
|
|
|
mean value: 0.801175100795781
|
|
|
|
key: train_fscore
|
|
value: [0.82407407 0.84615385 0.84545455 0.84162896 0.84137931 0.83410138
|
|
0.85067873 0.83027523 0.8375286 0.85327314]
|
|
|
|
mean value: 0.8404547821997773
|
|
|
|
key: test_precision
|
|
value: [0.86363636 0.88461538 0.72413793 0.85185185 0.75 0.79166667
|
|
0.76923077 0.86956522 0.73076923 0.66666667]
|
|
|
|
mean value: 0.7902140081862721
|
|
|
|
key: train_precision
|
|
value: [0.80909091 0.81304348 0.81578947 0.80869565 0.8206278 0.81531532
|
|
0.8209607 0.81165919 0.81696429 0.82173913]
|
|
|
|
mean value: 0.8153885938879937
|
|
|
|
key: test_recall
|
|
value: [0.79166667 0.95833333 0.875 0.95833333 0.625 0.79166667
|
|
0.86956522 0.86956522 0.82608696 0.60869565]
|
|
|
|
mean value: 0.817391304347826
|
|
|
|
key: train_recall
|
|
value: [0.83962264 0.88207547 0.87735849 0.87735849 0.86320755 0.85377358
|
|
0.88262911 0.84976526 0.85915493 0.88732394]
|
|
|
|
mean value: 0.8672269465851714
|
|
|
|
key: test_roc_auc
|
|
value: [0.83333333 0.91666667 0.76358696 0.89221014 0.70380435 0.78713768
|
|
0.80978261 0.87228261 0.76721014 0.65851449]
|
|
|
|
mean value: 0.8004528985507247
|
|
|
|
key: train_roc_auc
|
|
value: [0.82075472 0.83962264 0.8400877 0.83539286 0.83770706 0.83064266
|
|
0.84461644 0.82582603 0.83287935 0.84696386]
|
|
|
|
mean value: 0.83544933120737
|
|
|
|
key: test_jcc
|
|
value: [0.7037037 0.85185185 0.65625 0.82142857 0.51724138 0.65517241
|
|
0.68965517 0.76923077 0.63333333 0.46666667]
|
|
|
|
mean value: 0.6764533861732138
|
|
|
|
key: train_jcc
|
|
value: [0.7007874 0.73333333 0.73228346 0.7265625 0.72619048 0.71541502
|
|
0.74015748 0.70980392 0.72047244 0.74409449]
|
|
|
|
mean value: 0.7249100526445834
|
|
|
|
MCC on Blind test: 0.36
|
|
|
|
Accuracy on Blind test: 0.75
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'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: [0.07653546 0.1252203 0.06999874 0.14294457 0.07059503 0.26261544
|
|
0.16687584 0.13104296 0.11848068 0.065135 ]
|
|
|
|
mean value: 0.12294440269470215
|
|
|
|
key: score_time
|
|
value: [0.01110458 0.01102161 0.01080799 0.01129913 0.01188827 0.01266766
|
|
0.0108943 0.01096749 0.01307154 0.01065111]
|
|
|
|
mean value: 0.011437368392944337
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.91485507 0.95825929 1. 0.91804649
|
|
1. 1. 0.91833182 0.95825929]
|
|
|
|
mean value: 0.9667751969880165
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.95744681 0.9787234 1. 0.95744681
|
|
1. 1. 0.95744681 0.9787234 ]
|
|
|
|
mean value: 0.9829787234042553
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.95833333 0.97959184 1. 0.96
|
|
1. 1. 0.95833333 0.97777778]
|
|
|
|
mean value: 0.9834036281179138
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.95833333 0.96 1. 0.92307692
|
|
1. 1. 0.92 1. ]
|
|
|
|
mean value: 0.9761410256410257
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 1. 1. 1.
|
|
1. 1. 1. 0.95652174]
|
|
|
|
mean value: 0.9914855072463769
|
|
|
|
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. 0.95742754 0.97826087 1. 0.95652174
|
|
1. 1. 0.95833333 0.97826087]
|
|
|
|
mean value: 0.9828804347826087
|
|
|
|
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. 0.92 0.96 1. 0.92307692
|
|
1. 1. 0.92 0.95652174]
|
|
|
|
mean value: 0.9679598662207358
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.85
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.05300355 0.08489585 0.06476498 0.07816267 0.04999113 0.03786612
|
|
0.07270861 0.03970623 0.05691147 0.04838085]
|
|
|
|
mean value: 0.058639144897460936
|
|
|
|
key: score_time
|
|
value: [0.02078748 0.01884246 0.01222396 0.01230502 0.01227593 0.01591635
|
|
0.01233792 0.01229692 0.0122869 0.02182603]
|
|
|
|
mean value: 0.015109896659851074
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.9591663 0.95825929 0.84147165 0.95833333 0.91804649
|
|
0.91833182 0.91833182 0.87979456 0.83303222]
|
|
|
|
mean value: 0.9143933798818509
|
|
|
|
key: train_mcc
|
|
value: [0.98130676 0.98130676 0.98135106 0.99063227 0.98135106 0.985981
|
|
0.98134942 0.98134942 0.99063185 0.98134942]
|
|
|
|
mean value: 0.9836609039565108
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.97916667 0.9787234 0.91489362 0.9787234 0.95744681
|
|
0.95744681 0.95744681 0.93617021 0.91489362]
|
|
|
|
mean value: 0.9554078014184397
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.99056604 0.99058824 0.99529412 0.99058824 0.99294118
|
|
0.99058824 0.99058824 0.99529412 0.99058824]
|
|
|
|
mean value: 0.9917602663706993
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.97959184 0.97959184 0.92307692 0.9787234 0.96
|
|
0.95833333 0.95833333 0.93877551 0.91666667]
|
|
|
|
mean value: 0.9572684681073739
|
|
|
|
key: train_fscore
|
|
value: [0.99065421 0.99065421 0.99065421 0.99530516 0.99065421 0.99297424
|
|
0.99069767 0.99069767 0.9953271 0.99069767]
|
|
|
|
mean value: 0.9918316351684586
|
|
|
|
key: test_precision
|
|
value: [0.96 0.96 0.96 0.85714286 1. 0.92307692
|
|
0.92 0.92 0.88461538 0.88 ]
|
|
|
|
mean value: 0.9264835164835165
|
|
|
|
key: train_precision
|
|
value: [0.98148148 0.98148148 0.98148148 0.99065421 0.98148148 0.98604651
|
|
0.98156682 0.98156682 0.99069767 0.98156682]
|
|
|
|
mean value: 0.9838024778409408
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.95833333 1.
|
|
1. 1. 1. 0.95652174]
|
|
|
|
mean value: 0.9914855072463769
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.97916667 0.97826087 0.91304348 0.97916667 0.95652174
|
|
0.95833333 0.95833333 0.9375 0.91576087]
|
|
|
|
mean value: 0.9555253623188406
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.99056604 0.99061033 0.99530516 0.99061033 0.99295775
|
|
0.99056604 0.99056604 0.99528302 0.99056604]
|
|
|
|
mean value: 0.9917596775622287
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.96 0.96 0.85714286 0.95833333 0.92307692
|
|
0.92 0.92 0.88461538 0.84615385]
|
|
|
|
mean value: 0.9189322344322344
|
|
|
|
key: train_jcc
|
|
value: [0.98148148 0.98148148 0.98148148 0.99065421 0.98148148 0.98604651
|
|
0.98156682 0.98156682 0.99069767 0.98156682]
|
|
|
|
mean value: 0.9838024778409408
|
|
|
|
MCC on Blind test: 0.65
|
|
|
|
Accuracy on Blind test: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01909685 0.00983787 0.01058388 0.00967264 0.00952291 0.00940132
|
|
0.0095005 0.00957775 0.00979638 0.00966644]
|
|
|
|
mean value: 0.010665655136108398
|
|
|
|
key: score_time
|
|
value: [0.01086402 0.00888133 0.00861168 0.00844646 0.0084846 0.00855875
|
|
0.00849605 0.00850463 0.00886607 0.00875497]
|
|
|
|
mean value: 0.008846855163574219
|
|
|
|
key: test_mcc
|
|
value: [0.83624201 0.77459667 0.55422693 0.65942029 0.44874504 0.61706091
|
|
0.79418308 0.74773263 0.4121128 0.45173716]
|
|
|
|
mean value: 0.6296057512401287
|
|
|
|
key: train_mcc
|
|
value: [0.69347833 0.69042715 0.7080502 0.63711098 0.65605073 0.63644692
|
|
0.66968112 0.6444195 0.6445973 0.68248723]
|
|
|
|
mean value: 0.6662749462958447
|
|
|
|
key: test_accuracy
|
|
value: [0.91666667 0.875 0.76595745 0.82978723 0.72340426 0.80851064
|
|
0.89361702 0.87234043 0.70212766 0.72340426]
|
|
|
|
mean value: 0.8110815602836879
|
|
|
|
key: train_accuracy
|
|
value: [0.84198113 0.83962264 0.84941176 0.81647059 0.82588235 0.81647059
|
|
0.83058824 0.81882353 0.82117647 0.83764706]
|
|
|
|
mean value: 0.82980743618202
|
|
|
|
key: test_fscore
|
|
value: [0.92 0.88888889 0.8 0.83333333 0.74509804 0.81632653
|
|
0.89795918 0.875 0.72 0.73469388]
|
|
|
|
mean value: 0.8231299853274643
|
|
|
|
key: train_fscore
|
|
value: [0.8540305 0.85281385 0.86026201 0.82589286 0.83482143 0.82511211
|
|
0.84347826 0.83150985 0.82882883 0.84901532]
|
|
|
|
mean value: 0.8405765009786585
|
|
|
|
key: test_precision
|
|
value: [0.88461538 0.8 0.70967742 0.83333333 0.7037037 0.8
|
|
0.84615385 0.84 0.66666667 0.69230769]
|
|
|
|
mean value: 0.7776458046135466
|
|
|
|
key: train_precision
|
|
value: [0.79352227 0.788 0.80081301 0.78389831 0.79237288 0.78632479
|
|
0.7854251 0.77868852 0.7965368 0.79508197]
|
|
|
|
mean value: 0.7900663637656673
|
|
|
|
key: test_recall
|
|
value: [0.95833333 1. 0.91666667 0.83333333 0.79166667 0.83333333
|
|
0.95652174 0.91304348 0.7826087 0.7826087 ]
|
|
|
|
mean value: 0.8768115942028986
|
|
|
|
key: train_recall
|
|
value: [0.9245283 0.92924528 0.92924528 0.87264151 0.88207547 0.86792453
|
|
0.91079812 0.89201878 0.86384977 0.91079812]
|
|
|
|
mean value: 0.8983125166090885
|
|
|
|
key: test_roc_auc
|
|
value: [0.91666667 0.875 0.76268116 0.82971014 0.72192029 0.80797101
|
|
0.89492754 0.87318841 0.70380435 0.72463768]
|
|
|
|
mean value: 0.8110507246376812
|
|
|
|
key: train_roc_auc
|
|
value: [0.84198113 0.83962264 0.84959917 0.81660244 0.82601426 0.81659137
|
|
0.83039906 0.8186509 0.82107583 0.83747453]
|
|
|
|
mean value: 0.8298011338471077
|
|
|
|
key: test_jcc
|
|
value: [0.85185185 0.8 0.66666667 0.71428571 0.59375 0.68965517
|
|
0.81481481 0.77777778 0.5625 0.58064516]
|
|
|
|
mean value: 0.7051947159100941
|
|
|
|
key: train_jcc
|
|
value: [0.74524715 0.74339623 0.75478927 0.70342205 0.7164751 0.70229008
|
|
0.72932331 0.71161049 0.70769231 0.73764259]
|
|
|
|
mean value: 0.7251888560493678
|
|
|
|
MCC on Blind test: 0.59
|
|
|
|
Accuracy on Blind test: 0.83
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01637173 0.02228785 0.01941609 0.02553582 0.02302885 0.02078366
|
|
0.02198863 0.02079201 0.02677321 0.02678776]
|
|
|
|
mean value: 0.02237656116485596
|
|
|
|
key: score_time
|
|
value: [0.00879383 0.01094794 0.01212692 0.01175642 0.01176858 0.01171994
|
|
0.01172137 0.01155329 0.01219416 0.01182032]
|
|
|
|
mean value: 0.011440277099609375
|
|
|
|
key: test_mcc
|
|
value: [0.87576054 1. 0.79308818 0.91804649 0.84254172 0.73387289
|
|
0.91833182 0.74682354 0.74682354 0.87917396]
|
|
|
|
mean value: 0.8454462682005697
|
|
|
|
key: train_mcc
|
|
value: [0.92717265 0.98130676 0.96715612 0.99063227 0.97193552 0.81059048
|
|
0.95850284 0.90481925 0.82661049 0.99530506]
|
|
|
|
mean value: 0.9334031432938857
|
|
|
|
key: test_accuracy
|
|
value: [0.9375 1. 0.89361702 0.95744681 0.91489362 0.85106383
|
|
0.95744681 0.87234043 0.87234043 0.93617021]
|
|
|
|
mean value: 0.919281914893617
|
|
|
|
key: train_accuracy
|
|
value: [0.96226415 0.99056604 0.98352941 0.99529412 0.98588235 0.89647059
|
|
0.97882353 0.95058824 0.90588235 0.99764706]
|
|
|
|
mean value: 0.9646947835738069
|
|
|
|
key: test_fscore
|
|
value: [0.93617021 1. 0.90196078 0.96 0.90909091 0.87272727
|
|
0.95833333 0.86363636 0.86363636 0.93023256]
|
|
|
|
mean value: 0.919578779764346
|
|
|
|
key: train_fscore
|
|
value: [0.96078431 0.99065421 0.98360656 0.99530516 0.98571429 0.90598291
|
|
0.97931034 0.94840295 0.89637306 0.99765808]
|
|
|
|
mean value: 0.9643791862577102
|
|
|
|
key: test_precision
|
|
value: [0.95652174 1. 0.85185185 0.92307692 1. 0.77419355
|
|
0.92 0.9047619 0.9047619 1. ]
|
|
|
|
mean value: 0.9235167871970116
|
|
|
|
key: train_precision
|
|
value: [1. 0.98148148 0.97674419 0.99065421 0.99519231 0.828125
|
|
0.95945946 0.99484536 1. 0.9953271 ]
|
|
|
|
mean value: 0.9721829103915718
|
|
|
|
key: test_recall
|
|
value: [0.91666667 1. 0.95833333 1. 0.83333333 1.
|
|
1. 0.82608696 0.82608696 0.86956522]
|
|
|
|
mean value: 0.9230072463768116
|
|
|
|
key: train_recall
|
|
value: [0.9245283 1. 0.99056604 1. 0.97641509 1.
|
|
1. 0.90610329 0.81220657 1. ]
|
|
|
|
mean value: 0.9609819293117193
|
|
|
|
key: test_roc_auc
|
|
value: [0.9375 1. 0.89221014 0.95652174 0.91666667 0.84782609
|
|
0.95833333 0.87137681 0.87137681 0.93478261]
|
|
|
|
mean value: 0.9186594202898551
|
|
|
|
key: train_roc_auc
|
|
value: [0.96226415 0.99056604 0.98354593 0.99530516 0.98586013 0.89671362
|
|
0.97877358 0.95069315 0.90610329 0.99764151]
|
|
|
|
mean value: 0.9647466560368501
|
|
|
|
key: test_jcc
|
|
value: [0.88 1. 0.82142857 0.92307692 0.83333333 0.77419355
|
|
0.92 0.76 0.76 0.86956522]
|
|
|
|
mean value: 0.854159759361723
|
|
|
|
key: train_jcc
|
|
value: [0.9245283 0.98148148 0.96774194 0.99065421 0.97183099 0.828125
|
|
0.95945946 0.90186916 0.81220657 0.9953271 ]
|
|
|
|
mean value: 0.933322420428677
|
|
|
|
MCC on Blind test: 0.76
|
|
|
|
Accuracy on Blind test: 0.92
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01740003 0.01784468 0.02007461 0.01927519 0.01789665 0.01702976
|
|
0.01722717 0.01723099 0.01678109 0.01704574]
|
|
|
|
mean value: 0.017780590057373046
|
|
|
|
key: score_time
|
|
value: [0.01170635 0.01180816 0.01206303 0.0126965 0.01173472 0.01176977
|
|
0.01149845 0.01182127 0.01149845 0.01173759]
|
|
|
|
mean value: 0.011833429336547852
|
|
|
|
key: test_mcc
|
|
value: [0.91986621 0.74053163 0.91833182 0.91804649 0.77125066 0.79308818
|
|
0.87318841 0.7070024 0.73692303 0.71722586]
|
|
|
|
mean value: 0.8095454694268561
|
|
|
|
key: train_mcc
|
|
value: [0.94444751 0.86721746 0.78884802 0.97674215 0.8290691 0.9273503
|
|
0.95774087 0.87907709 0.86330895 0.93449419]
|
|
|
|
mean value: 0.8968295643339719
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 0.85416667 0.95744681 0.95744681 0.87234043 0.89361702
|
|
0.93617021 0.85106383 0.85106383 0.85106383]
|
|
|
|
mean value: 0.8982712765957447
|
|
|
|
key: train_accuracy
|
|
value: [0.97169811 0.92924528 0.88470588 0.98823529 0.90823529 0.96235294
|
|
0.97882353 0.93647059 0.92705882 0.96705882]
|
|
|
|
mean value: 0.9453884572697003
|
|
|
|
key: test_fscore
|
|
value: [0.96 0.87272727 0.95652174 0.96 0.85714286 0.90196078
|
|
0.93617021 0.8372093 0.86792453 0.82926829]
|
|
|
|
mean value: 0.8978924989390643
|
|
|
|
key: train_fscore
|
|
value: [0.97235023 0.9339207 0.87002653 0.98834499 0.89922481 0.96363636
|
|
0.97902098 0.93266833 0.9321663 0.96666667]
|
|
|
|
mean value: 0.9438025895476471
|
|
|
|
key: test_precision
|
|
value: [0.92307692 0.77419355 1. 0.92307692 1. 0.85185185
|
|
0.91666667 0.9 0.76666667 0.94444444]
|
|
|
|
mean value: 0.8999977024170572
|
|
|
|
key: train_precision
|
|
value: [0.95045045 0.87603306 0.99393939 0.97695853 0.99428571 0.92982456
|
|
0.97222222 0.99468085 0.87295082 0.98067633]
|
|
|
|
mean value: 0.9542021924736528
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.91666667 1. 0.75 0.95833333
|
|
0.95652174 0.7826087 1. 0.73913043]
|
|
|
|
mean value: 0.9103260869565217
|
|
|
|
key: train_recall
|
|
value: [0.99528302 1. 0.77358491 1. 0.82075472 1.
|
|
0.98591549 0.87793427 1. 0.95305164]
|
|
|
|
mean value: 0.9406524049960139
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 0.85416667 0.95833333 0.95652174 0.875 0.89221014
|
|
0.9365942 0.84963768 0.85416667 0.84873188]
|
|
|
|
mean value: 0.8983695652173913
|
|
|
|
key: train_roc_auc
|
|
value: [0.97169811 0.92924528 0.88444503 0.98826291 0.90802994 0.96244131
|
|
0.9788068 0.93660865 0.92688679 0.96709186]
|
|
|
|
mean value: 0.9453516697670299
|
|
|
|
key: test_jcc
|
|
value: [0.92307692 0.77419355 0.91666667 0.92307692 0.75 0.82142857
|
|
0.88 0.72 0.76666667 0.70833333]
|
|
|
|
mean value: 0.8183442632636181
|
|
|
|
key: train_jcc
|
|
value: [0.94618834 0.87603306 0.76995305 0.97695853 0.81690141 0.92982456
|
|
0.95890411 0.87383178 0.87295082 0.93548387]
|
|
|
|
mean value: 0.8957029521431291
|
|
|
|
MCC on Blind test: 0.71
|
|
|
|
Accuracy on Blind test: 0.91
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.22525454 0.20638967 0.20975685 0.20803928 0.20734549 0.20901322
|
|
0.2099731 0.20846248 0.20936227 0.21185827]
|
|
|
|
mean value: 0.21054551601409913
|
|
|
|
key: score_time
|
|
value: [0.0150938 0.01513886 0.01519561 0.01499867 0.01480699 0.01701713
|
|
0.01484537 0.01529884 0.01508498 0.01632452]
|
|
|
|
mean value: 0.015380477905273438
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.95833333 0.91485507 0.95833333 0.91804649
|
|
0.95833333 1. 0.91833182 0.95825929]
|
|
|
|
mean value: 0.9584492678474537
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.9787234 0.95744681 0.9787234 0.95744681
|
|
0.9787234 1. 0.95744681 0.9787234 ]
|
|
|
|
mean value: 0.9787234042553191
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.9787234 0.95833333 0.9787234 0.96
|
|
0.9787234 1. 0.95833333 0.97777778]
|
|
|
|
mean value: 0.9790614657210401
|
|
|
|
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. 0.95833333 1. 0.92307692
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.975974358974359
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 0.95833333 0.95833333 1.
|
|
1. 1. 1. 0.95652174]
|
|
|
|
mean value: 0.9831521739130435
|
|
|
|
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. 0.97916667 0.95742754 0.97916667 0.95652174
|
|
0.97916667 1. 0.95833333 0.97826087]
|
|
|
|
mean value: 0.9788043478260869
|
|
|
|
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. 0.95833333 0.92 0.95833333 0.92307692
|
|
0.95833333 1. 0.92 0.95652174]
|
|
|
|
mean value: 0.9594598662207359
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
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: /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]
|
|
/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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.05935359 0.05659366 0.07029271 0.05852938 0.08223605 0.06015468
|
|
0.06851172 0.07797432 0.09515691 0.07843113]
|
|
|
|
mean value: 0.07072341442108154
|
|
|
|
key: score_time
|
|
value: [0.02356625 0.02673054 0.02482605 0.03660083 0.02371502 0.03025317
|
|
0.02513838 0.02481318 0.03210163 0.01969957]
|
|
|
|
mean value: 0.02674446105957031
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.91833182 0.91485507 0.95833333 0.91804649
|
|
0.95833333 0.95825929 0.91833182 0.95825929]
|
|
|
|
mean value: 0.9502750457477226
|
|
|
|
key: train_mcc
|
|
value: [0.99529409 0.99061012 0.99530506 1. 1. 1.
|
|
0.99530506 0.99530516 0.99530506 0.99530506]
|
|
|
|
mean value: 0.9962429618909044
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.95744681 0.95744681 0.9787234 0.95744681
|
|
0.9787234 0.9787234 0.95744681 0.9787234 ]
|
|
|
|
mean value: 0.9744680851063829
|
|
|
|
key: train_accuracy
|
|
value: [0.99764151 0.99528302 0.99764706 1. 1. 1.
|
|
0.99764706 0.99764706 0.99764706 0.99764706]
|
|
|
|
mean value: 0.9981159822419534
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.95652174 0.95833333 0.9787234 0.96
|
|
0.9787234 0.97777778 0.95833333 0.97777778]
|
|
|
|
mean value: 0.9746190769863295
|
|
|
|
key: train_fscore
|
|
value: [0.99764706 0.99530516 0.99763593 1. 1. 1.
|
|
0.99765808 0.99764706 0.99765808 0.99765808]
|
|
|
|
mean value: 0.9981209454648332
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 0.95833333 1. 0.92307692
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.975974358974359
|
|
|
|
key: train_precision
|
|
value: [0.99530516 0.99065421 1. 1. 1. 1.
|
|
0.9953271 1. 0.9953271 0.9953271 ]
|
|
|
|
mean value: 0.997194067833794
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.91666667 0.95833333 0.95833333 1.
|
|
1. 0.95652174 1. 0.95652174]
|
|
|
|
mean value: 0.9746376811594203
|
|
|
|
key: train_recall
|
|
value: [1. 1. 0.99528302 1. 1. 1.
|
|
1. 0.99530516 1. 1. ]
|
|
|
|
mean value: 0.9990588183187173
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 0.95833333 0.95742754 0.97916667 0.95652174
|
|
0.97916667 0.97826087 0.95833333 0.97826087]
|
|
|
|
mean value: 0.9745471014492754
|
|
|
|
key: train_roc_auc
|
|
value: [0.99764151 0.99528302 0.99764151 1. 1. 1.
|
|
0.99764151 0.99765258 0.99764151 0.99764151]
|
|
|
|
mean value: 0.998114314819736
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 0.91666667 0.92 0.95833333 0.92307692
|
|
0.95833333 0.95652174 0.92 0.95652174]
|
|
|
|
mean value: 0.9509453734671126
|
|
|
|
key: train_jcc
|
|
value: [0.99530516 0.99065421 0.99528302 1. 1. 1.
|
|
0.9953271 0.99530516 0.9953271 0.9953271 ]
|
|
|
|
mean value: 0.9962528861525114
|
|
|
|
MCC on Blind test: 0.85
|
|
|
|
Accuracy on Blind test: 0.95
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.12989521 0.16610837 0.20399642 0.19648147 0.15128088 0.15928936
|
|
0.13438392 0.10588217 0.20968366 0.20359349]
|
|
|
|
mean value: 0.1660594940185547
|
|
|
|
key: score_time
|
|
value: [0.02352571 0.02397847 0.02493739 0.02676702 0.01454568 0.0274508
|
|
0.01461458 0.01485085 0.01615381 0.01493263]
|
|
|
|
mean value: 0.020175695419311523
|
|
|
|
key: test_mcc
|
|
value: [0.75261781 0.797925 0.74682354 0.87917396 0.7876601 0.83243502
|
|
0.48913043 0.75645593 0.7085716 0.66243303]
|
|
|
|
mean value: 0.7413226422034183
|
|
|
|
key: train_mcc
|
|
value: [0.98117574 0.96750869 0.98135106 0.97193799 0.96732825 0.96732825
|
|
0.97656701 0.97193552 0.97193552 0.9767396 ]
|
|
|
|
mean value: 0.9733807629642168
|
|
|
|
key: test_accuracy
|
|
value: [0.875 0.89583333 0.87234043 0.93617021 0.89361702 0.91489362
|
|
0.74468085 0.87234043 0.85106383 0.82978723]
|
|
|
|
mean value: 0.868572695035461
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.98349057 0.99058824 0.98588235 0.98352941 0.98352941
|
|
0.98823529 0.98588235 0.98588235 0.98823529]
|
|
|
|
mean value: 0.9865821309655938
|
|
|
|
key: test_fscore
|
|
value: [0.88 0.90196078 0.88 0.94117647 0.89795918 0.92
|
|
0.73913043 0.88 0.85714286 0.83333333]
|
|
|
|
mean value: 0.8730703063834229
|
|
|
|
key: train_fscore
|
|
value: [0.99061033 0.9837587 0.99065421 0.98598131 0.98368298 0.98368298
|
|
0.98834499 0.98604651 0.98604651 0.98839907]
|
|
|
|
mean value: 0.9867207594245768
|
|
|
|
key: test_precision
|
|
value: [0.84615385 0.85185185 0.84615385 0.88888889 0.88 0.88461538
|
|
0.73913043 0.81481481 0.80769231 0.8 ]
|
|
|
|
mean value: 0.8359301374953548
|
|
|
|
key: train_precision
|
|
value: [0.98598131 0.96803653 0.98148148 0.97685185 0.97235023 0.97235023
|
|
0.98148148 0.97695853 0.97695853 0.97706422]
|
|
|
|
mean value: 0.9769514384610619
|
|
|
|
key: test_recall
|
|
value: [0.91666667 0.95833333 0.91666667 1. 0.91666667 0.95833333
|
|
0.73913043 0.95652174 0.91304348 0.86956522]
|
|
|
|
mean value: 0.9144927536231884
|
|
|
|
key: train_recall
|
|
value: [0.99528302 1. 1. 0.99528302 0.99528302 0.99528302
|
|
0.99530516 0.99530516 0.99530516 1. ]
|
|
|
|
mean value: 0.9967047568429445
|
|
|
|
key: test_roc_auc
|
|
value: [0.875 0.89583333 0.87137681 0.93478261 0.89311594 0.91394928
|
|
0.74456522 0.8740942 0.85235507 0.83061594]
|
|
|
|
mean value: 0.8685688405797101
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.98349057 0.99061033 0.98590442 0.983557 0.983557
|
|
0.98821862 0.98586013 0.98586013 0.98820755]
|
|
|
|
mean value: 0.9865831783151741
|
|
|
|
key: test_jcc
|
|
value: [0.78571429 0.82142857 0.78571429 0.88888889 0.81481481 0.85185185
|
|
0.5862069 0.78571429 0.75 0.71428571]
|
|
|
|
mean value: 0.7784619594964423
|
|
|
|
key: train_jcc
|
|
value: [0.98139535 0.96803653 0.98148148 0.97235023 0.96788991 0.96788991
|
|
0.97695853 0.97247706 0.97247706 0.97706422]
|
|
|
|
mean value: 0.973802028089704
|
|
|
|
MCC on Blind test: 0.34
|
|
|
|
Accuracy on Blind test: 0.79
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.94548035 0.93381166 0.8602922 0.82730603 0.84126878 0.83702135
|
|
0.85695696 0.83312058 0.83952045 0.84913468]
|
|
|
|
mean value: 0.8623913049697876
|
|
|
|
key: score_time
|
|
value: [0.00987339 0.0107429 0.00943804 0.00917506 0.00945663 0.01050067
|
|
0.00942159 0.00934029 0.009269 0.01059294]
|
|
|
|
mean value: 0.00978105068206787
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.95833333 0.91485507 0.95833333 0.91804649
|
|
0.91833182 0.95825929 0.91833182 0.95825929]
|
|
|
|
mean value: 0.9502750457477226
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.9787234 0.95744681 0.9787234 0.95744681
|
|
0.95744681 0.9787234 0.95744681 0.9787234 ]
|
|
|
|
mean value: 0.9744680851063829
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.9787234 0.95833333 0.9787234 0.96
|
|
0.95833333 0.97777778 0.95833333 0.97777778]
|
|
|
|
mean value: 0.9748002364066194
|
|
|
|
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. 0.95833333 1. 0.92307692
|
|
0.92 1. 0.92 1. ]
|
|
|
|
mean value: 0.9721410256410257
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 0.95833333 0.95833333 1.
|
|
1. 0.95652174 1. 0.95652174]
|
|
|
|
mean value: 0.9788043478260869
|
|
|
|
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. 0.97916667 0.95742754 0.97916667 0.95652174
|
|
0.95833333 0.97826087 0.95833333 0.97826087]
|
|
|
|
mean value: 0.9745471014492754
|
|
|
|
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. 0.95833333 0.92 0.95833333 0.92307692
|
|
0.92 0.95652174 0.92 0.95652174]
|
|
|
|
mean value: 0.951278706800446
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.85
|
|
|
|
Accuracy on Blind test: 0.95
|
|
|
|
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/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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03128076 0.0312593 0.03092837 0.03662229 0.07130241 0.02808523
|
|
0.02973843 0.02836013 0.02838182 0.0289793 ]
|
|
|
|
mean value: 0.03449380397796631
|
|
|
|
key: score_time
|
|
value: [0.01245046 0.01270437 0.0125792 0.01430178 0.01291919 0.0146637
|
|
0.0147078 0.01468539 0.01472926 0.03894806]
|
|
|
|
mean value: 0.0162689208984375
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.91804649 0.95825929 0.95825929 1.
|
|
0.95833333 0.91833182 1. 0.95825929]
|
|
|
|
mean value: 0.9669489522155359
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.95744681 0.9787234 0.9787234 1.
|
|
0.9787234 0.95744681 1. 0.9787234 ]
|
|
|
|
mean value: 0.9829787234042553
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.96 0.97959184 0.97959184 1.
|
|
0.9787234 0.95833333 1. 0.97777778]
|
|
|
|
mean value: 0.9834018188835818
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.92307692 0.96 0.96 1.
|
|
0.95833333 0.92 1. 1. ]
|
|
|
|
mean value: 0.9721410256410257
|
|
|
|
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. 0.95652174]
|
|
|
|
mean value: 0.9956521739130435
|
|
|
|
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. 0.95652174 0.97826087 0.97826087 1.
|
|
0.97916667 0.95833333 1. 0.97826087]
|
|
|
|
mean value: 0.9828804347826087
|
|
|
|
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. 0.92307692 0.96 0.96 1.
|
|
0.95833333 0.92 1. 0.95652174]
|
|
|
|
mean value: 0.9677931995540692
|
|
|
|
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: 0.77
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03286505 0.01581883 0.03775501 0.03883982 0.03876495 0.03876901
|
|
0.03254771 0.03515482 0.03292871 0.0627017 ]
|
|
|
|
mean value: 0.03661456108093262
|
|
|
|
key: score_time
|
|
value: [0.01635623 0.01602483 0.02327514 0.02148223 0.02205324 0.0202868
|
|
0.02265191 0.02122545 0.01483178 0.0392158 ]
|
|
|
|
mean value: 0.02174034118652344
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.91485507 0.91804649 1. 0.87917396
|
|
0.95833333 0.87979456 0.87979456 0.87318841]
|
|
|
|
mean value: 0.9262352687335804
|
|
|
|
key: train_mcc
|
|
value: [0.98130676 0.98130676 0.98135106 0.985981 0.98135106 0.98135106
|
|
0.9767396 0.98134942 0.98598008 0.96758129]
|
|
|
|
mean value: 0.9804298099281881
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.95744681 0.95744681 1. 0.93617021
|
|
0.9787234 0.93617021 0.93617021 0.93617021]
|
|
|
|
mean value: 0.9617464539007092
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.99056604 0.99058824 0.99294118 0.99058824 0.99058824
|
|
0.98823529 0.99058824 0.99294118 0.98352941]
|
|
|
|
mean value: 0.9901132075471698
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.95833333 0.96 1. 0.94117647
|
|
0.9787234 0.93877551 0.93877551 0.93617021]
|
|
|
|
mean value: 0.9631546278085702
|
|
|
|
key: train_fscore
|
|
value: [0.99065421 0.99065421 0.99065421 0.99297424 0.99065421 0.99065421
|
|
0.98839907 0.99069767 0.99300699 0.98383372]
|
|
|
|
mean value: 0.9902182724509417
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.95833333 0.92307692 1. 0.88888889
|
|
0.95833333 0.88461538 0.88461538 0.91666667]
|
|
|
|
mean value: 0.9374529914529914
|
|
|
|
key: train_precision
|
|
value: [0.98148148 0.98148148 0.98148148 0.98604651 0.98148148 0.98148148
|
|
0.97706422 0.98156682 0.98611111 0.96818182]
|
|
|
|
mean value: 0.9806377888788228
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 1. 1. 1.
|
|
1. 1. 1. 0.95652174]
|
|
|
|
mean value: 0.9914855072463769
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.95742754 0.95652174 1. 0.93478261
|
|
0.97916667 0.9375 0.9375 0.9365942 ]
|
|
|
|
mean value: 0.9618659420289856
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.99056604 0.99061033 0.99295775 0.99061033 0.99061033
|
|
0.98820755 0.99056604 0.99292453 0.98349057]
|
|
|
|
mean value: 0.9901109487111347
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.92 0.92307692 1. 0.88888889
|
|
0.95833333 0.88461538 0.88461538 0.88 ]
|
|
|
|
mean value: 0.9299529914529915
|
|
|
|
key: train_jcc
|
|
value: [0.98148148 0.98148148 0.98148148 0.98604651 0.98148148 0.98148148
|
|
0.97706422 0.98156682 0.98611111 0.96818182]
|
|
|
|
mean value: 0.9806377888788228
|
|
|
|
MCC on Blind test: 0.76
|
|
|
|
Accuracy on Blind test: 0.92
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.32522726 0.34228802 0.31509209 0.38272142 0.18838811 0.29327464
|
|
0.16214776 0.30777717 0.37448525 0.20261431]
|
|
|
|
mean value: 0.28940160274505616
|
|
|
|
key: score_time
|
|
value: [0.02093887 0.02248716 0.02073622 0.0349288 0.01229739 0.01782584
|
|
0.01267815 0.02243018 0.02416015 0.01202416]
|
|
|
|
mean value: 0.020050692558288574
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.9591663 0.91485507 0.8729597 1. 0.87917396
|
|
0.95833333 0.87979456 0.87979456 0.87318841]
|
|
|
|
mean value: 0.9176432193713958
|
|
|
|
key: train_mcc
|
|
value: [0.98130676 0.98130676 0.98135106 0.99063227 0.98135106 0.98135106
|
|
0.9767396 0.98134942 0.98598008 0.96758129]
|
|
|
|
mean value: 0.9808949366045362
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.97916667 0.95744681 0.93617021 1. 0.93617021
|
|
0.9787234 0.93617021 0.93617021 0.93617021]
|
|
|
|
mean value: 0.9575354609929078
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.99056604 0.99058824 0.99529412 0.99058824 0.99058824
|
|
0.98823529 0.99058824 0.99294118 0.98352941]
|
|
|
|
mean value: 0.9903485016648169
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.97959184 0.95833333 0.93877551 1. 0.94117647
|
|
0.9787234 0.93877551 0.93877551 0.93617021]
|
|
|
|
mean value: 0.9589913625024478
|
|
|
|
key: train_fscore
|
|
value: /home/tanu/git/LSHTM_analysis/scripts/ml/./embb_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/./embb_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)
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
[0.99065421 0.99065421 0.99065421 0.99530516 0.99065421 0.99065421
|
|
0.98839907 0.99069767 0.99300699 0.98383372]
|
|
|
|
mean value: 0.9904513649952787
|
|
|
|
key: test_precision
|
|
value: [0.96 0.96 0.95833333 0.92 1. 0.88888889
|
|
0.95833333 0.88461538 0.88461538 0.91666667]
|
|
|
|
mean value: 0.9331452991452991
|
|
|
|
key: train_precision
|
|
value: [0.98148148 0.98148148 0.98148148 0.99065421 0.98148148 0.98148148
|
|
0.97706422 0.98156682 0.98611111 0.96818182]
|
|
|
|
mean value: 0.9810985582767797
|
|
|
|
key: test_recall
|
|
value: [1. 1. 0.95833333 0.95833333 1. 1.
|
|
1. 1. 1. 0.95652174]
|
|
|
|
mean value: 0.9873188405797102
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.97916667 0.95742754 0.93568841 1. 0.93478261
|
|
0.97916667 0.9375 0.9375 0.9365942 ]
|
|
|
|
mean value: 0.9576992753623189
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.99056604 0.99061033 0.99530516 0.99061033 0.99061033
|
|
0.98820755 0.99056604 0.99292453 0.98349057]
|
|
|
|
mean value: 0.9903456904951723
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.96 0.92 0.88461538 1. 0.88888889
|
|
0.95833333 0.88461538 0.88461538 0.88 ]
|
|
|
|
mean value: 0.9221068376068375
|
|
|
|
key: train_jcc
|
|
value: [0.98148148 0.98148148 0.98148148 0.99065421 0.98148148 0.98148148
|
|
0.97706422 0.98156682 0.98611111 0.96818182]
|
|
|
|
mean value: 0.9810985582767797
|
|
|
|
MCC on Blind test: 0.76
|
|
|
|
Accuracy on Blind test: 0.92
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03559804 0.03706646 0.03697729 0.03628969 0.03722024 0.03593397
|
|
0.05639243 0.03652668 0.0473063 0.04089761]
|
|
|
|
mean value: 0.040020871162414554
|
|
|
|
key: score_time
|
|
value: [0.01556301 0.01522923 0.01559758 0.01228142 0.01532984 0.01520514
|
|
0.01509237 0.01523328 0.01505256 0.01558781]
|
|
|
|
mean value: 0.015017223358154298
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.83624201 0.84147165 0.87917396 0.79418308 0.87917396
|
|
0.87979456 0.84254172 0.80641033 0.74773263]
|
|
|
|
mean value: 0.8465890200000376
|
|
|
|
key: train_mcc
|
|
value: [0.9584112 0.93546207 0.95400282 0.95851094 0.95332408 0.97215397
|
|
0.96303222 0.95399286 0.96303222 0.95361289]
|
|
|
|
mean value: 0.956553529117059
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.91666667 0.91489362 0.93617021 0.89361702 0.93617021
|
|
0.93617021 0.91489362 0.89361702 0.87234043]
|
|
|
|
mean value: 0.9193705673758865
|
|
|
|
key: train_accuracy
|
|
value: [0.97877358 0.96698113 0.97647059 0.97882353 0.97647059 0.98588235
|
|
0.98117647 0.97647059 0.98117647 0.97647059]
|
|
|
|
mean value: 0.977869589345172
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.91304348 0.92307692 0.94117647 0.88888889 0.94117647
|
|
0.93877551 0.92 0.90196078 0.875 ]
|
|
|
|
mean value: 0.9222690362655653
|
|
|
|
key: train_fscore
|
|
value: [0.97921478 0.96788991 0.97695853 0.97921478 0.97674419 0.98604651
|
|
0.98156682 0.97706422 0.98156682 0.97695853]
|
|
|
|
mean value: 0.9783225078559948
|
|
|
|
key: test_precision
|
|
value: [0.96 0.95454545 0.85714286 0.88888889 0.95238095 0.88888889
|
|
0.88461538 0.85185185 0.82142857 0.84 ]
|
|
|
|
mean value: 0.889974284974285
|
|
|
|
key: train_precision
|
|
value: [0.95927602 0.94196429 0.95495495 0.95927602 0.96330275 0.97247706
|
|
0.9638009 0.95515695 0.9638009 0.95927602]
|
|
|
|
mean value: 0.9593285872109042
|
|
|
|
key: test_recall
|
|
value: [1. 0.875 1. 1. 0.83333333 1.
|
|
1. 1. 1. 0.91304348]
|
|
|
|
mean value: 0.9621376811594203
|
|
|
|
key: train_recall
|
|
value: [1. 0.99528302 1. 1. 0.99056604 1.
|
|
1. 1. 1. 0.99530516]
|
|
|
|
mean value: 0.9981154220923022
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.91666667 0.91304348 0.93478261 0.89492754 0.93478261
|
|
0.9375 0.91666667 0.89583333 0.87318841]
|
|
|
|
mean value: 0.9196557971014493
|
|
|
|
key: train_roc_auc
|
|
value: [0.97877358 0.96698113 0.97652582 0.97887324 0.97650368 0.98591549
|
|
0.98113208 0.97641509 0.98113208 0.97642617]
|
|
|
|
mean value: 0.9778678359464966
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.84 0.85714286 0.88888889 0.8 0.88888889
|
|
0.88461538 0.85185185 0.82142857 0.77777778]
|
|
|
|
mean value: 0.8570594220594221
|
|
|
|
key: train_jcc
|
|
value: [0.95927602 0.93777778 0.95495495 0.95927602 0.95454545 0.97247706
|
|
0.9638009 0.95515695 0.9638009 0.95495495]
|
|
|
|
mean value: 0.9576021003279818
|
|
|
|
MCC on Blind test: 0.69
|
|
|
|
Accuracy on Blind test: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.98532057 0.93763423 0.93471265 1.03396702 0.87530398 0.97497272
|
|
0.87058783 0.99826312 1.04000139 0.85827327]
|
|
|
|
mean value: 0.9509036779403687
|
|
|
|
key: score_time
|
|
value: [0.01235247 0.01532173 0.01533556 0.01511788 0.0151372 0.01530886
|
|
0.01517558 0.01581669 0.01546574 0.01564217]
|
|
|
|
mean value: 0.015067386627197265
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.95825929 0.91804649 0.91485507 0.87917396
|
|
0.91833182 0.91833182 0.87979456 0.95833333]
|
|
|
|
mean value: 0.9304292658366822
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.9787234 0.95744681 0.95744681 0.93617021
|
|
0.95744681 0.95744681 0.93617021 0.9787234 ]
|
|
|
|
mean value: 0.9638741134751774
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.97959184 0.96 0.95833333 0.94117647
|
|
0.95833333 0.95833333 0.93877551 0.9787234 ]
|
|
|
|
mean value: 0.9652859058517024
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.96 0.92307692 0.95833333 0.88888889
|
|
0.92 0.92 0.88461538 0.95833333]
|
|
|
|
mean value: 0.9373247863247863
|
|
|
|
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. 0.95833333 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.97826087 0.95652174 0.95742754 0.93478261
|
|
0.95833333 0.95833333 0.9375 0.97916667]
|
|
|
|
mean value: 0.9639492753623189
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.96 0.92307692 0.92 0.88888889
|
|
0.92 0.92 0.88461538 0.95833333]
|
|
|
|
mean value: 0.933491452991453
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
Accuracy on Blind test: 0.93
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03243518 0.01119995 0.0105989 0.00996256 0.01015925 0.01087189
|
|
0.00985813 0.00995874 0.00988674 0.00992584]
|
|
|
|
mean value: 0.012485718727111817
|
|
|
|
key: score_time
|
|
value: [0.01239109 0.00981951 0.00932717 0.0095005 0.00951529 0.00951171
|
|
0.00873876 0.00869417 0.00872993 0.00874829]
|
|
|
|
mean value: 0.009497642517089844
|
|
|
|
key: test_mcc
|
|
value: [0.58430655 0.58536941 0.53649441 0.76896316 0.63164625 0.66534784
|
|
0.55975995 0.67023783 0.61347187 0.52364889]
|
|
|
|
mean value: 0.6139246156336728
|
|
|
|
key: train_mcc
|
|
value: [0.63964829 0.65520184 0.67178493 0.75679144 0.6481871 0.61300581
|
|
0.6557305 0.62005499 0.6575798 0.64771738]
|
|
|
|
mean value: 0.6565702084437408
|
|
|
|
key: test_accuracy
|
|
value: [0.77083333 0.79166667 0.74468085 0.87234043 0.78723404 0.80851064
|
|
0.76595745 0.80851064 0.78723404 0.74468085]
|
|
|
|
mean value: 0.7881648936170212
|
|
|
|
key: train_accuracy
|
|
value: [0.80188679 0.81132075 0.82117647 0.87529412 0.80941176 0.78823529
|
|
0.81176471 0.79529412 0.81411765 0.80941176]
|
|
|
|
mean value: 0.8137913429522753
|
|
|
|
key: test_fscore
|
|
value: [0.80701754 0.8 0.79310345 0.88888889 0.82758621 0.84210526
|
|
0.79245283 0.83636364 0.81481481 0.77777778]
|
|
|
|
mean value: 0.8180110410223755
|
|
|
|
key: train_fscore
|
|
value: [0.82995951 0.83673469 0.8436214 0.88248337 0.83367556 0.81854839
|
|
0.83739837 0.82281059 0.83844581 0.83435583]
|
|
|
|
mean value: 0.8378033529898218
|
|
|
|
key: test_precision
|
|
value: [0.6969697 0.76923077 0.67647059 0.8 0.70588235 0.72727273
|
|
0.7 0.71875 0.70967742 0.67741935]
|
|
|
|
mean value: 0.7181672908843213
|
|
|
|
key: train_precision
|
|
value: [0.72695035 0.73741007 0.74817518 0.83263598 0.73818182 0.71478873
|
|
0.73835125 0.72661871 0.74275362 0.73913043]
|
|
|
|
mean value: 0.7444996160361183
|
|
|
|
key: test_recall
|
|
value: [0.95833333 0.83333333 0.95833333 1. 1. 1.
|
|
0.91304348 1. 0.95652174 0.91304348]
|
|
|
|
mean value: 0.9532608695652174
|
|
|
|
key: train_recall
|
|
value: [0.96698113 0.96698113 0.96698113 0.93867925 0.95754717 0.95754717
|
|
0.96713615 0.94835681 0.96244131 0.95774648]
|
|
|
|
mean value: 0.9590397732305784
|
|
|
|
key: test_roc_auc
|
|
value: [0.77083333 0.79166667 0.74003623 0.86956522 0.7826087 0.80434783
|
|
0.76902174 0.8125 0.79076087 0.74818841]
|
|
|
|
mean value: 0.7879528985507247
|
|
|
|
key: train_roc_auc
|
|
value: [0.80188679 0.81132075 0.82151874 0.87544291 0.8097595 0.78863274
|
|
0.81139826 0.79493312 0.81376783 0.80906192]
|
|
|
|
mean value: 0.813772256178581
|
|
|
|
key: test_jcc
|
|
value: [0.67647059 0.66666667 0.65714286 0.8 0.70588235 0.72727273
|
|
0.65625 0.71875 0.6875 0.63636364]
|
|
|
|
mean value: 0.6932298828622359
|
|
|
|
key: train_jcc
|
|
value: [0.70934256 0.71929825 0.72953737 0.78968254 0.71478873 0.69283276
|
|
0.72027972 0.69896194 0.72183099 0.71578947]
|
|
|
|
mean value: 0.7212344326893423
|
|
|
|
MCC on Blind test: 0.36
|
|
|
|
Accuracy on Blind test: 0.67
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.00995135 0.00994587 0.00999403 0.01020265 0.01116991 0.01009464
|
|
0.01000333 0.01018357 0.01000619 0.01009297]
|
|
|
|
mean value: 0.010164451599121094
|
|
|
|
key: score_time
|
|
value: [0.00876784 0.00907183 0.00884032 0.00955534 0.00936484 0.00870538
|
|
0.00877094 0.00887036 0.00877738 0.00873828]
|
|
|
|
mean value: 0.00894625186920166
|
|
|
|
key: test_mcc
|
|
value: [0.66666667 0.55381862 0.60807084 0.66121206 0.45948781 0.74682354
|
|
0.7023605 0.61775362 0.62091661 0.57560058]
|
|
|
|
mean value: 0.6212710850613246
|
|
|
|
key: train_mcc
|
|
value: [0.64176651 0.69358916 0.69412025 0.6384571 0.66604642 0.63878972
|
|
0.67062341 0.65285056 0.66194531 0.67568413]
|
|
|
|
mean value: 0.6633872575029867
|
|
|
|
key: test_accuracy
|
|
value: [0.83333333 0.77083333 0.78723404 0.82978723 0.72340426 0.87234043
|
|
0.85106383 0.80851064 0.80851064 0.78723404]
|
|
|
|
mean value: 0.8072251773049646
|
|
|
|
key: train_accuracy
|
|
value: [0.82075472 0.84669811 0.84705882 0.81882353 0.83294118 0.81882353
|
|
0.83529412 0.82588235 0.83058824 0.83764706]
|
|
|
|
mean value: 0.8314511653718091
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 0.74418605 0.82142857 0.84 0.69767442 0.88
|
|
0.84444444 0.80851064 0.79069767 0.77272727]
|
|
|
|
mean value: 0.8033002399766378
|
|
|
|
key: train_fscore
|
|
value: [0.81818182 0.84486874 0.8463357 0.81355932 0.83054893 0.81265207
|
|
0.83490566 0.82125604 0.82692308 0.8353222 ]
|
|
|
|
mean value: 0.8284553538491453
|
|
|
|
key: test_precision
|
|
value: [0.83333333 0.84210526 0.71875 0.80769231 0.78947368 0.84615385
|
|
0.86363636 0.79166667 0.85 0.80952381]
|
|
|
|
mean value: 0.8152335274374748
|
|
|
|
key: train_precision
|
|
value: [0.83009709 0.85507246 0.84834123 0.8358209 0.84057971 0.83919598
|
|
0.83886256 0.84577114 0.84729064 0.84951456]
|
|
|
|
mean value: 0.8430546275962256
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.66666667 0.95833333 0.875 0.625 0.91666667
|
|
0.82608696 0.82608696 0.73913043 0.73913043]
|
|
|
|
mean value: 0.8005434782608696
|
|
|
|
key: train_recall
|
|
value: [0.80660377 0.83490566 0.84433962 0.79245283 0.82075472 0.78773585
|
|
0.83098592 0.79812207 0.80751174 0.82159624]
|
|
|
|
mean value: 0.8145008415271503
|
|
|
|
key: test_roc_auc
|
|
value: [0.83333333 0.77083333 0.78351449 0.82880435 0.72554348 0.87137681
|
|
0.85054348 0.80887681 0.80706522 0.78623188]
|
|
|
|
mean value: 0.8066123188405797
|
|
|
|
key: train_roc_auc
|
|
value: [0.82075472 0.84669811 0.84705244 0.81876163 0.83291257 0.81875055
|
|
0.83530428 0.82594783 0.83064266 0.83768491]
|
|
|
|
mean value: 0.831450969970768
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 0.59259259 0.6969697 0.72413793 0.53571429 0.78571429
|
|
0.73076923 0.67857143 0.65384615 0.62962963]
|
|
|
|
mean value: 0.6742230949127501
|
|
|
|
key: train_jcc
|
|
value: [0.69230769 0.73140496 0.73360656 0.68571429 0.71020408 0.68442623
|
|
0.71659919 0.69672131 0.70491803 0.71721311]
|
|
|
|
mean value: 0.7073115454517357
|
|
|
|
MCC on Blind test: 0.24
|
|
|
|
Accuracy on Blind test: 0.72
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01062346 0.01046181 0.01027966 0.01027012 0.00923038 0.01032376
|
|
0.00914669 0.00929403 0.00919199 0.0092175 ]
|
|
|
|
mean value: 0.00980393886566162
|
|
|
|
key: score_time
|
|
value: [0.01194811 0.0115335 0.01710606 0.01177764 0.01119661 0.01210093
|
|
0.01123142 0.01134849 0.01124072 0.01107049]
|
|
|
|
mean value: 0.012055397033691406
|
|
|
|
key: test_mcc
|
|
value: [0.37796447 0.58536941 0.54211097 0.74682354 0.47117841 0.57560058
|
|
0.5326087 0.27717391 0.59613578 0.62296012]
|
|
|
|
mean value: 0.5327925887131418
|
|
|
|
key: train_mcc
|
|
value: [0.77135191 0.76238897 0.76537738 0.77324744 0.78639656 0.74127961
|
|
0.77751928 0.7674169 0.78085895 0.78611085]
|
|
|
|
mean value: 0.7711947857648866
|
|
|
|
key: test_accuracy
|
|
value: [0.6875 0.79166667 0.76595745 0.87234043 0.72340426 0.78723404
|
|
0.76595745 0.63829787 0.78723404 0.80851064]
|
|
|
|
mean value: 0.7628102836879432
|
|
|
|
key: train_accuracy
|
|
value: [0.88443396 0.87735849 0.88 0.88470588 0.89176471 0.86823529
|
|
0.88705882 0.88235294 0.88705882 0.88941176]
|
|
|
|
mean value: 0.8832380688124306
|
|
|
|
key: test_fscore
|
|
value: [0.70588235 0.7826087 0.79245283 0.88 0.68292683 0.8
|
|
0.76595745 0.63829787 0.80769231 0.81632653]
|
|
|
|
mean value: 0.7672144865503812
|
|
|
|
key: train_fscore
|
|
value: [0.88888889 0.88546256 0.88641425 0.88988764 0.8959276 0.875
|
|
0.89237668 0.88738739 0.89427313 0.8967033 ]
|
|
|
|
mean value: 0.8892321433570249
|
|
|
|
key: test_precision
|
|
value: [0.66666667 0.81818182 0.72413793 0.84615385 0.82352941 0.76923077
|
|
0.75 0.625 0.72413793 0.76923077]
|
|
|
|
mean value: 0.751626914329754
|
|
|
|
key: train_precision
|
|
value: [0.8558952 0.83057851 0.83966245 0.84978541 0.86086957 0.83050847
|
|
0.85407725 0.85281385 0.84232365 0.84297521]
|
|
|
|
mean value: 0.8459489567776202
|
|
|
|
key: test_recall
|
|
value: [0.75 0.75 0.875 0.91666667 0.58333333 0.83333333
|
|
0.7826087 0.65217391 0.91304348 0.86956522]
|
|
|
|
mean value: 0.792572463768116
|
|
|
|
key: train_recall
|
|
value: [0.9245283 0.94811321 0.93867925 0.93396226 0.93396226 0.9245283
|
|
0.9342723 0.92488263 0.95305164 0.95774648]
|
|
|
|
mean value: 0.9373726636548853
|
|
|
|
key: test_roc_auc
|
|
value: [0.6875 0.79166667 0.76358696 0.87137681 0.72644928 0.78623188
|
|
0.76630435 0.63858696 0.78985507 0.80978261]
|
|
|
|
mean value: 0.7631340579710145
|
|
|
|
key: train_roc_auc
|
|
value: [0.88443396 0.87735849 0.88013774 0.88482151 0.89186376 0.86836744
|
|
0.88694747 0.88225264 0.88690318 0.8892506 ]
|
|
|
|
mean value: 0.883233678802374
|
|
|
|
key: test_jcc
|
|
value: [0.54545455 0.64285714 0.65625 0.78571429 0.51851852 0.66666667
|
|
0.62068966 0.46875 0.67741935 0.68965517]
|
|
|
|
mean value: 0.6271975341636076
|
|
|
|
key: train_jcc
|
|
value: [0.8 0.7944664 0.796 0.80161943 0.81147541 0.77777778
|
|
0.80566802 0.79757085 0.80876494 0.812749 ]
|
|
|
|
mean value: 0.8006091834594148
|
|
|
|
MCC on Blind test: 0.23
|
|
|
|
Accuracy on Blind test: 0.71
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01806951 0.01799679 0.01846004 0.01809216 0.01817918 0.02112007
|
|
0.01827812 0.01846528 0.01819468 0.01822948]
|
|
|
|
mean value: 0.018508529663085936
|
|
|
|
key: score_time
|
|
value: [0.01089907 0.01080108 0.0109477 0.01094437 0.01074457 0.01117706
|
|
0.01091409 0.01087308 0.01078081 0.01093388]
|
|
|
|
mean value: 0.010901570320129395
|
|
|
|
key: test_mcc
|
|
value: [0.87576054 0.70894901 0.84147165 0.74456522 0.7085716 0.82971014
|
|
0.82971014 0.87318841 0.70289855 0.66243303]
|
|
|
|
mean value: 0.7777258290636638
|
|
|
|
key: train_mcc
|
|
value: [0.8825567 0.86367849 0.89711505 0.83573407 0.86823456 0.90624936
|
|
0.86429074 0.8929484 0.86883893 0.88802975]
|
|
|
|
mean value: 0.8767676043524585
|
|
|
|
key: test_accuracy
|
|
value: [0.9375 0.85416667 0.91489362 0.87234043 0.85106383 0.91489362
|
|
0.91489362 0.93617021 0.85106383 0.82978723]
|
|
|
|
mean value: 0.887677304964539
|
|
|
|
key: train_accuracy
|
|
value: [0.94103774 0.93160377 0.94823529 0.91764706 0.93411765 0.95294118
|
|
0.93176471 0.94588235 0.93411765 0.94352941]
|
|
|
|
mean value: 0.9380876803551609
|
|
|
|
key: test_fscore
|
|
value: [0.93877551 0.85714286 0.92307692 0.875 0.84444444 0.91666667
|
|
0.91304348 0.93617021 0.85106383 0.83333333]
|
|
|
|
mean value: 0.8888717255682367
|
|
|
|
key: train_fscore
|
|
value: [0.94199536 0.93271462 0.94907407 0.91606715 0.93396226 0.95348837
|
|
0.93333333 0.94736842 0.93548387 0.94495413]
|
|
|
|
mean value: 0.9388441587193233
|
|
|
|
key: test_precision
|
|
value: [0.92 0.84 0.85714286 0.875 0.9047619 0.91666667
|
|
0.91304348 0.91666667 0.83333333 0.8 ]
|
|
|
|
mean value: 0.8776614906832299
|
|
|
|
key: train_precision
|
|
value: [0.92694064 0.91780822 0.93181818 0.93170732 0.93396226 0.94036697
|
|
0.91441441 0.92410714 0.91855204 0.92376682]
|
|
|
|
mean value: 0.9263444003580998
|
|
|
|
key: test_recall
|
|
value: [0.95833333 0.875 1. 0.875 0.79166667 0.91666667
|
|
0.91304348 0.95652174 0.86956522 0.86956522]
|
|
|
|
mean value: 0.902536231884058
|
|
|
|
key: train_recall
|
|
value: [0.95754717 0.94811321 0.96698113 0.9009434 0.93396226 0.96698113
|
|
0.95305164 0.97183099 0.95305164 0.96713615]
|
|
|
|
mean value: 0.9519598724422004
|
|
|
|
key: test_roc_auc
|
|
value: [0.9375 0.85416667 0.91304348 0.87228261 0.85235507 0.91485507
|
|
0.91485507 0.9365942 0.85144928 0.83061594]
|
|
|
|
mean value: 0.8877717391304347
|
|
|
|
key: train_roc_auc
|
|
value: [0.94103774 0.93160377 0.9482793 0.91760785 0.93411728 0.95297413
|
|
0.9317145 0.94582115 0.93407299 0.94347374]
|
|
|
|
mean value: 0.9380702453716007
|
|
|
|
key: test_jcc
|
|
value: [0.88461538 0.75 0.85714286 0.77777778 0.73076923 0.84615385
|
|
0.84 0.88 0.74074074 0.71428571]
|
|
|
|
mean value: 0.8021485551485551
|
|
|
|
key: train_jcc
|
|
value: [0.89035088 0.87391304 0.9030837 0.84513274 0.87610619 0.91111111
|
|
0.875 0.9 0.87878788 0.89565217]
|
|
|
|
mean value: 0.8849137722976903
|
|
|
|
MCC on Blind test: 0.61
|
|
|
|
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(
|
|
/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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.72561026 1.88701367 1.86633086 2.24649811 1.92326665 1.91666341
|
|
2.07458687 2.2624228 1.85074711 1.71887541]
|
|
|
|
mean value: 1.9472015142440795
|
|
|
|
key: score_time
|
|
value: [0.01893616 0.01246476 0.01241136 0.01250052 0.01235723 0.01385999
|
|
0.01298881 0.01465106 0.01807356 0.01239204]
|
|
|
|
mean value: 0.014063549041748048
|
|
|
|
key: test_mcc
|
|
value: [0.91986621 1. 0.87917396 0.91804649 0.91485507 0.91804649
|
|
0.91833182 0.91833182 0.91833182 0.87979456]
|
|
|
|
mean value: 0.9184778254578256
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 1. 0.93617021 0.95744681 0.95744681 0.95744681
|
|
0.95744681 0.95744681 0.95744681 0.93617021]
|
|
|
|
mean value: 0.9575354609929079
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.96 1. 0.94117647 0.96 0.95833333 0.96
|
|
0.95833333 0.95833333 0.95833333 0.93877551]
|
|
|
|
mean value: 0.959328531412565
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.92307692 1. 0.88888889 0.92307692 0.95833333 0.92307692
|
|
0.92 0.92 0.92 0.88461538]
|
|
|
|
mean value: 0.9261068376068377
|
|
|
|
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. 0.95833333 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 1. 0.93478261 0.95652174 0.95742754 0.95652174
|
|
0.95833333 0.95833333 0.95833333 0.9375 ]
|
|
|
|
mean value: 0.9576086956521739
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.92307692 1. 0.88888889 0.92307692 0.92 0.92307692
|
|
0.92 0.92 0.92 0.88461538]
|
|
|
|
mean value: 0.9222735042735043
|
|
|
|
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: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02804613 0.01730657 0.01720572 0.01606226 0.01802039 0.01650405
|
|
0.01708031 0.02256703 0.02096868 0.01860905]
|
|
|
|
mean value: 0.01923701763153076
|
|
|
|
key: score_time
|
|
value: [0.01204467 0.00912833 0.00858259 0.00851583 0.00865173 0.00868559
|
|
0.00865889 0.01151872 0.00977397 0.00944185]
|
|
|
|
mean value: 0.009500217437744141
|
|
|
|
key: test_mcc
|
|
value: [1. 0.9591663 0.95825929 0.87318841 0.95833333 0.91804649
|
|
1. 1. 0.87318841 1. ]
|
|
|
|
mean value: 0.9540182234670455
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.97916667 0.9787234 0.93617021 0.9787234 0.95744681
|
|
1. 1. 0.93617021 1. ]
|
|
|
|
mean value: 0.9766400709219858
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 0.97959184 0.97959184 0.93617021 0.9787234 0.96
|
|
1. 1. 0.93617021 1. ]
|
|
|
|
mean value: 0.9770247503256622
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 0.96 0.96 0.95652174 1. 0.92307692
|
|
1. 1. 0.91666667 1. ]
|
|
|
|
mean value: 0.9716265328874024
|
|
|
|
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. 0.91666667 0.95833333 1.
|
|
1. 1. 0.95652174 1. ]
|
|
|
|
mean value: 0.9831521739130434
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.97916667 0.97826087 0.9365942 0.97916667 0.95652174
|
|
1. 1. 0.9365942 1. ]
|
|
|
|
mean value: 0.9766304347826087
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 0.96 0.96 0.88 0.95833333 0.92307692
|
|
1. 1. 0.88 1. ]
|
|
|
|
mean value: 0.9561410256410257
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.76
|
|
|
|
Accuracy on Blind test: 0.92
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.11010218 0.12877584 0.12205791 0.12047315 0.11927867 0.12103677
|
|
0.11555839 0.11260557 0.11527324 0.11709452]
|
|
|
|
mean value: 0.11822562217712403
|
|
|
|
key: score_time
|
|
value: [0.01767063 0.01941776 0.01895857 0.01897836 0.01894307 0.01897812
|
|
0.01759982 0.01753116 0.01889586 0.01917958]
|
|
|
|
mean value: 0.018615293502807616
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 1. 1. 0.91833182 0.95825929
|
|
0.91833182 0.95833333 0.87318841 0.95833333]
|
|
|
|
mean value: 0.9543944310392729
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 1. 1. 0.95744681 0.9787234
|
|
0.95744681 0.9787234 0.93617021 0.9787234 ]
|
|
|
|
mean value: 0.9766400709219858
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 1. 1. 0.95652174 0.97959184
|
|
0.95833333 0.9787234 0.93617021 0.9787234 ]
|
|
|
|
mean value: 0.9767655767209752
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 1. 1. 1. 0.96
|
|
0.92 0.95833333 0.91666667 0.95833333]
|
|
|
|
mean value: 0.9673333333333334
|
|
|
|
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. 0.91666667 1.
|
|
1. 1. 0.95652174 1. ]
|
|
|
|
mean value: 0.9873188405797102
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 1. 1. 0.95833333 0.97826087
|
|
0.95833333 0.97916667 0.9365942 0.97916667]
|
|
|
|
mean value: 0.9769021739130435
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 1. 1. 0.91666667 0.96
|
|
0.92 0.95833333 0.88 0.95833333]
|
|
|
|
mean value: 0.9553333333333334
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.65
|
|
|
|
Accuracy on Blind test: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01130509 0.01110768 0.01131582 0.01148224 0.01140404 0.01134396
|
|
0.01064348 0.01050138 0.01147485 0.01104021]
|
|
|
|
mean value: 0.011161875724792481
|
|
|
|
key: score_time
|
|
value: [0.0096271 0.00953174 0.00901699 0.00921893 0.00950503 0.00938177
|
|
0.00951791 0.00918484 0.00888681 0.00962782]
|
|
|
|
mean value: 0.009349894523620606
|
|
|
|
key: test_mcc
|
|
value: [0.80942721 0.8819171 0.87917396 0.87917396 0.95833333 0.87917396
|
|
0.87979456 0.95833333 0.84254172 0.84254172]
|
|
|
|
mean value: 0.8810410865788145
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.89583333 0.9375 0.93617021 0.93617021 0.9787234 0.93617021
|
|
0.93617021 0.9787234 0.91489362 0.91489362]
|
|
|
|
mean value: 0.9365248226950355
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.90566038 0.94117647 0.94117647 0.94117647 0.9787234 0.94117647
|
|
0.93877551 0.9787234 0.92 0.92 ]
|
|
|
|
mean value: 0.9406588578426152
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.82758621 0.88888889 0.88888889 0.88888889 1. 0.88888889
|
|
0.88461538 0.95833333 0.85185185 0.85185185]
|
|
|
|
mean value: 0.8929794184104529
|
|
|
|
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. 0.95833333 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.89583333 0.9375 0.93478261 0.93478261 0.97916667 0.93478261
|
|
0.9375 0.97916667 0.91666667 0.91666667]
|
|
|
|
mean value: 0.9366847826086957
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.82758621 0.88888889 0.88888889 0.88888889 0.95833333 0.88888889
|
|
0.88461538 0.95833333 0.85185185 0.85185185]
|
|
|
|
mean value: 0.8888127517437863
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.19
|
|
|
|
Accuracy on Blind test: 0.72
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.60023022 1.59667087 1.52723384 1.55534792 1.51916361 1.52378392
|
|
1.5456574 1.5113728 1.5141468 1.51703024]
|
|
|
|
mean value: 1.5410637617111207
|
|
|
|
key: score_time
|
|
value: [0.09908462 0.09626317 0.09038067 0.09022117 0.08990765 0.09193945
|
|
0.0896976 0.08957601 0.08992004 0.08951664]
|
|
|
|
mean value: 0.09165070056915284
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 0.95825929 0.95833333 0.95825929
|
|
0.95833333 1. 0.91833182 1. ]
|
|
|
|
mean value: 0.9751517070408319
|
|
|
|
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. 0.9787234 0.9787234 0.9787234
|
|
0.9787234 1. 0.95744681 1. ]
|
|
|
|
mean value: 0.9872340425531915
|
|
|
|
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. 0.97959184 0.9787234 0.97959184
|
|
0.9787234 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.9874963815313359
|
|
|
|
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. 0.96 1. 0.96
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.9798333333333333
|
|
|
|
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. 0.95833333 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
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. 0.97826087 0.97916667 0.97826087
|
|
0.97916667 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.9873188405797102
|
|
|
|
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. 0.96 0.95833333 0.96
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.9756666666666667
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.77
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000...05', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.00179815 0.9441576 0.96113086 0.97564363 0.93518424 0.95993948
|
|
0.93158221 0.94652319 1.05990982 0.92956758]
|
|
|
|
mean value: 0.9645436763763428
|
|
|
|
key: score_time
|
|
value: [0.25799084 0.25076985 0.19741035 0.21032572 0.25018573 0.18364358
|
|
0.25544143 0.23659778 0.24778247 0.24875593]
|
|
|
|
mean value: 0.23389036655426027
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 1. 0.95825929 1. 0.95825929
|
|
0.95833333 1. 0.91833182 0.8729597 ]
|
|
|
|
mean value: 0.9625309737127884
|
|
|
|
key: train_mcc
|
|
value: [0.98594778 0.98594778 0.985981 0.99063227 0.98135106 0.99063227
|
|
0.98598008 0.98598008 0.98598008 0.97656701]
|
|
|
|
mean value: 0.9854999385905859
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 1. 0.9787234 1. 0.9787234
|
|
0.9787234 1. 0.95744681 0.93617021]
|
|
|
|
mean value: 0.980895390070922
|
|
|
|
key: train_accuracy
|
|
value: [0.99292453 0.99292453 0.99294118 0.99529412 0.99058824 0.99529412
|
|
0.99294118 0.99294118 0.99294118 0.98823529]
|
|
|
|
mean value: 0.9927025527192008
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 1. 0.97959184 1. 0.97959184
|
|
0.9787234 1. 0.95833333 0.93333333]
|
|
|
|
mean value: 0.9809165581126067
|
|
|
|
key: train_fscore
|
|
value: [0.99297424 0.99297424 0.99297424 0.99530516 0.99065421 0.99530516
|
|
0.99300699 0.99300699 0.99300699 0.98834499]
|
|
|
|
mean value: 0.9927553218239576
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 1. 0.96 1. 0.96
|
|
0.95833333 1. 0.92 0.95454545]
|
|
|
|
mean value: 0.9712878787878788
|
|
|
|
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: [0.98604651 0.98604651 0.98604651 0.99065421 0.98148148 0.99065421
|
|
0.98611111 0.98611111 0.98611111 0.98148148]
|
|
|
|
mean value: 0.9860744242394971
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.91304348]
|
|
|
|
mean value: 0.991304347826087
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.99530516]
|
|
|
|
mean value: 0.9995305164319249
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 1. 0.97826087 1. 0.97826087
|
|
0.97916667 1. 0.95833333 0.93568841]
|
|
|
|
mean value: 0.9808876811594203
|
|
|
|
key: train_roc_auc
|
|
value: [0.99292453 0.99292453 0.99295775 0.99530516 0.99061033 0.99530516
|
|
0.99292453 0.99292453 0.99292453 0.98821862]
|
|
|
|
mean value: 0.9927019665160776
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 1. 0.96 1. 0.96
|
|
0.95833333 1. 0.92 0.875 ]
|
|
|
|
mean value: 0.9633333333333334
|
|
|
|
key: train_jcc
|
|
value: [0.98604651 0.98604651 0.98604651 0.99065421 0.98148148 0.99065421
|
|
0.98611111 0.98611111 0.98611111 0.97695853]
|
|
|
|
mean value: 0.9856221286259111
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01124263 0.01145625 0.01059389 0.01023984 0.01007009 0.01031852
|
|
0.01000977 0.01002431 0.01013947 0.01004243]
|
|
|
|
mean value: 0.010413718223571778
|
|
|
|
key: score_time
|
|
value: [0.00964642 0.0091002 0.00911355 0.00865507 0.00888038 0.00887156
|
|
0.00882554 0.00868821 0.0087142 0.0088203 ]
|
|
|
|
mean value: 0.008931541442871093
|
|
|
|
key: test_mcc
|
|
value: [0.66666667 0.55381862 0.60807084 0.66121206 0.45948781 0.74682354
|
|
0.7023605 0.61775362 0.62091661 0.57560058]
|
|
|
|
mean value: 0.6212710850613246
|
|
|
|
key: train_mcc
|
|
value: [0.64176651 0.69358916 0.69412025 0.6384571 0.66604642 0.63878972
|
|
0.67062341 0.65285056 0.66194531 0.67568413]
|
|
|
|
mean value: 0.6633872575029867
|
|
|
|
key: test_accuracy
|
|
value: [0.83333333 0.77083333 0.78723404 0.82978723 0.72340426 0.87234043
|
|
0.85106383 0.80851064 0.80851064 0.78723404]
|
|
|
|
mean value: 0.8072251773049646
|
|
|
|
key: train_accuracy
|
|
value: [0.82075472 0.84669811 0.84705882 0.81882353 0.83294118 0.81882353
|
|
0.83529412 0.82588235 0.83058824 0.83764706]
|
|
|
|
mean value: 0.8314511653718091
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 0.74418605 0.82142857 0.84 0.69767442 0.88
|
|
0.84444444 0.80851064 0.79069767 0.77272727]
|
|
|
|
mean value: 0.8033002399766378
|
|
|
|
key: train_fscore
|
|
value: [0.81818182 0.84486874 0.8463357 0.81355932 0.83054893 0.81265207
|
|
0.83490566 0.82125604 0.82692308 0.8353222 ]
|
|
|
|
mean value: 0.8284553538491453
|
|
|
|
key: test_precision
|
|
value: [0.83333333 0.84210526 0.71875 0.80769231 0.78947368 0.84615385
|
|
0.86363636 0.79166667 0.85 0.80952381]
|
|
|
|
mean value: 0.8152335274374748
|
|
|
|
key: train_precision
|
|
value: [0.83009709 0.85507246 0.84834123 0.8358209 0.84057971 0.83919598
|
|
0.83886256 0.84577114 0.84729064 0.84951456]
|
|
|
|
mean value: 0.8430546275962256
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.66666667 0.95833333 0.875 0.625 0.91666667
|
|
0.82608696 0.82608696 0.73913043 0.73913043]
|
|
|
|
mean value: 0.8005434782608696
|
|
|
|
key: train_recall
|
|
value: [0.80660377 0.83490566 0.84433962 0.79245283 0.82075472 0.78773585
|
|
0.83098592 0.79812207 0.80751174 0.82159624]
|
|
|
|
mean value: 0.8145008415271503
|
|
|
|
key: test_roc_auc
|
|
value: [0.83333333 0.77083333 0.78351449 0.82880435 0.72554348 0.87137681
|
|
0.85054348 0.80887681 0.80706522 0.78623188]
|
|
|
|
mean value: 0.8066123188405797
|
|
|
|
key: train_roc_auc
|
|
value: [0.82075472 0.84669811 0.84705244 0.81876163 0.83291257 0.81875055
|
|
0.83530428 0.82594783 0.83064266 0.83768491]
|
|
|
|
mean value: 0.831450969970768
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 0.59259259 0.6969697 0.72413793 0.53571429 0.78571429
|
|
0.73076923 0.67857143 0.65384615 0.62962963]
|
|
|
|
mean value: 0.6742230949127501
|
|
|
|
key: train_jcc
|
|
value: [0.69230769 0.73140496 0.73360656 0.68571429 0.71020408 0.68442623
|
|
0.71659919 0.69672131 0.70491803 0.71721311]
|
|
|
|
mean value: 0.7073115454517357
|
|
|
|
MCC on Blind test: 0.24
|
|
|
|
Accuracy on Blind test: 0.72
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'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: [0.37783813 0.05852675 0.05905557 0.06046104 0.09306598 0.07523513
|
|
0.06004477 0.10583544 0.05751801 0.06485915]
|
|
|
|
mean value: 0.10124399662017822
|
|
|
|
key: score_time
|
|
value: [0.011482 0.01243949 0.0107584 0.01045561 0.01188087 0.01066089
|
|
0.01125288 0.01084256 0.01075172 0.01038194]
|
|
|
|
mean value: 0.011090636253356934
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 1. 0.95825929 1. 0.91804649
|
|
1. 1. 0.91833182 1. ]
|
|
|
|
mean value: 0.9753803910673312
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 1. 0.9787234 1. 0.95744681
|
|
1. 1. 0.95744681 1. ]
|
|
|
|
mean value: 0.9872783687943263
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 1. 0.97959184 1. 0.96
|
|
1. 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.9877517006802721
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 1. 0.96 1. 0.92307692
|
|
1. 1. 0.92 1. ]
|
|
|
|
mean value: 0.9763076923076923
|
|
|
|
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: [0.97916667 1. 1. 0.97826087 1. 0.95652174
|
|
1. 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.9872282608695653
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 1. 0.96 1. 0.92307692
|
|
1. 1. 0.92 1. ]
|
|
|
|
mean value: 0.9763076923076923
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.84
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.05164719 0.07034683 0.05269408 0.06650853 0.04133916 0.08873439
|
|
0.04844427 0.06881714 0.09706879 0.06255484]
|
|
|
|
mean value: 0.06481552124023438
|
|
|
|
key: score_time
|
|
value: [0.02070856 0.01259923 0.02254486 0.01224828 0.01215291 0.02161407
|
|
0.01211524 0.0236063 0.03557587 0.02322817]
|
|
|
|
mean value: 0.019639348983764647
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.91986621 0.95825929 0.7876601 0.95825929 0.91804649
|
|
0.95833333 0.91833182 0.87979456 0.74773263]
|
|
|
|
mean value: 0.9005450031133301
|
|
|
|
key: train_mcc
|
|
value: [0.98130676 0.98130676 0.98135106 0.985981 0.97674215 0.985981
|
|
0.98134942 0.9767396 0.99063185 0.97656701]
|
|
|
|
mean value: 0.9817956624850078
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.95833333 0.9787234 0.89361702 0.9787234 0.95744681
|
|
0.9787234 0.95744681 0.93617021 0.87234043]
|
|
|
|
mean value: 0.9490691489361702
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.99056604 0.99058824 0.99294118 0.98823529 0.99294118
|
|
0.99058824 0.98823529 0.99529412 0.98823529]
|
|
|
|
mean value: 0.990819089900111
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.96 0.97959184 0.89795918 0.97959184 0.96
|
|
0.9787234 0.95833333 0.93877551 0.875 ]
|
|
|
|
mean value: 0.9507566941670285
|
|
|
|
key: train_fscore
|
|
value: [0.99065421 0.99065421 0.99065421 0.99297424 0.98834499 0.99297424
|
|
0.99069767 0.98839907 0.9953271 0.98834499]
|
|
|
|
mean value: 0.990902492041226
|
|
|
|
key: test_precision
|
|
value: [0.96 0.92307692 0.96 0.88 0.96 0.92307692
|
|
0.95833333 0.92 0.88461538 0.84 ]
|
|
|
|
mean value: 0.9209102564102564
|
|
|
|
key: train_precision
|
|
value: [0.98148148 0.98148148 0.98148148 0.98604651 0.97695853 0.98604651
|
|
0.98156682 0.97706422 0.99069767 0.98148148]
|
|
|
|
mean value: 0.9824306189405951
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 0.91666667 1. 1.
|
|
1. 1. 1. 0.91304348]
|
|
|
|
mean value: 0.9829710144927536
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.99530516]
|
|
|
|
mean value: 0.9995305164319249
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.95833333 0.97826087 0.89311594 0.97826087 0.95652174
|
|
0.97916667 0.95833333 0.9375 0.87318841]
|
|
|
|
mean value: 0.9491847826086957
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.99056604 0.99061033 0.99295775 0.98826291 0.99295775
|
|
0.99056604 0.98820755 0.99528302 0.98821862]
|
|
|
|
mean value: 0.9908196031535123
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.92307692 0.96 0.81481481 0.96 0.92307692
|
|
0.95833333 0.92 0.88461538 0.77777778]
|
|
|
|
mean value: 0.9081695156695156
|
|
|
|
key: train_jcc
|
|
value: [0.98148148 0.98148148 0.98148148 0.98604651 0.97695853 0.98604651
|
|
0.98156682 0.97706422 0.99069767 0.97695853]
|
|
|
|
mean value: 0.9819783233270092
|
|
|
|
MCC on Blind test: 0.65
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02485466 0.01053357 0.01036429 0.01023698 0.00984693 0.00982547
|
|
0.01032138 0.00967765 0.00987291 0.00981092]
|
|
|
|
mean value: 0.011534476280212402
|
|
|
|
key: score_time
|
|
value: [0.0122416 0.0091176 0.00868559 0.00866842 0.00861287 0.00868249
|
|
0.00895524 0.00866818 0.00882983 0.00874233]
|
|
|
|
mean value: 0.009120416641235352
|
|
|
|
key: test_mcc
|
|
value: [0.79235477 0.58333333 0.68038162 0.57713344 0.44874504 0.66801039
|
|
0.74456522 0.74773263 0.44746377 0.58428436]
|
|
|
|
mean value: 0.627400457665346
|
|
|
|
key: train_mcc
|
|
value: [0.63436617 0.70064323 0.64424245 0.60057643 0.68446036 0.62946543
|
|
0.6123175 0.60680665 0.58648411 0.67794049]
|
|
|
|
mean value: 0.6377302820559942
|
|
|
|
key: test_accuracy
|
|
value: [0.89583333 0.79166667 0.82978723 0.78723404 0.72340426 0.82978723
|
|
0.87234043 0.87234043 0.72340426 0.78723404]
|
|
|
|
mean value: 0.8113031914893617
|
|
|
|
key: train_accuracy
|
|
value: [0.81603774 0.8490566 0.82117647 0.8 0.84 0.81411765
|
|
0.80470588 0.80235294 0.79294118 0.83764706]
|
|
|
|
mean value: 0.8178035516093229
|
|
|
|
key: test_fscore
|
|
value: [0.89795918 0.79166667 0.85185185 0.7826087 0.74509804 0.84615385
|
|
0.86956522 0.875 0.72340426 0.8 ]
|
|
|
|
mean value: 0.8183307755924147
|
|
|
|
key: train_fscore
|
|
value: [0.82352941 0.85520362 0.82727273 0.80369515 0.84821429 0.81922197
|
|
0.81431767 0.81081081 0.79816514 0.84494382]
|
|
|
|
mean value: 0.8245374604768366
|
|
|
|
key: test_precision
|
|
value: [0.88 0.79166667 0.76666667 0.81818182 0.7037037 0.78571429
|
|
0.86956522 0.84 0.70833333 0.74074074]
|
|
|
|
mean value: 0.7904572432398519
|
|
|
|
key: train_precision
|
|
value: [0.79130435 0.82173913 0.79824561 0.78733032 0.80508475 0.79555556
|
|
0.77777778 0.77922078 0.78026906 0.81034483]
|
|
|
|
mean value: 0.7946872153237035
|
|
|
|
key: test_recall
|
|
value: [0.91666667 0.79166667 0.95833333 0.75 0.79166667 0.91666667
|
|
0.86956522 0.91304348 0.73913043 0.86956522]
|
|
|
|
mean value: 0.8516304347826087
|
|
|
|
key: train_recall
|
|
value: [0.85849057 0.89150943 0.85849057 0.82075472 0.89622642 0.84433962
|
|
0.85446009 0.84507042 0.81690141 0.88262911]
|
|
|
|
mean value: 0.8568872353618566
|
|
|
|
key: test_roc_auc
|
|
value: [0.89583333 0.79166667 0.82699275 0.78804348 0.72192029 0.82789855
|
|
0.87228261 0.87318841 0.72373188 0.78894928]
|
|
|
|
mean value: 0.8110507246376811
|
|
|
|
key: train_roc_auc
|
|
value: [0.81603774 0.8490566 0.82126406 0.80004872 0.84013199 0.81418859
|
|
0.80458854 0.80225219 0.79288467 0.83754097]
|
|
|
|
mean value: 0.8177994065019045
|
|
|
|
key: test_jcc
|
|
value: [0.81481481 0.65517241 0.74193548 0.64285714 0.59375 0.73333333
|
|
0.76923077 0.77777778 0.56666667 0.66666667]
|
|
|
|
mean value: 0.6962205069011242
|
|
|
|
key: train_jcc
|
|
value: [0.7 0.74703557 0.70542636 0.67181467 0.73643411 0.69379845
|
|
0.68679245 0.68181818 0.66412214 0.73151751]
|
|
|
|
mean value: 0.701875944144646
|
|
|
|
MCC on Blind test: 0.57
|
|
|
|
Accuracy on Blind test: 0.82
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.0187788 0.02403235 0.02057099 0.02665544 0.0274291 0.02563572
|
|
0.02585411 0.02280402 0.02943254 0.02313924]
|
|
|
|
mean value: 0.024433231353759764
|
|
|
|
key: score_time
|
|
value: [0.00922704 0.011024 0.01134968 0.0116055 0.01221514 0.01204228
|
|
0.01203728 0.01174498 0.01166892 0.01158929]
|
|
|
|
mean value: 0.011450409889221191
|
|
|
|
key: test_mcc
|
|
value: [0.91666667 1. 0.95825929 0.91804649 0.95833333 0.91804649
|
|
0.91833182 0.87318841 0.91833182 0.73387289]
|
|
|
|
mean value: 0.911307722069712
|
|
|
|
key: train_mcc
|
|
value: [0.98117574 0.99056604 0.98589335 1. 1. 0.99530516
|
|
0.99063185 0.98589304 0.99063185 0.90133634]
|
|
|
|
mean value: 0.9821433376250255
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 1. 0.9787234 0.95744681 0.9787234 0.95744681
|
|
0.95744681 0.93617021 0.95744681 0.85106383]
|
|
|
|
mean value: 0.9532801418439717
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.99528302 0.99294118 1. 1. 0.99764706
|
|
0.99529412 0.99294118 0.99529412 0.94823529]
|
|
|
|
mean value: 0.9908201997780244
|
|
|
|
key: test_fscore
|
|
value: [0.95833333 1. 0.97959184 0.96 0.9787234 0.96
|
|
0.95833333 0.93617021 0.95833333 0.82051282]
|
|
|
|
mean value: 0.9509998274268792
|
|
|
|
key: train_fscore
|
|
value: [0.99052133 0.99528302 0.99294118 1. 1. 0.99764706
|
|
0.9953271 0.99297424 0.9953271 0.94554455]
|
|
|
|
mean value: 0.990556558011506
|
|
|
|
key: test_precision
|
|
value: [0.95833333 1. 0.96 0.92307692 1. 0.92307692
|
|
0.92 0.91666667 0.92 1. ]
|
|
|
|
mean value: 0.9521153846153846
|
|
|
|
key: train_precision
|
|
value: [0.9952381 0.99528302 0.99061033 1. 1. 0.99530516
|
|
0.99069767 0.99065421 0.99069767 1. ]
|
|
|
|
mean value: 0.9948486161508452
|
|
|
|
key: test_recall
|
|
value: [0.95833333 1. 1. 1. 0.95833333 1.
|
|
1. 0.95652174 1. 0.69565217]
|
|
|
|
mean value: 0.9568840579710145
|
|
|
|
key: train_recall
|
|
value: [0.98584906 0.99528302 0.99528302 1. 1. 1.
|
|
1. 0.99530516 1. 0.89671362]
|
|
|
|
mean value: 0.9868433873682345
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 1. 0.97826087 0.95652174 0.97916667 0.95652174
|
|
0.95833333 0.9365942 0.95833333 0.84782609]
|
|
|
|
mean value: 0.9529891304347826
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.99528302 0.99294667 1. 1. 0.99765258
|
|
0.99528302 0.9929356 0.99528302 0.94835681]
|
|
|
|
mean value: 0.9908306758791744
|
|
|
|
key: test_jcc
|
|
value: [0.92 1. 0.96 0.92307692 0.95833333 0.92307692
|
|
0.92 0.88 0.92 0.69565217]
|
|
|
|
mean value: 0.9100139353400223
|
|
|
|
key: train_jcc
|
|
value: [0.98122066 0.99061033 0.98598131 1. 1. 0.99530516
|
|
0.99069767 0.98604651 0.99069767 0.89671362]
|
|
|
|
mean value: 0.9817272934134548
|
|
|
|
MCC on Blind test: 0.74
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01827669 0.01878524 0.01713681 0.01825714 0.01762176 0.01692224
|
|
0.01713347 0.03406692 0.03884649 0.02093482]
|
|
|
|
mean value: 0.021798157691955568
|
|
|
|
key: score_time
|
|
value: [0.01160049 0.01146793 0.0116024 0.01156139 0.01157475 0.01155829
|
|
0.01159716 0.01203728 0.01981354 0.01466298]
|
|
|
|
mean value: 0.012747621536254883
|
|
|
|
key: test_mcc
|
|
value: [0.91986621 0.84515425 0.73387289 0.91804649 0.95833333 0.8729597
|
|
0.82971014 0.83303222 0.87979456 0.66534784]
|
|
|
|
mean value: 0.8456117647830276
|
|
|
|
key: train_mcc
|
|
value: [0.97651287 0.95389198 0.90562996 0.99530516 0.99530516 0.98589304
|
|
0.91729911 0.98598008 0.9767396 0.66227566]
|
|
|
|
mean value: 0.9354832629135601
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 0.91666667 0.85106383 0.95744681 0.9787234 0.93617021
|
|
0.91489362 0.91489362 0.93617021 0.80851064]
|
|
|
|
mean value: 0.9172872340425532
|
|
|
|
key: train_accuracy
|
|
value: [0.98820755 0.97641509 0.95058824 0.99764706 0.99764706 0.99294118
|
|
0.95764706 0.99294118 0.98823529 0.80470588]
|
|
|
|
mean value: 0.9646975582685905
|
|
|
|
key: test_fscore
|
|
value: [0.96 0.90909091 0.87272727 0.96 0.9787234 0.93877551
|
|
0.91304348 0.91666667 0.93877551 0.75675676]
|
|
|
|
mean value: 0.9144559508165957
|
|
|
|
key: train_fscore
|
|
value: [0.9882904 0.97584541 0.95280899 0.99764706 0.99764706 0.9929078
|
|
0.95631068 0.99300699 0.98839907 0.75801749]
|
|
|
|
mean value: 0.9600880953839794
|
|
|
|
key: test_precision
|
|
value: [0.92307692 1. 0.77419355 0.92307692 1. 0.92
|
|
0.91304348 0.88 0.88461538 1. ]
|
|
|
|
mean value: 0.9218006257417197
|
|
|
|
key: train_precision
|
|
value: [0.98139535 1. 0.90987124 0.99530516 0.99530516 0.99526066
|
|
0.98994975 0.98611111 0.97706422 1. ]
|
|
|
|
mean value: 0.9830262665656325
|
|
|
|
key: test_recall
|
|
value: [1. 0.83333333 1. 1. 0.95833333 0.95833333
|
|
0.91304348 0.95652174 1. 0.60869565]
|
|
|
|
mean value: 0.9228260869565218
|
|
|
|
key: train_recall
|
|
value: [0.99528302 0.95283019 1. 1. 1. 0.99056604
|
|
0.92488263 1. 1. 0.61032864]
|
|
|
|
mean value: 0.9473890512888653
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 0.91666667 0.84782609 0.95652174 0.97916667 0.93568841
|
|
0.91485507 0.91576087 0.9375 0.80434783]
|
|
|
|
mean value: 0.9166666666666667
|
|
|
|
key: train_roc_auc
|
|
value: [0.98820755 0.97641509 0.95070423 0.99765258 0.99765258 0.9929356
|
|
0.95772433 0.99292453 0.98820755 0.80516432]
|
|
|
|
mean value: 0.9647588360350784
|
|
|
|
key: test_jcc
|
|
value: [0.92307692 0.83333333 0.77419355 0.92307692 0.95833333 0.88461538
|
|
0.84 0.84615385 0.88461538 0.60869565]
|
|
|
|
mean value: 0.8476094328766138
|
|
|
|
key: train_jcc
|
|
value: [0.97685185 0.95283019 0.90987124 0.99530516 0.99530516 0.98591549
|
|
0.91627907 0.98611111 0.97706422 0.61032864]
|
|
|
|
mean value: 0.9305862146322227
|
|
|
|
MCC on Blind test: 0.66
|
|
|
|
Accuracy on Blind test: 0.86
|
|
|
|
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))]
|
|
/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]
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.18860149 0.15423441 0.15698409 0.15563679 0.1604104 0.15294838
|
|
0.15343952 0.15225554 0.15263629 0.15226817]
|
|
|
|
mean value: 0.15794150829315184
|
|
|
|
key: score_time
|
|
value: [0.01522923 0.01599598 0.01546097 0.01514339 0.01510668 0.01532531
|
|
0.01511621 0.01518488 0.01510167 0.01504898]
|
|
|
|
mean value: 0.015271329879760742
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 1. 0.87318841 1. 0.91804649
|
|
0.95833333 1. 0.91833182 1. ]
|
|
|
|
mean value: 0.9627066358398119
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 1. 0.93617021 1. 0.95744681
|
|
0.9787234 1. 0.95744681 1. ]
|
|
|
|
mean value: 0.980895390070922
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 1. 0.93617021 1. 0.96
|
|
0.9787234 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.9812818787089304
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 1. 0.95652174 1. 0.92307692
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.9717931995540692
|
|
|
|
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. 0.91666667 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9916666666666667
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 1. 0.9365942 1. 0.95652174
|
|
0.97916667 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.9809782608695652
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 1. 0.88 1. 0.92307692
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.9641410256410257
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.87
|
|
|
|
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: 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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.05438924 0.04935265 0.07661438 0.05114532 0.06886196 0.05817604
|
|
0.05181217 0.04145455 0.0442059 0.07277322]
|
|
|
|
mean value: 0.05687854290008545
|
|
|
|
key: score_time
|
|
value: [0.02017879 0.02160907 0.03887582 0.02092552 0.02372575 0.01804256
|
|
0.02759147 0.02330613 0.02905583 0.02864385]
|
|
|
|
mean value: 0.02519547939300537
|
|
|
|
key: test_mcc
|
|
value: [1. 0.9591663 0.95825929 0.91804649 0.95833333 0.91804649
|
|
0.95833333 1. 0.91833182 1. ]
|
|
|
|
mean value: 0.9588517071014725
|
|
|
|
key: train_mcc
|
|
value: [0.98594778 0.99061012 1. 1. 1. 1.
|
|
0.99530506 1. 0.99530506 0.99530506]
|
|
|
|
mean value: 0.9962473081638858
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.97916667 0.9787234 0.95744681 0.9787234 0.95744681
|
|
0.9787234 1. 0.95744681 1. ]
|
|
|
|
mean value: 0.9787677304964539
|
|
|
|
key: train_accuracy
|
|
value: [0.99292453 0.99528302 1. 1. 1. 1.
|
|
0.99764706 1. 0.99764706 0.99764706]
|
|
|
|
mean value: 0.99811487236404
|
|
|
|
key: test_fscore
|
|
value: [1. 0.97959184 0.97959184 0.96 0.9787234 0.96
|
|
0.9787234 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.979496381531336
|
|
|
|
key: train_fscore
|
|
value: [0.99297424 0.99530516 1. 1. 1. 1.
|
|
0.99765808 1. 0.99765808 0.99765808]
|
|
|
|
mean value: 0.9981253642071005
|
|
|
|
key: test_precision
|
|
value: [1. 0.96 0.96 0.92307692 1. 0.92307692
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.964448717948718
|
|
|
|
key: train_precision
|
|
value: [0.98604651 0.99065421 1. 1. 1. 1.
|
|
0.9953271 1. 0.9953271 0.9953271 ]
|
|
|
|
mean value: 0.9962682025646599
|
|
|
|
key: test_recall
|
|
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]
|
|
[1. 1. 1. 1. 0.95833333 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.97916667 0.97826087 0.95652174 0.97916667 0.95652174
|
|
0.97916667 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.978713768115942
|
|
|
|
key: train_roc_auc
|
|
value: [0.99292453 0.99528302 1. 1. 1. 1.
|
|
0.99764151 1. 0.99764151 0.99764151]
|
|
|
|
mean value: 0.9981132075471698
|
|
|
|
key: test_jcc
|
|
value: [1. 0.96 0.96 0.92307692 0.95833333 0.92307692
|
|
0.95833333 1. 0.92 1. ]
|
|
|
|
mean value: 0.9602820512820514
|
|
|
|
key: train_jcc
|
|
value: [0.98604651 0.99065421 1. 1. 1. 1.
|
|
0.9953271 1. 0.9953271 0.9953271 ]
|
|
|
|
mean value: 0.9962682025646599
|
|
|
|
MCC on Blind test: 0.83
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.12563443 0.16855145 0.15119171 0.20417213 0.1421361 0.15556145
|
|
0.16540718 0.16756272 0.161484 0.16609502]
|
|
|
|
mean value: 0.16077961921691894
|
|
|
|
key: score_time
|
|
value: [0.02336335 0.02358079 0.02387118 0.03854656 0.0183835 0.02387309
|
|
0.02388835 0.02370787 0.02346325 0.02983546]
|
|
|
|
mean value: 0.025251340866088868
|
|
|
|
key: test_mcc
|
|
value: [0.8819171 0.91986621 0.84147165 0.87917396 0.79418308 0.87917396
|
|
0.84254172 0.75645593 0.84254172 0.78804348]
|
|
|
|
mean value: 0.8425368811729802
|
|
|
|
key: train_mcc
|
|
value: [0.99529409 0.99529409 0.99530516 0.99530516 0.98589304 1.
|
|
1. 1. 0.99530506 0.99530516]
|
|
|
|
mean value: 0.9957701771956576
|
|
|
|
key: test_accuracy
|
|
value: [0.9375 0.95833333 0.91489362 0.93617021 0.89361702 0.93617021
|
|
0.91489362 0.87234043 0.91489362 0.89361702]
|
|
|
|
mean value: 0.9172429078014185
|
|
|
|
key: train_accuracy
|
|
value: [0.99764151 0.99764151 0.99764706 0.99764706 0.99294118 1.
|
|
1. 1. 0.99764706 0.99764706]
|
|
|
|
mean value: 0.9978812430632631
|
|
|
|
key: test_fscore
|
|
value: [0.94117647 0.96 0.92307692 0.94117647 0.88888889 0.94117647
|
|
0.92 0.88 0.92 0.89361702]
|
|
|
|
mean value: 0.9209112245007114
|
|
|
|
key: train_fscore
|
|
value: [0.99764706 0.99764706 0.99764706 0.99764706 0.9929078 1.
|
|
1. 1. 0.99765808 0.99764706]
|
|
|
|
mean value: 0.9978801175161379
|
|
|
|
key: test_precision
|
|
value: [0.88888889 0.92307692 0.85714286 0.88888889 0.95238095 0.88888889
|
|
0.85185185 0.81481481 0.85185185 0.875 ]
|
|
|
|
mean value: 0.8792785917785918
|
|
|
|
key: train_precision
|
|
value: [0.99530516 0.99530516 0.99530516 0.99530516 0.99526066 1.
|
|
1. 1. 0.9953271 1. ]
|
|
|
|
mean value: 0.9971808423587842
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.83333333 1.
|
|
1. 0.95652174 1. 0.91304348]
|
|
|
|
mean value: 0.9702898550724638
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 0.99056604 1.
|
|
1. 1. 1. 0.99530516]
|
|
|
|
mean value: 0.9985871202055098
|
|
|
|
key: test_roc_auc
|
|
value: [0.9375 0.95833333 0.91304348 0.93478261 0.89492754 0.93478261
|
|
0.91666667 0.8740942 0.91666667 0.89402174]
|
|
|
|
mean value: 0.917481884057971
|
|
|
|
key: train_roc_auc
|
|
value: [0.99764151 0.99764151 0.99765258 0.99765258 0.9929356 1.
|
|
1. 1. 0.99764151 0.99765258]
|
|
|
|
mean value: 0.9978817875808309
|
|
|
|
key: test_jcc
|
|
value: [0.88888889 0.92307692 0.85714286 0.88888889 0.8 0.88888889
|
|
0.85185185 0.78571429 0.85185185 0.80769231]
|
|
|
|
mean value: 0.8543996743996743
|
|
|
|
key: train_jcc
|
|
value: [0.99530516 0.99530516 0.99530516 0.99530516 0.98591549 1.
|
|
1. 1. 0.9953271 0.99530516]
|
|
|
|
mean value: 0.995776841735773
|
|
|
|
MCC on Blind test: 0.31
|
|
|
|
Accuracy on Blind test: 0.79
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.63860369 0.61433911 0.62631059 0.55984473 0.56437945 0.5705359
|
|
0.55959272 0.56756783 0.56334019 0.56177235]
|
|
|
|
mean value: 0.5826286554336548
|
|
|
|
key: score_time
|
|
value: [0.01178908 0.00929523 0.01308513 0.00907826 0.00972509 0.00932693
|
|
0.00939345 0.00972891 0.00956774 0.00933242]
|
|
|
|
mean value: 0.010032224655151366
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.9591663 1. 0.95825929 0.95833333 0.91804649
|
|
1. 1. 0.91833182 1. ]
|
|
|
|
mean value: 0.967130354866919
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.97916667 1. 0.9787234 0.9787234 0.95744681
|
|
1. 1. 0.95744681 1. ]
|
|
|
|
mean value: 0.9830673758865248
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.97959184 1. 0.97959184 0.9787234 0.96
|
|
1. 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.9835832247792734
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 0.96 1. 0.96 1. 0.92307692
|
|
1. 1. 0.92 1. ]
|
|
|
|
mean value: 0.9723076923076923
|
|
|
|
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. 0.95833333 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.97916667 1. 0.97826087 0.97916667 0.95652174
|
|
1. 1. 0.95833333 1. ]
|
|
|
|
mean value: 0.9830615942028986
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.96 1. 0.96 0.95833333 0.92307692
|
|
1. 1. 0.92 1. ]
|
|
|
|
mean value: 0.9681410256410257
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.85
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02648783 0.03151965 0.02891946 0.02913499 0.02851081 0.02859592
|
|
0.02840805 0.02885747 0.02888227 0.0306499 ]
|
|
|
|
mean value: 0.0289966344833374
|
|
|
|
key: score_time
|
|
value: [0.01299691 0.01276255 0.01519513 0.0127933 0.01490784 0.01260257
|
|
0.01631975 0.0153079 0.02151155 0.02148819]
|
|
|
|
mean value: 0.01558856964111328
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.95825929 0.91833182 0.91833182 1.
|
|
1. 0.91485507 0.91804649 0.91804649]
|
|
|
|
mean value: 0.9545870993079677
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.9787234 0.95744681 0.95744681 1.
|
|
1. 0.95744681 0.95744681 0.95744681]
|
|
|
|
mean value: 0.9765957446808511
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.97959184 0.95652174 0.95652174 1.
|
|
1. 0.95652174 0.95454545 0.95454545]
|
|
|
|
mean value: 0.9758247963216907
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.96 1. 1. 1.
|
|
1. 0.95652174 1. 1. ]
|
|
|
|
mean value: 0.9916521739130435
|
|
|
|
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. 0.91666667 0.91666667 1.
|
|
1. 0.95652174 0.91304348 0.91304348]
|
|
|
|
mean value: 0.9615942028985507
|
|
|
|
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. 0.97826087 0.95833333 0.95833333 1.
|
|
1. 0.95742754 0.95652174 0.95652174]
|
|
|
|
mean value: 0.9765398550724638
|
|
|
|
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. 0.96 0.91666667 0.91666667 1.
|
|
1. 0.91666667 0.91304348 0.91304348]
|
|
|
|
mean value: 0.9536086956521739
|
|
|
|
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: 0.79
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02392817 0.02470946 0.01540208 0.01530647 0.04976296 0.04024053
|
|
0.03483343 0.04155397 0.0376513 0.01532578]
|
|
|
|
mean value: 0.029871416091918946
|
|
|
|
key: score_time
|
|
value: [0.01954985 0.01194859 0.01190138 0.0120008 0.01226473 0.01302767
|
|
0.02832317 0.01217866 0.01212168 0.0119648 ]
|
|
|
|
mean value: 0.014528131484985352
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.91986621 0.91804649 0.87917396 1. 0.87917396
|
|
0.95833333 0.87979456 0.87979456 0.91833182]
|
|
|
|
mean value: 0.9191681205540845
|
|
|
|
key: train_mcc
|
|
value: [0.97668677 0.97668677 0.97674215 0.985981 0.98135106 0.98135106
|
|
0.9767396 0.97215032 0.98598008 0.9767396 ]
|
|
|
|
mean value: 0.9790408418215171
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.95833333 0.95744681 0.93617021 1. 0.93617021
|
|
0.9787234 0.93617021 0.93617021 0.95744681]
|
|
|
|
mean value: 0.9575797872340426
|
|
|
|
key: train_accuracy
|
|
value: [0.98820755 0.98820755 0.98823529 0.99294118 0.99058824 0.99058824
|
|
0.98823529 0.98588235 0.99294118 0.98823529]
|
|
|
|
mean value: 0.9894062153163152
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.96 0.96 0.94117647 1. 0.94117647
|
|
0.9787234 0.93877551 0.93877551 0.95833333]
|
|
|
|
mean value: 0.9596552535907981
|
|
|
|
key: train_fscore
|
|
value: [0.98834499 0.98834499 0.98834499 0.99297424 0.99065421 0.99065421
|
|
0.98839907 0.98611111 0.99300699 0.98839907]
|
|
|
|
mean value: 0.9895233863095408
|
|
|
|
key: test_precision
|
|
value: [0.96 0.92307692 0.92307692 0.88888889 1. 0.88888889
|
|
0.95833333 0.88461538 0.88461538 0.92 ]
|
|
|
|
mean value: 0.9231495726495726
|
|
|
|
key: train_precision
|
|
value: [0.97695853 0.97695853 0.97695853 0.98604651 0.98148148 0.98148148
|
|
0.97706422 0.97260274 0.98611111 0.97706422]
|
|
|
|
mean value: 0.9792727341831847
|
|
|
|
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: /home/tanu/git/LSHTM_analysis/scripts/ml/./embb_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/./embb_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)
|
|
[0.97916667 0.95833333 0.95652174 0.93478261 1. 0.93478261
|
|
0.97916667 0.9375 0.9375 0.95833333]
|
|
|
|
mean value: 0.9576086956521739
|
|
|
|
key: train_roc_auc
|
|
value: [0.98820755 0.98820755 0.98826291 0.99295775 0.99061033 0.99061033
|
|
0.98820755 0.98584906 0.99292453 0.98820755]
|
|
|
|
mean value: 0.9894045088138896
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.92307692 0.92307692 0.88888889 1. 0.88888889
|
|
0.95833333 0.88461538 0.88461538 0.92 ]
|
|
|
|
mean value: 0.9231495726495726
|
|
|
|
key: train_jcc
|
|
value: [0.97695853 0.97695853 0.97695853 0.98604651 0.98148148 0.98148148
|
|
0.97706422 0.97260274 0.98611111 0.97706422]
|
|
|
|
mean value: 0.9792727341831847
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
Accuracy on Blind test: 0.93
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.19476819 0.20674205 0.26244783 0.27413368 0.27175689 0.19468117
|
|
0.31302524 0.2471962 0.14654851 0.19013238]
|
|
|
|
mean value: 0.23014321327209472
|
|
|
|
key: score_time
|
|
value: [0.01197314 0.02168083 0.02361894 0.02394915 0.02224946 0.01713872
|
|
0.0120697 0.01210713 0.0119493 0.01193929]
|
|
|
|
mean value: 0.016867566108703613
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.91986621 0.91804649 0.87917396 1. 0.87917396
|
|
0.95833333 0.87979456 0.87979456 0.91833182]
|
|
|
|
mean value: 0.9191681205540845
|
|
|
|
key: train_mcc
|
|
value: [0.98130676 0.97668677 0.97674215 0.985981 0.98135106 0.985981
|
|
0.9767396 0.97215032 0.98598008 0.9767396 ]
|
|
|
|
mean value: 0.9799658348496263
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.95833333 0.95744681 0.93617021 1. 0.93617021
|
|
0.9787234 0.93617021 0.93617021 0.95744681]
|
|
|
|
mean value: 0.9575797872340426
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.98820755 0.98823529 0.99294118 0.99058824 0.99294118
|
|
0.98823529 0.98588235 0.99294118 0.98823529]
|
|
|
|
mean value: 0.989877358490566
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.96 0.96 0.94117647 1. 0.94117647
|
|
0.9787234 0.93877551 0.93877551 0.95833333]
|
|
|
|
mean value: 0.9596552535907981
|
|
|
|
key: train_fscore
|
|
value: [0.99065421 0.98834499 0.98834499 0.99297424 0.99065421 0.99297424
|
|
0.98839907 0.98611111 0.99300699 0.98839907]
|
|
|
|
mean value: 0.9899863113626299
|
|
|
|
key: test_precision
|
|
value: [0.96 0.92307692 0.92307692 0.88888889 1. 0.88888889
|
|
0.95833333 0.88461538 0.88461538 0.92 ]
|
|
|
|
mean value: 0.9231495726495726
|
|
|
|
key: train_precision
|
|
value: [0.98148148 0.97695853 0.97695853 0.98604651 0.98148148 0.98604651
|
|
0.97706422 0.97260274 0.98611111 0.97706422]
|
|
|
|
mean value: 0.9801815328114132
|
|
|
|
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: [0.97916667 0.95833333 0.95652174 0.93478261 1. 0.93478261
|
|
0.97916667 0.9375 0.9375 0.95833333]
|
|
|
|
mean value: 0.9576086956521739
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.98820755 0.98826291 0.99295775 0.99061033 0.99295775
|
|
0.98820755 0.98584906 0.99292453 0.98820755]
|
|
|
|
mean value: 0.9898750996545309
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.92307692 0.92307692 0.88888889 1. 0.88888889
|
|
0.95833333 0.88461538 0.88461538 0.92 ]
|
|
|
|
mean value: 0.9231495726495726
|
|
|
|
key: train_jcc
|
|
value: [0.98148148 0.97695853 0.97695853 0.98604651 0.98148148 0.98604651
|
|
0.97706422 0.97260274 0.98611111 0.97706422]
|
|
|
|
mean value: 0.9801815328114132
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
Accuracy on Blind test: 0.93
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03795266 0.02573371 0.03174782 0.02996969 0.02600169 0.02538538
|
|
0.02709675 0.02577019 0.02770662 0.02684879]
|
|
|
|
mean value: 0.02842133045196533
|
|
|
|
key: score_time
|
|
value: [0.01199293 0.0115788 0.01219726 0.01195335 0.01168251 0.01168489
|
|
0.01168656 0.01150799 0.0114634 0.01173162]
|
|
|
|
mean value: 0.011747932434082032
|
|
|
|
key: test_mcc
|
|
value: [0.69047619 1. 0.41475753 1. 0.69047619 0.22537447
|
|
0.73192505 0.41475753 0.84515425 0.84515425]
|
|
|
|
mean value: 0.6858075475054671
|
|
|
|
key: train_mcc
|
|
value: [0.91316192 0.8784029 0.89621789 0.89788027 0.87836615 0.91316192
|
|
0.91644829 0.93097223 0.89869147 0.88048896]
|
|
|
|
mean value: 0.900379200228071
|
|
|
|
key: test_accuracy
|
|
value: [0.84615385 1. 0.69230769 1. 0.84615385 0.61538462
|
|
0.84615385 0.69230769 0.91666667 0.91666667]
|
|
|
|
mean value: 0.8371794871794872
|
|
|
|
key: train_accuracy
|
|
value: [0.95652174 0.93913043 0.94782609 0.94782609 0.93913043 0.95652174
|
|
0.95652174 0.96521739 0.94827586 0.93965517]
|
|
|
|
mean value: 0.9496626686656672
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 1. 0.71428571 1. 0.85714286 0.70588235
|
|
0.83333333 0.66666667 0.92307692 0.92307692]
|
|
|
|
mean value: 0.8456798103856927
|
|
|
|
key: train_fscore
|
|
value: [0.95726496 0.93913043 0.94736842 0.94642857 0.9380531 0.95575221
|
|
0.95412844 0.96428571 0.94642857 0.9380531 ]
|
|
|
|
mean value: 0.9486893517689673
|
|
|
|
key: test_precision
|
|
value: [0.83333333 1. 0.625 1. 0.85714286 0.6
|
|
1. 0.8 0.85714286 0.85714286]
|
|
|
|
mean value: 0.8429761904761904
|
|
|
|
key: train_precision
|
|
value: [0.94915254 0.94736842 0.96428571 0.98148148 0.94642857 0.96428571
|
|
1. 0.98181818 0.98148148 0.96363636]
|
|
|
|
mean value: 0.9679938471843021
|
|
|
|
key: test_recall
|
|
value: [0.83333333 1. 0.83333333 1. 0.85714286 0.85714286
|
|
0.71428571 0.57142857 1. 1. ]
|
|
|
|
mean value: 0.8666666666666667
|
|
|
|
key: train_recall
|
|
value: [0.96551724 0.93103448 0.93103448 0.9137931 0.92982456 0.94736842
|
|
0.9122807 0.94736842 0.9137931 0.9137931 ]
|
|
|
|
mean value: 0.9305807622504537
|
|
|
|
key: test_roc_auc
|
|
value: [0.8452381 1. 0.70238095 1. 0.8452381 0.5952381
|
|
0.85714286 0.70238095 0.91666667 0.91666667]
|
|
|
|
mean value: 0.8380952380952381
|
|
|
|
key: train_roc_auc
|
|
value: [0.95644283 0.93920145 0.94797338 0.94812462 0.93905021 0.95644283
|
|
0.95614035 0.96506352 0.94827586 0.93965517]
|
|
|
|
mean value: 0.9496370235934664
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 1. 0.55555556 1. 0.75 0.54545455
|
|
0.71428571 0.5 0.85714286 0.85714286]
|
|
|
|
mean value: 0.7493867243867244
|
|
|
|
key: train_jcc
|
|
value: [0.91803279 0.8852459 0.9 0.89830508 0.88333333 0.91525424
|
|
0.9122807 0.93103448 0.89830508 0.88333333]
|
|
|
|
mean value: 0.9025124946483924
|
|
|
|
MCC on Blind test: 0.57
|
|
|
|
Accuracy on Blind test: 0.82
|
|
|
|
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(
|
|
[('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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.63031912 0.66760516 0.64497495 0.58545446 0.67853045 0.53832674
|
|
0.57423687 0.59362006 0.73715329 0.8035605 ]
|
|
|
|
mean value: 0.6453781604766846
|
|
|
|
key: score_time
|
|
value: [0.01580167 0.01174617 0.01520562 0.02407861 0.01920891 0.01185036
|
|
0.01532388 0.01180005 0.01528311 0.01332784]
|
|
|
|
mean value: 0.01536262035369873
|
|
|
|
key: test_mcc
|
|
value: [0.85391256 1. 0.23809524 0.85391256 0.69047619 0.7200823
|
|
0.73192505 0.54761905 0.84515425 0.84515425]
|
|
|
|
mean value: 0.7326331467841938
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.92307692 1. 0.61538462 0.92307692 0.84615385 0.84615385
|
|
0.84615385 0.76923077 0.91666667 0.91666667]
|
|
|
|
mean value: 0.8602564102564103
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.90909091 1. 0.61538462 0.90909091 0.85714286 0.875
|
|
0.83333333 0.76923077 0.92307692 0.92307692]
|
|
|
|
mean value: 0.8614427239427239
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.57142857 1. 0.85714286 0.77777778
|
|
1. 0.83333333 0.85714286 0.85714286]
|
|
|
|
mean value: 0.8753968253968254
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.83333333 1. 0.66666667 0.83333333 0.85714286 1.
|
|
0.71428571 0.71428571 1. 1. ]
|
|
|
|
mean value: 0.861904761904762
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.91666667 1. 0.61904762 0.91666667 0.8452381 0.83333333
|
|
0.85714286 0.77380952 0.91666667 0.91666667]
|
|
|
|
mean value: 0.8595238095238096
|
|
|
|
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 1. 0.44444444 0.83333333 0.75 0.77777778
|
|
0.71428571 0.625 0.85714286 0.85714286]
|
|
|
|
mean value: 0.7692460317460318
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.62
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01238108 0.01127577 0.01497674 0.01421952 0.00946546 0.01414895
|
|
0.01068878 0.00998735 0.01448131 0.00993919]
|
|
|
|
mean value: 0.012156414985656738
|
|
|
|
key: score_time
|
|
value: [0.01499891 0.00944257 0.01214433 0.00992179 0.01070023 0.01319957
|
|
0.00970149 0.01296663 0.01003146 0.00911283]
|
|
|
|
mean value: 0.011221981048583985
|
|
|
|
key: test_mcc
|
|
value: [ 0.22537447 0.59160798 0.38095238 0.59160798 0.6172134 -0.22537447
|
|
0.28288947 0.6172134 0. 0.70710678]
|
|
|
|
mean value: 0.3788591393386089
|
|
|
|
key: train_mcc
|
|
value: [0.67341081 0.60831313 0.70159234 0.55669497 0.64191595 0.63468548
|
|
0.71712411 0.65677488 0.63869039 0.63869039]
|
|
|
|
mean value: 0.6467892446231506
|
|
|
|
key: test_accuracy
|
|
value: [0.61538462 0.76923077 0.69230769 0.76923077 0.76923077 0.38461538
|
|
0.61538462 0.76923077 0.5 0.83333333]
|
|
|
|
mean value: 0.6717948717948719
|
|
|
|
key: train_accuracy
|
|
value: [0.8173913 0.7826087 0.83478261 0.75652174 0.80869565 0.8
|
|
0.85217391 0.8173913 0.80172414 0.80172414]
|
|
|
|
mean value: 0.8073013493253374
|
|
|
|
key: test_fscore
|
|
value: [0.44444444 0.66666667 0.66666667 0.66666667 0.72727273 0.2
|
|
0.54545455 0.72727273 0.4 0.8 ]
|
|
|
|
mean value: 0.5844444444444444
|
|
|
|
key: train_fscore
|
|
value: [0.78350515 0.73684211 0.80808081 0.70212766 0.7755102 0.75789474
|
|
0.83495146 0.78787879 0.7628866 0.7628866 ]
|
|
|
|
mean value: 0.7712564108547103
|
|
|
|
key: test_precision
|
|
value: [0.66666667 1. 0.66666667 1. 1. 0.33333333
|
|
0.75 1. 0.5 1. ]
|
|
|
|
mean value: 0.7916666666666666
|
|
|
|
key: train_precision
|
|
value: [0.97435897 0.94594595 0.97560976 0.91666667 0.92682927 0.94736842
|
|
0.93478261 0.92857143 0.94871795 0.94871795]
|
|
|
|
mean value: 0.944756896711744
|
|
|
|
key: test_recall
|
|
value: [0.33333333 0.5 0.66666667 0.5 0.57142857 0.14285714
|
|
0.42857143 0.57142857 0.33333333 0.66666667]
|
|
|
|
mean value: 0.4714285714285714
|
|
|
|
key: train_recall
|
|
value: [0.65517241 0.60344828 0.68965517 0.56896552 0.66666667 0.63157895
|
|
0.75438596 0.68421053 0.63793103 0.63793103]
|
|
|
|
mean value: 0.652994555353902
|
|
|
|
key: test_roc_auc
|
|
value: [0.5952381 0.75 0.69047619 0.75 0.78571429 0.4047619
|
|
0.63095238 0.78571429 0.5 0.83333333]
|
|
|
|
mean value: 0.6726190476190476
|
|
|
|
key: train_roc_auc
|
|
value: [0.81881428 0.78418028 0.83605566 0.75816697 0.80747126 0.79854809
|
|
0.85133091 0.81624319 0.80172414 0.80172414]
|
|
|
|
mean value: 0.8074258923169995
|
|
|
|
key: test_jcc
|
|
value: [0.28571429 0.5 0.5 0.5 0.57142857 0.11111111
|
|
0.375 0.57142857 0.25 0.66666667]
|
|
|
|
mean value: 0.43313492063492065
|
|
|
|
key: train_jcc
|
|
value: [0.6440678 0.58333333 0.6779661 0.54098361 0.63333333 0.61016949
|
|
0.71666667 0.65 0.61666667 0.61666667]
|
|
|
|
mean value: 0.6289853663054552
|
|
|
|
MCC on Blind test: 0.43
|
|
|
|
Accuracy on Blind test: 0.81
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.00863647 0.00878501 0.0087626 0.00969172 0.00983548 0.00977182
|
|
0.00952625 0.00949526 0.00977659 0.00879169]
|
|
|
|
mean value: 0.009307289123535156
|
|
|
|
key: score_time
|
|
value: [0.00888968 0.00842905 0.00842333 0.00938821 0.00932121 0.00914335
|
|
0.00904346 0.00930882 0.00930953 0.00844479]
|
|
|
|
mean value: 0.008970141410827637
|
|
|
|
key: test_mcc
|
|
value: [0.54761905 0.21957752 0.23809524 0.7200823 0.54761905 0.09759001
|
|
0.50709255 0.09759001 0. 0.33333333]
|
|
|
|
mean value: 0.3308599050329999
|
|
|
|
key: train_mcc
|
|
value: [0.70722413 0.63989131 0.72363756 0.60255132 0.65541674 0.66173728
|
|
0.6354556 0.67183925 0.62667956 0.60570315]
|
|
|
|
mean value: 0.6530135892935511
|
|
|
|
key: test_accuracy
|
|
value: [0.76923077 0.61538462 0.61538462 0.84615385 0.76923077 0.53846154
|
|
0.69230769 0.53846154 0.5 0.66666667]
|
|
|
|
mean value: 0.6551282051282051
|
|
|
|
key: train_accuracy
|
|
value: [0.85217391 0.8173913 0.86086957 0.8 0.82608696 0.82608696
|
|
0.8173913 0.83478261 0.81034483 0.80172414]
|
|
|
|
mean value: 0.8246851574212893
|
|
|
|
key: test_fscore
|
|
value: [0.76923077 0.54545455 0.61538462 0.8 0.76923077 0.5
|
|
0.6 0.5 0.25 0.66666667]
|
|
|
|
mean value: 0.6015967365967365
|
|
|
|
key: train_fscore
|
|
value: [0.84684685 0.80733945 0.85714286 0.79279279 0.81481481 0.80769231
|
|
0.81081081 0.82568807 0.7962963 0.79279279]
|
|
|
|
mean value: 0.8152217042125299
|
|
|
|
key: test_precision
|
|
value: [0.71428571 0.6 0.57142857 1. 0.83333333 0.6
|
|
1. 0.6 0.5 0.66666667]
|
|
|
|
mean value: 0.7085714285714285
|
|
|
|
key: train_precision
|
|
value: [0.88679245 0.8627451 0.88888889 0.83018868 0.8627451 0.89361702
|
|
0.83333333 0.86538462 0.86 0.83018868]
|
|
|
|
mean value: 0.861388386628262
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.5 0.66666667 0.66666667 0.71428571 0.42857143
|
|
0.42857143 0.42857143 0.16666667 0.66666667]
|
|
|
|
mean value: 0.5499999999999999
|
|
|
|
key: train_recall
|
|
value: [0.81034483 0.75862069 0.82758621 0.75862069 0.77192982 0.73684211
|
|
0.78947368 0.78947368 0.74137931 0.75862069]
|
|
|
|
mean value: 0.7742891712038718
|
|
|
|
key: test_roc_auc
|
|
value: [0.77380952 0.60714286 0.61904762 0.83333333 0.77380952 0.54761905
|
|
0.71428571 0.54761905 0.5 0.66666667]
|
|
|
|
mean value: 0.6583333333333333
|
|
|
|
key: train_roc_auc
|
|
value: [0.85254083 0.81790684 0.86116152 0.80036298 0.82562008 0.8253176
|
|
0.81715064 0.83439201 0.81034483 0.80172414]
|
|
|
|
mean value: 0.8246521476104053
|
|
|
|
key: test_jcc
|
|
value: [0.625 0.375 0.44444444 0.66666667 0.625 0.33333333
|
|
0.42857143 0.33333333 0.14285714 0.5 ]
|
|
|
|
mean value: 0.4474206349206349
|
|
|
|
key: train_jcc
|
|
value: [0.734375 0.67692308 0.75 0.65671642 0.6875 0.67741935
|
|
0.68181818 0.703125 0.66153846 0.65671642]
|
|
|
|
mean value: 0.6886131910939326
|
|
|
|
MCC on Blind test: 0.36
|
|
|
|
Accuracy on Blind test: 0.75
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.00935054 0.00946498 0.0086019 0.0082736 0.00825453 0.00824285
|
|
0.00813723 0.00829768 0.00874615 0.00841093]
|
|
|
|
mean value: 0.008578038215637207
|
|
|
|
key: score_time
|
|
value: [0.01578259 0.01445484 0.0116303 0.00913668 0.00928998 0.00917983
|
|
0.00935197 0.00938654 0.00985885 0.01002717]
|
|
|
|
mean value: 0.010809874534606934
|
|
|
|
key: test_mcc
|
|
value: [ 0.21957752 0.38095238 0.05143445 0.53674504 0.6172134 -0.05143445
|
|
0.39477102 0.41475753 0.66666667 0.16903085]
|
|
|
|
mean value: 0.33997144029272197
|
|
|
|
key: train_mcc
|
|
value: [0.51862783 0.60488298 0.56987466 0.55693742 0.49198609 0.53638962
|
|
0.53090997 0.56896524 0.5130534 0.58760596]
|
|
|
|
mean value: 0.5479233165249815
|
|
|
|
key: test_accuracy
|
|
value: [0.61538462 0.69230769 0.53846154 0.76923077 0.76923077 0.46153846
|
|
0.61538462 0.69230769 0.83333333 0.58333333]
|
|
|
|
mean value: 0.657051282051282
|
|
|
|
key: train_accuracy
|
|
value: [0.75652174 0.8 0.7826087 0.77391304 0.73913043 0.76521739
|
|
0.76521739 0.7826087 0.75 0.79310345]
|
|
|
|
mean value: 0.7708320839580209
|
|
|
|
key: test_fscore
|
|
value: [0.54545455 0.66666667 0.4 0.72727273 0.72727273 0.36363636
|
|
0.44444444 0.66666667 0.83333333 0.54545455]
|
|
|
|
mean value: 0.592020202020202
|
|
|
|
key: train_fscore
|
|
value: [0.74074074 0.78899083 0.7706422 0.75471698 0.7 0.74285714
|
|
0.75675676 0.76635514 0.7184466 0.78571429]
|
|
|
|
mean value: 0.7525220676852601
|
|
|
|
key: test_precision
|
|
value: [0.6 0.66666667 0.5 0.8 1. 0.5
|
|
1. 0.8 0.83333333 0.6 ]
|
|
|
|
mean value: 0.73
|
|
|
|
key: train_precision
|
|
value: [0.8 0.84313725 0.82352941 0.83333333 0.81395349 0.8125
|
|
0.77777778 0.82 0.82222222 0.81481481]
|
|
|
|
mean value: 0.8161268303186908
|
|
|
|
key: test_recall
|
|
value: [0.5 0.66666667 0.33333333 0.66666667 0.57142857 0.28571429
|
|
0.28571429 0.57142857 0.83333333 0.5 ]
|
|
|
|
mean value: 0.5214285714285715
|
|
|
|
key: train_recall
|
|
value: [0.68965517 0.74137931 0.72413793 0.68965517 0.61403509 0.68421053
|
|
0.73684211 0.71929825 0.63793103 0.75862069]
|
|
|
|
mean value: 0.6995765275257109
|
|
|
|
key: test_roc_auc
|
|
value: [0.60714286 0.69047619 0.52380952 0.76190476 0.78571429 0.47619048
|
|
0.64285714 0.70238095 0.83333333 0.58333333]
|
|
|
|
mean value: 0.6607142857142857
|
|
|
|
key: train_roc_auc
|
|
value: [0.75710829 0.80051422 0.7831216 0.77465215 0.73805203 0.76451906
|
|
0.76497278 0.78206292 0.75 0.79310345]
|
|
|
|
mean value: 0.770810647307925
|
|
|
|
key: test_jcc
|
|
value: [0.375 0.5 0.25 0.57142857 0.57142857 0.22222222
|
|
0.28571429 0.5 0.71428571 0.375 ]
|
|
|
|
mean value: 0.4365079365079365
|
|
|
|
key: train_jcc
|
|
value: [0.58823529 0.65151515 0.62686567 0.60606061 0.53846154 0.59090909
|
|
0.60869565 0.62121212 0.56060606 0.64705882]
|
|
|
|
mean value: 0.6039620010227331
|
|
|
|
MCC on Blind test: 0.27
|
|
|
|
Accuracy on Blind test: 0.68
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01144338 0.01029992 0.00980878 0.01067209 0.01021671 0.01395416
|
|
0.01023436 0.01021194 0.01642919 0.01143122]
|
|
|
|
mean value: 0.011470174789428711
|
|
|
|
key: score_time
|
|
value: [0.00896978 0.00912261 0.00946689 0.00968432 0.01609945 0.01113772
|
|
0.00966287 0.00931144 0.01310802 0.01041579]
|
|
|
|
mean value: 0.010697889328002929
|
|
|
|
key: test_mcc
|
|
value: [0.54761905 0.54761905 0.09759001 0.85714286 0.85714286 0.05143445
|
|
0.6172134 0.41475753 0.70710678 0.57735027]
|
|
|
|
mean value: 0.5274976248033695
|
|
|
|
key: train_mcc
|
|
value: [0.86286805 0.82797711 0.8784029 0.82652169 0.844687 0.86133853
|
|
0.82662636 0.84361766 0.79310345 0.7787612 ]
|
|
|
|
mean value: 0.8343903951567592
|
|
|
|
key: test_accuracy
|
|
value: [0.76923077 0.76923077 0.53846154 0.92307692 0.92307692 0.53846154
|
|
0.76923077 0.69230769 0.83333333 0.75 ]
|
|
|
|
mean value: 0.7506410256410256
|
|
|
|
key: train_accuracy
|
|
value: [0.93043478 0.91304348 0.93913043 0.91304348 0.92173913 0.93043478
|
|
0.91304348 0.92173913 0.89655172 0.88793103]
|
|
|
|
mean value: 0.9167091454272863
|
|
|
|
key: test_fscore
|
|
value: [0.76923077 0.76923077 0.57142857 0.92307692 0.92307692 0.625
|
|
0.72727273 0.66666667 0.85714286 0.8 ]
|
|
|
|
mean value: 0.7632126207126207
|
|
|
|
key: train_fscore
|
|
value: [0.93333333 0.91666667 0.93913043 0.91525424 0.92307692 0.92857143
|
|
0.9137931 0.92173913 0.89655172 0.89256198]
|
|
|
|
mean value: 0.918067896521116
|
|
|
|
key: test_precision
|
|
value: [0.71428571 0.71428571 0.5 0.85714286 1. 0.55555556
|
|
1. 0.8 0.75 0.66666667]
|
|
|
|
mean value: 0.7557936507936508
|
|
|
|
key: train_precision
|
|
value: [0.90322581 0.88709677 0.94736842 0.9 0.9 0.94545455
|
|
0.89830508 0.9137931 0.89655172 0.85714286]
|
|
|
|
mean value: 0.9048938316627165
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.83333333 0.66666667 1. 0.85714286 0.71428571
|
|
0.57142857 0.57142857 1. 1. ]
|
|
|
|
mean value: 0.8047619047619048
|
|
|
|
key: train_recall
|
|
value: [0.96551724 0.94827586 0.93103448 0.93103448 0.94736842 0.9122807
|
|
0.92982456 0.92982456 0.89655172 0.93103448]
|
|
|
|
mean value: 0.9322746521476104
|
|
|
|
key: test_roc_auc
|
|
value: [0.77380952 0.77380952 0.54761905 0.92857143 0.92857143 0.52380952
|
|
0.78571429 0.70238095 0.83333333 0.75 ]
|
|
|
|
mean value: 0.7547619047619047
|
|
|
|
key: train_roc_auc
|
|
value: [0.93012704 0.91273442 0.93920145 0.91288566 0.92196007 0.93027828
|
|
0.91318814 0.92180883 0.89655172 0.88793103]
|
|
|
|
mean value: 0.9166666666666666
|
|
|
|
key: test_jcc
|
|
value: [0.625 0.625 0.4 0.85714286 0.85714286 0.45454545
|
|
0.57142857 0.5 0.75 0.66666667]
|
|
|
|
mean value: 0.6306926406926406
|
|
|
|
key: train_jcc
|
|
value: [0.875 0.84615385 0.8852459 0.84375 0.85714286 0.86666667
|
|
0.84126984 0.85483871 0.8125 0.80597015]
|
|
|
|
mean value: 0.8488537971803706
|
|
|
|
MCC on Blind test: 0.51
|
|
|
|
Accuracy on Blind test: 0.78
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.67943549 0.5001564 0.42651844 0.46594143 0.68203807 0.49212933
|
|
0.43587995 0.4478724 0.44818687 0.62777424]
|
|
|
|
mean value: 0.52059326171875
|
|
|
|
key: score_time
|
|
value: [0.01202297 0.01209712 0.01210523 0.01199317 0.0121572 0.01203156
|
|
0.01206231 0.01210475 0.01202416 0.01205945]
|
|
|
|
mean value: 0.012065792083740234
|
|
|
|
key: test_mcc
|
|
value: [0.69047619 0.85714286 0.23809524 0.85391256 0.69047619 0.38575837
|
|
0.6172134 0.41475753 0.84515425 0.84515425]
|
|
|
|
mean value: 0.64381408552342
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.84615385 0.92307692 0.61538462 0.92307692 0.84615385 0.69230769
|
|
0.76923077 0.69230769 0.91666667 0.91666667]
|
|
|
|
mean value: 0.8141025641025641
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 0.92307692 0.61538462 0.90909091 0.85714286 0.75
|
|
0.72727273 0.66666667 0.92307692 0.92307692]
|
|
|
|
mean value: 0.8128121878121878
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.83333333 0.85714286 0.57142857 1. 0.85714286 0.66666667
|
|
1. 0.8 0.85714286 0.85714286]
|
|
|
|
mean value: 0.83
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.83333333 1. 0.66666667 0.83333333 0.85714286 0.85714286
|
|
0.57142857 0.57142857 1. 1. ]
|
|
|
|
mean value: 0.819047619047619
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.8452381 0.92857143 0.61904762 0.91666667 0.8452381 0.67857143
|
|
0.78571429 0.70238095 0.91666667 0.91666667]
|
|
|
|
mean value: 0.8154761904761905
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 0.85714286 0.44444444 0.83333333 0.75 0.6
|
|
0.57142857 0.5 0.85714286 0.85714286]
|
|
|
|
mean value: 0.6984920634920635
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.47
|
|
|
|
Accuracy on Blind test: 0.77
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01786566 0.01201987 0.01014161 0.01033139 0.01072526 0.01073861
|
|
0.01079178 0.01086593 0.01103258 0.01176143]
|
|
|
|
mean value: 0.011627411842346192
|
|
|
|
key: score_time
|
|
value: [0.02414203 0.00892425 0.00843573 0.00838995 0.00836587 0.00921845
|
|
0.0085516 0.00863719 0.00848961 0.00929165]
|
|
|
|
mean value: 0.010244631767272949
|
|
|
|
key: test_mcc
|
|
value: [0.69047619 0.85391256 0.85714286 0.7200823 0.85714286 0.69047619
|
|
0.6172134 0.85714286 1. 0.84515425]
|
|
|
|
mean value: 0.7988743470610898
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.84615385 0.92307692 0.92307692 0.84615385 0.92307692 0.84615385
|
|
0.76923077 0.92307692 1. 0.91666667]
|
|
|
|
mean value: 0.8916666666666667
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 0.90909091 0.92307692 0.8 0.92307692 0.85714286
|
|
0.72727273 0.92307692 1. 0.90909091]
|
|
|
|
mean value: 0.8805161505161505
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.83333333 1. 0.85714286 1. 1. 0.85714286
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9547619047619047
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.83333333 1. 0.66666667 0.85714286 0.85714286
|
|
0.57142857 0.85714286 1. 0.83333333]
|
|
|
|
mean value: 0.8309523809523809
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.8452381 0.91666667 0.92857143 0.83333333 0.92857143 0.8452381
|
|
0.78571429 0.92857143 1. 0.91666667]
|
|
|
|
mean value: 0.8928571428571429
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 0.83333333 0.85714286 0.66666667 0.85714286 0.75
|
|
0.57142857 0.85714286 1. 0.83333333]
|
|
|
|
mean value: 0.794047619047619
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.84
|
|
|
|
Accuracy on Blind test: 0.94
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.08564305 0.0855217 0.08444643 0.08605838 0.08570886 0.08505464
|
|
0.08590603 0.08637238 0.08750439 0.08654571]
|
|
|
|
mean value: 0.08587615489959717
|
|
|
|
key: score_time
|
|
value: [0.0169692 0.01684976 0.01798987 0.01815295 0.01674366 0.01676559
|
|
0.01780319 0.01775026 0.01702905 0.01721311]
|
|
|
|
mean value: 0.017326664924621583
|
|
|
|
key: test_mcc
|
|
value: [0.54761905 0.53674504 0.28288947 1. 0.54761905 0.21957752
|
|
0.73192505 0.41475753 0.84515425 1. ]
|
|
|
|
mean value: 0.6126286967146753
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.76923077 0.76923077 0.61538462 1. 0.76923077 0.61538462
|
|
0.84615385 0.69230769 0.91666667 1. ]
|
|
|
|
mean value: 0.7993589743589744
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.76923077 0.72727273 0.66666667 1. 0.76923077 0.66666667
|
|
0.83333333 0.66666667 0.90909091 1. ]
|
|
|
|
mean value: 0.8008158508158508
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.71428571 0.8 0.55555556 1. 0.83333333 0.625
|
|
1. 0.8 1. 1. ]
|
|
|
|
mean value: 0.8328174603174603
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.66666667 0.83333333 1. 0.71428571 0.71428571
|
|
0.71428571 0.57142857 0.83333333 1. ]
|
|
|
|
mean value: 0.7880952380952381
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.77380952 0.76190476 0.63095238 1. 0.77380952 0.60714286
|
|
0.85714286 0.70238095 0.91666667 1. ]
|
|
|
|
mean value: 0.8023809523809524
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.625 0.57142857 0.5 1. 0.625 0.5
|
|
0.71428571 0.5 0.83333333 1. ]
|
|
|
|
mean value: 0.6869047619047619
|
|
|
|
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: 0.82
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.00941038 0.00976324 0.00924373 0.00916433 0.00904441 0.00874352
|
|
0.00868464 0.00868464 0.00975919 0.00865602]
|
|
|
|
mean value: 0.00911540985107422
|
|
|
|
key: score_time
|
|
value: [0.00924158 0.00930309 0.00881243 0.00875664 0.00948048 0.00849533
|
|
0.00843406 0.00846982 0.00866628 0.00851464]
|
|
|
|
mean value: 0.008817434310913086
|
|
|
|
key: test_mcc
|
|
value: [-0.07142857 0.09759001 0.38575837 0.38095238 0.50709255 -0.05143445
|
|
-0.22537447 -0.09759001 0.16903085 0.50709255]
|
|
|
|
mean value: 0.1601689223133994
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.46153846 0.53846154 0.69230769 0.69230769 0.69230769 0.46153846
|
|
0.38461538 0.46153846 0.58333333 0.75 ]
|
|
|
|
mean value: 0.5717948717948718
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.46153846 0.57142857 0.6 0.66666667 0.6 0.36363636
|
|
0.2 0.53333333 0.54545455 0.72727273]
|
|
|
|
mean value: 0.526933066933067
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.42857143 0.5 0.75 0.66666667 1. 0.5
|
|
0.33333333 0.5 0.6 0.8 ]
|
|
|
|
mean value: 0.6078571428571429
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.5 0.66666667 0.5 0.66666667 0.42857143 0.28571429
|
|
0.14285714 0.57142857 0.5 0.66666667]
|
|
|
|
mean value: 0.4928571428571428
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.46428571 0.54761905 0.67857143 0.69047619 0.71428571 0.47619048
|
|
0.4047619 0.45238095 0.58333333 0.75 ]
|
|
|
|
mean value: 0.5761904761904763
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.3 0.4 0.42857143 0.5 0.42857143 0.22222222
|
|
0.11111111 0.36363636 0.375 0.57142857]
|
|
|
|
mean value: 0.3700541125541125
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.28
|
|
|
|
Accuracy on Blind test: 0.66
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.08392501 1.12183738 1.07715893 1.09046221 1.09416127 1.07969999
|
|
1.0809691 1.09054375 1.16435218 1.1308887 ]
|
|
|
|
mean value: 1.1013998508453369
|
|
|
|
key: score_time
|
|
value: [0.09405518 0.09530878 0.08752489 0.08691955 0.09251165 0.08721852
|
|
0.09045005 0.08988142 0.09494495 0.14808369]
|
|
|
|
mean value: 0.09668986797332764
|
|
|
|
key: test_mcc
|
|
value: [0.85391256 0.85391256 0.54761905 1. 0.85714286 0.69047619
|
|
0.73192505 0.28288947 1. 1. ]
|
|
|
|
mean value: 0.781787775253993
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.92307692 0.92307692 0.76923077 1. 0.92307692 0.84615385
|
|
0.84615385 0.61538462 1. 1. ]
|
|
|
|
mean value: 0.8846153846153846
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.90909091 0.90909091 0.76923077 1. 0.92307692 0.85714286
|
|
0.83333333 0.54545455 1. 1. ]
|
|
|
|
mean value: 0.8746420246420246
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.71428571 1. 1. 0.85714286
|
|
1. 0.75 1. 1. ]
|
|
|
|
mean value: 0.9321428571428572
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.83333333 0.83333333 1. 0.85714286 0.85714286
|
|
0.71428571 0.42857143 1. 1. ]
|
|
|
|
mean value: 0.8357142857142857
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.91666667 0.91666667 0.77380952 1. 0.92857143 0.8452381
|
|
0.85714286 0.63095238 1. 1. ]
|
|
|
|
mean value: 0.886904761904762
|
|
|
|
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 0.83333333 0.625 1. 0.85714286 0.75
|
|
0.71428571 0.375 1. 1. ]
|
|
|
|
mean value: 0.7988095238095239
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.77
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000...05', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.85078669 0.89104939 0.92695355 0.86620474 0.89045572 0.85404968
|
|
0.94689822 0.90455604 0.87475681 0.832757 ]
|
|
|
|
mean value: 0.8838467836380005
|
|
|
|
key: score_time
|
|
value: [0.15100479 0.22465754 0.24103928 0.15397239 0.23011994 0.21453023
|
|
0.1931324 0.19848132 0.17958975 0.21422601]
|
|
|
|
mean value: 0.200075364112854
|
|
|
|
key: test_mcc
|
|
value: [0.69047619 0.85391256 0.54761905 1. 0.85714286 0.54761905
|
|
0.85714286 0.28288947 1. 1. ]
|
|
|
|
mean value: 0.7636802038760468
|
|
|
|
key: train_mcc
|
|
value: [0.98275345 0.96521476 1. 0.98275345 0.98275862 0.96521476
|
|
0.98275862 0.98275862 0.94841684 0.96551724]
|
|
|
|
mean value: 0.9758146361555415
|
|
|
|
key: test_accuracy
|
|
value: [0.84615385 0.92307692 0.76923077 1. 0.92307692 0.76923077
|
|
0.92307692 0.61538462 1. 1. ]
|
|
|
|
mean value: 0.8769230769230769
|
|
|
|
key: train_accuracy
|
|
value: [0.99130435 0.9826087 1. 0.99130435 0.99130435 0.9826087
|
|
0.99130435 0.99130435 0.97413793 0.98275862]
|
|
|
|
mean value: 0.987863568215892
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 0.90909091 0.76923077 1. 0.92307692 0.76923077
|
|
0.92307692 0.54545455 1. 1. ]
|
|
|
|
mean value: 0.8672494172494172
|
|
|
|
key: train_fscore
|
|
value: [0.99145299 0.98275862 1. 0.99145299 0.99130435 0.98245614
|
|
0.99130435 0.99130435 0.97435897 0.98275862]
|
|
|
|
mean value: 0.9879151382473406
|
|
|
|
key: test_precision
|
|
value: [0.83333333 1. 0.71428571 1. 1. 0.83333333
|
|
1. 0.75 1. 1. ]
|
|
|
|
mean value: /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(
|
|
0.9130952380952381
|
|
|
|
key: train_precision
|
|
value: [0.98305085 0.98275862 1. 0.98305085 0.98275862 0.98245614
|
|
0.98275862 0.98275862 0.96610169 0.98275862]
|
|
|
|
mean value: 0.9828452633629662
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.83333333 0.83333333 1. 0.85714286 0.71428571
|
|
0.85714286 0.42857143 1. 1. ]
|
|
|
|
mean value: 0.8357142857142857
|
|
|
|
key: train_recall
|
|
value: [1. 0.98275862 1. 1. 1. 0.98245614
|
|
1. 1. 0.98275862 0.98275862]
|
|
|
|
mean value: 0.9930732002419842
|
|
|
|
key: test_roc_auc
|
|
value: [0.8452381 0.91666667 0.77380952 1. 0.92857143 0.77380952
|
|
0.92857143 0.63095238 1. 1. ]
|
|
|
|
mean value: 0.8797619047619049
|
|
|
|
key: train_roc_auc
|
|
value: [0.99122807 0.98260738 1. 0.99122807 0.99137931 0.98260738
|
|
0.99137931 0.99137931 0.97413793 0.98275862]
|
|
|
|
mean value: 0.9878705384150029
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 0.83333333 0.625 1. 0.85714286 0.625
|
|
0.85714286 0.375 1. 1. ]
|
|
|
|
mean value: 0.7886904761904762
|
|
|
|
key: train_jcc
|
|
value: [0.98305085 0.96610169 1. 0.98305085 0.98275862 0.96551724
|
|
0.98275862 0.98275862 0.95 0.96610169]
|
|
|
|
mean value: 0.9762098188194038
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.0233314 0.00888824 0.0088563 0.00979137 0.00896597 0.00866175
|
|
0.0086174 0.00890756 0.00927162 0.00887132]
|
|
|
|
mean value: 0.010416293144226074
|
|
|
|
key: score_time
|
|
value: [0.01118445 0.00862479 0.00877213 0.00939393 0.00836325 0.0084722
|
|
0.00883579 0.00862408 0.00886917 0.00878406]
|
|
|
|
mean value: 0.008992385864257813
|
|
|
|
key: test_mcc
|
|
value: [0.54761905 0.21957752 0.23809524 0.7200823 0.54761905 0.09759001
|
|
0.50709255 0.09759001 0. 0.33333333]
|
|
|
|
mean value: 0.3308599050329999
|
|
|
|
key: train_mcc
|
|
value: [0.70722413 0.63989131 0.72363756 0.60255132 0.65541674 0.66173728
|
|
0.6354556 0.67183925 0.62667956 0.60570315]
|
|
|
|
mean value: 0.6530135892935511
|
|
|
|
key: test_accuracy
|
|
value: [0.76923077 0.61538462 0.61538462 0.84615385 0.76923077 0.53846154
|
|
0.69230769 0.53846154 0.5 0.66666667]
|
|
|
|
mean value: 0.6551282051282051
|
|
|
|
key: train_accuracy
|
|
value: [0.85217391 0.8173913 0.86086957 0.8 0.82608696 0.82608696
|
|
0.8173913 0.83478261 0.81034483 0.80172414]
|
|
|
|
mean value: 0.8246851574212893
|
|
|
|
key: test_fscore
|
|
value: [0.76923077 0.54545455 0.61538462 0.8 0.76923077 0.5
|
|
0.6 0.5 0.25 0.66666667]
|
|
|
|
mean value: 0.6015967365967365
|
|
|
|
key: train_fscore
|
|
value: [0.84684685 0.80733945 0.85714286 0.79279279 0.81481481 0.80769231
|
|
0.81081081 0.82568807 0.7962963 0.79279279]
|
|
|
|
mean value: 0.8152217042125299
|
|
|
|
key: test_precision
|
|
value: [0.71428571 0.6 0.57142857 1. 0.83333333 0.6
|
|
1. 0.6 0.5 0.66666667]
|
|
|
|
mean value: 0.7085714285714285
|
|
|
|
key: train_precision
|
|
value: [0.88679245 0.8627451 0.88888889 0.83018868 0.8627451 0.89361702
|
|
0.83333333 0.86538462 0.86 0.83018868]
|
|
|
|
mean value: 0.861388386628262
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.5 0.66666667 0.66666667 0.71428571 0.42857143
|
|
0.42857143 0.42857143 0.16666667 0.66666667]
|
|
|
|
mean value: 0.5499999999999999
|
|
|
|
key: train_recall
|
|
value: [0.81034483 0.75862069 0.82758621 0.75862069 0.77192982 0.73684211
|
|
0.78947368 0.78947368 0.74137931 0.75862069]
|
|
|
|
mean value: 0.7742891712038718
|
|
|
|
key: test_roc_auc
|
|
value: [0.77380952 0.60714286 0.61904762 0.83333333 0.77380952 0.54761905
|
|
0.71428571 0.54761905 0.5 0.66666667]
|
|
|
|
mean value: 0.6583333333333333
|
|
|
|
key: train_roc_auc
|
|
value: [0.85254083 0.81790684 0.86116152 0.80036298 0.82562008 0.8253176
|
|
0.81715064 0.83439201 0.81034483 0.80172414]
|
|
|
|
mean value: 0.8246521476104053
|
|
|
|
key: test_jcc
|
|
value: [0.625 0.375 0.44444444 0.66666667 0.625 0.33333333
|
|
0.42857143 0.33333333 0.14285714 0.5 ]
|
|
|
|
mean value: 0.4474206349206349
|
|
|
|
key: train_jcc
|
|
value: [0.734375 0.67692308 0.75 0.65671642 0.6875 0.67741935
|
|
0.68181818 0.703125 0.66153846 0.65671642]
|
|
|
|
mean value: 0.6886131910939326
|
|
|
|
MCC on Blind test: 0.36
|
|
|
|
Accuracy on Blind test: 0.75
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'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: [0.08384514 0.0381968 0.03783607 0.04650593 0.05221581 0.04448318
|
|
0.04230928 0.0424881 0.04949498 0.04466009]
|
|
|
|
mean value: 0.048203539848327634
|
|
|
|
key: score_time
|
|
value: [0.01125002 0.01158834 0.01091051 0.01122379 0.01046062 0.01033902
|
|
0.01011562 0.01050091 0.01127529 0.01067138]
|
|
|
|
mean value: 0.010833549499511718
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.85714286 1. 0.85714286 0.69047619
|
|
0.85391256 0.85714286 1. 1. ]
|
|
|
|
mean value: 0.9115817325734729
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.92307692 1. 0.92307692 0.84615385
|
|
0.92307692 0.92307692 1. 1. ]
|
|
|
|
mean value: 0.9538461538461539
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.92307692 1. 0.92307692 0.85714286
|
|
0.93333333 0.92307692 1. 1. ]
|
|
|
|
mean value: 0.955970695970696
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.85714286 1. 1. 0.85714286
|
|
0.875 1. 1. 1. ]
|
|
|
|
mean value: 0.9589285714285715
|
|
|
|
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. 0.85714286 0.85714286
|
|
1. 0.85714286 1. 1. ]
|
|
|
|
mean value: 0.9571428571428571
|
|
|
|
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. 0.92857143 1. 0.92857143 0.8452381
|
|
0.91666667 0.92857143 1. 1. ]
|
|
|
|
mean value: 0.9547619047619048
|
|
|
|
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. 0.85714286 1. 0.85714286 0.75
|
|
0.875 0.85714286 1. 1. ]
|
|
|
|
mean value: 0.9196428571428571
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.84
|
|
|
|
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: /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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02836633 0.04502583 0.04571962 0.04593706 0.04734015 0.04650164
|
|
0.04553771 0.04560113 0.0467062 0.04733253]
|
|
|
|
mean value: 0.0444068193435669
|
|
|
|
key: score_time
|
|
value: [0.02347183 0.02313876 0.02329445 0.02252793 0.02254844 0.02021003
|
|
0.02292895 0.02178693 0.01712394 0.02160978]
|
|
|
|
mean value: 0.021864104270935058
|
|
|
|
key: test_mcc
|
|
value: [-0.23809524 0.09759001 0.07142857 0.53674504 -0.23809524 -0.28288947
|
|
-0.23809524 -0.05143445 0.35355339 0. ]
|
|
|
|
mean value: 0.0010707370234811727
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.38461538 0.53846154 0.53846154 0.76923077 0.38461538 0.38461538
|
|
0.38461538 0.46153846 0.66666667 0.5 ]
|
|
|
|
mean value: 0.5012820512820513
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.33333333 0.57142857 0.5 0.72727273 0.42857143 0.5
|
|
0.42857143 0.36363636 0.71428571 0. ]
|
|
|
|
mean value: 0.45670995670995673
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.33333333 0.5 0.5 0.8 0.42857143 0.44444444
|
|
0.42857143 0.5 0.625 0. ]
|
|
|
|
mean value: 0.4559920634920635
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.33333333 0.66666667 0.5 0.66666667 0.42857143 0.57142857
|
|
0.42857143 0.28571429 0.83333333 0. ]
|
|
|
|
mean value: 0.4714285714285714
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.38095238 0.54761905 0.53571429 0.76190476 0.38095238 0.36904762
|
|
0.38095238 0.47619048 0.66666667 0.5 ]
|
|
|
|
mean value: 0.5
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.2 0.4 0.33333333 0.57142857 0.27272727 0.33333333
|
|
0.27272727 0.22222222 0.55555556 0. ]
|
|
|
|
mean value: 0.31613275613275615
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.29
|
|
|
|
Accuracy on Blind test: 0.7
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02023911 0.00888801 0.00882196 0.00845432 0.00848579 0.00847077
|
|
0.00843596 0.00848818 0.00840211 0.0085299 ]
|
|
|
|
mean value: 0.009721612930297852
|
|
|
|
key: score_time
|
|
value: [0.01174545 0.00873327 0.00836468 0.00834036 0.00851059 0.00834084
|
|
0.0083468 0.00833607 0.00833488 0.0084765 ]
|
|
|
|
mean value: 0.008752942085266113
|
|
|
|
key: test_mcc
|
|
value: [0.54761905 0.69047619 0.41475753 1. 0.69047619 0.38095238
|
|
0.85714286 0.41475753 0.50709255 0.57735027]
|
|
|
|
mean value: 0.6080624550699656
|
|
|
|
key: train_mcc
|
|
value: [0.67183925 0.65214761 0.68725429 0.65352243 0.65603842 0.74023645
|
|
0.68878902 0.65264753 0.69006556 0.69130113]
|
|
|
|
mean value: 0.6783841689212754
|
|
|
|
key: test_accuracy
|
|
value: [0.76923077 0.84615385 0.69230769 1. 0.84615385 0.69230769
|
|
0.92307692 0.69230769 0.75 0.75 ]
|
|
|
|
mean value: 0.7961538461538462
|
|
|
|
key: train_accuracy
|
|
value: [0.83478261 0.82608696 0.84347826 0.82608696 0.82608696 0.86956522
|
|
0.84347826 0.82608696 0.84482759 0.84482759]
|
|
|
|
mean value: 0.8385307346326837
|
|
|
|
key: test_fscore
|
|
value: [0.76923077 0.83333333 0.71428571 1. 0.85714286 0.71428571
|
|
0.92307692 0.66666667 0.72727273 0.8 ]
|
|
|
|
mean value: 0.8005294705294705
|
|
|
|
key: train_fscore
|
|
value: [0.84297521 0.82758621 0.84745763 0.83333333 0.83333333 0.87179487
|
|
0.84745763 0.82758621 0.84745763 0.85 ]
|
|
|
|
mean value: 0.8428982040222144
|
|
|
|
key: test_precision
|
|
value: [0.71428571 0.83333333 0.625 1. 0.85714286 0.71428571
|
|
1. 0.8 0.8 0.66666667]
|
|
|
|
mean value: 0.8010714285714285
|
|
|
|
key: train_precision
|
|
value: [0.80952381 0.82758621 0.83333333 0.80645161 0.79365079 0.85
|
|
0.81967213 0.81355932 0.83333333 0.82258065]
|
|
|
|
mean value: 0.8209691187983778
|
|
|
|
key: test_recall
|
|
value: [0.83333333 0.83333333 0.83333333 1. 0.85714286 0.71428571
|
|
0.85714286 0.57142857 0.66666667 1. ]
|
|
|
|
mean value: 0.8166666666666667
|
|
|
|
key: train_recall
|
|
value: [0.87931034 0.82758621 0.86206897 0.86206897 0.87719298 0.89473684
|
|
0.87719298 0.84210526 0.86206897 0.87931034]
|
|
|
|
mean value: 0.8663641863278887
|
|
|
|
key: test_roc_auc
|
|
value: [0.77380952 0.8452381 0.70238095 1. 0.8452381 0.69047619
|
|
0.92857143 0.70238095 0.75 0.75 ]
|
|
|
|
mean value: 0.7988095238095239
|
|
|
|
key: train_roc_auc
|
|
value: [0.83439201 0.82607381 0.84331518 0.82577132 0.82652753 0.86978221
|
|
0.84376891 0.82622505 0.84482759 0.84482759]
|
|
|
|
mean value: 0.8385511191772534
|
|
|
|
key: test_jcc
|
|
value: [0.625 0.71428571 0.55555556 1. 0.75 0.55555556
|
|
0.85714286 0.5 0.57142857 0.66666667]
|
|
|
|
mean value: 0.6795634920634921
|
|
|
|
key: train_jcc
|
|
value: [0.72857143 0.70588235 0.73529412 0.71428571 0.71428571 0.77272727
|
|
0.73529412 0.70588235 0.73529412 0.73913043]
|
|
|
|
mean value: 0.7286647623476268
|
|
|
|
MCC on Blind test: 0.54
|
|
|
|
Accuracy on Blind test: 0.8
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01005077 0.01331925 0.01500654 0.0135138 0.01394367 0.01668572
|
|
0.01392817 0.01403165 0.01488256 0.01436186]
|
|
|
|
mean value: 0.01397240161895752
|
|
|
|
key: score_time
|
|
value: [0.0085218 0.01149607 0.01154041 0.01155686 0.01167226 0.01140022
|
|
0.01124787 0.01124716 0.01127458 0.0112884 ]
|
|
|
|
mean value: 0.011124563217163087
|
|
|
|
key: test_mcc
|
|
value: [0.69047619 1. 0.23809524 1. 0.69047619 0.59160798
|
|
0.73192505 0.38095238 0.66666667 1. ]
|
|
|
|
mean value: 0.6990199699688028
|
|
|
|
key: train_mcc
|
|
value: [0.96521476 0.96578908 0.98275862 0.96521476 0.96578908 1.
|
|
1. 1. 0.98290472 1. ]
|
|
|
|
mean value: 0.9827671016628527
|
|
|
|
key: test_accuracy
|
|
value: [0.84615385 1. 0.61538462 1. 0.84615385 0.76923077
|
|
0.84615385 0.69230769 0.83333333 1. ]
|
|
|
|
mean value: 0.8448717948717949
|
|
|
|
key: train_accuracy
|
|
value: [0.9826087 0.9826087 0.99130435 0.9826087 0.9826087 1.
|
|
1. 1. 0.99137931 1. ]
|
|
|
|
mean value: 0.991311844077961
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 1. 0.61538462 1. 0.85714286 0.82352941
|
|
0.83333333 0.71428571 0.83333333 1. ]
|
|
|
|
mean value: 0.8510342598577892
|
|
|
|
key: train_fscore
|
|
value: [0.98275862 0.98305085 0.99130435 0.98275862 0.98214286 1.
|
|
1. 1. 0.99130435 1. ]
|
|
|
|
mean value: 0.9913319641631968
|
|
|
|
key: test_precision
|
|
value: [0.83333333 1. 0.57142857 1. 0.85714286 0.7
|
|
1. 0.71428571 0.83333333 1. ]
|
|
|
|
mean value: 0.8509523809523809
|
|
|
|
key: train_precision
|
|
value: [0.98275862 0.96666667 1. 0.98275862 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9932183908045977
|
|
|
|
key: test_recall
|
|
value: [0.83333333 1. 0.66666667 1. 0.85714286 1.
|
|
0.71428571 0.71428571 0.83333333 1. ]
|
|
|
|
mean value: 0.861904761904762
|
|
|
|
key: train_recall
|
|
value: [0.98275862 1. 0.98275862 0.98275862 0.96491228 1.
|
|
1. 1. 0.98275862 1. ]
|
|
|
|
mean value: 0.9895946763460375
|
|
|
|
key: test_roc_auc
|
|
value: [0.8452381 1. 0.61904762 1. 0.8452381 0.75
|
|
0.85714286 0.69047619 0.83333333 1. ]
|
|
|
|
mean value: 0.844047619047619
|
|
|
|
key: train_roc_auc
|
|
value: [0.98260738 0.98245614 0.99137931 0.98260738 0.98245614 1.
|
|
1. 1. 0.99137931 1. ]
|
|
|
|
mean value: 0.9912885662431942
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 1. 0.44444444 1. 0.75 0.7
|
|
0.71428571 0.55555556 0.71428571 1. ]
|
|
|
|
mean value: 0.7592857142857143
|
|
|
|
key: train_jcc
|
|
value: [0.96610169 0.96666667 0.98275862 0.96610169 0.96491228 1.
|
|
1. 1. 0.98275862 1. ]
|
|
|
|
mean value: 0.982929957857824
|
|
|
|
MCC on Blind test: 0.57
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01256061 0.0125916 0.01268959 0.01258993 0.01242638 0.01272082
|
|
0.01294756 0.01275706 0.01278591 0.01278853]
|
|
|
|
mean value: 0.012685799598693847
|
|
|
|
key: score_time
|
|
value: [0.01131773 0.01125407 0.01127744 0.0112536 0.01128745 0.01124287
|
|
0.01123714 0.01124907 0.01120949 0.01123095]
|
|
|
|
mean value: 0.011255979537963867
|
|
|
|
key: test_mcc
|
|
value: [0.41475753 1. 0.23809524 1. 0.69047619 0.46056619
|
|
0.6172134 0.46056619 0.84515425 1. ]
|
|
|
|
mean value: 0.6726828987095116
|
|
|
|
key: train_mcc
|
|
value: [0.65354202 0.98275345 0.96580942 0.94909248 0.94909248 0.83908633
|
|
1. 0.69641781 1. 0.96609178]
|
|
|
|
mean value: 0.90018857756883
|
|
|
|
key: test_accuracy
|
|
value: [0.69230769 1. 0.61538462 1. 0.84615385 0.69230769
|
|
0.76923077 0.69230769 0.91666667 1. ]
|
|
|
|
mean value: 0.8224358974358974
|
|
|
|
key: train_accuracy
|
|
value: [0.8 0.99130435 0.9826087 0.97391304 0.97391304 0.91304348
|
|
1. 0.82608696 1. 0.98275862]
|
|
|
|
mean value: 0.9443628185907047
|
|
|
|
key: test_fscore
|
|
value: [0.71428571 1. 0.61538462 1. 0.85714286 0.77777778
|
|
0.72727273 0.77777778 0.92307692 1. ]
|
|
|
|
mean value: 0.8392718392718392
|
|
|
|
key: train_fscore
|
|
value: [0.83453237 0.99145299 0.98245614 0.97478992 0.97297297 0.91935484
|
|
1. 0.85074627 1. 0.98245614]
|
|
|
|
mean value: 0.9508761642561219
|
|
|
|
key: test_precision
|
|
value: [0.625 1. 0.57142857 1. 0.85714286 0.63636364
|
|
1. 0.63636364 0.85714286 1. ]
|
|
|
|
mean value: 0.8183441558441559
|
|
|
|
key: train_precision
|
|
value: [0.71604938 0.98305085 1. 0.95081967 1. 0.85074627
|
|
1. 0.74025974 1. 1. ]
|
|
|
|
mean value: 0.924092591122128
|
|
|
|
key: test_recall
|
|
value: [0.83333333 1. 0.66666667 1. 0.85714286 1.
|
|
0.57142857 1. 1. 1. ]
|
|
|
|
mean value: 0.8928571428571428
|
|
|
|
key: train_recall
|
|
value: [1. 1. 0.96551724 1. 0.94736842 1.
|
|
1. 1. 1. 0.96551724]
|
|
|
|
mean value: 0.9878402903811252
|
|
|
|
key: test_roc_auc
|
|
value: [0.70238095 1. 0.61904762 1. 0.8452381 0.66666667
|
|
0.78571429 0.66666667 0.91666667 1. ]
|
|
|
|
mean value: 0.8202380952380952
|
|
|
|
key: train_roc_auc
|
|
value: [0.79824561 0.99122807 0.98275862 0.97368421 0.97368421 0.9137931
|
|
1. 0.82758621 1. 0.98275862]
|
|
|
|
mean value: 0.9443738656987296
|
|
|
|
key: test_jcc
|
|
value: [0.55555556 1. 0.44444444 1. 0.75 0.63636364
|
|
0.57142857 0.63636364 0.85714286 1. ]
|
|
|
|
mean value: 0.7451298701298701
|
|
|
|
key: train_jcc
|
|
value: [0.71604938 0.98305085 0.96551724 0.95081967 0.94736842 0.85074627
|
|
1. 0.74025974 1. 0.96551724]
|
|
|
|
mean value: 0.9119328815032532
|
|
|
|
MCC on Blind test: 0.6
|
|
|
|
Accuracy on Blind test: 0.86
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.10978818 0.0888536 0.08917451 0.08824492 0.08961439 0.08953667
|
|
0.0876596 0.08931637 0.08974218 0.0894413 ]
|
|
|
|
mean value: 0.09113717079162598
|
|
|
|
key: score_time
|
|
value: [0.01434731 0.01432204 0.01435041 0.01434278 0.01452613 0.01458097
|
|
0.01449966 0.01477194 0.01456094 0.01462173]
|
|
|
|
mean value: 0.014492392539978027
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.85714286 1. 0.85714286 0.69047619
|
|
0.85391256 0.85714286 1. 1. ]
|
|
|
|
mean value: 0.9115817325734729
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.92307692 1. 0.92307692 0.84615385
|
|
0.92307692 0.92307692 1. 1. ]
|
|
|
|
mean value: 0.9538461538461539
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.92307692 1. 0.92307692 0.85714286
|
|
0.93333333 0.92307692 1. 1. ]
|
|
|
|
mean value: 0.955970695970696
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.85714286 1. 1. 0.85714286
|
|
0.875 1. 1. 1. ]
|
|
|
|
mean value: 0.9589285714285715
|
|
|
|
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. 0.85714286 0.85714286
|
|
1. 0.85714286 1. 1. ]
|
|
|
|
mean value: 0.9571428571428571
|
|
|
|
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. 0.92857143 1. 0.92857143 0.8452381
|
|
0.91666667 0.92857143 1. 1. ]
|
|
|
|
mean value: 0.9547619047619048
|
|
|
|
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. 0.85714286 1. 0.85714286 0.75
|
|
0.875 0.85714286 1. 1. ]
|
|
|
|
mean value: 0.9196428571428571
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.77
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03722787 0.03666306 0.04423785 0.04910994 0.0469203 0.03398895
|
|
0.05052757 0.04784632 0.04474521 0.03417397]
|
|
|
|
mean value: 0.042544102668762206
|
|
|
|
key: score_time
|
|
value: [0.02255177 0.03727555 0.02196121 0.03718948 0.0280652 0.03217888
|
|
0.0372963 0.0358758 0.02540016 0.02633619]
|
|
|
|
mean value: 0.030413055419921876
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.85714286 0.85391256 0.85714286 0.69047619
|
|
0.41475753 0.85714286 1. 0.84515425]
|
|
|
|
mean value: 0.8375729111466371
|
|
|
|
key: train_mcc
|
|
value: [1. 0.98275862 0.96580942 0.98275862 0.98275345 0.98275345
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9896833563154478
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.92307692 0.92307692 0.92307692 0.84615385
|
|
0.69230769 0.92307692 1. 0.91666667]
|
|
|
|
mean value: 0.9147435897435897
|
|
|
|
key: train_accuracy
|
|
value: [1. 0.99130435 0.9826087 0.99130435 0.99130435 0.99130435
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9947826086956522
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.92307692 0.90909091 0.92307692 0.85714286
|
|
0.66666667 0.92307692 1. 0.90909091]
|
|
|
|
mean value: 0.911122211122211
|
|
|
|
key: train_fscore
|
|
value: [1. 0.99130435 0.98245614 0.99130435 0.99115044 0.99115044
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9947365720958803
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.85714286 1. 1. 0.85714286
|
|
0.8 1. 1. 1. ]
|
|
|
|
mean value: 0.9514285714285714
|
|
|
|
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. 0.83333333 0.85714286 0.85714286
|
|
0.57142857 0.85714286 1. 0.83333333]
|
|
|
|
mean value: 0.8809523809523809
|
|
|
|
key: train_recall
|
|
value: [1. 0.98275862 0.96551724 0.98275862 0.98245614 0.98245614
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9895946763460375
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 0.92857143 0.91666667 0.92857143 0.8452381
|
|
0.70238095 0.92857143 1. 0.91666667]
|
|
|
|
mean value: 0.9166666666666667
|
|
|
|
key: train_roc_auc
|
|
value: [1. 0.99137931 0.98275862 0.99137931 0.99122807 0.99122807
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9947973381730187
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 0.85714286 0.83333333 0.85714286 0.75
|
|
0.5 0.85714286 1. 0.83333333]
|
|
|
|
mean value: 0.8488095238095238
|
|
|
|
key: train_jcc
|
|
value: [1. 0.98275862 0.96551724 0.98275862 0.98245614 0.98245614
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9895946763460375
|
|
|
|
MCC on Blind test: 0.87
|
|
|
|
Accuracy on Blind test: 0.95
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03394532 0.04183817 0.04181433 0.01808524 0.01776004 0.01770258
|
|
0.04135323 0.04181385 0.0413518 0.04163599]
|
|
|
|
mean value: 0.033730053901672365
|
|
|
|
key: score_time
|
|
value: [0.02100396 0.02063131 0.02093244 0.01198602 0.01199174 0.01195073
|
|
0.02184963 0.02145576 0.02225876 0.02242255]
|
|
|
|
mean value: 0.018648290634155275
|
|
|
|
key: test_mcc
|
|
value: [ 0.21957752 0.21957752 0.05143445 0.38095238 0.6172134 -0.38095238
|
|
0.6172134 0.09759001 0.33333333 0.16903085]
|
|
|
|
mean value: 0.23249704740848293
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.61538462 0.61538462 0.53846154 0.69230769 0.76923077 0.30769231
|
|
0.76923077 0.53846154 0.66666667 0.58333333]
|
|
|
|
mean value: 0.6096153846153847
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.54545455 0.54545455 0.4 0.66666667 0.72727273 0.30769231
|
|
0.72727273 0.5 0.66666667 0.61538462]
|
|
|
|
mean value: 0.5701864801864802
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.6 0.6 0.5 0.66666667 1. 0.33333333
|
|
1. 0.6 0.66666667 0.57142857]
|
|
|
|
mean value: 0.6538095238095238
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.5 0.5 0.33333333 0.66666667 0.57142857 0.28571429
|
|
0.57142857 0.42857143 0.66666667 0.66666667]
|
|
|
|
mean value: 0.519047619047619
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.60714286 0.60714286 0.52380952 0.69047619 0.78571429 0.30952381
|
|
0.78571429 0.54761905 0.66666667 0.58333333]
|
|
|
|
mean value: 0.6107142857142857
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.375 0.375 0.25 0.5 0.57142857 0.18181818
|
|
0.57142857 0.33333333 0.5 0.44444444]
|
|
|
|
mean value: 0.41024531024531025
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.15
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.2526629 0.21842432 0.17766285 0.21489167 0.21150613 0.21513367
|
|
0.23505592 0.24541807 0.25272918 0.24624586]
|
|
|
|
mean value: 0.2269730567932129
|
|
|
|
key: score_time
|
|
value: [0.00917435 0.00882459 0.0093894 0.00901055 0.0092473 0.00960231
|
|
0.00897694 0.0090704 0.00971723 0.00938821]
|
|
|
|
mean value: 0.009240126609802246
|
|
|
|
key: test_mcc
|
|
value: [0.69047619 1. 0.85714286 0.7200823 0.85714286 0.69047619
|
|
0.6172134 0.85714286 1. 0.84515425]
|
|
|
|
mean value: 0.8134830906780932
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.84615385 1. 0.92307692 0.84615385 0.92307692 0.84615385
|
|
0.76923077 0.92307692 1. 0.91666667]
|
|
|
|
mean value: 0.8993589743589744
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 1. 0.92307692 0.8 0.92307692 0.85714286
|
|
0.72727273 0.92307692 1. 0.90909091]
|
|
|
|
mean value: 0.8896070596070595
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.83333333 1. 0.85714286 1. 1. 0.85714286
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9547619047619047
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.83333333 1. 1. 0.66666667 0.85714286 0.85714286
|
|
0.57142857 0.85714286 1. 0.83333333]
|
|
|
|
mean value: 0.8476190476190476
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.8452381 1. 0.92857143 0.83333333 0.92857143 0.8452381
|
|
0.78571429 0.92857143 1. 0.91666667]
|
|
|
|
mean value: 0.9011904761904762
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 1. 0.85714286 0.66666667 0.85714286 0.75
|
|
0.57142857 0.85714286 1. 0.83333333]
|
|
|
|
mean value: 0.8107142857142857
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.81
|
|
|
|
Accuracy on Blind test: 0.93
|
|
|
|
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")
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01597977 0.01589251 0.01919055 0.0156846 0.0159266 0.03238654
|
|
0.015728 0.01596689 0.01582837 0.01635146]
|
|
|
|
mean value: 0.017893528938293456
|
|
|
|
key: score_time
|
|
value: [0.01175785 0.01177335 0.01175261 0.01169562 0.01170611 0.01192379
|
|
0.011729 0.0116961 0.01449633 0.01262498]
|
|
|
|
mean value: 0.012115573883056641
|
|
|
|
key: test_mcc
|
|
value: [-0.39477102 0.38575837 0.41475753 0.41475753 0.6172134 0.07142857
|
|
0.28288947 0.38095238 0. 0. ]
|
|
|
|
mean value: 0.21729862470954434
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.38461538 0.69230769 0.69230769 0.69230769 0.76923077 0.53846154
|
|
0.61538462 0.69230769 0.5 0.5 ]
|
|
|
|
mean value: 0.6076923076923076
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0. 0.6 0.71428571 0.71428571 0.72727273 0.57142857
|
|
0.54545455 0.71428571 0.5 0.25 ]
|
|
|
|
mean value: 0.5337012987012987
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0. 0.75 0.625 0.625 1. 0.57142857
|
|
0.75 0.71428571 0.5 0.5 ]
|
|
|
|
mean value: 0.6035714285714285
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0. 0.5 0.83333333 0.83333333 0.57142857 0.57142857
|
|
0.42857143 0.71428571 0.5 0.16666667]
|
|
|
|
mean value: 0.5119047619047619
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.35714286 0.67857143 0.70238095 0.70238095 0.78571429 0.53571429
|
|
0.63095238 0.69047619 0.5 0.5 ]
|
|
|
|
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. 0.42857143 0.55555556 0.55555556 0.57142857 0.4
|
|
0.375 0.55555556 0.33333333 0.14285714]
|
|
|
|
mean value: 0.3917857142857143
|
|
|
|
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: 0.69
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02921104 0.03584313 0.03252697 0.03251433 0.03238583 0.03220725
|
|
0.03238225 0.03236103 0.0324204 0.03242779]
|
|
|
|
mean value: 0.03242800235748291
|
|
|
|
key: score_time
|
|
value: [0.0210228 0.02015209 0.02146673 0.02286077 0.01991081 0.02133226
|
|
0.02285671 0.02036667 0.01795983 0.01158285]
|
|
|
|
mean value: 0.01995115280151367
|
|
|
|
key: test_mcc
|
|
value: [0.85391256 1. 0.23809524 0.85391256 0.69047619 0.53674504
|
|
0.85714286 0.69047619 0.84515425 1. ]
|
|
|
|
mean value: 0.7565914898700619
|
|
|
|
key: train_mcc
|
|
value: [0.96578908 1. 1. 1. 0.98275862 1.
|
|
0.98275862 0.98275862 0.98290472 0.98290472]
|
|
|
|
mean value: 0.9879874383818003
|
|
|
|
key: test_accuracy
|
|
value: [0.92307692 1. 0.61538462 0.92307692 0.84615385 0.76923077
|
|
0.92307692 0.84615385 0.91666667 1. ]
|
|
|
|
mean value: 0.8762820512820513
|
|
|
|
key: train_accuracy
|
|
value: [0.9826087 1. 1. 1. 0.99130435 1.
|
|
0.99130435 0.99130435 0.99137931 0.99137931]
|
|
|
|
mean value: 0.9939280359820091
|
|
|
|
key: test_fscore
|
|
value: [0.90909091 1. 0.61538462 0.90909091 0.85714286 0.8
|
|
0.92307692 0.85714286 0.92307692 1. ]
|
|
|
|
mean value: 0.8794005994005993
|
|
|
|
key: train_fscore
|
|
value: [0.98305085 1. 1. 1. 0.99130435 1.
|
|
0.99130435 0.99130435 0.99145299 0.99145299]
|
|
|
|
mean value: 0.9939869873841871
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.57142857 1. 0.85714286 0.75
|
|
1. 0.85714286 0.85714286 1. ]
|
|
|
|
mean value: 0.8892857142857142
|
|
|
|
key: train_precision
|
|
value: [0.96666667 1. 1. 1. 0.98275862 1.
|
|
0.98275862 0.98275862 0.98305085 0.98305085]
|
|
|
|
mean value: 0.9881044223650887
|
|
|
|
key: test_recall
|
|
value: [0.83333333 1. 0.66666667 0.83333333 0.85714286 0.85714286
|
|
0.85714286 0.85714286 1. 1. ]
|
|
|
|
mean value: 0.8761904761904762
|
|
|
|
key: train_recall
|
|
value: /home/tanu/git/LSHTM_analysis/scripts/ml/./embb_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/./embb_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)
|
|
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.91666667 1. 0.61904762 0.91666667 0.8452381 0.76190476
|
|
0.92857143 0.8452381 0.91666667 1. ]
|
|
|
|
mean value: 0.875
|
|
|
|
key: train_roc_auc
|
|
value: [0.98245614 1. 1. 1. 0.99137931 1.
|
|
0.99137931 0.99137931 0.99137931 0.99137931]
|
|
|
|
mean value: 0.9939352692075014
|
|
|
|
key: test_jcc
|
|
value: [0.83333333 1. 0.44444444 0.83333333 0.75 0.66666667
|
|
0.85714286 0.75 0.85714286 1. ]
|
|
|
|
mean value: 0.7992063492063493
|
|
|
|
key: train_jcc
|
|
value: [0.96666667 1. 1. 1. 0.98275862 1.
|
|
0.98275862 0.98275862 0.98305085 0.98305085]
|
|
|
|
mean value: 0.9881044223650887
|
|
|
|
MCC on Blind test: 0.68
|
|
|
|
Accuracy on Blind test: 0.88
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.19426394 0.21456623 0.29082108 0.19818377 0.18314624 0.18398261
|
|
0.18422413 0.18269467 0.19156814 0.18524098]
|
|
|
|
mean value: 0.20086917877197266
|
|
|
|
key: score_time
|
|
value: [0.02032614 0.01979113 0.0323503 0.01989031 0.02298355 0.02142334
|
|
0.01958489 0.02317214 0.02198434 0.02293348]
|
|
|
|
mean value: 0.02244396209716797
|
|
|
|
key: test_mcc
|
|
value: [0.69047619 0.85714286 0.23809524 0.85391256 0.69047619 0.53674504
|
|
0.85714286 0.69047619 0.84515425 0.84515425]
|
|
|
|
mean value: 0.7104775637218217
|
|
|
|
key: train_mcc
|
|
value: [0.84454685 0.82607381 1. 1. 0.86085904 1.
|
|
0.98275862 0.98275862 0.86258195 0.8104653 ]
|
|
|
|
mean value: 0.917004418850212
|
|
|
|
key: test_accuracy
|
|
value: [0.84615385 0.92307692 0.61538462 0.92307692 0.84615385 0.76923077
|
|
0.92307692 0.84615385 0.91666667 0.91666667]
|
|
|
|
mean value: 0.8525641025641025
|
|
|
|
key: train_accuracy
|
|
value: [0.92173913 0.91304348 1. 1. 0.93043478 1.
|
|
0.99130435 0.99130435 0.93103448 0.90517241]
|
|
|
|
mean value: 0.9584032983508246
|
|
|
|
key: test_fscore
|
|
value: [0.83333333 0.92307692 0.61538462 0.90909091 0.85714286 0.8
|
|
0.92307692 0.85714286 0.92307692 0.92307692]
|
|
|
|
mean value: 0.8564402264402264
|
|
|
|
key: train_fscore
|
|
value: [0.92436975 0.9137931 1. 1. 0.92982456 1.
|
|
0.99130435 0.99130435 0.92982456 0.90598291]
|
|
|
|
mean value: 0.9586403575789533
|
|
|
|
key: test_precision
|
|
value: [0.83333333 0.85714286 0.57142857 1. 0.85714286 0.75
|
|
1. 0.85714286 0.85714286 0.85714286]
|
|
|
|
mean value: 0.844047619047619
|
|
|
|
key: train_precision
|
|
value: [0.90163934 0.9137931 1. 1. 0.92982456 1.
|
|
0.98275862 0.98275862 0.94642857 0.89830508]
|
|
|
|
mean value: 0.9555507906667724
|
|
|
|
key: test_recall
|
|
value: [0.83333333 1. 0.66666667 0.83333333 0.85714286 0.85714286
|
|
0.85714286 0.85714286 1. 1. ]
|
|
|
|
mean value: 0.8761904761904762
|
|
|
|
key: train_recall
|
|
value: [0.94827586 0.9137931 1. 1. 0.92982456 1.
|
|
1. 1. 0.9137931 0.9137931 ]
|
|
|
|
mean value: 0.9619479733817302
|
|
|
|
key: test_roc_auc
|
|
value: [0.8452381 0.92857143 0.61904762 0.91666667 0.8452381 0.76190476
|
|
0.92857143 0.8452381 0.91666667 0.91666667]
|
|
|
|
mean value: 0.8523809523809525
|
|
|
|
key: train_roc_auc
|
|
value: [0.92150635 0.9130369 1. 1. 0.93042952 1.
|
|
0.99137931 0.99137931 0.93103448 0.90517241]
|
|
|
|
mean value: 0.9583938294010889
|
|
|
|
key: test_jcc
|
|
value: [0.71428571 0.85714286 0.44444444 0.83333333 0.75 0.66666667
|
|
0.85714286 0.75 0.85714286 0.85714286]
|
|
|
|
mean value: 0.7587301587301587
|
|
|
|
key: train_jcc
|
|
value: [0.859375 0.84126984 1. 1. 0.86885246 1.
|
|
0.98275862 0.98275862 0.86885246 0.828125 ]
|
|
|
|
mean value: 0.9231992000681939
|
|
|
|
MCC on Blind test: 0.68
|
|
|
|
Accuracy on Blind test: 0.88
|
|
|
|
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(
|
|
[('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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.03565192 0.06346393 0.03620386 0.03337955 0.03851867 0.03506494
|
|
0.03530645 0.03576326 0.03483772 0.03537035]
|
|
|
|
mean value: 0.03835606575012207
|
|
|
|
key: score_time
|
|
value: [0.01240063 0.01168585 0.01392078 0.01166582 0.01392269 0.01418972
|
|
0.01411629 0.0143652 0.01440144 0.01440501]
|
|
|
|
mean value: 0.013507342338562012
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.9591663 0.84254172 0.95833333 0.84254172 0.84254172
|
|
0.8729597 1. 0.8047833 0.73387289]
|
|
|
|
mean value: 0.8815906981567883
|
|
|
|
key: train_mcc
|
|
value: [0.9584112 0.9584112 0.94369382 0.95850284 0.94950202 0.95399286
|
|
0.93449419 0.95851094 0.95851094 0.95851094]
|
|
|
|
mean value: 0.9532540960454174
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.97916667 0.91489362 0.9787234 0.91489362 0.91489362
|
|
0.93617021 1. 0.89361702 0.85106383]
|
|
|
|
mean value: 0.9362588652482269
|
|
|
|
key: train_accuracy
|
|
value: [0.97877358 0.97877358 0.97176471 0.97882353 0.97411765 0.97647059
|
|
0.96705882 0.97882353 0.97882353 0.97882353]
|
|
|
|
mean value: 0.9762253052164263
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.97959184 0.92 0.9787234 0.92 0.92
|
|
0.93877551 1. 0.90566038 0.87272727]
|
|
|
|
mean value: 0.9415070238014552
|
|
|
|
key: train_fscore
|
|
value: [0.97921478 0.97921478 0.97209302 0.97931034 0.97482838 0.97706422
|
|
0.96744186 0.97921478 0.97921478 0.97921478]
|
|
|
|
mean value: 0.9766811727020354
|
|
|
|
key: test_precision
|
|
value: [0.96 0.96 0.85185185 0.95833333 0.85185185 0.85185185
|
|
0.92 1. 0.82758621 0.77419355]
|
|
|
|
mean value: 0.8955668644172537
|
|
|
|
key: train_precision
|
|
value: [0.95927602 0.95927602 0.96313364 0.95945946 0.95089286 0.95515695
|
|
0.95412844 0.95927602 0.95927602 0.95927602]
|
|
|
|
mean value: 0.9579151438692668
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
0.95833333 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 0.98122066 1. 1. 1.
|
|
0.98113208 1. 1. 1. ]
|
|
|
|
mean value: 0.9962352732748694
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.97916667 0.91666667 0.97916667 0.91666667 0.91666667
|
|
0.93568841 1. 0.89130435 0.84782609]
|
|
|
|
mean value: 0.9362318840579711
|
|
|
|
key: train_roc_auc
|
|
value: [0.97877358 0.97877358 0.9717424 0.97877358 0.9740566 0.97641509
|
|
0.96709186 0.97887324 0.97887324 0.97887324]
|
|
|
|
mean value: 0.9762246434582337
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.96 0.85185185 0.95833333 0.85185185 0.85185185
|
|
0.88461538 1. 0.82758621 0.77419355]
|
|
|
|
mean value: 0.8920284028787921
|
|
|
|
key: train_jcc
|
|
value: [0.95927602 0.95927602 0.94570136 0.95945946 0.95089286 0.95515695
|
|
0.93693694 0.95927602 0.95927602 0.95927602]
|
|
|
|
mean value: 0.95445276521757
|
|
|
|
MCC on Blind test: 0.69
|
|
|
|
Accuracy on Blind test: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.81007576 0.9309032 0.87025023 0.86282897 0.89318562 0.83508945
|
|
0.91109014 0.83375049 0.83409715 1.01893091]
|
|
|
|
mean value: 0.8800201892852784
|
|
|
|
key: score_time
|
|
value: [0.01434565 0.02627158 0.0148766 0.01492572 0.01502728 0.01511455
|
|
0.01505971 0.0148592 0.01490593 0.01501441]
|
|
|
|
mean value: 0.01604006290435791
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.91833182 0.91485507 1. 0.84254172
|
|
0.95825929 1. 0.91804649 0.87917396]
|
|
|
|
mean value: 0.9390374663670524
|
|
|
|
key: train_mcc
|
|
value: [0.99529409 1. 0.99530506 0.99530506 1. 1.
|
|
1. 0.99530516 0.99530516 0.99530516]
|
|
|
|
mean value: 0.9971819705673264
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.95744681 0.95744681 1. 0.91489362
|
|
0.9787234 1. 0.95744681 0.93617021]
|
|
|
|
mean value: 0.9681294326241134
|
|
|
|
key: train_accuracy
|
|
value: [0.99764151 1. 0.99764706 0.99764706 1. 1.
|
|
1. 0.99764706 0.99764706 0.99764706]
|
|
|
|
mean value: 0.998587680355161
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.95833333 0.95652174 1. 0.92
|
|
0.97959184 1. 0.96 0.94117647]
|
|
|
|
mean value: 0.9695215216521391
|
|
|
|
key: train_fscore
|
|
value: [0.99764706 1. 0.99765808 0.99765808 1. 1.
|
|
1. 0.99764706 0.99764706 0.99764706]
|
|
|
|
mean value: 0.9985904394544702
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.92 0.95652174 1. 0.85185185
|
|
0.96 1. 0.92307692 0.88888889]
|
|
|
|
mean value: 0.9460339402948099
|
|
|
|
key: train_precision
|
|
value: [0.99530516 1. 0.9953271 0.9953271 1. 1.
|
|
1. 0.99530516 0.99530516 0.99530516]
|
|
|
|
mean value: 0.9971874862884472
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 0.95652174 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9956521739130435
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.95833333 0.95742754 1. 0.91666667
|
|
0.97826087 1. 0.95652174 0.93478261]
|
|
|
|
mean value: 0.9681159420289855
|
|
|
|
key: train_roc_auc
|
|
value: [0.99764151 1. 0.99764151 0.99764151 1. 1.
|
|
1. 0.99765258 0.99765258 0.99765258]
|
|
|
|
mean value: 0.998588227478076
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.92 0.91666667 1. 0.85185185
|
|
0.96 1. 0.92307692 0.88888889]
|
|
|
|
mean value: 0.942048433048433
|
|
|
|
key: train_jcc
|
|
value: [0.99530516 1. 0.9953271 0.9953271 1. 1.
|
|
1. 0.99530516 0.99530516 0.99530516]
|
|
|
|
mean value: 0.9971874862884472
|
|
|
|
MCC on Blind test: 0.77
|
|
|
|
Accuracy on Blind test: 0.92
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.0149312 0.01223946 0.01004553 0.00999355 0.00953579 0.00959325
|
|
0.00963593 0.00978613 0.00959849 0.00964022]
|
|
|
|
mean value: 0.010499954223632812
|
|
|
|
key: score_time
|
|
value: [0.01894641 0.00924206 0.00908518 0.00878143 0.00861955 0.00863671
|
|
0.00858808 0.00870037 0.00859714 0.00864291]
|
|
|
|
mean value: 0.00978398323059082
|
|
|
|
key: test_mcc
|
|
value: [0.65341026 0.48112522 0.66243303 0.51017582 0.67023783 0.70329486
|
|
0.46440394 0.68038162 0.51676308 0.57227835]
|
|
|
|
mean value: 0.5914504018381765
|
|
|
|
key: train_mcc
|
|
value: [0.64918382 0.63332199 0.61078097 0.69105202 0.65956936 0.59238965
|
|
0.62262204 0.64623983 0.66395163 0.77915912]
|
|
|
|
mean value: 0.6548270435607132
|
|
|
|
key: test_accuracy
|
|
value: [0.8125 0.70833333 0.82978723 0.72340426 0.80851064 0.82978723
|
|
0.72340426 0.82978723 0.74468085 0.76595745]
|
|
|
|
mean value: 0.7776152482269504
|
|
|
|
key: train_accuracy
|
|
value: [0.81132075 0.80188679 0.78588235 0.83058824 0.81647059 0.77882353
|
|
0.79764706 0.80941176 0.81882353 0.88705882]
|
|
|
|
mean value: 0.8137913429522753
|
|
|
|
key: test_fscore
|
|
value: [0.83636364 0.76666667 0.83333333 0.77192982 0.83636364 0.85185185
|
|
0.76363636 0.85185185 0.78571429 0.80701754]
|
|
|
|
mean value: 0.8104728994202679
|
|
|
|
key: train_fscore
|
|
value: [0.83471074 0.82786885 0.81836327 0.85245902 0.83950617 0.81124498
|
|
0.82304527 0.83298969 0.84057971 0.89285714]
|
|
|
|
mean value: 0.8373624850079823
|
|
|
|
key: test_precision
|
|
value: [0.74193548 0.63888889 0.8 0.64705882 0.71875 0.74193548
|
|
0.67741935 0.76666667 0.6875 0.6969697 ]
|
|
|
|
mean value: 0.7117124398635309
|
|
|
|
key: train_precision
|
|
value: [0.74264706 0.73188406 0.71180556 0.75636364 0.74725275 0.70877193
|
|
0.72992701 0.73992674 0.74907749 0.84745763]
|
|
|
|
mean value: 0.7465113850910606
|
|
|
|
key: test_recall
|
|
value: [0.95833333 0.95833333 0.86956522 0.95652174 1. 1.
|
|
0.875 0.95833333 0.91666667 0.95833333]
|
|
|
|
mean value: 0.9451086956521739
|
|
|
|
key: train_recall
|
|
value: [0.95283019 0.95283019 0.96244131 0.97652582 0.95774648 0.94835681
|
|
0.94339623 0.95283019 0.95754717 0.94339623]
|
|
|
|
mean value: 0.9547900611214457
|
|
|
|
key: test_roc_auc
|
|
value: [0.8125 0.70833333 0.83061594 0.72826087 0.8125 0.83333333
|
|
0.7201087 0.82699275 0.74094203 0.76177536]
|
|
|
|
mean value: 0.777536231884058
|
|
|
|
key: train_roc_auc
|
|
value: [0.81132075 0.80188679 0.78546594 0.83024404 0.81613739 0.77842369
|
|
0.79798919 0.80974843 0.81914917 0.88719107]
|
|
|
|
mean value: 0.8137556470900876
|
|
|
|
key: test_jcc
|
|
value: [0.71875 0.62162162 0.71428571 0.62857143 0.71875 0.74193548
|
|
0.61764706 0.74193548 0.64705882 0.67647059]
|
|
|
|
mean value: 0.6827026202808936
|
|
|
|
key: train_jcc
|
|
value: [0.71631206 0.70629371 0.69256757 0.74285714 0.72340426 0.68243243
|
|
0.6993007 0.71378092 0.725 0.80645161]
|
|
|
|
mean value: 0.7208400392139427
|
|
|
|
MCC on Blind test: 0.36
|
|
|
|
Accuracy on Blind test: 0.67
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01189566 0.00986743 0.00980163 0.01088667 0.00992584 0.00978422
|
|
0.00994849 0.00991154 0.01006746 0.01077795]
|
|
|
|
mean value: 0.010286688804626465
|
|
|
|
key: score_time
|
|
value: [0.01042056 0.00864029 0.00862408 0.00857353 0.00865674 0.00865436
|
|
0.00880051 0.00869632 0.00874519 0.01060295]
|
|
|
|
mean value: 0.009041452407836914
|
|
|
|
key: test_mcc
|
|
value: [0.62554324 0.79235477 0.44646172 0.61775362 0.7023605 0.79418308
|
|
0.49183384 0.61706091 0.62296012 0.53483083]
|
|
|
|
mean value: 0.6245342632639244
|
|
|
|
key: train_mcc
|
|
value: [0.63713987 0.67927551 0.67071983 0.70353884 0.69412703 0.63801934
|
|
0.67615952 0.64302391 0.65219436 0.67060882]
|
|
|
|
mean value: 0.6664807030298023
|
|
|
|
key: test_accuracy
|
|
value: [0.8125 0.89583333 0.72340426 0.80851064 0.85106383 0.89361702
|
|
0.74468085 0.80851064 0.80851064 0.76595745]
|
|
|
|
mean value: 0.8112588652482269
|
|
|
|
key: train_accuracy
|
|
value: [0.81839623 0.83962264 0.83529412 0.85176471 0.84705882 0.81882353
|
|
0.83764706 0.82117647 0.82588235 0.83529412]
|
|
|
|
mean value: 0.8330960044395117
|
|
|
|
key: test_fscore
|
|
value: [0.80851064 0.89795918 0.71111111 0.80851064 0.84444444 0.89795918
|
|
0.73913043 0.81632653 0.8 0.78431373]
|
|
|
|
mean value: 0.8108265890383289
|
|
|
|
key: train_fscore
|
|
value: [0.81534772 0.83886256 0.83412322 0.85176471 0.84705882 0.81622912
|
|
0.83292978 0.81642512 0.82211538 0.83412322]
|
|
|
|
mean value: 0.8308979660389407
|
|
|
|
key: test_precision
|
|
value: [0.82608696 0.88 0.72727273 0.79166667 0.86363636 0.84615385
|
|
0.77272727 0.8 0.85714286 0.74074074]
|
|
|
|
mean value: 0.8105427430862213
|
|
|
|
key: train_precision
|
|
value: [0.82926829 0.84285714 0.84210526 0.85377358 0.8490566 0.83009709
|
|
0.85572139 0.83663366 0.83823529 0.83809524]
|
|
|
|
mean value: 0.8415843563369898
|
|
|
|
key: test_recall
|
|
value: [0.79166667 0.91666667 0.69565217 0.82608696 0.82608696 0.95652174
|
|
0.70833333 0.83333333 0.75 0.83333333]
|
|
|
|
mean value: 0.813768115942029
|
|
|
|
key: train_recall
|
|
value: [0.80188679 0.83490566 0.82629108 0.84976526 0.84507042 0.8028169
|
|
0.81132075 0.79716981 0.80660377 0.83018868]
|
|
|
|
mean value: 0.8206019133669944
|
|
|
|
key: test_roc_auc
|
|
value: [0.8125 0.89583333 0.72282609 0.80887681 0.85054348 0.89492754
|
|
0.74547101 0.80797101 0.80978261 0.76449275]
|
|
|
|
mean value: 0.811322463768116
|
|
|
|
key: train_roc_auc
|
|
value: [0.81839623 0.83962264 0.83531535 0.85176942 0.84706351 0.81886128
|
|
0.83758526 0.82112012 0.8258371 0.83528213]
|
|
|
|
mean value: 0.8330853042785011
|
|
|
|
key: test_jcc
|
|
value: [0.67857143 0.81481481 0.55172414 0.67857143 0.73076923 0.81481481
|
|
0.5862069 0.68965517 0.66666667 0.64516129]
|
|
|
|
mean value: 0.6856955881427517
|
|
|
|
key: train_jcc
|
|
value: [0.68825911 0.72244898 0.71544715 0.74180328 0.73469388 0.68951613
|
|
0.71369295 0.68979592 0.69795918 0.71544715]
|
|
|
|
mean value: 0.7109063731217378
|
|
|
|
MCC on Blind test: 0.24
|
|
|
|
Accuracy on Blind test: 0.72
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01245904 0.01098251 0.0108161 0.00995302 0.01012731 0.01066542
|
|
0.00976992 0.0097394 0.00949478 0.00957537]
|
|
|
|
mean value: 0.010358285903930665
|
|
|
|
key: score_time
|
|
value: [0.0191009 0.01486564 0.0164752 0.01425385 0.01789713 0.01655769
|
|
0.01543355 0.01467013 0.01378918 0.01644468]
|
|
|
|
mean value: 0.015948796272277833
|
|
|
|
key: test_mcc
|
|
value: [0.6761234 0.70894901 0.67037015 0.33346345 0.58428436 0.57713344
|
|
0.68038162 0.53483083 0.54211097 0.44646172]
|
|
|
|
mean value: 0.5754108952180804
|
|
|
|
key: train_mcc
|
|
value: [0.75960018 0.75626659 0.7928403 0.80152423 0.77390055 0.75576923
|
|
0.7904833 0.78862899 0.76750882 0.77192711]
|
|
|
|
mean value: 0.7758449309009248
|
|
|
|
key: test_accuracy
|
|
value: [0.83333333 0.85416667 0.82978723 0.65957447 0.78723404 0.78723404
|
|
0.82978723 0.76595745 0.76595745 0.72340426]
|
|
|
|
mean value: 0.7836436170212766
|
|
|
|
key: train_accuracy
|
|
value: [0.87735849 0.87264151 0.89411765 0.89882353 0.88470588 0.87529412
|
|
0.89176471 0.89176471 0.88235294 0.88470588]
|
|
|
|
mean value: 0.8853529411764706
|
|
|
|
key: test_fscore
|
|
value: [0.84615385 0.85714286 0.84 0.69230769 0.8 0.79166667
|
|
0.85185185 0.78431373 0.79245283 0.73469388]
|
|
|
|
mean value: 0.799058334735281
|
|
|
|
key: train_fscore
|
|
value: [0.88392857 0.8826087 0.89977728 0.90380313 0.8908686 0.88248337
|
|
0.89823009 0.89732143 0.88687783 0.88888889]
|
|
|
|
mean value: 0.8914787883102976
|
|
|
|
key: test_precision
|
|
value: [0.78571429 0.84 0.77777778 0.62068966 0.74074074 0.76
|
|
0.76666667 0.74074074 0.72413793 0.72 ]
|
|
|
|
mean value: 0.7476467797847108
|
|
|
|
key: train_precision
|
|
value: [0.83898305 0.81854839 0.8559322 0.86324786 0.84745763 0.83613445
|
|
0.84583333 0.85169492 0.85217391 0.8558952 ]
|
|
|
|
mean value: 0.8465900943619682
|
|
|
|
key: test_recall
|
|
value: [0.91666667 0.875 0.91304348 0.7826087 0.86956522 0.82608696
|
|
0.95833333 0.83333333 0.875 0.75 ]
|
|
|
|
mean value: 0.859963768115942
|
|
|
|
key: train_recall
|
|
value: [0.93396226 0.95754717 0.94835681 0.94835681 0.93896714 0.9342723
|
|
0.95754717 0.94811321 0.9245283 0.9245283 ]
|
|
|
|
mean value: 0.9416179466737532
|
|
|
|
key: test_roc_auc
|
|
value: [0.83333333 0.85416667 0.83152174 0.66213768 0.78894928 0.78804348
|
|
0.82699275 0.76449275 0.76358696 0.72282609]
|
|
|
|
mean value: 0.7836050724637681
|
|
|
|
key: train_roc_auc
|
|
value: [0.87735849 0.87264151 0.89398972 0.89870671 0.88457791 0.87515502
|
|
0.89191912 0.89189698 0.88245194 0.88479936]
|
|
|
|
mean value: 0.8853496766764106
|
|
|
|
key: test_jcc
|
|
value: [0.73333333 0.75 0.72413793 0.52941176 0.66666667 0.65517241
|
|
0.74193548 0.64516129 0.65625 0.58064516]
|
|
|
|
mean value: 0.668271404501734
|
|
|
|
key: train_jcc
|
|
value: [0.792 0.78988327 0.81781377 0.8244898 0.80321285 0.78968254
|
|
0.81526104 0.81376518 0.79674797 0.8 ]
|
|
|
|
mean value: 0.8042856414513823
|
|
|
|
MCC on Blind test: 0.23
|
|
|
|
Accuracy on Blind test: 0.71
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01868391 0.01858497 0.02003932 0.01841021 0.01832843 0.01859832
|
|
0.01857591 0.01857018 0.01845574 0.01874232]
|
|
|
|
mean value: 0.018698930740356445
|
|
|
|
key: score_time
|
|
value: [0.01141477 0.01289392 0.01167035 0.01100302 0.01106143 0.01117897
|
|
0.01114178 0.0112474 0.01117516 0.01259255]
|
|
|
|
mean value: 0.011537933349609375
|
|
|
|
key: test_mcc
|
|
value: [0.87576054 0.797925 0.74456522 0.78804348 0.7196797 0.83303222
|
|
0.7023605 1. 0.61706091 0.62966842]
|
|
|
|
mean value: 0.7708095983949329
|
|
|
|
key: train_mcc
|
|
value: [0.8825567 0.87771008 0.86361925 0.89788945 0.88259016 0.86827011
|
|
0.86823456 0.88260313 0.85944441 0.89177278]
|
|
|
|
mean value: 0.8774690641416194
|
|
|
|
key: test_accuracy
|
|
value: [0.9375 0.89583333 0.87234043 0.89361702 0.85106383 0.91489362
|
|
0.85106383 1. 0.80851064 0.80851064]
|
|
|
|
mean value: 0.8833333333333333
|
|
|
|
key: train_accuracy
|
|
value: [0.94103774 0.93867925 0.93176471 0.94823529 0.94117647 0.93411765
|
|
0.93411765 0.94117647 0.92941176 0.94588235]
|
|
|
|
mean value: 0.9385599334073251
|
|
|
|
key: test_fscore
|
|
value: [0.93877551 0.88888889 0.86956522 0.89361702 0.8627451 0.91666667
|
|
0.85714286 1. 0.81632653 0.83018868]
|
|
|
|
mean value: 0.8873916469467138
|
|
|
|
key: train_fscore
|
|
value: [0.94199536 0.93953488 0.93144208 0.94977169 0.94199536 0.93457944
|
|
0.93396226 0.94172494 0.93055556 0.94562648]
|
|
|
|
mean value: 0.9391188051079586
|
|
|
|
key: test_precision
|
|
value: [0.92 0.95238095 0.86956522 0.875 0.78571429 0.88
|
|
0.84 1. 0.8 0.75862069]
|
|
|
|
mean value: 0.8681281145141715
|
|
|
|
key: train_precision
|
|
value: [0.92694064 0.9266055 0.93809524 0.92444444 0.93119266 0.93023256
|
|
0.93396226 0.93087558 0.91363636 0.9478673 ]
|
|
|
|
mean value: 0.9303852547488611
|
|
|
|
key: test_recall
|
|
value: [0.95833333 0.83333333 0.86956522 0.91304348 0.95652174 0.95652174
|
|
0.875 1. 0.83333333 0.91666667]
|
|
|
|
mean value: 0.9112318840579711
|
|
|
|
key: train_recall
|
|
value: [0.95754717 0.95283019 0.92488263 0.97652582 0.95305164 0.93896714
|
|
0.93396226 0.95283019 0.94811321 0.94339623]
|
|
|
|
mean value: 0.9482106475329968
|
|
|
|
key: test_roc_auc
|
|
value: [0.9375 0.89583333 0.87228261 0.89402174 0.85326087 0.91576087
|
|
0.85054348 1. 0.80797101 0.80615942]
|
|
|
|
mean value: 0.8833333333333333
|
|
|
|
key: train_roc_auc
|
|
value: [0.94103774 0.93867925 0.93178094 0.94816857 0.94114846 0.93410621
|
|
0.93411728 0.94120383 0.92945566 0.94587652]
|
|
|
|
mean value: 0.9385574453007353
|
|
|
|
key: test_jcc
|
|
value: [0.88461538 0.8 0.76923077 0.80769231 0.75862069 0.84615385
|
|
0.75 1. 0.68965517 0.70967742]
|
|
|
|
mean value: 0.8015645589116112
|
|
|
|
key: train_jcc
|
|
value: [0.89035088 0.88596491 0.87168142 0.90434783 0.89035088 0.87719298
|
|
0.87610619 0.88986784 0.87012987 0.89686099]
|
|
|
|
mean value: 0.8852853783915879
|
|
|
|
MCC on Blind test: 0.61
|
|
|
|
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(
|
|
/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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.89117432 2.15473008 1.99325037 1.50144362 2.20798397 1.97683716
|
|
1.90530825 2.01488137 1.97109532 1.8338623 ]
|
|
|
|
mean value: 1.945056676864624
|
|
|
|
key: score_time
|
|
value: [0.01231027 0.01525736 0.01529789 0.01275921 0.02150702 0.01229095
|
|
0.01705813 0.01328063 0.01221657 0.01224136]
|
|
|
|
mean value: 0.014421939849853516
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.80641033 0.91485507 0.91833182 0.87979456
|
|
0.95825929 0.95825929 0.84147165 0.76896316]
|
|
|
|
mean value: 0.9005511478530442
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.89361702 0.95744681 0.95744681 0.93617021
|
|
0.9787234 0.9787234 0.91489362 0.87234043]
|
|
|
|
mean value: 0.9468528368794327
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.90196078 0.95652174 0.95833333 0.93877551
|
|
0.97959184 0.97959184 0.92307692 0.88888889]
|
|
|
|
mean value: 0.9506332689151469
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.82142857 0.95652174 0.92 0.88461538
|
|
0.96 0.96 0.85714286 0.8 ]
|
|
|
|
mean value: 0.9119708552317248
|
|
|
|
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. 0.95652174 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9956521739130435
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.89583333 0.95742754 0.95833333 0.9375
|
|
0.97826087 0.97826087 0.91304348 0.86956522]
|
|
|
|
mean value: 0.9467391304347826
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.82142857 0.91666667 0.92 0.88461538
|
|
0.96 0.96 0.85714286 0.8 ]
|
|
|
|
mean value: 0.9079853479853479
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.75
|
|
|
|
Accuracy on Blind test: 0.92
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.04656196 0.0179081 0.01775861 0.01612544 0.01689601 0.01465082
|
|
0.01541829 0.0177598 0.01531911 0.01794672]
|
|
|
|
mean value: 0.019634485244750977
|
|
|
|
key: score_time
|
|
value: [0.01061916 0.00894713 0.00851369 0.00861025 0.008641 0.00860929
|
|
0.00852466 0.00857902 0.00854111 0.00859475]
|
|
|
|
mean value: 0.00881800651550293
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.95833333 0.91485507 1. 0.91833182
|
|
0.95825929 1. 0.95825929 0.91804649]
|
|
|
|
mean value: 0.9585251607876043
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.9787234 0.95744681 1. 0.95744681
|
|
0.9787234 1. 0.9787234 0.95744681]
|
|
|
|
mean value: 0.9787677304964539
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.9787234 0.95652174 1. 0.95833333
|
|
0.97959184 1. 0.97959184 0.96 ]
|
|
|
|
mean value: 0.9792353986923169
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.95833333 0.95652174 1. 0.92
|
|
0.96 1. 0.96 0.92307692]
|
|
|
|
mean value: 0.9637931995540692
|
|
|
|
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. 0.95652174 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9956521739130435
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.97916667 0.95742754 1. 0.95833333
|
|
0.97826087 1. 0.97826087 0.95652174]
|
|
|
|
mean value: 0.978713768115942
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.95833333 0.91666667 1. 0.92
|
|
0.96 1. 0.96 0.92307692]
|
|
|
|
mean value: 0.9598076923076924
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.76
|
|
|
|
Accuracy on Blind test: 0.92
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.10887742 0.11010265 0.1084106 0.10813427 0.10867953 0.10850334
|
|
0.10855818 0.10889173 0.10843754 0.10868287]
|
|
|
|
mean value: 0.10872781276702881
|
|
|
|
key: score_time
|
|
value: [0.01823473 0.01734877 0.01734352 0.01728845 0.01727915 0.01723552
|
|
0.01728439 0.01728725 0.01735067 0.01729393]
|
|
|
|
mean value: 0.017394638061523436
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.9591663 0.8729597 0.91485507 0.95825929 0.91833182
|
|
0.91804649 1. 0.95825929 0.91485507]
|
|
|
|
mean value: 0.9373899347059376
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.97916667 0.93617021 0.95744681 0.9787234 0.95744681
|
|
0.95744681 1. 0.9787234 0.95744681]
|
|
|
|
mean value: 0.9681737588652483
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.9787234 0.93333333 0.95652174 0.97777778 0.95833333
|
|
0.96 1. 0.97959184 0.95833333]
|
|
|
|
mean value: 0.9682206594632919
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.95454545 0.95652174 1. 0.92
|
|
0.92307692 1. 0.96 0.95833333]
|
|
|
|
mean value: 0.9632477450086145
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 0.95833333 0.91304348 0.95652174 0.95652174 1.
|
|
1. 1. 1. 0.95833333]
|
|
|
|
mean value: 0.9742753623188406
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.97916667 0.93568841 0.95742754 0.97826087 0.95833333
|
|
0.95652174 1. 0.97826087 0.95742754]
|
|
|
|
mean value: 0.9680253623188406
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.95833333 0.875 0.91666667 0.95652174 0.92
|
|
0.92307692 1. 0.96 0.92 ]
|
|
|
|
mean value: 0.9389598662207358
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.65
|
|
|
|
Accuracy on Blind test: 0.89
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.00975633 0.00998092 0.00981641 0.00978923 0.00991082 0.00979185
|
|
0.00982356 0.00965524 0.00995374 0.00987554]
|
|
|
|
mean value: 0.009835362434387207
|
|
|
|
key: score_time
|
|
value: [0.00857186 0.00859737 0.00854778 0.00885344 0.00864387 0.00861645
|
|
0.00850725 0.00863791 0.00859046 0.00856543]
|
|
|
|
mean value: 0.008613181114196778
|
|
|
|
key: test_mcc
|
|
value: [0.91986621 0.76063883 0.80641033 0.79418308 0.75645593 0.87979456
|
|
0.95825929 0.87917396 0.87917396 0.71722586]
|
|
|
|
mean value: 0.8351182014932017
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 0.875 0.89361702 0.89361702 0.87234043 0.93617021
|
|
0.9787234 0.93617021 0.93617021 0.85106383]
|
|
|
|
mean value: 0.9131205673758865
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.96 0.88461538 0.90196078 0.89795918 0.88 0.93877551
|
|
0.97959184 0.94117647 0.94117647 0.86792453]
|
|
|
|
mean value: 0.9193180169019712
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.92307692 0.82142857 0.82142857 0.84615385 0.81481481 0.88461538
|
|
0.96 0.88888889 0.88888889 0.79310345]
|
|
|
|
mean value: 0.8642399337571751
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 0.95833333 1. 0.95652174 0.95652174 1.
|
|
1. 1. 1. 0.95833333]
|
|
|
|
mean value: 0.9829710144927536
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 0.875 0.89583333 0.89492754 0.8740942 0.9375
|
|
0.97826087 0.93478261 0.93478261 0.84873188]
|
|
|
|
mean value: 0.9132246376811594
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.92307692 0.79310345 0.82142857 0.81481481 0.78571429 0.88461538
|
|
0.96 0.88888889 0.88888889 0.76666667]
|
|
|
|
mean value: 0.8527197872370286
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.19
|
|
|
|
Accuracy on Blind test: 0.72
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [1.54354858 1.54720092 1.52289224 1.50696182 1.53694749 1.54915142
|
|
1.57910442 1.58113194 1.5115912 1.53090119]
|
|
|
|
mean value: 1.5409431219100953
|
|
|
|
key: score_time
|
|
value: [0.0968163 0.08936691 0.08948493 0.0894146 0.09688139 0.09106207
|
|
0.09766769 0.09465098 0.09666371 0.08903265]
|
|
|
|
mean value: 0.09310412406921387
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.95833333 0.91485507 1. 0.95833333
|
|
0.95825929 1. 0.95825929 0.95825929]
|
|
|
|
mean value: 0.9706299613347321
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.9787234 0.95744681 1. 0.9787234
|
|
0.9787234 1. 0.9787234 0.9787234 ]
|
|
|
|
mean value: 0.9851063829787234
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.9787234 0.95652174 1. 0.9787234
|
|
0.97959184 1. 0.97959184 0.97959184]
|
|
|
|
mean value: 0.9852744057845154
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.95833333 0.95652174 1. 0.95833333
|
|
0.96 1. 0.96 0.96 ]
|
|
|
|
mean value: 0.9753188405797102
|
|
|
|
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. 0.95652174 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9956521739130435
|
|
|
|
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. 0.97916667 0.95742754 1. 0.97916667
|
|
0.97826087 1. 0.97826087 0.97826087]
|
|
|
|
mean value: 0.9850543478260869
|
|
|
|
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. 0.95833333 0.91666667 1. 0.95833333
|
|
0.96 1. 0.96 0.96 ]
|
|
|
|
mean value: 0.9713333333333334
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.73
|
|
|
|
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: 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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000...05', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.89836597 0.95232153 0.92037988 0.95837426 0.97386265 0.95863867
|
|
1.12983155 0.90902829 0.94883585 0.9371438 ]
|
|
|
|
mean value: 0.9586782455444336
|
|
|
|
key: score_time
|
|
value: [0.20848846 0.18111134 0.23739219 0.26125526 0.2038908 0.14349246
|
|
0.22535181 0.22659111 0.21095777 0.21967983]
|
|
|
|
mean value: 0.2118211030960083
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.95833333 0.95833333 1. 0.91833182
|
|
0.95825929 1. 0.95825929 0.95825929]
|
|
|
|
mean value: 0.9709776361813947
|
|
|
|
key: train_mcc
|
|
value: [0.98130676 0.98130676 0.98598008 0.99063185 0.98134942 0.98598008
|
|
0.99063227 0.985981 0.985981 0.98135106]
|
|
|
|
mean value: 0.9850500281670899
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.9787234 0.9787234 1. 0.95744681
|
|
0.9787234 1. 0.9787234 0.9787234 ]
|
|
|
|
mean value: 0.9851063829787234
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.99056604 0.99294118 0.99529412 0.99058824 0.99294118
|
|
0.99529412 0.99294118 0.99294118 0.99058824]
|
|
|
|
mean value: 0.9924661487236404
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.9787234 0.9787234 1. 0.95833333
|
|
0.97959184 1. 0.97959184 0.97959184]
|
|
|
|
mean value: 0.9854555652048054
|
|
|
|
key: train_fscore
|
|
value: [0.99065421 0.99065421 0.99300699 0.9953271 0.99069767 0.99300699
|
|
0.99530516 0.99297424 0.99297424 0.99065421]
|
|
|
|
mean value: 0.9925255022129764
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.95833333 0.95833333 1. 0.92
|
|
0.96 1. 0.96 0.96 ]
|
|
|
|
mean value: 0.9716666666666667
|
|
/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(
|
|
|
|
key: train_precision
|
|
value: [0.98148148 0.98148148 0.98611111 0.99069767 0.98156682 0.98611111
|
|
0.99065421 0.98604651 0.98604651 0.98148148]
|
|
|
|
mean value: 0.985167839022506
|
|
|
|
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. 0.97916667 0.97916667 1. 0.95833333
|
|
0.97826087 1. 0.97826087 0.97826087]
|
|
|
|
mean value: 0.9851449275362318
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.99056604 0.99292453 0.99528302 0.99056604 0.99292453
|
|
0.99530516 0.99295775 0.99295775 0.99061033]
|
|
|
|
mean value: 0.9924661174594738
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 0.95833333 0.95833333 1. 0.92
|
|
0.96 1. 0.96 0.96 ]
|
|
|
|
mean value: 0.9716666666666667
|
|
|
|
key: train_jcc
|
|
value: [0.98148148 0.98148148 0.98611111 0.99069767 0.98156682 0.98611111
|
|
0.99065421 0.98604651 0.98604651 0.98148148]
|
|
|
|
mean value: 0.985167839022506
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02579999 0.01128459 0.0112412 0.01133418 0.01121044 0.01131463
|
|
0.0112555 0.01078486 0.01135039 0.01105332]
|
|
|
|
mean value: 0.012662911415100097
|
|
|
|
key: score_time
|
|
value: [0.01103044 0.00971484 0.00965095 0.00953293 0.00953078 0.00956154
|
|
0.00947237 0.00922418 0.00936317 0.00902581]
|
|
|
|
mean value: 0.009610700607299804
|
|
|
|
key: test_mcc
|
|
value: [0.62554324 0.79235477 0.44646172 0.61775362 0.7023605 0.79418308
|
|
0.49183384 0.61706091 0.62296012 0.53483083]
|
|
|
|
mean value: 0.6245342632639244
|
|
|
|
key: train_mcc
|
|
value: [0.63713987 0.67927551 0.67071983 0.70353884 0.69412703 0.63801934
|
|
0.67615952 0.64302391 0.65219436 0.67060882]
|
|
|
|
mean value: 0.6664807030298023
|
|
|
|
key: test_accuracy
|
|
value: [0.8125 0.89583333 0.72340426 0.80851064 0.85106383 0.89361702
|
|
0.74468085 0.80851064 0.80851064 0.76595745]
|
|
|
|
mean value: 0.8112588652482269
|
|
|
|
key: train_accuracy
|
|
value: [0.81839623 0.83962264 0.83529412 0.85176471 0.84705882 0.81882353
|
|
0.83764706 0.82117647 0.82588235 0.83529412]
|
|
|
|
mean value: 0.8330960044395117
|
|
|
|
key: test_fscore
|
|
value: [0.80851064 0.89795918 0.71111111 0.80851064 0.84444444 0.89795918
|
|
0.73913043 0.81632653 0.8 0.78431373]
|
|
|
|
mean value: 0.8108265890383289
|
|
|
|
key: train_fscore
|
|
value: [0.81534772 0.83886256 0.83412322 0.85176471 0.84705882 0.81622912
|
|
0.83292978 0.81642512 0.82211538 0.83412322]
|
|
|
|
mean value: 0.8308979660389407
|
|
|
|
key: test_precision
|
|
value: [0.82608696 0.88 0.72727273 0.79166667 0.86363636 0.84615385
|
|
0.77272727 0.8 0.85714286 0.74074074]
|
|
|
|
mean value: 0.8105427430862213
|
|
|
|
key: train_precision
|
|
value: [0.82926829 0.84285714 0.84210526 0.85377358 0.8490566 0.83009709
|
|
0.85572139 0.83663366 0.83823529 0.83809524]
|
|
|
|
mean value: 0.8415843563369898
|
|
|
|
key: test_recall
|
|
value: [0.79166667 0.91666667 0.69565217 0.82608696 0.82608696 0.95652174
|
|
0.70833333 0.83333333 0.75 0.83333333]
|
|
|
|
mean value: 0.813768115942029
|
|
|
|
key: train_recall
|
|
value: [0.80188679 0.83490566 0.82629108 0.84976526 0.84507042 0.8028169
|
|
0.81132075 0.79716981 0.80660377 0.83018868]
|
|
|
|
mean value: 0.8206019133669944
|
|
|
|
key: test_roc_auc
|
|
value: [0.8125 0.89583333 0.72282609 0.80887681 0.85054348 0.89492754
|
|
0.74547101 0.80797101 0.80978261 0.76449275]
|
|
|
|
mean value: 0.811322463768116
|
|
|
|
key: train_roc_auc
|
|
value: [0.81839623 0.83962264 0.83531535 0.85176942 0.84706351 0.81886128
|
|
0.83758526 0.82112012 0.8258371 0.83528213]
|
|
|
|
mean value: 0.8330853042785011
|
|
|
|
key: test_jcc
|
|
value: [0.67857143 0.81481481 0.55172414 0.67857143 0.73076923 0.81481481
|
|
0.5862069 0.68965517 0.66666667 0.64516129]
|
|
|
|
mean value: 0.6856955881427517
|
|
|
|
key: train_jcc
|
|
value: [0.68825911 0.72244898 0.71544715 0.74180328 0.73469388 0.68951613
|
|
0.71369295 0.68979592 0.69795918 0.71544715]
|
|
|
|
mean value: 0.7109063731217378
|
|
|
|
MCC on Blind test: 0.24
|
|
|
|
Accuracy on Blind test: 0.72
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'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: [0.09291172 0.07183409 0.07470775 0.06999326 0.07060146 0.06885266
|
|
0.07158732 0.09916973 0.07233477 0.07627034]
|
|
|
|
mean value: 0.07682631015777588
|
|
|
|
key: score_time
|
|
value: [0.01091909 0.01086259 0.01081324 0.01077414 0.01067114 0.01110101
|
|
0.01050758 0.01261592 0.01171517 0.01140523]
|
|
|
|
mean value: 0.011138510704040528
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 0.95833333 1. 0.91833182
|
|
0.95825929 1. 0.95825929 1. ]
|
|
|
|
mean value: 0.9793183737074985
|
|
|
|
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. 0.9787234 1. 0.95744681
|
|
0.9787234 1. 0.9787234 1. ]
|
|
|
|
mean value: 0.9893617021276596
|
|
|
|
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. 0.9787234 1. 0.95833333
|
|
0.97959184 1. 0.97959184 1. ]
|
|
|
|
mean value: 0.989624041105804
|
|
|
|
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. 0.95833333 1. 0.92
|
|
0.96 1. 0.96 1. ]
|
|
|
|
mean value: 0.9798333333333333
|
|
|
|
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. 0.97916667 1. 0.95833333
|
|
0.97826087 1. 0.97826087 1. ]
|
|
|
|
mean value: 0.9894021739130435
|
|
|
|
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. 0.95833333 1. 0.92
|
|
0.96 1. 0.96 1. ]
|
|
|
|
mean value: 0.9798333333333333
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.84
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.05154467 0.0659585 0.0463624 0.05018473 0.07622552 0.04126978
|
|
0.09363246 0.08380437 0.0527842 0.04638553]
|
|
|
|
mean value: 0.06081521511077881
|
|
|
|
key: score_time
|
|
value: [0.02103281 0.01217628 0.01225781 0.02151728 0.01212764 0.01210999
|
|
0.02075386 0.02269864 0.01212978 0.02299881]
|
|
|
|
mean value: 0.016980290412902832
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.9591663 1. 0.91833182 0.87979456 0.84254172
|
|
0.87917396 0.95825929 0.84147165 0.91804649]
|
|
|
|
mean value: 0.9155952100173105
|
|
|
|
key: train_mcc
|
|
value: [0.98130676 0.97668677 0.98134942 0.98598008 0.98134942 0.98598008
|
|
0.985981 0.97674215 0.985981 0.98135106]
|
|
|
|
mean value: 0.9822707743330921
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.97916667 1. 0.95744681 0.93617021 0.91489362
|
|
0.93617021 0.9787234 0.91489362 0.95744681]
|
|
|
|
mean value: 0.9554078014184397
|
|
|
|
key: train_accuracy
|
|
value: [0.99056604 0.98820755 0.99058824 0.99294118 0.99058824 0.99294118
|
|
0.99294118 0.98823529 0.99294118 0.99058824]
|
|
|
|
mean value: 0.9910538290788014
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.9787234 1. 0.95833333 0.93877551 0.92
|
|
0.94117647 0.97959184 0.92307692 0.96 ]
|
|
|
|
mean value: 0.957926931492728
|
|
|
|
key: train_fscore
|
|
value: [0.99065421 0.98834499 0.99069767 0.99300699 0.99069767 0.99300699
|
|
0.99297424 0.98834499 0.99297424 0.99065421]
|
|
|
|
mean value: 0.9911356200507881
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 1. 0.92 0.88461538 0.85185185
|
|
0.88888889 0.96 0.85714286 0.92307692]
|
|
|
|
mean value: 0.9245575905575906
|
|
|
|
key: train_precision
|
|
value: [0.98148148 0.97695853 0.98156682 0.98611111 0.98156682 0.98611111
|
|
0.98604651 0.97695853 0.98604651 0.98148148]
|
|
|
|
mean value: 0.9824328899685238
|
|
|
|
key: test_recall
|
|
value: [1. 0.95833333 1. 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.97916667 1. 0.95833333 0.9375 0.91666667
|
|
0.93478261 0.97826087 0.91304348 0.95652174]
|
|
|
|
mean value: 0.9553442028985507
|
|
|
|
key: train_roc_auc
|
|
value: [0.99056604 0.98820755 0.99056604 0.99292453 0.99056604 0.99292453
|
|
0.99295775 0.98826291 0.99295775 0.99061033]
|
|
|
|
mean value: 0.9910543449375498
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.95833333 1. 0.92 0.88461538 0.85185185
|
|
0.88888889 0.96 0.85714286 0.92307692]
|
|
|
|
mean value: 0.9203909238909239
|
|
|
|
key: train_jcc
|
|
value: [0.98148148 0.97695853 0.98156682 0.98611111 0.98156682 0.98611111
|
|
0.98604651 0.97695853 0.98604651 0.98148148]
|
|
|
|
mean value: 0.9824328899685238
|
|
|
|
MCC on Blind test: 0.65
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01410866 0.01118493 0.01076555 0.01080847 0.01082301 0.01077867
|
|
0.01076889 0.01103401 0.01077867 0.01079345]
|
|
|
|
mean value: 0.011184430122375489
|
|
|
|
key: score_time
|
|
value: [0.01097441 0.00968647 0.00929713 0.00939417 0.00934315 0.0093956
|
|
0.00933146 0.00945067 0.00939775 0.00946617]
|
|
|
|
mean value: 0.009573698043823242
|
|
|
|
key: test_mcc
|
|
value: [0.70894901 0.75261781 0.57713344 0.70289855 0.53734864 0.68369322
|
|
0.57427536 0.7876601 0.4078185 0.49454913]
|
|
|
|
mean value: 0.62269437517749
|
|
|
|
key: train_mcc
|
|
value: [0.63045921 0.63884974 0.65404496 0.68238795 0.63568086 0.64907159
|
|
0.66989906 0.63929942 0.63584164 0.66194531]
|
|
|
|
mean value: 0.6497479742444074
|
|
|
|
key: test_accuracy
|
|
value: [0.85416667 0.875 0.78723404 0.85106383 0.76595745 0.82978723
|
|
0.78723404 0.89361702 0.70212766 0.74468085]
|
|
|
|
mean value: 0.8090868794326241
|
|
|
|
key: train_accuracy
|
|
value: [0.81367925 0.81839623 0.82588235 0.84 0.81647059 0.82352941
|
|
0.83294118 0.81882353 0.81647059 0.83058824]
|
|
|
|
mean value: 0.8236781354051055
|
|
|
|
key: test_fscore
|
|
value: [0.85714286 0.88 0.79166667 0.85106383 0.7755102 0.84615385
|
|
0.79166667 0.89795918 0.73076923 0.76923077]
|
|
|
|
mean value: 0.8191163254172372
|
|
|
|
key: train_fscore
|
|
value: [0.82247191 0.82539683 0.83333333 0.84684685 0.82511211 0.83069977
|
|
0.84116331 0.82460137 0.82432432 0.83410138]
|
|
|
|
mean value: 0.8308051182096419
|
|
|
|
key: test_precision
|
|
value: [0.84 0.84615385 0.76 0.83333333 0.73076923 0.75862069
|
|
0.79166667 0.88 0.67857143 0.71428571]
|
|
|
|
mean value: 0.7833400909435392
|
|
|
|
key: train_precision
|
|
value: [0.78540773 0.79475983 0.8008658 0.81385281 0.78969957 0.8
|
|
0.8 0.79735683 0.7887931 0.81531532]
|
|
|
|
mean value: 0.7986050983140889
|
|
|
|
key: test_recall
|
|
value: [0.875 0.91666667 0.82608696 0.86956522 0.82608696 0.95652174
|
|
0.79166667 0.91666667 0.79166667 0.83333333]
|
|
|
|
mean value: 0.8603260869565217
|
|
|
|
key: train_recall
|
|
value: [0.86320755 0.85849057 0.8685446 0.88262911 0.86384977 0.86384977
|
|
0.88679245 0.85377358 0.86320755 0.85377358]
|
|
|
|
mean value: 0.8658118522455488
|
|
|
|
key: test_roc_auc
|
|
value: [0.85416667 0.875 0.78804348 0.85144928 0.76721014 0.83242754
|
|
0.78713768 0.89311594 0.70018116 0.74275362]
|
|
|
|
mean value: 0.8091485507246376
|
|
|
|
key: train_roc_auc
|
|
value: [0.81367925 0.81839623 0.82578173 0.83989946 0.81635884 0.82343432
|
|
0.83306759 0.81890557 0.8165803 0.83064266]
|
|
|
|
mean value: 0.8236745947382408
|
|
|
|
key: test_jcc
|
|
value: [0.75 0.78571429 0.65517241 0.74074074 0.63333333 0.73333333
|
|
0.65517241 0.81481481 0.57575758 0.625 ]
|
|
|
|
mean value: 0.6969038911280291
|
|
|
|
key: train_jcc
|
|
value: [0.69847328 0.7027027 0.71428571 0.734375 0.70229008 0.71042471
|
|
0.72586873 0.70155039 0.70114943 0.71541502]
|
|
|
|
mean value: 0.710653504470758
|
|
|
|
MCC on Blind test: 0.57
|
|
|
|
Accuracy on Blind test: 0.82
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01804495 0.02205133 0.02854848 0.02732158 0.02588081 0.02757978
|
|
0.0229466 0.03042245 0.02564573 0.02404499]
|
|
|
|
mean value: 0.02524867057800293
|
|
|
|
key: score_time
|
|
value: [0.00939441 0.01101851 0.01172376 0.01171947 0.01173043 0.01165342
|
|
0.01170754 0.01168323 0.01165724 0.01164365]
|
|
|
|
mean value: 0.011393165588378907
|
|
|
|
key: test_mcc
|
|
value: [0.91986621 0.9591663 0.91833182 0.91485507 0.87979456 0.84254172
|
|
0.95825929 0.95825929 0.95825929 0.8047833 ]
|
|
|
|
mean value: 0.9114116856943231
|
|
|
|
key: train_mcc
|
|
value: [0.91841073 0.96295001 0.99063185 0.99530506 0.98134942 0.99530506
|
|
1. 0.99063227 0.99063227 0.98135106]
|
|
|
|
mean value: 0.9806567731795999
|
|
|
|
key: test_accuracy
|
|
value: [0.95833333 0.97916667 0.95744681 0.95744681 0.93617021 0.91489362
|
|
0.9787234 0.9787234 0.9787234 0.89361702]
|
|
|
|
mean value: 0.9533244680851064
|
|
|
|
key: train_accuracy
|
|
value: [0.95754717 0.98113208 0.99529412 0.99764706 0.99058824 0.99764706
|
|
1. 0.99529412 0.99529412 0.99058824]
|
|
|
|
mean value: 0.990103218645949
|
|
|
|
key: test_fscore
|
|
value: [0.95652174 0.97959184 0.95833333 0.95652174 0.93877551 0.92
|
|
0.97959184 0.97959184 0.97959184 0.90566038]
|
|
|
|
mean value: 0.9554180046095551
|
|
|
|
key: train_fscore
|
|
value: [0.95566502 0.98148148 0.9953271 0.99765808 0.99069767 0.99765808
|
|
1. 0.99530516 0.99530516 0.99065421]
|
|
|
|
mean value: 0.9899751976830926
|
|
|
|
key: test_precision
|
|
value: [1. 0.96 0.92 0.95652174 0.88461538 0.85185185
|
|
0.96 0.96 0.96 0.82758621]
|
|
|
|
mean value: 0.9280575182494223
|
|
|
|
key: train_precision
|
|
value: [1. 0.96363636 0.99069767 0.9953271 0.98156682 0.9953271
|
|
1. 0.99065421 0.99065421 0.98148148]
|
|
|
|
mean value: 0.9889344956635377
|
|
|
|
key: test_recall
|
|
value: [0.91666667 1. 1. 0.95652174 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9873188405797102
|
|
|
|
key: train_recall
|
|
value: [0.91509434 1. 1. 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9915094339622641
|
|
|
|
key: test_roc_auc
|
|
value: [0.95833333 0.97916667 0.95833333 0.95742754 0.9375 0.91666667
|
|
0.97826087 0.97826087 0.97826087 0.89130435]
|
|
|
|
mean value: 0.9533514492753623
|
|
|
|
key: train_roc_auc
|
|
value: [0.95754717 0.98113208 0.99528302 0.99764151 0.99056604 0.99764151
|
|
1. 0.99530516 0.99530516 0.99061033]
|
|
|
|
mean value: 0.9901031978031712
|
|
|
|
key: test_jcc
|
|
value: [0.91666667 0.96 0.92 0.91666667 0.88461538 0.85185185
|
|
0.96 0.96 0.96 0.82758621]
|
|
|
|
mean value: 0.9157386776697122
|
|
|
|
key: train_jcc
|
|
value: [0.91509434 0.96363636 0.99069767 0.9953271 0.98156682 0.9953271
|
|
1. 0.99065421 0.99065421 0.98148148]
|
|
|
|
mean value: 0.9804439296258018
|
|
|
|
MCC on Blind test: 0.71
|
|
|
|
Accuracy on Blind test: 0.9
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.01751876 0.0172987 0.01691103 0.01572132 0.01613498 0.01923203
|
|
0.0173223 0.01733422 0.01822901 0.01838923]
|
|
|
|
mean value: 0.017409157752990723
|
|
|
|
key: score_time
|
|
value: [0.01176405 0.01167679 0.01175261 0.01165009 0.01167178 0.01167154
|
|
0.01167941 0.01166654 0.01170206 0.01169348]
|
|
|
|
mean value: 0.01169283390045166
|
|
|
|
key: test_mcc
|
|
value: [0.8819171 1. 0.70329486 0.8729597 0.70329486 0.78804348
|
|
0.73387289 0.91804649 0.91804649 0.76896316]
|
|
|
|
mean value: 0.8288439037171799
|
|
|
|
key: train_mcc
|
|
value: [0.8588975 0.96295001 0.74410644 0.97648101 0.74028876 0.99058818
|
|
0.84282793 0.92297178 0.97215397 0.82661049]
|
|
|
|
mean value: 0.8837876078404974
|
|
|
|
key: test_accuracy
|
|
value: [0.9375 1. 0.82978723 0.93617021 0.82978723 0.89361702
|
|
0.85106383 0.95744681 0.95744681 0.87234043]
|
|
|
|
mean value: 0.9065159574468085
|
|
|
|
key: train_accuracy
|
|
value: [0.9245283 0.98113208 0.85647059 0.98823529 0.85411765 0.99529412
|
|
0.91529412 0.96 0.98588235 0.90588235]
|
|
|
|
mean value: 0.9366836847946726
|
|
|
|
key: test_fscore
|
|
value: [0.94117647 1. 0.85185185 0.93333333 0.85185185 0.89361702
|
|
0.87272727 0.96 0.96 0.88888889]
|
|
|
|
mean value: 0.915344669051803
|
|
|
|
key: train_fscore
|
|
value: [0.92982456 0.98148148 0.87474333 0.9882904 0.87295082 0.99530516
|
|
0.92173913 0.96145125 0.98604651 0.9137931 ]
|
|
|
|
mean value: 0.9425625744168039
|
|
|
|
key: test_precision
|
|
value: [0.88888889 1. 0.74193548 0.95454545 0.74193548 0.875
|
|
0.77419355 0.92307692 0.92307692 0.8 ]
|
|
|
|
mean value: 0.8622652705717222
|
|
|
|
key: train_precision
|
|
value: [0.86885246 0.96363636 0.77737226 0.98598131 0.77454545 0.99530516
|
|
0.85483871 0.92576419 0.97247706 0.84126984]
|
|
|
|
mean value: 0.896004282000958
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 0.91304348 1. 0.91304348
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9826086956521739
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 0.99061033 1. 0.99530516
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9985915492957746
|
|
|
|
key: test_roc_auc
|
|
value: [0.9375 1. 0.83333333 0.93568841 0.83333333 0.89402174
|
|
0.84782609 0.95652174 0.95652174 0.86956522]
|
|
|
|
mean value: 0.9064311594202898
|
|
|
|
key: train_roc_auc
|
|
value: [0.9245283 0.98113208 0.85613208 0.98822969 0.85377358 0.99529409
|
|
0.91549296 0.9600939 0.98591549 0.90610329]
|
|
|
|
mean value: 0.9366695455753388
|
|
|
|
key: test_jcc
|
|
value: [0.88888889 1. 0.74193548 0.875 0.74193548 0.80769231
|
|
0.77419355 0.92307692 0.92307692 0.8 ]
|
|
|
|
mean value: 0.8475799558864076
|
|
|
|
key: train_jcc
|
|
value: [0.86885246 0.96363636 0.77737226 0.97685185 0.77454545 0.99065421
|
|
0.85483871 0.92576419 0.97247706 0.84126984]
|
|
|
|
mean value: 0.8946262404738445
|
|
|
|
MCC on Blind test: 0.71
|
|
|
|
Accuracy on Blind test: 0.9
|
|
|
|
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))]
|
|
/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]
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.1842308 0.17368841 0.15581465 0.16468692 0.16333556 0.16491508
|
|
0.16548753 0.16415215 0.15618253 0.1561389 ]
|
|
|
|
mean value: 0.1648632526397705
|
|
|
|
key: score_time
|
|
value: [0.01613069 0.01626849 0.01646876 0.01641393 0.0164125 0.01640797
|
|
0.01651359 0.01523924 0.01514077 0.01519299]
|
|
|
|
mean value: 0.016018891334533693
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 0.9591663 0.95833333 0.95833333 1. 0.91833182
|
|
0.95825929 1. 0.95825929 0.87917396]
|
|
|
|
mean value: 0.9549023644261122
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 0.97916667 0.9787234 0.9787234 1. 0.95744681
|
|
0.9787234 1. 0.9787234 0.93617021]
|
|
|
|
mean value: 0.9766843971631205
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 0.9787234 0.9787234 0.9787234 1. 0.95833333
|
|
0.97959184 1. 0.97959184 0.94117647]
|
|
|
|
mean value: 0.9774455526891608
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.95833333 0.95833333 1. 0.92
|
|
0.96 1. 0.96 0.88888889]
|
|
|
|
mean value: 0.9605555555555556
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 0.95833333 1. 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 0.97916667 0.97916667 0.97916667 1. 0.95833333
|
|
0.97826087 1. 0.97826087 0.93478261]
|
|
|
|
mean value: 0.9766304347826087
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 0.95833333 0.95833333 0.95833333 1. 0.92
|
|
0.96 1. 0.96 0.88888889]
|
|
|
|
mean value: 0.9563888888888888
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.87
|
|
|
|
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: 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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.05078888 0.04690146 0.0549891 0.05241156 0.06411147 0.04866076
|
|
0.06251597 0.07328773 0.06806421 0.05429673]
|
|
|
|
mean value: 0.05760278701782227
|
|
|
|
key: score_time
|
|
value: [0.01889825 0.02064395 0.02360368 0.02269864 0.01972151 0.02119589
|
|
0.0327642 0.03937674 0.02679276 0.03134727]
|
|
|
|
mean value: 0.025704288482666017
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.95833333 0.91833182 1. 0.91833182
|
|
0.95825929 0.95833333 0.95825929 0.95825929]
|
|
|
|
mean value: 0.9587274487406885
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 0.99530506 0.99063185 0.99063185 1.
|
|
1. 0.99058818 1. 0.99530516]
|
|
|
|
mean value: 0.9962462115879616
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.9787234 0.95744681 1. 0.95744681
|
|
0.9787234 0.9787234 0.9787234 0.9787234 ]
|
|
|
|
mean value: 0.9787677304964539
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 0.99764706 0.99529412 0.99529412 1.
|
|
1. 0.99529412 1. 0.99764706]
|
|
|
|
mean value: 0.9981176470588236
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.9787234 0.95833333 1. 0.95833333
|
|
0.97959184 0.9787234 0.97959184 0.97959184]
|
|
|
|
mean value: 0.9792480822116081
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 0.99765808 0.9953271 0.9953271 1.
|
|
1. 0.99528302 1. 0.99764706]
|
|
|
|
mean value: 0.9981242362924223
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.95833333 0.92 1. 0.92
|
|
0.96 1. 0.96 0.96 ]
|
|
|
|
mean value: 0.9638333333333333
|
|
|
|
key: train_precision
|
|
value: [1. 1. 0.9953271 0.99069767 0.99069767 1.
|
|
1. 0.99528302 1. 0.99530516]
|
|
|
|
mean value: 0.9967310634828122
|
|
|
|
key: test_recall
|
|
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]
|
|
[1. 1. 1. 1. 1. 1.
|
|
1. 0.95833333 1. 1. ]
|
|
|
|
mean value: 0.9958333333333333
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 0.99528302 1. 1. ]
|
|
|
|
mean value: 0.9995283018867924
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.97916667 0.95833333 1. 0.95833333
|
|
0.97826087 0.97916667 0.97826087 0.97826087]
|
|
|
|
mean value: 0.9788949275362319
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 0.99764151 0.99528302 0.99528302 1.
|
|
1. 0.99529409 1. 0.99765258]
|
|
|
|
mean value: 0.9981154220923023
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.95833333 0.92 1. 0.92
|
|
0.96 0.95833333 0.96 0.96 ]
|
|
|
|
mean value: 0.9596666666666667
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 0.9953271 0.99069767 0.99069767 1.
|
|
1. 0.99061033 1. 0.99530516]
|
|
|
|
mean value: 0.9962637944598695
|
|
|
|
MCC on Blind test: 0.8
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.13153625 0.16104722 0.1615622 0.16053796 0.16203284 0.18379307
|
|
0.20143414 0.19101357 0.16114759 0.13982606]
|
|
|
|
mean value: 0.16539309024810792
|
|
|
|
key: score_time
|
|
value: [0.02348018 0.02348733 0.0235014 0.02349448 0.02353978 0.02359962
|
|
0.02344251 0.02358198 0.02802014 0.02346206]
|
|
|
|
mean value: 0.02396094799041748
|
|
|
|
key: test_mcc
|
|
value: [0.8819171 0.91666667 0.74773263 0.79418308 0.87979456 0.91833182
|
|
0.84147165 0.76896316 0.84147165 0.75474102]
|
|
|
|
mean value: 0.8345273331863536
|
|
|
|
key: train_mcc
|
|
value: [0.99529409 1. 0.99530506 0.99530506 0.99530506 1.
|
|
0.98589335 0.99530516 0.99530516 1. ]
|
|
|
|
mean value: 0.9957712949452199
|
|
|
|
key: test_accuracy
|
|
value: [0.9375 0.95833333 0.87234043 0.89361702 0.93617021 0.95744681
|
|
0.91489362 0.87234043 0.91489362 0.87234043]
|
|
|
|
mean value: 0.9129875886524823
|
|
|
|
key: train_accuracy
|
|
value: [0.99764151 1. 0.99764706 0.99764706 0.99764706 1.
|
|
0.99294118 0.99764706 0.99764706 1. ]
|
|
|
|
mean value: 0.9978817980022198
|
|
|
|
key: test_fscore
|
|
value: [0.94117647 0.95833333 0.875 0.89795918 0.93877551 0.95833333
|
|
0.92307692 0.88888889 0.92307692 0.88461538]
|
|
|
|
mean value: 0.9189235950790573
|
|
|
|
key: train_fscore
|
|
value: [0.99764706 1. 0.99765808 0.99765808 0.99765808 1.
|
|
0.99294118 0.99764706 0.99764706 1. ]
|
|
|
|
mean value: 0.9978856591817055
|
|
|
|
key: test_precision
|
|
value: [0.88888889 0.95833333 0.84 0.84615385 0.88461538 0.92
|
|
0.85714286 0.8 0.85714286 0.82142857]
|
|
|
|
mean value: 0.8673705738705738
|
|
|
|
key: train_precision
|
|
value: [0.99530516 1. 0.9953271 0.9953271 0.9953271 1.
|
|
0.99061033 0.99530516 0.99530516 1. ]
|
|
|
|
mean value: 0.996250713000746
|
|
|
|
key: test_recall
|
|
value: [1. 0.95833333 0.91304348 0.95652174 1. 1.
|
|
1. 1. 1. 0.95833333]
|
|
|
|
mean value: 0.9786231884057971
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
0.99528302 1. 1. 1. ]
|
|
|
|
mean value: 0.9995283018867924
|
|
|
|
key: test_roc_auc
|
|
value: [0.9375 0.95833333 0.87318841 0.89492754 0.9375 0.95833333
|
|
0.91304348 0.86956522 0.91304348 0.87047101]
|
|
|
|
mean value: 0.912590579710145
|
|
|
|
key: train_roc_auc
|
|
value: [0.99764151 1. 0.99764151 0.99764151 0.99764151 1.
|
|
0.99294667 0.99765258 0.99765258 1. ]
|
|
|
|
mean value: 0.9978817875808309
|
|
|
|
key: test_jcc
|
|
value: [0.88888889 0.92 0.77777778 0.81481481 0.88461538 0.92
|
|
0.85714286 0.8 0.85714286 0.79310345]
|
|
|
|
mean value: 0.8513486028658442
|
|
|
|
key: train_jcc
|
|
value: [0.99530516 1. 0.9953271 0.9953271 0.9953271 1.
|
|
0.98598131 0.99530516 0.99530516 1. ]
|
|
|
|
mean value: 0.9957878109780177
|
|
|
|
MCC on Blind test: 0.31
|
|
|
|
Accuracy on Blind test: 0.79
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.56000113 0.56888103 0.56448817 0.549757 0.55608559 0.56176829
|
|
0.5581181 0.56202459 0.5552206 0.56254649]
|
|
|
|
mean value: 0.5598891019821167
|
|
|
|
key: score_time
|
|
value: [0.01020789 0.00940442 0.00912881 0.00919271 0.00928235 0.00907826
|
|
0.00915623 0.00917006 0.00924325 0.00930262]
|
|
|
|
mean value: 0.009316658973693848
|
|
|
|
key: test_mcc
|
|
value: [0.9591663 1. 0.95833333 0.91485507 1. 0.91833182
|
|
0.95825929 1. 0.95825929 1. ]
|
|
|
|
mean value: 0.9667205114201297
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97916667 1. 0.9787234 0.95744681 1. 0.95744681
|
|
0.9787234 1. 0.9787234 1. ]
|
|
|
|
mean value: 0.9830230496453901
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.97959184 1. 0.9787234 0.95652174 1. 0.95833333
|
|
0.97959184 1. 0.97959184 1. ]
|
|
|
|
mean value: 0.9832353986923169
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.96 1. 0.95833333 0.95652174 1. 0.92
|
|
0.96 1. 0.96 1. ]
|
|
|
|
mean value: 0.9714855072463768
|
|
|
|
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. 0.95652174 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9956521739130435
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.97916667 1. 0.97916667 0.95742754 1. 0.95833333
|
|
0.97826087 1. 0.97826087 1. ]
|
|
|
|
mean value: 0.9830615942028985
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.96 1. 0.95833333 0.91666667 1. 0.92
|
|
0.96 1. 0.96 1. ]
|
|
|
|
mean value: 0.9675
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.85
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.04724836 0.02826905 0.02789617 0.02829599 0.02833748 0.0285368
|
|
0.02765012 0.02901912 0.04195118 0.02951407]
|
|
|
|
mean value: 0.03167183399200439
|
|
|
|
key: score_time
|
|
value: [0.02039742 0.01246238 0.01912665 0.01498961 0.01664877 0.01496887
|
|
0.01526523 0.0150125 0.01996708 0.01542878]
|
|
|
|
mean value: 0.016426730155944824
|
|
|
|
key: test_mcc
|
|
value: [1. 0.91986621 0.83243502 0.95825929 0.91804649 1.
|
|
1. 1. 1. 0.91485507]
|
|
|
|
mean value: 0.9543462083649876
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.95833333 0.91489362 0.9787234 0.95744681 1.
|
|
1. 1. 1. 0.95744681]
|
|
|
|
mean value: 0.9766843971631206
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 0.95652174 0.90909091 0.97777778 0.95454545 1.
|
|
1. 1. 1. 0.95833333]
|
|
|
|
mean value: 0.975626921387791
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.95238095 1. 1. 1.
|
|
1. 1. 1. 0.95833333]
|
|
|
|
mean value: 0.9910714285714286
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 0.91666667 0.86956522 0.95652174 0.91304348 1.
|
|
1. 1. 1. 0.95833333]
|
|
|
|
mean value: 0.9614130434782608
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.95833333 0.91394928 0.97826087 0.95652174 1.
|
|
1. 1. 1. 0.95742754]
|
|
|
|
mean value: 0.9764492753623188
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 0.91666667 0.83333333 0.95652174 0.91304348 1.
|
|
1. 1. 1. 0.92 ]
|
|
|
|
mean value: 0.9539565217391305
|
|
|
|
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: 0.79
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.02758026 0.05485988 0.03708529 0.03730607 0.03710651 0.0371542
|
|
0.04041576 0.03962588 0.03754663 0.03745675]
|
|
|
|
mean value: 0.03861372470855713
|
|
|
|
key: score_time
|
|
value: [0.02137327 0.02091146 0.02237916 0.02355099 0.02399397 0.01998377
|
|
0.02394271 0.02328444 0.02324319 0.02394271]
|
|
|
|
mean value: 0.02266056537628174
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.95833333 0.95833333 0.84254172 0.84254172
|
|
0.87917396 1. 0.91804649 0.84147165]
|
|
|
|
mean value: 0.9240442204746091
|
|
|
|
key: train_mcc
|
|
value: [0.96750869 0.97668677 0.9767396 0.98598008 0.97215032 0.98134942
|
|
0.985981 0.97674215 0.97674215 0.97674215]
|
|
|
|
mean value: 0.9776622331191687
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.9787234 0.9787234 0.91489362 0.91489362
|
|
0.93617021 1. 0.95744681 0.91489362]
|
|
|
|
mean value: 0.9595744680851064
|
|
|
|
key: train_accuracy
|
|
value: [0.98349057 0.98820755 0.98823529 0.99294118 0.98588235 0.99058824
|
|
0.99294118 0.98823529 0.98823529 0.98823529]
|
|
|
|
mean value: 0.9886992230854607
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.9787234 0.9787234 0.92 0.92
|
|
0.94117647 1. 0.96 0.92307692]
|
|
|
|
mean value: 0.9621700202175797
|
|
|
|
key: train_fscore
|
|
value: [0.9837587 0.98834499 0.98839907 0.99300699 0.98611111 0.99069767
|
|
0.99297424 0.98834499 0.98834499 0.98834499]
|
|
|
|
mean value: 0.988832774341435
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.95833333 0.95833333 0.85185185 0.85185185
|
|
0.88888889 1. 0.92307692 0.85714286]
|
|
|
|
mean value: 0.9289479039479039
|
|
|
|
key: train_precision
|
|
value: [0.96803653 0.97695853 0.97706422 0.98611111 0.97260274 0.98156682
|
|
0.98604651 0.97695853 0.97695853 0.97695853]
|
|
|
|
mean value: 0.9779262033987883
|
|
|
|
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: /home/tanu/git/LSHTM_analysis/scripts/ml/./embb_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/./embb_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)
|
|
[1. 1. 0.97916667 0.97916667 0.91666667 0.91666667
|
|
0.93478261 1. 0.95652174 0.91304348]
|
|
|
|
mean value: 0.9596014492753624
|
|
|
|
key: train_roc_auc
|
|
value: [0.98349057 0.98820755 0.98820755 0.99292453 0.98584906 0.99056604
|
|
0.99295775 0.98826291 0.98826291 0.98826291]
|
|
|
|
mean value: 0.9886991761892107
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 0.95833333 0.95833333 0.85185185 0.85185185
|
|
0.88888889 1. 0.92307692 0.85714286]
|
|
|
|
mean value: 0.9289479039479039
|
|
|
|
key: train_jcc
|
|
value: [0.96803653 0.97695853 0.97706422 0.98611111 0.97260274 0.98156682
|
|
0.98604651 0.97695853 0.97695853 0.97695853]
|
|
|
|
mean value: 0.9779262033987883
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
Accuracy on Blind test: 0.93
|
|
|
|
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_ppi2_affinity', 'interface_dist',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=168)),
|
|
('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: [0.25773263 0.26639366 0.26582193 0.28191543 0.27604246 0.31778526
|
|
0.26713467 0.27099061 0.27422667 0.26525044]
|
|
|
|
mean value: 0.27432937622070314
|
|
|
|
key: score_time
|
|
value: [0.02232027 0.02227116 0.02303052 0.02353454 0.02763891 0.02054596
|
|
0.023844 0.02344608 0.02244258 0.02367902]
|
|
|
|
mean value: 0.023275303840637206
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.95833333 0.95833333 0.84254172 0.91833182
|
|
0.87917396 1. 0.91804649 0.84147165]
|
|
|
|
mean value: 0.9316232309670757
|
|
|
|
key: train_mcc
|
|
value: [0.96750869 0.97668677 0.9767396 0.98598008 0.97215032 0.98598008
|
|
0.985981 0.97674215 0.97674215 0.97674215]
|
|
|
|
mean value: 0.9781252982543283
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.9787234 0.9787234 0.91489362 0.95744681
|
|
0.93617021 1. 0.95744681 0.91489362]
|
|
|
|
mean value: 0.9638297872340426
|
|
|
|
key: train_accuracy
|
|
value: [0.98349057 0.98820755 0.98823529 0.99294118 0.98588235 0.99294118
|
|
0.99294118 0.98823529 0.98823529 0.98823529]
|
|
|
|
mean value: 0.9889345172031077
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.9787234 0.9787234 0.92 0.95833333
|
|
0.94117647 1. 0.96 0.92307692]
|
|
|
|
mean value: 0.966003353550913
|
|
|
|
key: train_fscore
|
|
value: [0.9837587 0.98834499 0.98839907 0.99300699 0.98611111 0.99300699
|
|
0.99297424 0.98834499 0.98834499 0.98834499]
|
|
|
|
mean value: 0.9890637062002738
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.95833333 0.95833333 0.85185185 0.92
|
|
0.88888889 1. 0.92307692 0.85714286]
|
|
|
|
mean value: 0.9357627187627188
|
|
|
|
key: train_precision
|
|
value: [0.96803653 0.97695853 0.97706422 0.98611111 0.97260274 0.98611111
|
|
0.98604651 0.97695853 0.97695853 0.97695853]
|
|
|
|
mean value: 0.9783806324822497
|
|
|
|
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. 0.97916667 0.97916667 0.91666667 0.95833333
|
|
0.93478261 1. 0.95652174 0.91304348]
|
|
|
|
mean value: 0.963768115942029
|
|
|
|
key: train_roc_auc
|
|
value: [0.98349057 0.98820755 0.98820755 0.99292453 0.98584906 0.99292453
|
|
0.99295775 0.98826291 0.98826291 0.98826291]
|
|
|
|
mean value: 0.9889350252458144
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 0.95833333 0.95833333 0.85185185 0.92
|
|
0.88888889 1. 0.92307692 0.85714286]
|
|
|
|
mean value: 0.9357627187627188
|
|
|
|
key: train_jcc
|
|
value: [0.96803653 0.97695853 0.97706422 0.98611111 0.97260274 0.98611111
|
|
0.98604651 0.97695853 0.97695853 0.97695853]
|
|
|
|
mean value: 0.9783806324822497
|
|
|
|
MCC on Blind test: 0.78
|
|
|
|
Accuracy on Blind test: 0.93
|