14264 lines
896 KiB
Text
14264 lines
896 KiB
Text
/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_rt.py:550: SettingWithCopyWarning:
|
|
A value is trying to be set on a copy of a slice from a DataFrame
|
|
|
|
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
|
|
mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/xgboost/compat.py:36: FutureWarning: pandas.Int64Index is deprecated and will be removed from pandas in a future version. Use pandas.Index with the appropriate dtype instead.
|
|
from pandas import MultiIndex, Int64Index
|
|
1.22.4
|
|
1.4.1
|
|
|
|
aaindex_df contains non-numerical data
|
|
|
|
Total no. of non-numerial columns: 2
|
|
|
|
Selecting numerical data only
|
|
|
|
PASS: successfully selected numerical columns only for aaindex_df
|
|
|
|
Now checking for NA in the remaining aaindex_cols
|
|
|
|
Counting aaindex_df cols with NA
|
|
ncols with NA: 4 columns
|
|
Dropping these...
|
|
Original ncols: 127
|
|
|
|
Revised df ncols: 123
|
|
|
|
Checking NA in revised df...
|
|
|
|
PASS: cols with NA successfully dropped from aaindex_df
|
|
Proceeding with combining aa_df with other features_df
|
|
|
|
PASS: ncols match
|
|
Expected ncols: 123
|
|
Got: 123
|
|
|
|
Total no. of columns in clean aa_df: 123
|
|
|
|
Proceeding to merge, expected nrows in merged_df: 531
|
|
|
|
PASS: my_features_df and aa_df successfully combined
|
|
nrows: 531
|
|
ncols: 286
|
|
count of NULL values before imputation
|
|
|
|
or_mychisq 263
|
|
log10_or_mychisq 263
|
|
dtype: int64
|
|
count of NULL values AFTER imputation
|
|
|
|
mutationinformation 0
|
|
or_rawI 0
|
|
logorI 0
|
|
dtype: int64
|
|
|
|
PASS: OR values imputed, data ready for ML
|
|
|
|
Total no. of features for aaindex: 123
|
|
|
|
No. of numerical features: 167
|
|
No. of categorical features: 7
|
|
|
|
index: 0
|
|
ind: 1
|
|
|
|
Mask count check: True
|
|
|
|
index: 1
|
|
ind: 2
|
|
|
|
Mask count check: True
|
|
Original Data
|
|
Counter({0: 409, 1: 3}) Data dim: (412, 174)
|
|
|
|
-------------------------------------------------------------
|
|
Successfully split data: REVERSE training
|
|
imputed values: training set
|
|
actual values: blind test set
|
|
Train data size: (412, 174)
|
|
Test data size: (119, 174)
|
|
y_train numbers: Counter({0: 409, 1: 3})
|
|
y_train ratio: 136.33333333333334
|
|
|
|
y_test_numbers: Counter({0: 76, 1: 43})
|
|
y_test ratio: 1.7674418604651163
|
|
-------------------------------------------------------------
|
|
Simple Random OverSampling
|
|
Counter({0: 409, 1: 409})
|
|
(818, 174)
|
|
Simple Random UnderSampling
|
|
Counter({0: 3, 1: 3})
|
|
(6, 174)
|
|
Simple Combined Over and UnderSampling
|
|
Counter({0: 409, 1: 409})
|
|
(818, 174)
|
|
SMOTE_NC OverSampling
|
|
Counter({0: 409, 1: 409})
|
|
(818, 174)
|
|
|
|
#####################################################################
|
|
|
|
Running ML analysis: REVERSE training
|
|
|
|
Gene name: gid
|
|
Drug name: streptomycin
|
|
|
|
Output directory: /home/tanu/git/Data/streptomycin/output/ml/tts_rt/
|
|
|
|
Sanity checks:
|
|
Total input features: 174
|
|
|
|
Training data size: (412, 174)
|
|
Test data size: (119, 174)
|
|
|
|
Target feature numbers (training data): Counter({0: 409, 1: 3})
|
|
Target features ratio (training data: 136.33333333333334
|
|
|
|
Target feature numbers (test data): Counter({0: 76, 1: 43})
|
|
Target features ratio (test data): 1.7674418604651163
|
|
|
|
#####################################################################
|
|
|
|
|
|
================================================================
|
|
|
|
Strucutral features (n): 35
|
|
These are:
|
|
Common stablity features: ['ligand_distance', 'ligand_affinity_change', 'duet_stability_change', 'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts', 'mcsm_na_affinity']
|
|
FoldX columns: ['electro_rr', 'electro_mm', 'electro_sm', 'electro_ss', 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss', 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss', 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss', 'vdwclashes_rr', 'vdwclashes_mm', 'vdwclashes_sm', 'vdwclashes_ss', 'volumetric_rr', 'volumetric_mm', 'volumetric_ss']
|
|
Other struc columns: ['rsa', 'kd_values', 'rd_values']
|
|
================================================================
|
|
|
|
AAindex features (n): 123
|
|
These are:
|
|
['ALTS910101', 'AZAE970101', 'AZAE970102', 'BASU010101', 'BENS940101', 'BENS940102', 'BENS940103', 'BENS940104', 'BETM990101', 'BLAJ010101', 'BONM030101', 'BONM030102', 'BONM030103', 'BONM030104', 'BONM030105', 'BONM030106', 'BRYS930101', 'CROG050101', 'CSEM940101', 'DAYM780301', 'DAYM780302', 'DOSZ010101', 'DOSZ010102', 'DOSZ010103', 'DOSZ010104', 'FEND850101', 'FITW660101', 'GEOD900101', 'GIAG010101', 'GONG920101', 'GRAR740104', 'HENS920101', 'HENS920102', 'HENS920103', 'HENS920104', 'JOHM930101', 'JOND920103', 'JOND940101', 'KANM000101', 'KAPO950101', 'KESO980101', 'KESO980102', 'KOLA920101', 'KOLA930101', 'KOSJ950100_RSA_SST', 'KOSJ950100_SST', 'KOSJ950110_RSA', 'KOSJ950115', 'LEVJ860101', 'LINK010101', 'LIWA970101', 'LUTR910101', 'LUTR910102', 'LUTR910103', 'LUTR910104', 'LUTR910105', 'LUTR910106', 'LUTR910107', 'LUTR910108', 'LUTR910109', 'MCLA710101', 'MCLA720101', 'MEHP950102', 'MICC010101', 'MIRL960101', 'MIYS850102', 'MIYS850103', 'MIYS930101', 'MIYS960101', 'MIYS960102', 'MIYS960103', 'MIYS990106', 'MIYS990107', 'MIYT790101', 'MOHR870101', 'MOOG990101', 'MUET010101', 'MUET020101', 'MUET020102', 'NAOD960101', 'NGPC000101', 'NIEK910101', 'NIEK910102', 'OGAK980101', 'OVEJ920100_RSA', 'OVEJ920101', 'OVEJ920102', 'OVEJ920103', 'PRLA000101', 'PRLA000102', 'QUIB020101', 'QU_C930101', 'QU_C930102', 'QU_C930103', 'RIER950101', 'RISJ880101', 'RUSR970101', 'RUSR970102', 'RUSR970103', 'SIMK990101', 'SIMK990102', 'SIMK990103', 'SIMK990104', 'SIMK990105', 'SKOJ000101', 'SKOJ000102', 'SKOJ970101', 'TANS760101', 'TANS760102', 'THOP960101', 'TOBD000101', 'TOBD000102', 'TUDE900101', 'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101', 'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106']
|
|
================================================================
|
|
|
|
Evolutionary features (n): 3
|
|
These are:
|
|
['consurf_score', 'snap2_score', 'provean_score']
|
|
================================================================
|
|
|
|
Genomic features (n): 6
|
|
These are:
|
|
['maf', 'logorI']
|
|
['lineage_proportion', 'dist_lineage_proportion', 'lineage_count_all', 'lineage_count_unique']
|
|
================================================================
|
|
|
|
Categorical features (n): 7
|
|
These are:
|
|
['ss_class', 'aa_prop_change', 'electrostatics_change', 'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site']
|
|
================================================================
|
|
|
|
|
|
Pass: No. of features match
|
|
|
|
#####################################################################
|
|
|
|
|
|
Model_name: Logistic Regression
|
|
Model func: LogisticRegression(random_state=42)
|
|
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 2 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 2 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 2 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LogisticRegression(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01989913 0.02139759 0.02002597 0.03451586 0.0280056 0.03632236
|
|
0.02027631 0.02962422 0.03100157 0.03250861]
|
|
|
|
mean value: 0.027357721328735353
|
|
|
|
key: score_time
|
|
value: [0.0128715 0.01213503 0.01457286 0.01133895 0.01129723 0.01150632
|
|
0.01147532 0.01419973 0.01247072 0.01238894]
|
|
|
|
mean value: 0.012425661087036133
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Logistic RegressionCV
|
|
Model func: LogisticRegressionCV(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LogisticRegressionCV(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=5.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[0.32015514 0.29606748 0.34469795 0.32714677 0.5100379 0.35257006
|
|
0.34146309 0.32645774 0.33970666 0.30980587]
|
|
|
|
mean value: 0.34681086540222167
|
|
|
|
key: score_time
|
|
value: [0.01249838 0.01282454 0.01188016 0.01201582 0.01188278 0.01193213
|
|
0.01159549 0.01159835 0.01162362 0.01247168]
|
|
|
|
mean value: 0.012032294273376464
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Gaussian NB
|
|
Model func: GaussianNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GaussianNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01610732 0.01534462 0.01008058 0.01067209 0.01061916 0.01147008
|
|
0.01083493 0.01097155 0.01086569 0.01091909]
|
|
|
|
mean value: 0.011788511276245117
|
|
|
|
key: score_time
|
|
value: [0.0125947 0.01148891 0.00836134 0.00904775 0.0091002 0.00894094
|
|
0.00898957 0.00901532 0.00915742 0.01016784]
|
|
|
|
mean value: 0.00968639850616455
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
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. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Naive Bayes
|
|
Model func: BernoulliNB()
|
|
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', BernoulliNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01143622 0.01087689 0.01108122 0.01111841 0.01095366 0.01134276
|
|
0.01103449 0.01116729 0.01100588 0.01114798]
|
|
|
|
mean value: 0.011116480827331543
|
|
|
|
key: score_time
|
|
value: [0.00971389 0.00984168 0.00832176 0.00884438 0.0087328 0.00878572
|
|
0.00879002 0.00871754 0.00878549 0.00984311]
|
|
|
|
mean value: 0.009037637710571289
|
|
|
|
key: test_mcc
|
|
value: [-0.02439024 0. nan nan nan nan
|
|
nan nan nan 0. ]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [-0.00543478 -0.00666528 -0.00815217 -0.00815217 -0.0066472 -0.00815217
|
|
-0.00815217 -0.00815217 -0.00815217 -0.0066472 ]
|
|
|
|
mean value: -0.007430750394168724
|
|
|
|
key: test_accuracy
|
|
value: [0.95238095 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.98918919 0.98648649 0.98382749 0.98382749 0.98652291 0.98382749
|
|
0.98382749 0.98382749 0.98382749 0.98652291]
|
|
|
|
mean value: 0.9851686457346835
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.48780488 0.5 nan nan nan nan
|
|
nan nan nan 0.5 ]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.49728261 0.49592391 0.49592391 0.49592391 0.49728261 0.49592391
|
|
0.49592391 0.49592391 0.49592391 0.49593496]
|
|
|
|
mean value: 0.4961967568045246
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: -0.07
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: K-Nearest Neighbors
|
|
Model func: KNeighborsClassifier()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', KNeighborsClassifier())])
|
|
|
|
key: fit_time
|
|
value: [0.01051664 0.0111444 0.01057911 0.01073694 0.01086092 0.01030827
|
|
0.01071453 0.01029611 0.01004815 0.00915384]
|
|
|
|
mean value: 0.010435891151428223
|
|
|
|
key: score_time
|
|
value: [0.08815837 0.01870036 0.01156998 0.01183891 0.01103091 0.01112247
|
|
0.01270485 0.01529336 0.01064134 0.01371527]
|
|
|
|
mean value: 0.02047758102416992
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: SVM
|
|
Model func: SVC(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', SVC(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01050568 0.01019382 0.01052141 0.01041746 0.01076007 0.01149678
|
|
0.01037335 0.01086855 0.01035285 0.01040316]
|
|
|
|
mean value: 0.010589313507080079
|
|
|
|
key: score_time
|
|
value: [0.00910854 0.00907183 0.00823593 0.00835204 0.00827742 0.00894523
|
|
0.00806546 0.00815535 0.00801182 0.0088501 ]
|
|
|
|
mean value: 0.008507370948791504
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
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/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', MLPClassifier(max_iter=500, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.07598901 0.08371949 0.0635035 0.06438303 0.06469774 0.06213498
|
|
0.06427479 0.06431317 0.06999135 0.07021499]
|
|
|
|
mean value: 0.06832220554351806
|
|
|
|
key: score_time
|
|
value: [0.01199293 0.01225996 0.0116899 0.01158714 0.01154232 0.01144671
|
|
0.01235509 0.01183105 0.01171947 0.0125463 ]
|
|
|
|
mean value: 0.011897087097167969
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Decision Tree
|
|
Model func: DecisionTreeClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', DecisionTreeClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[0.01785231 0.01330876 0.01328421 0.01276445 0.0128417 0.01568699
|
|
0.01443124 0.01690936 0.01593995 0.01157117]
|
|
|
|
mean value: 0.014459013938903809
|
|
|
|
key: score_time
|
|
value: [0.01500154 0.00937605 0.00824142 0.00831437 0.00889111 0.00872159
|
|
0.00888252 0.00857997 0.00813174 0.00908661]
|
|
|
|
mean value: 0.009322690963745116
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
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. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.12
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Extra Trees
|
|
Model func: ExtraTreesClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', ExtraTreesClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.08993912 0.08948255 0.0866437 0.08457899 0.08424997 0.08384418
|
|
0.08424282 0.08384633 0.08527565 0.08414817]
|
|
|
|
mean value: 0.08562514781951905
|
|
|
|
key: score_time
|
|
value: [0.01871276 0.0188036 0.01643777 0.02006221 0.01625156 0.0163331
|
|
0.0162921 0.01657963 0.01643276 0.01721597]
|
|
|
|
mean value: 0.017312145233154295
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
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. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
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: 0.64
|
|
|
|
Model_name: Extra Tree
|
|
Model func: ExtraTreeClassifier(random_state=42)
|
|
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', ExtraTreeClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01054931 0.00981259 0.00974107 0.00977802 0.00951934 0.00969315
|
|
0.01019955 0.00981641 0.00991702 0.00960732]
|
|
|
|
mean value: 0.00986337661743164
|
|
|
|
key: score_time
|
|
value: [0.00950408 0.00891519 0.00787663 0.0080781 0.00800753 0.00796795
|
|
0.00864196 0.00863695 0.00802159 0.00875759]
|
|
|
|
mean value: 0.008440756797790527
|
|
|
|
key: test_mcc
|
|
value: [-0.03492151 0. nan nan nan nan
|
|
nan nan nan -0.025 ]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.92857143 0.97619048 nan nan nan nan
|
|
nan nan nan 0.95121951]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.47560976 0.5 nan nan nan nan
|
|
nan nan nan 0.4875 ]
|
|
|
|
mean value: nan
|
|
|
|
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. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: -0.07
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: 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/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
|
|
warn(
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
RandomForestClassifier(n_estimators=1000, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [1.04075599 1.02801013 1.07141137 1.08398533 1.13270688 1.07735205
|
|
1.07241106 1.07471728 1.07248068 1.03925109]
|
|
|
|
mean value: 1.0693081855773925
|
|
|
|
key: score_time
|
|
value: [0.09357929 0.09518886 0.09432316 0.09397125 0.08665419 0.08706093
|
|
0.08933854 0.08832955 0.08816171 0.09343171]
|
|
|
|
mean value: 0.09100391864776611
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
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. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
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: 0.64
|
|
|
|
Model_name: Random Forest2
|
|
Model func: RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000...05', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10,
|
|
oob_score=True, random_state=42))])
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
|
|
key: fit_time
|
|
value: [1.84526539 0.94256401 0.87784743 0.87131786 0.87920451 0.88232422
|
|
0.87456799 0.91457176 0.89835405 0.87264204]
|
|
|
|
mean value: 0.9858659267425537
|
|
|
|
key: score_time
|
|
value: [0.2224977 0.1898675 0.21597195 0.26002526 0.21300793 0.2356112
|
|
0.20910764 0.22935915 0.21669412 0.21950126]
|
|
|
|
mean value: 0.22116436958312988
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Naive Bayes
|
|
Model func: BernoulliNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', BernoulliNB())])
|
|
|
|
key: fit_time
|
|
value: [0.02475333 0.0101583 0.01128387 0.01099753 0.01108003 0.01017022
|
|
0.0107851 0.00999808 0.01097155 0.01101136]
|
|
|
|
mean value: 0.012120938301086426
|
|
|
|
key: score_time
|
|
value: [0.00987434 0.00949407 0.00875926 0.00866365 0.00858641 0.00872087
|
|
0.00876784 0.00811195 0.00882792 0.00923276]
|
|
|
|
mean value: 0.008903908729553222
|
|
|
|
key: test_mcc
|
|
value: [-0.02439024 0. nan nan nan nan
|
|
nan nan nan 0. ]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [-0.00543478 -0.00666528 -0.00815217 -0.00815217 -0.0066472 -0.00815217
|
|
-0.00815217 -0.00815217 -0.00815217 -0.0066472 ]
|
|
|
|
mean value: -0.007430750394168724
|
|
|
|
key: test_accuracy
|
|
value: [0.95238095 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.98918919 0.98648649 0.98382749 0.98382749 0.98652291 0.98382749
|
|
0.98382749 0.98382749 0.98382749 0.98652291]
|
|
|
|
mean value: 0.9851686457346835
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.48780488 0.5 nan nan nan nan
|
|
nan nan nan 0.5 ]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.49728261 0.49592391 0.49592391 0.49592391 0.49728261 0.49592391
|
|
0.49592391 0.49592391 0.49592391 0.49593496]
|
|
|
|
mean value: 0.4961967568045246
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: -0.07
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
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: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000...
|
|
interaction_constraints=None, learning_rate=None,
|
|
max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan,
|
|
monotone_constraints=None, n_estimators=100,
|
|
n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None,
|
|
reg_lambda=None, scale_pos_weight=None,
|
|
subsample=None, tree_method=None,
|
|
use_label_encoder=False,
|
|
validate_parameters=None, verbosity=0))])
|
|
|
|
key: fit_time
|
|
value: [0.15044928 0.04897809 0.05639958 0.06074142 0.08801484 0.05432439
|
|
0.05890536 0.06162691 0.06117535 0.05631852]
|
|
|
|
mean value: 0.06969337463378907
|
|
|
|
key: score_time
|
|
value: [0.01093197 0.01076651 0.00965357 0.00998425 0.01001692 0.00999784
|
|
0.01029325 0.01003051 0.00980496 0.011235 ]
|
|
|
|
mean value: 0.010271477699279784
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0.70614799 0.70614799 0.81538947 0.81538947 0.81538947 1.
|
|
0.81538947 0.81538947 0.81538947 1. ]
|
|
|
|
mean value: 0.8304632782242238
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.9972973 0.9972973 0.99730458 0.99730458 0.99730458 1.
|
|
0.99730458 0.99730458 0.99730458 1. ]
|
|
|
|
mean value: 0.997842208785605
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0.66666667 0.66666667 0.8 0.8 0.8 1.
|
|
0.8 0.8 0.8 1. ]
|
|
|
|
mean value: 0.8133333333333334
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0.5 0.5 0.66666667 0.66666667 0.66666667 1.
|
|
0.66666667 0.66666667 0.66666667 1. ]
|
|
|
|
mean value: 0.7
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.75 0.75 0.83333333 0.83333333 0.83333333 1.
|
|
0.83333333 0.83333333 0.83333333 1. ]
|
|
|
|
mean value: 0.85
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0.5 0.5 0.66666667 0.66666667 0.66666667 1.
|
|
0.66666667 0.66666667 0.66666667 1. ]
|
|
|
|
mean value: 0.7
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
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/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LinearDiscriminantAnalysis())])
|
|
|
|
key: fit_time
|
|
value: [0.04444814 0.05598116 0.06279087 0.03509378 0.04921556 0.07959771
|
|
0.06728888 0.06242537 0.07381535 0.03813124]
|
|
|
|
mean value: 0.05687880516052246
|
|
|
|
key: score_time
|
|
value: [0.01246095 0.02204037 0.02578568 0.01153469 0.01158452 0.02235889
|
|
0.02250266 0.02209353 0.02209496 0.0125103 ]
|
|
|
|
mean value: 0.01849665641784668
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 0.86484794 0.86484794 0.86484794 0.86484794
|
|
1. 0.86484794 1. 0.81538947]
|
|
|
|
mean value: 0.9139629158315105
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 0.99730458 0.99730458 0.99730458 0.99730458
|
|
1. 0.99730458 1. 0.99730458]
|
|
|
|
mean value: 0.9983827493261456
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 0.85714286 0.85714286 0.85714286 0.85714286
|
|
1. 0.85714286 1. 0.8 ]
|
|
|
|
mean value: 0.9085714285714286
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 0.75 0.75 0.75 0.75
|
|
1. 0.75 1. 0.66666667]
|
|
|
|
mean value: 0.8416666666666667
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 0.9986413 0.9986413 0.9986413 0.9986413
|
|
1. 0.9986413 1. 0.99864499]
|
|
|
|
mean value: 0.9991851508188996
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 0.75 0.75 0.75 0.75
|
|
1. 0.75 1. 0.66666667]
|
|
|
|
mean value: 0.8416666666666667
|
|
|
|
MCC on Blind test: 0.1
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Multinomial
|
|
Model func: MultinomialNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', MultinomialNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01979399 0.01152015 0.01133204 0.01063061 0.01144385 0.01150703
|
|
0.01080608 0.01222038 0.01035595 0.01057076]
|
|
|
|
mean value: 0.012018084526062012
|
|
|
|
key: score_time
|
|
value: [0.01043391 0.0104506 0.00911331 0.00911403 0.00901508 0.00888371
|
|
0.00888872 0.00870442 0.00886321 0.01030731]
|
|
|
|
mean value: 0.009377431869506837
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0.
|
|
0. 0. 0.57578775 0. ]
|
|
|
|
mean value: 0.05757877486813449
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99460916 0.99460916]
|
|
|
|
mean value: 0.9929889997814526
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0.5 0. ]
|
|
|
|
mean value: 0.05
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 1. 0.]
|
|
|
|
mean value: 0.1
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0.
|
|
0. 0. 0.33333333 0. ]
|
|
|
|
mean value: 0.03333333333333333
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5
|
|
0.5 0.5 0.66666667 0.5 ]
|
|
|
|
mean value: 0.5166666666666666
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
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/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[0. 0. 0. 0. 0. 0.
|
|
0. 0. 0.33333333 0. ]
|
|
|
|
mean value: 0.03333333333333333
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Passive Aggresive
|
|
Model func: PassiveAggressiveClassifier(n_jobs=10, random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
PassiveAggressiveClassifier(n_jobs=10, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01436138 0.01534724 0.01509571 0.01730561 0.01619768 0.01917768
|
|
0.01716328 0.02114773 0.01738644 0.0191133 ]
|
|
|
|
mean value: 0.017229604721069335
|
|
|
|
key: score_time
|
|
value: [0.00999451 0.01163411 0.01093435 0.01128221 0.01092696 0.0112462
|
|
0.0111506 0.01127481 0.0135498 0.01213241]
|
|
|
|
mean value: 0.011412596702575684
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 0.70614799 0.81538947 1. 1. 0.57578775
|
|
1. 0.81538947 0.81538947 1. ]
|
|
|
|
mean value: 0.8728104139802464
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 0.9972973 0.99730458 1. 1. 0.99460916
|
|
1. 0.99730458 0.99730458 1. ]
|
|
|
|
mean value: 0.9983820208348511
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 0.66666667 0.8 1. 1. 0.5
|
|
1. 0.8 0.8 1. ]
|
|
|
|
mean value: 0.8566666666666667
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 0.5 0.66666667 1. 1. 0.33333333
|
|
1. 0.66666667 0.66666667 1. ]
|
|
|
|
mean value: 0.7833333333333333
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [1. 0.75 0.83333333 1. 1. 0.66666667
|
|
1. 0.83333333 0.83333333 1. ]
|
|
|
|
mean value: 0.8916666666666666
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [1. 0.5 0.66666667 1. 1. 0.33333333
|
|
1. 0.66666667 0.66666667 1. ]
|
|
|
|
mean value: 0.7833333333333333
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
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: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', SGDClassifier(n_jobs=10, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01883221 0.01770854 0.01782966 0.01542687 0.01819515 0.01625967
|
|
0.01974487 0.01578569 0.01943088 0.01426744]
|
|
|
|
mean value: 0.017348098754882812
|
|
|
|
key: score_time
|
|
value: [0.01210117 0.0125072 0.01142359 0.01086974 0.01098657 0.01108551
|
|
0.01127458 0.011127 0.01064634 0.01213956]
|
|
|
|
mean value: 0.011416125297546386
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 1. 1. 1. 1.
|
|
0.57578775 0.57578775 1. 1. ]
|
|
|
|
mean value: 0.715157549736269
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 1. 1. 1. 1.
|
|
0.99460916 0.99460916 1. 1. ]
|
|
|
|
mean value: 0.997840751803016
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 1. 1. 1. 1. 0.5 0.5 1. 1. ]
|
|
|
|
mean value: 0.7
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 0.8
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 1. 1. 1. 1.
|
|
0.33333333 0.33333333 1. 1. ]
|
|
|
|
mean value: 0.6666666666666666
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 1. 1. 1. 1.
|
|
0.66666667 0.66666667 1. 1. ]
|
|
|
|
mean value: 0.8333333333333334
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 1. 1. 1. 1.
|
|
0.33333333 0.33333333 1. 1. ]
|
|
|
|
mean value: 0.6666666666666666
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: AdaBoost Classifier
|
|
Model func: AdaBoostClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', AdaBoostClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.16987848 0.15895891 0.14807296 0.15208459 0.15941596 0.15608859
|
|
0.14817023 0.15044117 0.14882445 0.15114546]
|
|
|
|
mean value: 0.15430808067321777
|
|
|
|
key: score_time
|
|
value: [0.01673746 0.01536226 0.01484203 0.01564717 0.01588035 0.01446342
|
|
0.01494956 0.01494145 0.01467395 0.01594186]
|
|
|
|
mean value: 0.015343952178955077
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
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. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.12
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Bagging Classifier
|
|
Model func: BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)
|
|
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
BaggingClassifier(n_jobs=10, oob_score=True,
|
|
random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.05544281 0.06112909 0.0427177 0.06485868 0.04066658 0.05549884
|
|
0.05135918 0.06852889 0.06360698 0.06171417]
|
|
|
|
mean value: 0.05655229091644287
|
|
|
|
key: score_time
|
|
value: [0.02798557 0.02249169 0.0232358 0.01667023 0.02339268 0.02715111
|
|
0.03077722 0.03415179 0.03425574 0.04068136]
|
|
|
|
mean value: 0.02807931900024414
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 0.57578775 0.57578775 0.57578775 1.
|
|
0.81538947 0.57578775 1. 0. ]
|
|
|
|
mean value: 0.711854046113585
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 0.99460916 0.99460916 0.99460916 1.
|
|
0.99730458 0.99460916 1. 0.99460916]
|
|
|
|
mean value: 0.9970350404312669
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 0.5 0.5 0.5 1. 0.8 0.5 1. 0. ]
|
|
|
|
mean value: 0.68
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 0.]
|
|
|
|
mean value: 0.9
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 0.33333333 0.33333333 0.33333333 1.
|
|
0.66666667 0.33333333 1. 0. ]
|
|
|
|
mean value: 0.6
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 0.66666667 0.66666667 0.66666667 1.
|
|
0.83333333 0.66666667 1. 0.5 ]
|
|
|
|
mean value: 0.7999999999999999
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 0.33333333 0.33333333 0.33333333 1.
|
|
0.66666667 0.33333333 1. 0. ]
|
|
|
|
mean value: 0.6
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
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: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GaussianProcessClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.09493756 0.12387276 0.14413285 0.13103056 0.12700105 0.14302993
|
|
0.10722637 0.10728407 0.13245082 0.1236937 ]
|
|
|
|
mean value: 0.12346596717834472
|
|
|
|
key: score_time
|
|
value: [0.02551651 0.02611494 0.02803993 0.02623105 0.02616787 0.02645826
|
|
0.02657771 0.0264411 0.02686644 0.02554941]
|
|
|
|
mean value: 0.02639632225036621
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0.70614799 0.70614799 0.81538947 0.81538947 0.81538947 0.81538947
|
|
0.81538947 0.81538947 0.81538947 1. ]
|
|
|
|
mean value: 0.812002224865271
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.9972973 0.9972973 0.99730458 0.99730458 0.99730458 0.99730458
|
|
0.99730458 0.99730458 0.99730458 1. ]
|
|
|
|
mean value: 0.9975726670066293
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0.66666667 0.66666667 0.8 0.8 0.8 0.8
|
|
0.8 0.8 0.8 1. ]
|
|
|
|
mean value: 0.7933333333333333
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0.5 0.5 0.66666667 0.66666667 0.66666667 0.66666667
|
|
0.66666667 0.66666667 0.66666667 1. ]
|
|
|
|
mean value: 0.6666666666666666
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.75 0.75 0.83333333 0.83333333 0.83333333 0.83333333
|
|
0.83333333 0.83333333 0.83333333 1. ]
|
|
|
|
mean value: 0.8333333333333333
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0.5 0.5 0.66666667 0.66666667 0.66666667 0.66666667
|
|
0.66666667 0.66666667 0.66666667 1. ]
|
|
|
|
mean value: 0.6666666666666666
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Gradient Boosting
|
|
Model func: GradientBoostingClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GradientBoostingClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.37525511 0.36695719 0.36911511 0.36837983 0.36991143 0.51728988
|
|
0.37010503 0.52289772 0.52321172 0.20602083]
|
|
|
|
mean value: 0.39891438484191893
|
|
|
|
key: score_time
|
|
value: [0.00933504 0.00948024 0.00845313 0.00824428 0.00835323 0.00815487
|
|
0.00842738 0.00815463 0.00849557 0.009197 ]
|
|
|
|
mean value: 0.008629536628723145
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
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. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.12
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: QDA
|
|
Model func: QuadraticDiscriminantAnalysis()
|
|
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/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:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', QuadraticDiscriminantAnalysis())])
|
|
|
|
key: fit_time
|
|
value: [0.02627063 0.0297873 0.07492399 0.05087018 0.038692 0.03735232
|
|
0.03435063 0.03712821 0.02941561 0.02809024]
|
|
|
|
mean value: 0.03868811130523682
|
|
|
|
key: score_time
|
|
value: [0.01187539 0.03454638 0.0263474 0.01137161 0.02450061 0.0197978
|
|
0.02197385 0.01114798 0.01123142 0.01212859]
|
|
|
|
mean value: 0.01849210262298584
|
|
|
|
key: test_mcc
|
|
value: [-0.02439024 -0.03492151 nan nan nan nan
|
|
nan nan nan -0.025 ]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.95238095 0.92857143 nan nan nan nan
|
|
nan nan nan 0.95121951]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.48780488 0.47560976 nan nan nan nan
|
|
nan nan nan 0.4875 ]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Ridge Classifier
|
|
Model func: RidgeClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', RidgeClassifier(random_state=42))])
|
|
|
|
key: fit_time /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/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 2 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 2 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1592: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no true nor predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, "true nor predicted", "F-score is", len(true_sum))
|
|
/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: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 due to no true 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/model_selection/_validation.py:776: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 767, in _score
|
|
scores = scorer(estimator, X_test, y_test)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 106, in __call__
|
|
score = scorer._score(cached_call, estimator, *args, **kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_scorer.py", line 267, in _score
|
|
return self._sign * self._score_func(y_true, y_pred, **self._kwargs)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 569, in roc_auc_score
|
|
return _average_binary_score(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
|
|
return binary_metric(y_true, y_score, sample_weight=sample_weight)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_ranking.py", line 338, in _binary_roc_auc_score
|
|
raise ValueError(
|
|
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
|
|
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 2 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py:680: UserWarning: The least populated class in y has only 3 members, which is less than n_splits=10.
|
|
warnings.warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_rt.py:114: SettingWithCopyWarning:
|
|
A value is trying to be set on a copy of a slice from a DataFrame
|
|
|
|
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
|
|
baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_rt.py:117: 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)
|
|
|
|
value: [0.02520037 0.03303194 0.03606892 0.03627133 0.03032136 0.03611326
|
|
0.03608656 0.03004909 0.03638005 0.03393817]
|
|
|
|
mean value: 0.03334610462188721
|
|
|
|
key: score_time
|
|
value: [0.02206588 0.02527237 0.02517176 0.02519727 0.02531409 0.02258182
|
|
0.02516508 0.02220869 0.02191806 0.02567792]
|
|
|
|
mean value: 0.024057292938232423
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Ridge ClassifierCV
|
|
Model func: RidgeClassifierCV(cv=10)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', RidgeClassifierCV(cv=10))])
|
|
|
|
key: fit_time
|
|
value: [0.24358463 0.24829793 0.2510066 0.25444627 0.25330687 0.26447606
|
|
0.27128458 0.30404878 0.25829268 0.25916886]
|
|
|
|
mean value: 0.26079132556915285
|
|
|
|
key: score_time
|
|
value: [0.02582049 0.02625751 0.02527237 0.02232337 0.02252817 0.0247674
|
|
0.02487659 0.02488422 0.02405882 0.02176929]
|
|
|
|
mean value: 0.024255824089050294
|
|
|
|
key: test_mcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_mcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_accuracy
|
|
value: [0.97619048 0.97619048 nan nan nan nan
|
|
nan nan nan 0.97560976]
|
|
|
|
mean value: nan
|
|
|
|
key: train_accuracy
|
|
value: [0.99459459 0.99459459 0.99191375 0.99191375 0.99191375 0.99191375
|
|
0.99191375 0.99191375 0.99191375 0.99460916]
|
|
|
|
mean value: 0.9927194580024769
|
|
|
|
key: test_fscore
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_fscore
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_precision
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_precision
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_recall
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_recall
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.5 0.5 nan nan nan nan nan nan nan 0.5]
|
|
|
|
mean value: nan
|
|
|
|
key: train_roc_auc
|
|
value: [0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5]
|
|
|
|
mean value: 0.5
|
|
|
|
key: test_jcc
|
|
value: [ 0. 0. nan nan nan nan nan nan nan 0.]
|
|
|
|
mean value: nan
|
|
|
|
key: train_jcc
|
|
value: [0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
|
|
|
|
mean value: 0.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Logistic Regression
|
|
Model func: LogisticRegression(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LogisticRegression(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.02864671 0.02664042 0.02762151 0.0318346 0.02810979 0.03002357
|
|
0.02838254 0.0265522 0.02744389 0.02837777]
|
|
|
|
mean value: 0.028363299369812012
|
|
|
|
key: score_time
|
|
value: [0.01195574 0.01175928 0.01182771 0.01192236 0.01198316 0.0118866
|
|
0.01181173 0.01239872 0.01185322 0.01191878]
|
|
|
|
mean value: 0.011931729316711426
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 0.97590007 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9927409901994627
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99728629 0.99728629 0.99728629 1. 0.99728629
|
|
0.99728629 0.99728629 0.99728997 0.99728995]
|
|
|
|
mean value: 0.9975583961405413
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 0.98780488 1.
|
|
1. 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9963264077085215
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 1. 0.9986413
|
|
0.9986413 0.9986413 0.99864315 0.99864315]
|
|
|
|
mean value: 0.9987775426228541
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 0.98765432 1.
|
|
1. 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9963260449204224
|
|
|
|
key: train_fscore
|
|
value: [0.99863946 0.99863946 0.99863946 0.99863946 1. 0.99863946
|
|
0.99863946 0.99863946 0.99864315 0.99863946]
|
|
|
|
mean value: 0.9987758794155382
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 1. 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9951800232288037
|
|
|
|
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. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 0.98780488 1. 0.98780488 1.
|
|
1. 1. 0.98780488 1. ]
|
|
|
|
mean value: 0.9963414634146341
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 1. 0.9986413
|
|
0.9986413 0.9986413 0.99864499 0.9986413 ]
|
|
|
|
mean value: 0.9987775421232474
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 0.97619048 1. 0.97560976 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9927409988385598
|
|
|
|
key: train_jcc
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Logistic RegressionCV
|
|
Model func: LogisticRegressionCV(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LogisticRegressionCV(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.70233035 0.524055 0.48847866 0.48064637 0.50587416 0.51395321
|
|
0.51212144 0.46806359 0.46835923 0.67188501]
|
|
|
|
mean value: 0.5335767030715942
|
|
|
|
key: score_time
|
|
value: [0.01204348 0.01221061 0.01208615 0.01207471 0.01226497 0.01208091
|
|
0.01211357 0.01209903 0.01210117 0.01218176]
|
|
|
|
mean value: 0.012125635147094726
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
0.97590007 0.97590007 0.97560976 1. ]
|
|
|
|
mean value: 0.9903309974943161
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99728629 0.99728629 0.99728629 1. 1.
|
|
1. 0.99456522 0.99728997 0.99728995]
|
|
|
|
mean value: 0.9978290306424038
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 0.98780488 0.98765432 1. ]
|
|
|
|
mean value: 0.9951068955133996
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 1. 1.
|
|
1. 0.99728261 0.99864315 0.99864315]
|
|
|
|
mean value: 0.9989134121880715
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 1.
|
|
0.98795181 0.98795181 0.98765432 1. ]
|
|
|
|
mean value: 0.995121225643314
|
|
|
|
key: train_fscore
|
|
value: [0.99863946 0.99863946 0.99863946 0.99863946 1. 1.
|
|
1. 0.99728261 0.99864315 0.99863946]
|
|
|
|
mean value: 0.9989123035504096
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
0.97619048 0.97619048 0.97560976 1. ]
|
|
|
|
mean value: 0.9927990708478514
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 0.99728261 1. 1. ]
|
|
|
|
mean value: 0.9997282608695652
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 1.
|
|
1. 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9980985625073642
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 0.98780488 0.98780488 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 1. 1.
|
|
1. 0.99728261 0.99864499 0.9986413 ]
|
|
|
|
mean value: 0.9989134116884648
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
0.97619048 0.97619048 0.97560976 1. ]
|
|
|
|
mean value: 0.9903600464576074
|
|
|
|
key: train_jcc
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 1.
|
|
1. 0.99457995 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9978282962177448
|
|
|
|
MCC on Blind test: 0.1
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Gaussian NB
|
|
Model func: GaussianNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GaussianNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01617408 0.01320672 0.01180935 0.01129079 0.01151109 0.0114429
|
|
0.01146865 0.0116272 0.01405287 0.01234508]
|
|
|
|
mean value: 0.012492871284484864
|
|
|
|
key: score_time
|
|
value: [0.01227593 0.00933051 0.00936937 0.00899673 0.00907826 0.00901532
|
|
0.00900316 0.00899124 0.00994086 0.00929475]
|
|
|
|
mean value: 0.009529614448547363
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975900072948534
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99728629 0.99728629 0.99728629 1. 0.99728629
|
|
0.99728629 0.99728629 0.99728997 0.99728995]
|
|
|
|
mean value: 0.9975583961405413
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 1. 0.9986413
|
|
0.9986413 0.9986413 0.99864315 0.99864315]
|
|
|
|
mean value: 0.9987775426228541
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9987654320987654
|
|
|
|
key: train_fscore
|
|
value: [0.99863946 0.99863946 0.99863946 0.99863946 1. 0.99863946
|
|
0.99863946 0.99863946 0.99864315 0.99863946]
|
|
|
|
mean value: 0.9987758794155382
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 1. 0.9986413
|
|
0.9986413 0.9986413 0.99864499 0.9986413 ]
|
|
|
|
mean value: 0.9987775421232474
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_jcc
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
MCC on Blind test: -0.07
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: Naive Bayes
|
|
Model func: BernoulliNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', BernoulliNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01663947 0.01513195 0.01523376 0.01532173 0.01524663 0.01522851
|
|
0.01521087 0.01525855 0.01529098 0.02192926]
|
|
|
|
mean value: 0.01604917049407959
|
|
|
|
key: score_time
|
|
value: [0.01222825 0.01201463 0.01202512 0.01207089 0.01205087 0.01207089
|
|
0.01207471 0.01207829 0.01202965 0.01265216]
|
|
|
|
mean value: 0.012129545211791992
|
|
|
|
key: test_mcc
|
|
value: [1. 0.92932038 0.97590007 0.97590007 0.95121951 0.95235327
|
|
0.95235327 0.95235327 1. 1. ]
|
|
|
|
mean value: 0.9689399834833974
|
|
|
|
key: train_mcc
|
|
value: [0.97039895 0.97572001 0.96510517 0.97305604 0.97318546 0.97039895
|
|
0.97039895 0.97039895 0.96779073 0.96515328]
|
|
|
|
mean value: 0.9701606488894258
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.96341463 0.98780488 0.98780488 0.97560976 0.97560976
|
|
0.97560976 0.97560976 1. 1. ]
|
|
|
|
mean value: 0.9841463414634146
|
|
|
|
key: train_accuracy
|
|
value: [0.98505435 0.98777174 0.98233696 0.98641304 0.98641304 0.98505435
|
|
0.98505435 0.98505435 0.98371777 0.98236092]
|
|
|
|
mean value: 0.9849230871335024
|
|
|
|
key: test_fscore
|
|
value: [1. 0.96470588 0.98795181 0.98795181 0.97560976 0.97619048
|
|
0.97619048 0.97619048 1. 1. ]
|
|
|
|
mean value: 0.9844790681479763
|
|
|
|
key: train_fscore
|
|
value: [0.9852349 0.98788694 0.98259705 0.98655914 0.98659517 0.9852349
|
|
0.9852349 0.9852349 0.98395722 0.98259705]
|
|
|
|
mean value: 0.9851132185205181
|
|
|
|
key: test_precision
|
|
value: [1. 0.93181818 0.97619048 0.97619048 0.97560976 0.95348837
|
|
0.95348837 0.95348837 1. 1. ]
|
|
|
|
mean value: 0.9720274006575765
|
|
|
|
key: train_precision
|
|
value: [0.9734748 0.97866667 0.96833773 0.97606383 0.97354497 0.9734748
|
|
0.9734748 0.9734748 0.97097625 0.96833773]
|
|
|
|
mean value: 0.9729826389282483
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.96341463 0.98780488 0.98780488 0.97560976 0.97560976
|
|
0.97560976 0.97560976 1. 1. ]
|
|
|
|
mean value: 0.9841463414634146
|
|
|
|
key: train_roc_auc
|
|
value: [0.98505435 0.98777174 0.98233696 0.98641304 0.98641304 0.98505435
|
|
0.98505435 0.98505435 0.98369933 0.98238114]
|
|
|
|
mean value: 0.9849232649935196
|
|
|
|
key: test_jcc
|
|
value: [1. 0.93181818 0.97619048 0.97619048 0.95238095 0.95348837
|
|
0.95348837 0.95348837 1. 1. ]
|
|
|
|
mean value: 0.9697045202859156
|
|
|
|
key: train_jcc
|
|
value: [0.97089947 0.97606383 0.96578947 0.9734748 0.97354497 0.97089947
|
|
0.97089947 0.97089947 0.96842105 0.96578947]
|
|
|
|
mean value: 0.9706681487991099
|
|
|
|
MCC on Blind test: 0.07
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: K-Nearest Neighbors
|
|
Model func: KNeighborsClassifier()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', KNeighborsClassifier())])
|
|
|
|
key: fit_time
|
|
value: [0.01525855 0.01103139 0.01229334 0.01178408 0.01259732 0.01231575
|
|
0.01306176 0.01331615 0.01320744 0.01262689]
|
|
|
|
mean value: 0.012749266624450684
|
|
|
|
key: score_time
|
|
value: [0.0398953 0.01294327 0.01847672 0.01840377 0.01431727 0.01472712
|
|
0.0146594 0.01454973 0.01474571 0.01453471]
|
|
|
|
mean value: 0.017725300788879395
|
|
|
|
key: test_mcc
|
|
value: [1. 0.97590007 0.97590007 1. 0.97590007 1.
|
|
0.97590007 0.9067647 1. 0.97559506]
|
|
|
|
mean value: 0.9785960048885964
|
|
|
|
key: train_mcc
|
|
value: [0.98644582 0.98644582 0.98644582 0.98644582 0.9865041 0.98644582
|
|
0.98914504 0.98914504 0.99186249 0.98915981]
|
|
|
|
mean value: 0.9878045610087458
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.98780488 0.98780488 1. 0.98780488 1.
|
|
0.98780488 0.95121951 1. 0.98765432]
|
|
|
|
mean value: 0.9890093345377898
|
|
|
|
key: train_accuracy
|
|
value: [0.99320652 0.99320652 0.99320652 0.99320652 0.99320652 0.99320652
|
|
0.99456522 0.99456522 0.99592944 0.99457259]
|
|
|
|
mean value: 0.9938871600495547
|
|
|
|
key: test_fscore
|
|
value: [1. 0.98795181 0.98795181 1. 0.98765432 1.
|
|
0.98795181 0.95348837 1. 0.98795181]
|
|
|
|
mean value: 0.989294992199634
|
|
|
|
key: train_fscore
|
|
value: [0.9932341 0.9932341 0.9932341 0.9932341 0.99325236 0.9932341
|
|
0.99457995 0.99457995 0.99594046 0.99457995]
|
|
|
|
mean value: 0.993910315982957
|
|
|
|
key: test_precision
|
|
value: [1. 0.97619048 0.97619048 1. 1. 1.
|
|
0.97619048 0.91111111 1. 0.97619048]
|
|
|
|
mean value: 0.9815873015873016
|
|
|
|
key: train_precision
|
|
value: [0.98921833 0.98921833 0.98921833 0.98921833 0.98659517 0.98921833
|
|
0.99189189 0.99189189 0.99459459 0.99189189]
|
|
|
|
mean value: 0.9902957088737857
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.98780488 0.98780488 1. 0.98780488 1.
|
|
0.98780488 0.95121951 1. 0.9875 ]
|
|
|
|
mean value: 0.9889939024390244
|
|
|
|
key: train_roc_auc
|
|
value: [0.99320652 0.99320652 0.99320652 0.99320652 0.99320652 0.99320652
|
|
0.99456522 0.99456522 0.9959276 0.99457626]
|
|
|
|
mean value: 0.9938873424060328
|
|
|
|
key: test_jcc
|
|
value: [1. 0.97619048 0.97619048 1. 0.97560976 1.
|
|
0.97619048 0.91111111 1. 0.97619048]
|
|
|
|
mean value: 0.9791482771970577
|
|
|
|
key: train_jcc
|
|
value: [0.98655914 0.98655914 0.98655914 0.98655914 0.98659517 0.98655914
|
|
0.98921833 0.98921833 0.99191375 0.98921833]
|
|
|
|
mean value: 0.9878959606341104
|
|
|
|
MCC on Blind test: -0.04
|
|
|
|
Accuracy on Blind test: 0.62
|
|
|
|
Model_name: SVM
|
|
Model func: SVC(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', SVC(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01619244 0.01553178 0.01565218 0.01461983 0.01578021 0.01494431
|
|
0.01576471 0.01583004 0.01758289 0.01549101]
|
|
|
|
mean value: 0.015738940238952635
|
|
|
|
key: score_time
|
|
value: [0.01130342 0.01001787 0.01011443 0.01000953 0.01020145 0.01054621
|
|
0.01036334 0.01090264 0.01029825 0.01063371]
|
|
|
|
mean value: 0.010439085960388183
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975900072948534
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99728629 0.99728629 0.99728629 1. 0.99728629
|
|
0.99728629 0.99728629 0.99728997 0.99728995]
|
|
|
|
mean value: 0.9975583961405413
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 1. 0.9986413
|
|
0.9986413 0.9986413 0.99864315 0.99864315]
|
|
|
|
mean value: 0.9987775426228541
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9987654320987654
|
|
|
|
key: train_fscore
|
|
value: [0.99863946 0.99863946 0.99863946 0.99863946 1. 0.99863946
|
|
0.99863946 0.99863946 0.99864315 0.99863946]
|
|
|
|
mean value: 0.9987758794155382
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 1. 0.9986413
|
|
0.9986413 0.9986413 0.99864499 0.9986413 ]
|
|
|
|
mean value: 0.9987775421232474
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_jcc
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: MLP
|
|
Model func: MLPClassifier(max_iter=500, random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', MLPClassifier(max_iter=500, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.71033812 0.85398245 0.76243162 0.64253044 0.71102619 0.74322653
|
|
0.67659807 0.86070871 0.6764524 0.71408868]
|
|
|
|
mean value: 0.7351383209228516
|
|
|
|
key: score_time
|
|
value: [0.01244736 0.01238942 0.01265264 0.0124588 0.01265335 0.01254511
|
|
0.01257324 0.01247334 0.0125246 0.0124898 ]
|
|
|
|
mean value: 0.012520766258239746
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
0.97590007 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9927409901994627
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9963264077085215
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 1.
|
|
0.98795181 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9963260449204224
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
0.97619048 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9951800232288037
|
|
|
|
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. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98780488 1. ]
|
|
|
|
mean value: 0.9963414634146341
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
0.97619048 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9927409988385598
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: -0.01
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: Decision Tree
|
|
Model func: DecisionTreeClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', DecisionTreeClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.03180194 0.02575827 0.02321696 0.02543497 0.02257943 0.02369952
|
|
0.02363586 0.02361107 0.02385974 0.02565098]
|
|
|
|
mean value: 0.024924874305725098
|
|
|
|
key: score_time
|
|
value: [0.01251912 0.00972176 0.00946927 0.01002908 0.00947881 0.00931859
|
|
0.00975347 0.00951219 0.00998378 0.00985932]
|
|
|
|
mean value: 0.009964537620544434
|
|
|
|
key: test_mcc
|
|
value: [0.97590007 1. 0.97590007 1. 0.92710507 1.
|
|
0.97590007 1. 1. 1. ]
|
|
|
|
mean value: 0.9854805288146706
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.98780488 1. 0.98780488 1. 0.96341463 1.
|
|
0.98780488 1. 1. 1. ]
|
|
|
|
mean value: 0.9926829268292683
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.98765432 1. 0.98795181 1. 0.96385542 1.
|
|
0.98795181 1. 1. 1. ]
|
|
|
|
mean value: 0.9927413357132232
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 0.95238095 1.
|
|
0.97619048 1. 1. 1. ]
|
|
|
|
mean value: 0.9904761904761905
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.97560976 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.98780488 1. 0.98780488 1. 0.96341463 1.
|
|
0.98780488 1. 1. 1. ]
|
|
|
|
mean value: 0.9926829268292683
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.97560976 1. 0.97619048 1. 0.93023256 1.
|
|
0.97619048 1. 1. 1. ]
|
|
|
|
mean value: 0.9858223266618048
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Extra Trees
|
|
Model func: ExtraTreesClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', ExtraTreesClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.11132574 0.10388851 0.11121058 0.10519838 0.10347652 0.10427356
|
|
0.1079793 0.10282946 0.10855246 0.10818768]
|
|
|
|
mean value: 0.10669221878051757
|
|
|
|
key: score_time
|
|
value: [0.01775813 0.01951098 0.01936197 0.01826262 0.01819253 0.01921201
|
|
0.01875758 0.01807761 0.01975298 0.01824927]
|
|
|
|
mean value: 0.01871356964111328
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 0.97590007
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951800145897066
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 0.98765432
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975308641975309
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: -0.07
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: Extra Tree
|
|
Model func: ExtraTreeClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', ExtraTreeClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01084042 0.01063967 0.0104816 0.01065373 0.01052141 0.01053262
|
|
0.01071382 0.01055121 0.01071 0.01063275]
|
|
|
|
mean value: 0.01062772274017334
|
|
|
|
key: score_time
|
|
value: [0.00893998 0.00872803 0.00880671 0.00882053 0.00877452 0.00883174
|
|
0.00872397 0.00879312 0.00882244 0.00878716]
|
|
|
|
mean value: 0.00880281925201416
|
|
|
|
key: test_mcc
|
|
value: [0.97590007 1. 1. 1. 0.95121951 1.
|
|
1. 1. 1. 0.97559506]
|
|
|
|
mean value: 0.9902714641653124
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.98780488 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 0.98765432]
|
|
|
|
mean value: 0.9951068955133996
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.98795181 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 0.98795181]
|
|
|
|
mean value: 0.9951513370555393
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.97619048 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 0.97619048]
|
|
|
|
mean value: 0.9927990708478514
|
|
|
|
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. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.98780488 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 0.9875 ]
|
|
|
|
mean value: 0.9950914634146342
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.97619048 1. 1. 1. 0.95238095 1.
|
|
1. 1. 1. 0.97619048]
|
|
|
|
mean value: 0.9904761904761905
|
|
|
|
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: 0.61
|
|
|
|
Model_name: Random Forest
|
|
Model func: RandomForestClassifier(n_estimators=1000, random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
RandomForestClassifier(n_estimators=1000, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [1.67246389 1.67752552 1.6656456 1.67518735 1.64327574 1.6754415
|
|
1.67777348 1.66476154 1.69954181 1.70067692]
|
|
|
|
mean value: 1.6752293348312377
|
|
|
|
key: score_time
|
|
value: [0.14544225 0.09017467 0.09018755 0.09005737 0.09022903 0.09050894
|
|
0.08992743 0.09079027 0.09556842 0.09634709]
|
|
|
|
mean value: 0.09692330360412597
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 0.97590007
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951800145897066
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 0.98765432
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975308641975309
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
/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/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))
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
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: 0.64
|
|
|
|
Model_name: Random Forest2
|
|
Model func: RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000...05', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10,
|
|
oob_score=True, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.99092054 1.16540051 1.00584269 1.03182769 1.01105213 1.06261158
|
|
1.01615024 1.07495379 1.00184035 1.06114531]
|
|
|
|
mean value: 1.042174482345581
|
|
|
|
key: score_time
|
|
value: [0.22117782 0.23626304 0.23236489 0.18774223 0.22354317 0.23702693
|
|
0.22307229 0.25480652 0.24092126 0.26768947]
|
|
|
|
mean value: 0.23246076107025146
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 0.97590007
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951800145897066
|
|
|
|
key: train_mcc
|
|
value: [0.99457991 0.99457991 0.99457991 0.99457991 0.99728629 0.99728629
|
|
0.99457991 0.99457991 0.99458727 0.99458719]
|
|
|
|
mean value: 0.9951226477721911
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_accuracy
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 0.9986413 0.9986413
|
|
0.99728261 0.99728261 0.9972863 0.9972863 ]
|
|
|
|
mean value: 0.9975550852457082
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 0.98765432
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975308641975309
|
|
|
|
key: train_fscore
|
|
value: [0.9972752 0.9972752 0.9972752 0.9972752 0.99863946 0.99863946
|
|
0.9972752 0.9972752 0.99728261 0.9972752 ]
|
|
|
|
mean value: 0.9975487950777989
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_recall
|
|
value: [0.99456522 0.99456522 0.99456522 0.99456522 0.99728261 0.99728261
|
|
0.99456522 0.99456522 0.99457995 0.99456522]
|
|
|
|
mean value: 0.9951101684929893
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_roc_auc
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 0.9986413 0.9986413
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_jcc
|
|
value: [0.99456522 0.99456522 0.99456522 0.99456522 0.99728261 0.99728261
|
|
0.99456522 0.99456522 0.99457995 0.99456522]
|
|
|
|
mean value: 0.9951101684929893
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Naive Bayes
|
|
Model func: BernoulliNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', BernoulliNB())])
|
|
|
|
key: fit_time
|
|
value: [0.02661252 0.01637578 0.01948047 0.02643633 0.01708198 0.01650357
|
|
0.01662159 0.02180552 0.01668048 0.01667333]
|
|
|
|
mean value: 0.019427156448364256
|
|
|
|
key: score_time
|
|
value: [0.01385212 0.0119977 0.01221657 0.01216435 0.01208377 0.01212525
|
|
0.01216173 0.01243138 0.01215315 0.01216531]
|
|
|
|
mean value: 0.01233513355255127
|
|
|
|
key: test_mcc
|
|
value: [1. 0.92932038 0.97590007 0.97590007 0.95121951 0.95235327
|
|
0.95235327 0.95235327 1. 1. ]
|
|
|
|
mean value: 0.9689399834833974
|
|
|
|
key: train_mcc
|
|
value: [0.97039895 0.97572001 0.96510517 0.97305604 0.97318546 0.97039895
|
|
0.97039895 0.97039895 0.96779073 0.96515328]
|
|
|
|
mean value: 0.9701606488894258
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.96341463 0.98780488 0.98780488 0.97560976 0.97560976
|
|
0.97560976 0.97560976 1. 1. ]
|
|
|
|
mean value: 0.9841463414634146
|
|
|
|
key: train_accuracy
|
|
value: [0.98505435 0.98777174 0.98233696 0.98641304 0.98641304 0.98505435
|
|
0.98505435 0.98505435 0.98371777 0.98236092]
|
|
|
|
mean value: 0.9849230871335024
|
|
|
|
key: test_fscore
|
|
value: [1. 0.96470588 0.98795181 0.98795181 0.97560976 0.97619048
|
|
0.97619048 0.97619048 1. 1. ]
|
|
|
|
mean value: 0.9844790681479763
|
|
|
|
key: train_fscore
|
|
value: [0.9852349 0.98788694 0.98259705 0.98655914 0.98659517 0.9852349
|
|
0.9852349 0.9852349 0.98395722 0.98259705]
|
|
|
|
mean value: 0.9851132185205181
|
|
|
|
key: test_precision
|
|
value: [1. 0.93181818 0.97619048 0.97619048 0.97560976 0.95348837
|
|
0.95348837 0.95348837 1. 1. ]
|
|
|
|
mean value: 0.9720274006575765
|
|
|
|
key: train_precision
|
|
value: [0.9734748 0.97866667 0.96833773 0.97606383 0.97354497 0.9734748
|
|
0.9734748 0.9734748 0.97097625 0.96833773]
|
|
|
|
mean value: 0.9729826389282483
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.96341463 0.98780488 0.98780488 0.97560976 0.97560976
|
|
0.97560976 0.97560976 1. 1. ]
|
|
|
|
mean value: 0.9841463414634146
|
|
|
|
key: train_roc_auc
|
|
value: [0.98505435 0.98777174 0.98233696 0.98641304 0.98641304 0.98505435
|
|
0.98505435 0.98505435 0.98369933 0.98238114]
|
|
|
|
mean value: 0.9849232649935196
|
|
|
|
key: test_jcc
|
|
value: [1. 0.93181818 0.97619048 0.97619048 0.95238095 0.95348837
|
|
0.95348837 0.95348837 1. 1. ]
|
|
|
|
mean value: 0.9697045202859156
|
|
|
|
key: train_jcc
|
|
value: [0.97089947 0.97606383 0.96578947 0.9734748 0.97354497 0.97089947
|
|
0.97089947 0.97089947 0.96842105 0.96578947]
|
|
|
|
mean value: 0.9706681487991099
|
|
|
|
MCC on Blind test: 0.07
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: XGBoost
|
|
Model func: XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000...
|
|
interaction_constraints=None, learning_rate=None,
|
|
max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan,
|
|
monotone_constraints=None, n_estimators=100,
|
|
n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None,
|
|
reg_lambda=None, scale_pos_weight=None,
|
|
subsample=None, tree_method=None,
|
|
use_label_encoder=False,
|
|
validate_parameters=None, verbosity=0))])
|
|
|
|
key: fit_time
|
|
value: [0.20946097 0.30711532 0.08906627 0.08612251 0.10769844 0.08769441
|
|
0.09436107 0.2328229 0.15788984 0.26959753]
|
|
|
|
mean value: 0.1641829252243042
|
|
|
|
key: score_time
|
|
value: [0.01183629 0.011976 0.01166344 0.01103258 0.011132 0.01190448
|
|
0.01189089 0.01126862 0.01215935 0.01104069]
|
|
|
|
mean value: 0.01159043312072754
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 0.95121951 0.97590007
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9903019658092188
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 0.97560976 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 0.97560976 0.98765432
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951215884314131
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951800232288037
|
|
|
|
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. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
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. 0.98780488 1. 0.97560976 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
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. 0.97619048 1. 0.95238095 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.990418118466899
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: -0.07
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: LDA
|
|
Model func: LinearDiscriminantAnalysis()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LinearDiscriminantAnalysis())])
|
|
|
|
key: fit_time
|
|
value: [0.0522449 0.07058001 0.05262351 0.1267302 0.08981466 0.09062672
|
|
0.10652876 0.05881453 0.10278082 0.07908916]
|
|
|
|
mean value: 0.08298332691192627
|
|
|
|
key: score_time
|
|
value: [0.0192585 0.0122261 0.01217866 0.02735615 0.0230546 0.01231122
|
|
0.01231313 0.0156126 0.0154686 0.01230407]
|
|
|
|
mean value: 0.016208362579345704
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 0.97590007 0.97590007 1.
|
|
0.97590007 0.97590007 0.97560976 0.95174259]
|
|
|
|
mean value: 0.9830952635721183
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99456522 0.99728629 0.99728629 1. 0.99456522
|
|
0.99728629 0.99728629 0.99728997 0.99457258]
|
|
|
|
mean value: 0.9967424443232185
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 0.98780488 0.98780488 1.
|
|
0.98780488 0.98780488 0.98765432 0.97530864]
|
|
|
|
mean value: 0.9914182475158084
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.99728261 0.9986413 0.9986413 1. 0.99728261
|
|
0.9986413 0.9986413 0.99864315 0.9972863 ]
|
|
|
|
mean value: 0.9983701182821072
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 0.98795181 0.98765432 1.
|
|
0.98795181 0.98795181 0.98765432 0.97619048]
|
|
|
|
mean value: 0.9915354539852532
|
|
|
|
key: train_fscore
|
|
value: [0.99863946 0.99728261 0.99863946 0.99863946 1. 0.99728261
|
|
0.99863946 0.99863946 0.99864315 0.99728261]
|
|
|
|
mean value: 0.9983688252895401
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 0.97619048 1. 1.
|
|
0.97619048 0.97619048 0.97560976 0.95348837]
|
|
|
|
mean value: 0.9857669556762013
|
|
|
|
key: train_precision
|
|
value: [1. 0.99728261 1. 1. 1. 0.99728261
|
|
1. 1. 1. 0.99728261]
|
|
|
|
mean value: 0.9991847826086957
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 0.98780488 0.98780488 1.
|
|
0.98780488 0.98780488 0.98780488 0.975 ]
|
|
|
|
mean value: 0.9914024390243903
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.99728261 0.9986413 0.9986413 1. 0.99728261
|
|
0.9986413 0.9986413 0.99864499 0.99728629]
|
|
|
|
mean value: 0.998370301637799
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 0.97619048 0.97560976 1.
|
|
0.97619048 0.97619048 0.97560976 0.95348837]
|
|
|
|
mean value: 0.9833279312859574
|
|
|
|
key: train_jcc
|
|
value: [0.99728261 0.99457995 0.99728261 0.99728261 1. 0.99457995
|
|
0.99728261 0.99728261 0.99728997 0.99457995]
|
|
|
|
mean value: 0.9967442853776364
|
|
|
|
MCC on Blind test: 0.05
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Multinomial
|
|
Model func: MultinomialNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', MultinomialNB())])
|
|
|
|
key: fit_time
|
|
value: [0.02811432 0.01485062 0.01452565 0.01507163 0.01482677 0.01482296
|
|
0.01491022 0.01570797 0.01581764 0.01586032]
|
|
|
|
mean value: 0.01645081043243408
|
|
|
|
key: score_time
|
|
value: [0.01208687 0.0120523 0.0120635 0.0120616 0.0118196 0.0120852
|
|
0.01258612 0.01281214 0.01249075 0.01210594]
|
|
|
|
mean value: 0.012216401100158692
|
|
|
|
key: test_mcc
|
|
value: [1. 0.97590007 0.95235327 1. 0.92710507 1.
|
|
1. 0.88465174 0.97560976 0.97559506]
|
|
|
|
mean value: 0.9691214958271785
|
|
|
|
key: train_mcc
|
|
value: [0.96774867 0.97039895 0.97039895 0.97039895 0.97849211 0.96510517
|
|
0.96774867 0.98106882 0.97043771 0.97043965]
|
|
|
|
mean value: 0.9712237636315258
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.98780488 0.97560976 1. 0.96341463 1.
|
|
1. 0.93902439 0.98765432 0.98765432]
|
|
|
|
mean value: 0.9841162300511894
|
|
|
|
key: train_accuracy
|
|
value: [0.98369565 0.98505435 0.98505435 0.98505435 0.98913043 0.98233696
|
|
0.98369565 0.99048913 0.98507463 0.98507463]
|
|
|
|
mean value: 0.985466012329656
|
|
|
|
key: test_fscore
|
|
value: [1. 0.98795181 0.97619048 1. 0.96385542 1.
|
|
1. 0.94252874 0.98765432 0.98795181]
|
|
|
|
mean value: 0.9846132568954893
|
|
|
|
key: train_fscore
|
|
value: [0.98391421 0.9852349 0.9852349 0.9852349 0.98924731 0.98259705
|
|
0.98391421 0.99055331 0.98527443 0.9852349 ]
|
|
|
|
mean value: 0.9856440119660511
|
|
|
|
key: test_precision
|
|
value: [1. 0.97619048 0.95348837 1. 0.95238095 1.
|
|
1. 0.89130435 0.97560976 0.97619048]
|
|
|
|
mean value: 0.9725164380778576
|
|
|
|
key: train_precision
|
|
value: [0.97089947 0.9734748 0.9734748 0.9734748 0.9787234 0.96833773
|
|
0.97089947 0.98391421 0.97354497 0.9734748 ]
|
|
|
|
mean value: 0.974021846382926
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.98780488 0.97560976 1. 0.96341463 1.
|
|
1. 0.93902439 0.98780488 0.9875 ]
|
|
|
|
mean value: 0.9841158536585366
|
|
|
|
key: train_roc_auc
|
|
value: [0.98369565 0.98505435 0.98505435 0.98505435 0.98913043 0.98233696
|
|
0.98369565 0.99048913 0.98505803 0.98509117]
|
|
|
|
mean value: 0.9854660068339814
|
|
|
|
key: test_jcc
|
|
value: [1. 0.97619048 0.95348837 1. 0.93023256 1.
|
|
1. 0.89130435 0.97560976 0.97619048]
|
|
|
|
mean value: 0.9703015986537158
|
|
|
|
key: train_jcc
|
|
value: [0.96833773 0.97089947 0.97089947 0.97089947 0.9787234 0.96578947
|
|
0.96833773 0.98128342 0.97097625 0.97089947]
|
|
|
|
mean value: 0.9717045899036885
|
|
|
|
MCC on Blind test: 0.03
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: Passive Aggresive
|
|
Model func: PassiveAggressiveClassifier(n_jobs=10, random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
PassiveAggressiveClassifier(n_jobs=10, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.02199936 0.01965737 0.01917267 0.01896453 0.01923943 0.02606606
|
|
0.01948166 0.02033186 0.0212853 0.01985145]
|
|
|
|
mean value: 0.020604968070983887
|
|
|
|
key: score_time
|
|
value: [0.01192355 0.01183677 0.01220274 0.01208115 0.01211715 0.01216769
|
|
0.01209044 0.01894236 0.012146 0.01208568]
|
|
|
|
mean value: 0.01275935173034668
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
0.97590007 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9927409901994627
|
|
|
|
key: train_mcc
|
|
value: [1. 0.99728629 1. 0.99728629 1. 0.99728629
|
|
1. 1. 1. 0.99728995]
|
|
|
|
mean value: 0.9989148825342111
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9963264077085215
|
|
|
|
key: train_accuracy
|
|
value: [1. 0.9986413 1. 0.9986413 1. 0.9986413
|
|
1. 1. 1. 0.99864315]
|
|
|
|
mean value: 0.9994567060940357
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 1.
|
|
0.98795181 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9963260449204224
|
|
|
|
key: train_fscore
|
|
value: [1. 0.99863946 1. 0.99863946 1. 0.99863946
|
|
1. 1. 1. 0.99863946]
|
|
|
|
mean value: 0.9994557823129252
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
0.97619048 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9951800232288037
|
|
|
|
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. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [1. 0.99728261 1. 0.99728261 1. 0.99728261
|
|
1. 1. 1. 0.99728261]
|
|
|
|
mean value: 0.9989130434782609
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98780488 1. ]
|
|
|
|
mean value: 0.9963414634146341
|
|
|
|
key: train_roc_auc
|
|
value: [1. 0.9986413 1. 0.9986413 1. 0.9986413 1.
|
|
1. 1. 0.9986413]
|
|
|
|
mean value: 0.9994565217391305
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
0.97619048 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9927409988385598
|
|
|
|
key: train_jcc
|
|
value: [1. 0.99728261 1. 0.99728261 1. 0.99728261
|
|
1. 1. 1. 0.99728261]
|
|
|
|
mean value: 0.9989130434782609
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Stochastic GDescent
|
|
Model func: SGDClassifier(n_jobs=10, random_state=42)
|
|
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', SGDClassifier(n_jobs=10, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.02702713 0.01727796 0.0181396 0.01810908 0.016891 0.01763678
|
|
0.01881504 0.01880169 0.03385401 0.01738429]
|
|
|
|
mean value: 0.02039365768432617
|
|
|
|
key: score_time
|
|
value: [0.01218867 0.01202273 0.01220393 0.01227856 0.01208973 0.01210833
|
|
0.01978302 0.01922965 0.02226758 0.01182604]
|
|
|
|
mean value: 0.014599823951721191
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
0.97590007 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9927409901994627
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 0.99728629 1. 1.
|
|
1. 1. 1. 0.99728995]
|
|
|
|
mean value: 0.9994576243760325
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9963264077085215
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 0.9986413 1. 1.
|
|
1. 1. 1. 0.99864315]
|
|
|
|
mean value: 0.9997284452244706
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 1.
|
|
0.98795181 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9963260449204224
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 0.99863946 1. 1.
|
|
1. 1. 1. 0.99863946]
|
|
|
|
mean value: 0.9997278911564625
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
0.97619048 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9951800232288037
|
|
|
|
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. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 0.99728261 1. 1.
|
|
1. 1. 1. 0.99728261]
|
|
|
|
mean value: 0.9994565217391305
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98780488 1. ]
|
|
|
|
mean value: 0.9963414634146341
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 0.9986413 1. 1. 1.
|
|
1. 1. 0.9986413]
|
|
|
|
mean value: 0.9997282608695652
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
0.97619048 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9927409988385598
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 0.99728261 1. 1.
|
|
1. 1. 1. 0.99728261]
|
|
|
|
mean value: 0.9994565217391305
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: AdaBoost Classifier
|
|
Model func: AdaBoostClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', AdaBoostClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.35029912 0.34669185 0.34488606 0.34064388 0.32821965 0.32856464
|
|
0.33788705 0.32813716 0.32518172 0.32532883]
|
|
|
|
mean value: 0.3355839967727661
|
|
|
|
key: score_time
|
|
value: [0.01660323 0.01597118 0.01555681 0.01566911 0.01627326 0.01621413
|
|
0.01663399 0.01586509 0.01574016 0.01567173]
|
|
|
|
mean value: 0.016019868850708007
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 0.97590007
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951800145897066
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 0.98765432
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975308641975309
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.12
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Bagging Classifier
|
|
Model func: BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
BaggingClassifier(n_jobs=10, oob_score=True,
|
|
random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.16502285 0.18274188 0.16214156 0.16709042 0.15880084 0.15820289
|
|
0.16567898 0.18430805 0.16625166 0.08271599]
|
|
|
|
mean value: 0.15929551124572755
|
|
|
|
key: score_time
|
|
value: [0.0390625 0.03055167 0.02326536 0.02653861 0.03228641 0.02673721
|
|
0.03486085 0.03969193 0.04029655 0.03138304]
|
|
|
|
mean value: 0.0324674129486084
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 0.92710507 0.97590007
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9878905215198173
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.99728997]
|
|
|
|
mean value: 0.9994576263690622
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 0.96341463 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9939024390243902
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.99864315]
|
|
|
|
mean value: 0.9997284452244706
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 0.96385542 0.98765432
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9939461549903317
|
|
|
|
key: train_fscore
|
|
value: [0.99863946 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.99864315]
|
|
|
|
mean value: 0.9997282603679192
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 0.95238095 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9928571428571429
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.99728997]
|
|
|
|
mean value: 0.9997289972899729
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_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]
|
|
/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))
|
|
[0.99728261 1. 1. 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9997282608695652
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 0.98780488 1. 0.96341463 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9939024390243902
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.99864499]
|
|
|
|
mean value: 0.9997286290797691
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 0.97619048 1. 0.93023256 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9882032790427572
|
|
|
|
key: train_jcc
|
|
value: [0.99728261 1. 1. 1. 1. 1.
|
|
1. 1. 1. 0.99728997]
|
|
|
|
mean value: 0.9994572581595381
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Gaussian Process
|
|
Model func: GaussianProcessClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GaussianProcessClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.39215183 0.51867986 0.51008296 0.37460756 0.48715901 0.49438095
|
|
0.48513198 0.41793799 0.39081693 0.55535507]
|
|
|
|
mean value: 0.4626304149627686
|
|
|
|
key: score_time
|
|
value: [0.01875997 0.03882957 0.03196502 0.03138757 0.03683138 0.03812099
|
|
0.03802204 0.03779054 0.03119278 0.03178477]
|
|
|
|
mean value: 0.03346846103668213
|
|
|
|
key: test_mcc
|
|
value: [1. 0.97590007 0.97590007 1. 0.97590007 1.
|
|
1. 0.88465174 1. 1. ]
|
|
|
|
mean value: 0.9812351955774983
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99728629 0.99728629 0.99728629 0.99728629 0.99457991
|
|
0.99728629 0.99728629 1. 0.99728997]
|
|
|
|
mean value: 0.9972873914320465
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.98780488 0.98780488 1. 0.98780488 1.
|
|
1. 0.93902439 1. 1. ]
|
|
|
|
mean value: 0.9902439024390244
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 0.9986413 0.99728261
|
|
0.9986413 0.9986413 1. 0.99864315]
|
|
|
|
mean value: 0.9986414887027314
|
|
|
|
key: test_fscore
|
|
value: [1. 0.98795181 0.98795181 1. 0.98765432 1.
|
|
1. 0.94252874 1. 1. ]
|
|
|
|
mean value: 0.990608667107767
|
|
|
|
key: train_fscore
|
|
value: [0.99864315 0.99864315 0.99864315 0.99864315 0.99864315 0.99728997
|
|
0.99864315 0.99864315 1. 0.99864315]
|
|
|
|
mean value: 0.9986435156074762
|
|
|
|
key: test_precision
|
|
value: [1. 0.97619048 0.97619048 1. 1. 1.
|
|
1. 0.89130435 1. 1. ]
|
|
|
|
mean value: 0.9843685300207039
|
|
|
|
key: train_precision
|
|
value: [0.99728997 0.99728997 0.99728997 0.99728997 0.99728997 0.99459459
|
|
0.99728997 0.99728997 1. 0.99728997]
|
|
|
|
mean value: 0.9972914377792427
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.98780488 0.98780488 1. 0.98780488 1.
|
|
1. 0.93902439 1. 1. ]
|
|
|
|
mean value: 0.9902439024390244
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.9986413 0.9986413 0.9986413 0.9986413 0.99728261
|
|
0.9986413 0.9986413 1. 0.99864499]
|
|
|
|
mean value: 0.9986416725580299
|
|
|
|
key: test_jcc
|
|
value: [1. 0.97619048 0.97619048 1. 0.97560976 1.
|
|
1. 0.89130435 1. 1. ]
|
|
|
|
mean value: 0.98192950563046
|
|
|
|
key: train_jcc
|
|
value: [0.99728997 0.99728997 0.99728997 0.99728997 0.99728997 0.99459459
|
|
0.99728997 0.99728997 1. 0.99728997]
|
|
|
|
mean value: 0.9972914377792427
|
|
|
|
MCC on Blind test: -0.04
|
|
|
|
Accuracy on Blind test: 0.62
|
|
|
|
Model_name: Gradient Boosting
|
|
Model func: GradientBoostingClassifier(random_state=42)
|
|
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GradientBoostingClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [1.11634278 1.22586918 1.08421278 1.11571884 0.93970394 1.09515667
|
|
1.21813774 1.20429325 1.23972106 1.22192454]
|
|
|
|
mean value: 1.146108078956604
|
|
|
|
key: score_time
|
|
value: [0.00973034 0.00927925 0.00935864 0.00923634 0.00941062 0.00923848
|
|
0.00920224 0.00918889 0.00931549 0.00929356]
|
|
|
|
mean value: 0.009325385093688965
|
|
|
|
key: test_mcc
|
|
value: [0.97590007 1. 0.97590007 1. 0.95121951 0.97590007
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9878919731040722
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.98780488 1. 0.98780488 1. 0.97560976 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9939024390243902
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.98765432 1. 0.98795181 1. 0.97560976 0.98765432
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9938870205301785
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951800232288037
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [0.97560976 1. 1. 1. 0.97560976 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9926829268292683
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [0.98780488 1. 0.98780488 1. 0.97560976 0.98780488
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9939024390243902
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.97560976 1. 0.97619048 1. 0.95238095 0.97560976
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9879790940766551
|
|
|
|
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: 0.64
|
|
|
|
Model_name: QDA
|
|
Model func: QuadraticDiscriminantAnalysis()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', QuadraticDiscriminantAnalysis())])
|
|
|
|
key: fit_time
|
|
value: [0.03594899 0.03618169 0.03547835 0.03739643 0.0375247 0.03539371
|
|
0.03769898 0.0356102 0.03827429 0.03624153]
|
|
|
|
mean value: 0.03657488822937012
|
|
|
|
key: score_time
|
|
value: [0.01257873 0.01270938 0.01267934 0.017627 0.01313949 0.01514435
|
|
0.02065754 0.01593971 0.01886082 0.02063227]
|
|
|
|
mean value: 0.015996861457824706
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975900072948534
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98765432 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9987654320987654
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
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: 0.64
|
|
|
|
Model_name: Ridge Classifier
|
|
Model func: RidgeClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', RidgeClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.02517939 0.04055691 0.0403533 0.04039001 0.03876543 0.04039931
|
|
0.04014945 0.04073524 0.05057812 0.03798723]
|
|
|
|
mean value: 0.03950943946838379
|
|
|
|
key: score_time
|
|
value: [0.01878047 0.01876593 0.01878381 0.01876879 0.01878834 0.01874089
|
|
0.01880455 0.01884627 0.0188272 0.01871467]
|
|
|
|
mean value: 0.01878209114074707
|
|
|
|
key: test_mcc
|
|
value: [1. 0.97590007 1. 0.97590007 0.97590007 1.
|
|
0.95235327 1. 0.97560976 0.92840283]
|
|
|
|
mean value: 0.978406607327605
|
|
|
|
key: train_mcc
|
|
value: [0.99456522 0.99456522 0.99456522 0.99456522 0.99728629 0.99456522
|
|
0.99728629 0.99456522 0.99457258 0.99457258]
|
|
|
|
mean value: 0.9951109049120375
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.98780488 1. 0.98780488 0.98780488 1.
|
|
0.97560976 1. 0.98765432 0.96296296]
|
|
|
|
mean value: 0.9889641674194519
|
|
|
|
key: train_accuracy
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 0.9986413 0.99728261
|
|
0.9986413 0.99728261 0.9972863 0.9972863 ]
|
|
|
|
mean value: 0.9975550852457082
|
|
|
|
key: test_fscore
|
|
value: [1. 0.98795181 1. 0.98795181 0.98765432 1.
|
|
0.97619048 1. 0.98765432 0.96470588]
|
|
|
|
mean value: 0.9892108614976557
|
|
|
|
key: train_fscore
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 0.99864315 0.99728261
|
|
0.99863946 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550837448487
|
|
|
|
key: test_precision
|
|
value: [1. 0.97619048 1. 0.97619048 1. 1.
|
|
0.95348837 1. 0.97560976 0.93181818]
|
|
|
|
mean value: 0.9813297262389719
|
|
|
|
key: train_precision
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 0.99728997 0.99728261
|
|
1. 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975558206669024
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: /home/tanu/git/LSHTM_analysis/scripts/ml/./gid_rt.py:135: SettingWithCopyWarning:
|
|
A value is trying to be set on a copy of a slice from a DataFrame
|
|
|
|
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
|
|
smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_rt.py:138: 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)
|
|
[1. 0.98780488 1. 0.98780488 0.98780488 1.
|
|
0.97560976 1. 0.98780488 0.9625 ]
|
|
|
|
mean value: 0.9889329268292683
|
|
|
|
key: train_roc_auc
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 0.9986413 0.99728261
|
|
0.9986413 0.99728261 0.99728629 0.99728629]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_jcc
|
|
value: [1. 0.97619048 1. 0.97619048 0.97560976 1.
|
|
0.95348837 1. 0.97560976 0.93181818]
|
|
|
|
mean value: 0.978890701848728
|
|
|
|
key: train_jcc
|
|
value: [0.99457995 0.99457995 0.99457995 0.99457995 0.99728997 0.99457995
|
|
0.99728261 0.99457995 0.99459459 0.99457995]
|
|
|
|
mean value: 0.9951226796786181
|
|
|
|
MCC on Blind test: 0.1
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Ridge ClassifierCV
|
|
Model func: RidgeClassifierCV(cv=10)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', RidgeClassifierCV(cv=10))])
|
|
|
|
key: fit_time
|
|
value: [0.31079054 0.31409287 0.31281781 0.31339955 0.31390643 0.43118978
|
|
0.30926585 0.42711043 0.48189974 0.38591003]
|
|
|
|
mean value: 0.3600383043289185
|
|
|
|
key: score_time
|
|
value: [0.01892018 0.01887846 0.01886964 0.01884007 0.01896596 0.02387404
|
|
0.01898599 0.02272606 0.01887226 0.01887417]
|
|
|
|
mean value: 0.019780683517456054
|
|
|
|
key: test_mcc
|
|
value: [0.97590007 1. 1. 1. 0.97590007 1.
|
|
0.95235327 1. 0.97560976 0.95174259]
|
|
|
|
mean value: 0.983150575630985
|
|
|
|
key: train_mcc
|
|
value: [0.99185149 0.99185149 0.99185149 0.99185149 0.99188079 0.99185149
|
|
0.99185149 0.99185149 0.99186249 0.99457258]
|
|
|
|
mean value: 0.9921276278816327
|
|
|
|
key: test_accuracy
|
|
value: [0.98780488 1. 1. 1. 0.98780488 1.
|
|
0.97560976 1. 0.98765432 0.97530864]
|
|
|
|
mean value: 0.9914182475158084
|
|
|
|
key: train_accuracy
|
|
value: [0.99592391 0.99592391 0.99592391 0.99592391 0.99592391 0.99592391
|
|
0.99592391 0.99592391 0.99592944 0.9972863 ]
|
|
|
|
mean value: 0.9960607043832223
|
|
|
|
key: test_fscore
|
|
value: [0.98795181 1. 1. 1. 0.98765432 1.
|
|
0.97619048 1. 0.98765432 0.97619048]
|
|
|
|
mean value: 0.9915641401585177
|
|
|
|
key: train_fscore
|
|
value: [0.99592944 0.99592944 0.99592944 0.99592944 0.99594046 0.99592944
|
|
0.99592944 0.99592944 0.99594046 0.99728261]
|
|
|
|
mean value: 0.9960669634692498
|
|
|
|
key: test_precision
|
|
value: [0.97619048 1. 1. 1. 1. 1.
|
|
0.95348837 1. 0.97560976 0.95348837]
|
|
|
|
mean value: 0.9858776976474084
|
|
|
|
key: train_precision
|
|
value: [0.99457995 0.99457995 0.99457995 0.99457995 0.99191375 0.99457995
|
|
0.99457995 0.99457995 0.99459459 0.99728261]
|
|
|
|
mean value: 0.9945850570517181
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_recall
|
|
value: [0.99728261 0.99728261 0.99728261 0.99728261 1. 0.99728261
|
|
0.99728261 0.99728261 0.99728997 0.99728261]
|
|
|
|
mean value: 0.9975550842464946
|
|
|
|
key: test_roc_auc
|
|
value: [0.98780488 1. 1. 1. 0.98780488 1.
|
|
0.97560976 1. 0.98780488 0.975 ]
|
|
|
|
mean value: 0.9914024390243903
|
|
|
|
key: train_roc_auc
|
|
value: [0.99592391 0.99592391 0.99592391 0.99592391 0.99592391 0.99592391
|
|
0.99592391 0.99592391 0.9959276 0.99728629]
|
|
|
|
mean value: 0.9960605190291033
|
|
|
|
key: test_jcc
|
|
value: [0.97619048 1. 1. 1. 0.97560976 1.
|
|
0.95348837 1. 0.97560976 0.95348837]
|
|
|
|
mean value: 0.9834386732571645
|
|
|
|
key: train_jcc
|
|
value: [0.99189189 0.99189189 0.99189189 0.99189189 0.99191375 0.99189189
|
|
0.99189189 0.99189189 0.99191375 0.99457995]
|
|
|
|
mean value: 0.9921650682304156
|
|
|
|
MCC on Blind test: 0.1
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Logistic Regression
|
|
Model func: LogisticRegression(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LogisticRegression(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.0329392 0.03201771 0.02906203 0.03408504 0.03161645 0.03559852
|
|
0.03268695 0.03535366 0.03019762 0.03441501]
|
|
|
|
mean value: 0.03279721736907959
|
|
|
|
key: score_time
|
|
value: [0.01205301 0.01190281 0.01184726 0.01198125 0.01185298 0.01194119
|
|
0.01186681 0.01191092 0.01191902 0.0118854 ]
|
|
|
|
mean value: 0.011916065216064453
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
0.97590007 1. 0.97560976 0.97559506]
|
|
|
|
mean value: 0.9903004958504097
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98765432 0.98765432]
|
|
|
|
mean value: 0.995091839807287
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98795181 1.
|
|
0.98795181 1. 0.98765432 0.98795181]
|
|
|
|
mean value: 0.9951509742674401
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 0.97619048 1.
|
|
0.97619048 1. 0.97560976 0.97619048]
|
|
|
|
mean value: 0.990418118466899
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98780488 0.9875 ]
|
|
|
|
mean value: 0.9950914634146342
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97619048 1.
|
|
0.97619048 1. 0.97560976 0.97619048]
|
|
|
|
mean value: 0.990418118466899
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Logistic RegressionCV
|
|
Model func: LogisticRegressionCV(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:444: ConvergenceWarning: lbfgs failed to converge (status=1):
|
|
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
|
|
|
Increase the number of iterations (max_iter) or scale the data as shown in:
|
|
https://scikit-learn.org/stable/modules/preprocessing.html
|
|
Please also refer to the documentation for alternative solver options:
|
|
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
|
n_iter_i = _check_optimize_result(
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LogisticRegressionCV(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.69424486 0.52966881 0.6177032 0.60444522 0.52784967 0.58575439
|
|
0.54582286 0.50463963 0.53821635 0.62744951]
|
|
|
|
mean value: 0.5775794506072998
|
|
|
|
key: score_time
|
|
value: [0.01205277 0.01202464 0.0120728 0.01207852 0.01209378 0.01279664
|
|
0.0121026 0.01207995 0.01209998 0.01939416]
|
|
|
|
mean value: 0.012879586219787598
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
0.97590007 1. 0.97560976 0.97559506]
|
|
|
|
mean value: 0.9903004958504097
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 1. 1. 1. 1. 1.
|
|
1. 1. 0.99458719 1. ]
|
|
|
|
mean value: 0.9991873481454057
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98765432 0.98765432]
|
|
|
|
mean value: 0.995091839807287
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 1. 1. 1. 1. 1. 1.
|
|
1. 0.9972863 1. ]
|
|
|
|
mean value: 0.9995927600141584
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98795181 1.
|
|
0.98795181 1. 0.98765432 0.98795181]
|
|
|
|
mean value: 0.9951509742674401
|
|
|
|
key: train_fscore
|
|
value: [0.99864315 1. 1. 1. 1. 1.
|
|
1. 1. 0.9972973 1. ]
|
|
|
|
mean value: 0.9995940445194176
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 0.97619048 1.
|
|
0.97619048 1. 0.97560976 0.97619048]
|
|
|
|
mean value: 0.990418118466899
|
|
|
|
key: train_precision
|
|
value: [0.99728997 1. 1. 1. 1. 1.
|
|
1. 1. 0.99460916 1. ]
|
|
|
|
mean value: 0.9991899137320214
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98780488 0.9875 ]
|
|
|
|
mean value: 0.9950914634146342
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 1. 1. 1. 1. 1.
|
|
1. 1. 0.99728261 1. ]
|
|
|
|
mean value: 0.9995923913043478
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97619048 1.
|
|
0.97619048 1. 0.97560976 0.97619048]
|
|
|
|
mean value: 0.990418118466899
|
|
|
|
key: train_jcc
|
|
value: [0.99728997 1. 1. 1. 1. 1.
|
|
1. 1. 0.99460916 1. ]
|
|
|
|
mean value: 0.9991899137320214
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Gaussian NB
|
|
Model func: GaussianNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GaussianNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01523733 0.01386714 0.01118112 0.01092887 0.01209068 0.01093578
|
|
0.01087809 0.01114058 0.01089859 0.0110786 ]
|
|
|
|
mean value: 0.011823678016662597
|
|
|
|
key: score_time
|
|
value: [0.01218796 0.00947809 0.00929165 0.00916791 0.00912809 0.00901389
|
|
0.00895309 0.00893259 0.00899363 0.00910449]
|
|
|
|
mean value: 0.009425139427185059
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Naive Bayes
|
|
Model func: BernoulliNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', BernoulliNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01114893 0.01527357 0.01541328 0.01537609 0.01549268 0.01553464
|
|
0.01534081 0.01535797 0.01547241 0.01550865]
|
|
|
|
mean value: 0.01499190330505371
|
|
|
|
key: score_time
|
|
value: [0.01206446 0.01204586 0.01218605 0.01213098 0.01215172 0.01219511
|
|
0.01214266 0.0121603 0.01214004 0.01216531]
|
|
|
|
mean value: 0.0121382474899292
|
|
|
|
key: test_mcc
|
|
value: [0.97590007 0.88465174 1. 0.92932038 0.95235327 0.86294893
|
|
0.92932038 0.9067647 0.97560976 1. ]
|
|
|
|
mean value: 0.9416869214875435
|
|
|
|
key: train_mcc
|
|
value: [0.93933644 0.94447385 0.93422349 0.94963613 0.93933644 0.95222673
|
|
0.94190206 0.94963613 0.93685466 0.93431576]
|
|
|
|
mean value: 0.9421941684418391
|
|
|
|
key: test_accuracy
|
|
value: [0.98780488 0.93902439 1. 0.96341463 0.97560976 0.92682927
|
|
0.96341463 0.95121951 0.98765432 1. ]
|
|
|
|
mean value: 0.9694971394158386
|
|
|
|
key: train_accuracy
|
|
value: [0.96875 0.97146739 0.96603261 0.97418478 0.96875 0.97554348
|
|
0.9701087 0.97418478 0.96743555 0.9660787 ]
|
|
|
|
mean value: 0.9702535986077517
|
|
|
|
key: test_fscore
|
|
value: [0.98795181 0.94252874 1. 0.96470588 0.97619048 0.93181818
|
|
0.96470588 0.95348837 0.98765432 1. ]
|
|
|
|
mean value: 0.9709043658656318
|
|
|
|
key: train_fscore
|
|
value: [0.96969697 0.97225892 0.96714849 0.97483444 0.96969697 0.97612732
|
|
0.97097625 0.97483444 0.96850394 0.96714849]
|
|
|
|
mean value: 0.9711226219264782
|
|
|
|
key: test_precision
|
|
value: [0.97619048 0.89130435 1. 0.93181818 0.95348837 0.87234043
|
|
0.93181818 0.91111111 0.97560976 1. ]
|
|
|
|
mean value: 0.9443680852486537
|
|
|
|
key: train_precision
|
|
value: [0.94117647 0.94601542 0.93638677 0.95090439 0.94117647 0.95336788
|
|
0.94358974 0.95090439 0.9389313 0.93638677]
|
|
|
|
mean value: 0.943883960471372
|
|
|
|
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: [0.98780488 0.93902439 1. 0.96341463 0.97560976 0.92682927
|
|
0.96341463 0.95121951 0.98780488 1. ]
|
|
|
|
mean value: 0.9695121951219512
|
|
|
|
key: train_roc_auc
|
|
value: [0.96875 0.97146739 0.96603261 0.97418478 0.96875 0.97554348
|
|
0.9701087 0.97418478 0.9673913 0.96612466]
|
|
|
|
mean value: 0.9702537704724874
|
|
|
|
key: test_jcc
|
|
value: [0.97619048 0.89130435 1. 0.93181818 0.95348837 0.87234043
|
|
0.93181818 0.91111111 0.97560976 1. ]
|
|
|
|
mean value: 0.9443680852486537
|
|
|
|
key: train_jcc
|
|
value: [0.94117647 0.94601542 0.93638677 0.95090439 0.94117647 0.95336788
|
|
0.94358974 0.95090439 0.9389313 0.93638677]
|
|
|
|
mean value: 0.943883960471372
|
|
|
|
MCC on Blind test: -0.02
|
|
|
|
Accuracy on Blind test: 0.61
|
|
|
|
Model_name: K-Nearest Neighbors
|
|
Model func: KNeighborsClassifier()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', KNeighborsClassifier())])
|
|
|
|
key: fit_time
|
|
value: [0.02226114 0.01112175 0.01045632 0.01116967 0.01087809 0.01001072
|
|
0.01123738 0.01138449 0.0113101 0.01054335]
|
|
|
|
mean value: 0.012037301063537597
|
|
|
|
key: score_time
|
|
value: [0.03276396 0.01347852 0.01324391 0.01388717 0.01340795 0.0133779
|
|
0.01389813 0.01390147 0.01307583 0.01834106]
|
|
|
|
mean value: 0.01593759059906006
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 1. 1.
|
|
0.97590007 0.92932038 1. 0.97559506]
|
|
|
|
mean value: 0.9856715579691121
|
|
|
|
key: train_mcc
|
|
value: [0.99457991 0.99188079 0.99457991 0.99188079 0.98918887 0.98918887
|
|
0.99457991 0.99188079 0.99728995 1. ]
|
|
|
|
mean value: 0.9935049771214682
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 1. 1.
|
|
0.98780488 0.96341463 1. 0.98765432]
|
|
|
|
mean value: 0.9926678711231557
|
|
|
|
key: train_accuracy
|
|
value: [0.99728261 0.99592391 0.99728261 0.99592391 0.99456522 0.99456522
|
|
0.99728261 0.99592391 0.99864315 1. ]
|
|
|
|
mean value: 0.9967393147896879
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 1. 1.
|
|
0.98795181 0.96470588 1. 0.98795181]
|
|
|
|
mean value: 0.9928561304039688
|
|
|
|
key: train_fscore
|
|
value: [0.99728997 0.99594046 0.99728997 0.99594046 0.99459459 0.99459459
|
|
0.99728997 0.99594046 0.99864682 1. ]
|
|
|
|
mean value: 0.9967527308159012
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 1. 1.
|
|
0.97619048 0.93181818 1. 0.97619048]
|
|
|
|
mean value: 0.986038961038961
|
|
|
|
key: train_precision
|
|
value: [0.99459459 0.99191375 0.99459459 0.99191375 0.98924731 0.98924731
|
|
0.99459459 0.99191375 0.9972973 1. ]
|
|
|
|
mean value: 0.9935316944629179
|
|
|
|
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. 0.98780488 1. 1. 1.
|
|
0.98780488 0.96341463 1. 0.9875 ]
|
|
|
|
mean value: 0.9926524390243903
|
|
|
|
key: train_roc_auc
|
|
value: [0.99728261 0.99592391 0.99728261 0.99592391 0.99456522 0.99456522
|
|
0.99728261 0.99592391 0.9986413 1. ]
|
|
|
|
mean value: 0.9967391304347826
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 0.97619048 1. 1. 1.
|
|
0.97619048 0.93181818 1. 0.97619048]
|
|
|
|
mean value: 0.986038961038961
|
|
|
|
key: train_jcc
|
|
value: [0.99459459 0.99191375 0.99459459 0.99191375 0.98924731 0.98924731
|
|
0.99459459 0.99191375 0.9972973 1. ]
|
|
|
|
mean value: 0.9935316944629179
|
|
|
|
MCC on Blind test: -0.04
|
|
|
|
Accuracy on Blind test: 0.62
|
|
|
|
Model_name: SVM
|
|
Model func: SVC(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', SVC(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01453543 0.01398969 0.01407623 0.01436734 0.01439548 0.01450872
|
|
0.01414347 0.01427746 0.01414585 0.01460624]
|
|
|
|
mean value: 0.014304590225219727
|
|
|
|
key: score_time
|
|
value: [0.00989437 0.00991225 0.00994253 0.01007223 0.00993395 0.00997353
|
|
0.01007318 0.01002455 0.01004696 0.01010442]
|
|
|
|
mean value: 0.009997797012329102
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.04
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: MLP
|
|
Model func: MLPClassifier(max_iter=500, random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', MLPClassifier(max_iter=500, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.63227844 0.68658686 0.69631076 0.60605907 0.56783509 0.74490881
|
|
0.64789128 0.58463478 0.59095526 0.75249314]
|
|
|
|
mean value: 0.6509953498840332
|
|
|
|
key: score_time
|
|
value: [0.01274347 0.01283765 0.01293373 0.01239657 0.01241398 0.0129447
|
|
0.01250648 0.01243639 0.01243687 0.012429 ]
|
|
|
|
mean value: 0.012607884407043458
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 0.97590007 1.
|
|
0.97590007 1. 0.97560976 0.97559506]
|
|
|
|
mean value: 0.9903004958504097
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98765432 0.98765432]
|
|
|
|
mean value: 0.995091839807287
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 0.98795181 1.
|
|
0.98795181 1. 0.98765432 0.98795181]
|
|
|
|
mean value: 0.9951509742674401
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 0.97619048 1.
|
|
0.97619048 1. 0.97560976 0.97619048]
|
|
|
|
mean value: 0.990418118466899
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 0.98780488 1.
|
|
0.98780488 1. 0.98780488 0.9875 ]
|
|
|
|
mean value: 0.9950914634146342
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 0.97619048 1.
|
|
0.97619048 1. 0.97560976 0.97619048]
|
|
|
|
mean value: 0.990418118466899
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: -0.01
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: Decision Tree
|
|
Model func: DecisionTreeClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', DecisionTreeClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.02050948 0.01547027 0.01380348 0.01392651 0.0137167 0.01387787
|
|
0.01399446 0.01395702 0.01403189 0.01473165]
|
|
|
|
mean value: 0.014801931381225587
|
|
|
|
key: score_time
|
|
value: [0.01198721 0.00945163 0.00899053 0.00889421 0.0090096 0.0093956
|
|
0.00908327 0.00903606 0.00903368 0.00904965]
|
|
|
|
mean value: 0.009393143653869628
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 0.95235327 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9928253339434266
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9963414634146341
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 0.97619048 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9964142283419392
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 0.95348837 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.99296788482835
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 0.98780488 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9963414634146341
|
|
|
|
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. 0.97619048 1. 0.95348837 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.99296788482835
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: -0.07
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
Model_name: Extra Trees
|
|
Model func: ExtraTreesClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', ExtraTreesClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.09934592 0.10024786 0.09979486 0.10048461 0.09923458 0.10020065
|
|
0.10119796 0.1001811 0.09983778 0.10054326]
|
|
|
|
mean value: 0.10010685920715331
|
|
|
|
key: score_time
|
|
value: [0.01766944 0.01795363 0.01804757 0.01796603 0.01820993 0.01779008
|
|
0.01808906 0.01779771 0.01781273 0.01796579]
|
|
|
|
mean value: 0.017930197715759277
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Extra Tree
|
|
Model func: ExtraTreeClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', ExtraTreeClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01134396 0.01072454 0.01176214 0.01080966 0.01096106 0.01094961
|
|
0.0109365 0.01086211 0.01096129 0.01087928]
|
|
|
|
mean value: 0.011019015312194824
|
|
|
|
key: score_time
|
|
value: [0.00914168 0.00905848 0.00905871 0.00901318 0.00905085 0.00901198
|
|
0.00902629 0.00901985 0.00895357 0.00902128]
|
|
|
|
mean value: 0.009035587310791016
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 0.97590007 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975900072948534
|
|
|
|
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. 0.98780488 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
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. 0.98795181 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9987951807228915
|
|
|
|
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. 0.97619048 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9976190476190476
|
|
|
|
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. 0.98780488 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
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. 0.97619048 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9976190476190476
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.17
|
|
|
|
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/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(
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
RandomForestClassifier(n_estimators=1000, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [1.19025254 1.1910665 1.18577504 1.19194627 1.19458723 1.19427347
|
|
1.19646263 1.1843164 1.18629003 1.19279742]
|
|
|
|
mean value: 1.1907767534255982
|
|
|
|
key: score_time
|
|
value: [0.09081054 0.09237266 0.09046865 0.09148121 0.09427381 0.09148955
|
|
0.09354448 0.0937984 0.09317827 0.09427381]
|
|
|
|
mean value: 0.09256913661956787
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Random Forest2
|
|
Model func: RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000...05', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10,
|
|
oob_score=True, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.96961617 0.99249053 0.95078969 0.99913931 0.96326542 0.99250197
|
|
0.92212391 1.00464892 1.02766109 0.97350574]
|
|
|
|
mean value: 0.9795742750167846
|
|
|
|
key: score_time
|
|
value: [0.25640821 0.23247099 0.21121407 0.2550602 0.13452554 0.13529539
|
|
0.26445699 0.17845917 0.20959902 0.25679469]
|
|
|
|
mean value: 0.21342842578887938
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975900072948534
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99728629 1. 0.99728629 0.99728629 0.99728629
|
|
0.99728629 0.99728629 0.99728995 0.99728997]
|
|
|
|
mean value: 0.9975583961405413
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.9986413 1. 0.9986413 0.9986413 0.9986413
|
|
0.9986413 0.9986413 0.99864315 0.99864315]
|
|
|
|
mean value: 0.9987775426228541
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9987951807228915
|
|
|
|
key: train_fscore
|
|
value: [0.99864315 0.99864315 1. 0.99864315 0.99864315 0.99864315
|
|
0.99864315 0.99864315 0.99864682 0.99864315]
|
|
|
|
mean value: 0.9987792003202096
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9976190476190476
|
|
|
|
key: train_precision
|
|
value: [0.99728997 0.99728997 1. 0.99728997 0.99728997 0.99728997
|
|
0.99728997 0.99728997 0.9972973 0.99728997]
|
|
|
|
mean value: 0.9975617080495129
|
|
|
|
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. 0.98780488 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.9986413 1. 0.9986413 0.9986413 0.9986413
|
|
0.9986413 0.9986413 0.9986413 0.99864499]
|
|
|
|
mean value: 0.9987775421232474
|
|
|
|
key: test_jcc
|
|
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(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[1. 1. 0.97619048 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9976190476190476
|
|
|
|
key: train_jcc
|
|
value: [0.99728997 0.99728997 1. 0.99728997 0.99728997 0.99728997
|
|
0.99728997 0.99728997 0.9972973 0.99728997]
|
|
|
|
mean value: 0.9975617080495129
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Naive Bayes
|
|
Model func: BernoulliNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', BernoulliNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01321125 0.01969552 0.01535511 0.01532602 0.01544857 0.0153985
|
|
0.01541615 0.01543212 0.01560068 0.01556468]
|
|
|
|
mean value: 0.01564486026763916
|
|
|
|
key: score_time
|
|
value: [0.01237535 0.01205516 0.01218653 0.01213145 0.01213408 0.01213026
|
|
0.01214743 0.0121696 0.01210523 0.01215649]
|
|
|
|
mean value: 0.012159156799316406
|
|
|
|
key: test_mcc
|
|
value: [0.97590007 0.88465174 1. 0.92932038 0.95235327 0.86294893
|
|
0.92932038 0.9067647 0.97560976 1. ]
|
|
|
|
mean value: 0.9416869214875435
|
|
|
|
key: train_mcc
|
|
value: [0.93933644 0.94447385 0.93422349 0.94963613 0.93933644 0.95222673
|
|
0.94190206 0.94963613 0.93685466 0.93431576]
|
|
|
|
mean value: 0.9421941684418391
|
|
|
|
key: test_accuracy
|
|
value: [0.98780488 0.93902439 1. 0.96341463 0.97560976 0.92682927
|
|
0.96341463 0.95121951 0.98765432 1. ]
|
|
|
|
mean value: 0.9694971394158386
|
|
|
|
key: train_accuracy
|
|
value: [0.96875 0.97146739 0.96603261 0.97418478 0.96875 0.97554348
|
|
0.9701087 0.97418478 0.96743555 0.9660787 ]
|
|
|
|
mean value: 0.9702535986077517
|
|
|
|
key: test_fscore
|
|
value: [0.98795181 0.94252874 1. 0.96470588 0.97619048 0.93181818
|
|
0.96470588 0.95348837 0.98765432 1. ]
|
|
|
|
mean value: 0.9709043658656318
|
|
|
|
key: train_fscore
|
|
value: [0.96969697 0.97225892 0.96714849 0.97483444 0.96969697 0.97612732
|
|
0.97097625 0.97483444 0.96850394 0.96714849]
|
|
|
|
mean value: 0.9711226219264782
|
|
|
|
key: test_precision
|
|
value: [0.97619048 0.89130435 1. 0.93181818 0.95348837 0.87234043
|
|
0.93181818 0.91111111 0.97560976 1. ]
|
|
|
|
mean value: 0.9443680852486537
|
|
|
|
key: train_precision
|
|
value: [0.94117647 0.94601542 0.93638677 0.95090439 0.94117647 0.95336788
|
|
0.94358974 0.95090439 0.9389313 0.93638677]
|
|
|
|
mean value: 0.943883960471372
|
|
|
|
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: [0.98780488 0.93902439 1. 0.96341463 0.97560976 0.92682927
|
|
0.96341463 0.95121951 0.98780488 1. ]
|
|
|
|
mean value: 0.9695121951219512
|
|
|
|
key: train_roc_auc
|
|
value: [0.96875 0.97146739 0.96603261 0.97418478 0.96875 0.97554348
|
|
0.9701087 0.97418478 0.9673913 0.96612466]
|
|
|
|
mean value: 0.9702537704724874
|
|
|
|
key: test_jcc
|
|
value: [0.97619048 0.89130435 1. 0.93181818 0.95348837 0.87234043
|
|
0.93181818 0.91111111 0.97560976 1. ]
|
|
|
|
mean value: 0.9443680852486537
|
|
|
|
key: train_jcc
|
|
value: [0.94117647 0.94601542 0.93638677 0.95090439 0.94117647 0.95336788
|
|
0.94358974 0.95090439 0.9389313 0.93638677]
|
|
|
|
mean value: 0.943883960471372
|
|
|
|
MCC on Blind test: -0.02
|
|
|
|
Accuracy on Blind test: 0.61
|
|
|
|
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: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', '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: [0.08123899 0.05527997 0.05502272 0.06461287 0.06690979 0.07206774
|
|
0.05670714 0.06016827 0.06766629 0.06786704]
|
|
|
|
mean value: 0.0647540807723999
|
|
|
|
key: score_time
|
|
value: [0.01097345 0.01067019 0.01060772 0.01056099 0.01073909 0.01091695
|
|
0.01060534 0.01056409 0.0105958 0.01058125]
|
|
|
|
mean value: 0.010681486129760743
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975900072948534
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9987951807228915
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9976190476190476
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 0.98780488 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
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. 0.97619048 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9976190476190476
|
|
|
|
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: 0.64
|
|
|
|
Model_name: LDA
|
|
Model func: LinearDiscriminantAnalysis()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LinearDiscriminantAnalysis())])
|
|
|
|
key: fit_time
|
|
value: [0.04962325 0.06859589 0.04773283 0.0693655 0.05132008 0.0847261
|
|
0.05077052 0.10136676 0.05971193 0.07314157]
|
|
|
|
mean value: 0.06563544273376465
|
|
|
|
key: score_time
|
|
value: [0.01876545 0.01226377 0.01248384 0.01230836 0.01890564 0.01234889
|
|
0.01252794 0.01917291 0.01230669 0.01629901]
|
|
|
|
mean value: 0.014738249778747558
|
|
|
|
key: test_mcc
|
|
value: [1. 0.95235327 1. 0.97590007 1. 0.97590007
|
|
0.97590007 0.97590007 0.92852935 0.97559506]
|
|
|
|
mean value: 0.9760077968769325
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99457991 0.99728629 0.99728629 0.99728629 0.99728629
|
|
1. 0.99728629 0.99728995 0.99458727]
|
|
|
|
mean value: 0.9970174873769332
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.97560976 1. 0.98780488 1. 0.98780488
|
|
0.98780488 0.98780488 0.96296296 0.98765432]
|
|
|
|
mean value: 0.98774465522433
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.99728261 0.9986413 0.9986413 0.9986413 0.9986413
|
|
1. 0.9986413 0.99864315 0.9972863 ]
|
|
|
|
mean value: 0.9985059878473246
|
|
|
|
key: test_fscore
|
|
value: [1. 0.97619048 1. 0.98795181 1. 0.98795181
|
|
0.98795181 0.98795181 0.96385542 0.98795181]
|
|
|
|
mean value: 0.9879804934021801
|
|
|
|
key: train_fscore
|
|
value: [0.99864315 0.99728997 0.99864315 0.99864315 0.99864315 0.99864315
|
|
1. 0.99864315 0.99864682 0.99728997]
|
|
|
|
mean value: 0.9985085653207797
|
|
|
|
key: test_precision
|
|
value: [1. 0.95348837 1. 0.97619048 1. 0.97619048
|
|
0.97619048 0.97619048 0.93023256 0.97619048]
|
|
|
|
mean value: 0.9764673311184939
|
|
|
|
key: train_precision
|
|
value: [0.99728997 0.99459459 0.99728997 0.99728997 0.99728997 0.99728997
|
|
1. 0.99728997 0.9972973 0.99459459]
|
|
|
|
mean value: 0.9970226323884861
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.97560976 1. 0.98780488 1. 0.98780488
|
|
0.98780488 0.98780488 0.96341463 0.9875 ]
|
|
|
|
mean value: 0.9877743902439025
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.99728261 0.9986413 0.9986413 0.9986413 0.9986413
|
|
1. 0.9986413 0.9986413 0.99728997]
|
|
|
|
mean value: 0.9985061712030164
|
|
|
|
key: test_jcc
|
|
value: [1. 0.95348837 1. 0.97619048 1. 0.97619048
|
|
0.97619048 0.97619048 0.93023256 0.97619048]
|
|
|
|
mean value: 0.9764673311184939
|
|
|
|
key: train_jcc
|
|
value: [0.99728997 0.99459459 0.99728997 0.99728997 0.99728997 0.99728997
|
|
1. 0.99728997 0.9972973 0.99459459]
|
|
|
|
mean value: 0.9970226323884861
|
|
|
|
MCC on Blind test: 0.15
|
|
|
|
Accuracy on Blind test: 0.66
|
|
|
|
Model_name: Multinomial
|
|
Model func: MultinomialNB()
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', MultinomialNB())])
|
|
|
|
key: fit_time
|
|
value: [0.01434016 0.01459646 0.01467919 0.01464367 0.01464581 0.01465583
|
|
0.01470542 0.01461792 0.01474738 0.01468301]
|
|
|
|
mean value: 0.01463148593902588
|
|
|
|
key: score_time
|
|
value: [0.01197648 0.01193285 0.01184535 0.01183891 0.0118978 0.01192427
|
|
0.01189637 0.0118649 0.01187253 0.01188493]
|
|
|
|
mean value: 0.011893439292907714
|
|
|
|
key: test_mcc
|
|
value: [0.95235327 0.95235327 0.95235327 0.97590007 0.97590007 0.95235327
|
|
0.97590007 0.88465174 0.95180006 0.97559506]
|
|
|
|
mean value: 0.9549160133358575
|
|
|
|
key: train_mcc
|
|
value: [0.96003699 0.95742711 0.95742711 0.95482371 0.95482371 0.96003699
|
|
0.95742711 0.9626534 0.96008794 0.95229309]
|
|
|
|
mean value: 0.9577037142339239
|
|
|
|
key: test_accuracy
|
|
value: [0.97560976 0.97560976 0.97560976 0.98780488 0.98780488 0.97560976
|
|
0.98780488 0.93902439 0.97530864 0.98765432]
|
|
|
|
mean value: 0.976784101174345
|
|
|
|
key: train_accuracy
|
|
value: [0.97961957 0.97826087 0.97826087 0.97690217 0.97690217 0.97961957
|
|
0.97826087 0.98097826 0.97964722 0.97557666]
|
|
|
|
mean value: 0.9784028228423102
|
|
|
|
key: test_fscore
|
|
value: [0.97619048 0.97619048 0.97619048 0.98795181 0.98795181 0.97619048
|
|
0.98795181 0.94252874 0.97560976 0.98795181]
|
|
|
|
mean value: 0.9774707625407313
|
|
|
|
key: train_fscore
|
|
value: [0.98002663 0.9787234 0.9787234 0.97742364 0.97742364 0.98002663
|
|
0.9787234 0.98133333 0.98007968 0.97612732]
|
|
|
|
mean value: 0.978861108820245
|
|
|
|
key: test_precision
|
|
value: [0.95348837 0.95348837 0.95348837 0.97619048 0.97619048 0.95348837
|
|
0.97619048 0.89130435 0.95238095 0.97619048]
|
|
|
|
mean value: 0.9562400693341037
|
|
|
|
key: train_precision
|
|
value: [0.96083551 0.95833333 0.95833333 0.95584416 0.95584416 0.96083551
|
|
0.95833333 0.96335079 0.9609375 0.95336788]
|
|
|
|
mean value: 0.9586015490953057
|
|
|
|
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: [0.97560976 0.97560976 0.97560976 0.98780488 0.98780488 0.97560976
|
|
0.98780488 0.93902439 0.97560976 0.9875 ]
|
|
|
|
mean value: 0.9767987804878049
|
|
|
|
key: train_roc_auc
|
|
value: [0.97961957 0.97826087 0.97826087 0.97690217 0.97690217 0.97961957
|
|
0.97826087 0.98097826 0.97961957 0.97560976]
|
|
|
|
mean value: 0.9784033669141039
|
|
|
|
key: test_jcc
|
|
value: [0.95348837 0.95348837 0.95348837 0.97619048 0.97619048 0.95348837
|
|
0.97619048 0.89130435 0.95238095 0.97619048]
|
|
|
|
mean value: 0.9562400693341037
|
|
|
|
key: train_jcc
|
|
value: [0.96083551 0.95833333 0.95833333 0.95584416 0.95584416 0.96083551
|
|
0.95833333 0.96335079 0.9609375 0.95336788]
|
|
|
|
mean value: 0.9586015490953057
|
|
|
|
MCC on Blind test: 0.08
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Passive Aggresive
|
|
Model func: PassiveAggressiveClassifier(n_jobs=10, random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
PassiveAggressiveClassifier(n_jobs=10, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.01940751 0.02054787 0.02020812 0.02052116 0.01922226 0.0192306
|
|
0.01953673 0.01883125 0.01966619 0.01933861]
|
|
|
|
mean value: 0.019651031494140624
|
|
|
|
key: score_time
|
|
value: [0.01198006 0.01188064 0.01186681 0.0118916 0.0118022 0.01185632
|
|
0.01184344 0.01190782 0.01186085 0.01186776]
|
|
|
|
mean value: 0.011875748634338379
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9987654320987654
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9987654320987654
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.98780488 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.12
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Stochastic GDescent
|
|
Model func: SGDClassifier(n_jobs=10, random_state=42)
|
|
List of models: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
[('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', SGDClassifier(n_jobs=10, random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.0162499 0.01603103 0.01658034 0.01598787 0.01594448 0.01596522
|
|
0.01621485 0.01603603 0.01626325 0.01672888]
|
|
|
|
mean value: 0.01620018482208252
|
|
|
|
key: score_time
|
|
value: [0.01212835 0.01185083 0.01184201 0.01177883 0.01184797 0.01181841
|
|
0.01181817 0.01187229 0.0117836 0.01182961]
|
|
|
|
mean value: 0.011857008934020996
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9987654320987654
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9987654320987654
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.98780488 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
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: 0.64
|
|
|
|
Model_name: AdaBoost Classifier
|
|
Model func: AdaBoostClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:747: UserWarning: Some inputs do not have OOB scores. This probably means too few estimators were used to compute any reliable oob estimates.
|
|
warn(
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py:753: RuntimeWarning: invalid value encountered in true_divide
|
|
oob_decision_function = predictions / predictions.sum(axis=1)[:, np.newaxis]
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', AdaBoostClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.1933639 0.17780399 0.17868209 0.17682266 0.17803907 0.17734218
|
|
0.18125486 0.1778419 0.1783545 0.17764473]
|
|
|
|
mean value: 0.17971498966217042
|
|
|
|
key: score_time
|
|
value: [0.01552391 0.01565957 0.01562071 0.01566958 0.01566577 0.0158267
|
|
0.01566458 0.01561618 0.01578569 0.01569843]
|
|
|
|
mean value: 0.015673112869262696
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9975900072948534
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9987951807228915
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9976190476190476
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 0.98780488 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.998780487804878
|
|
|
|
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. 0.97619048 1. 1. 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9976190476190476
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.12
|
|
|
|
Accuracy on Blind test: 0.65
|
|
|
|
Model_name: Bagging Classifier
|
|
Model func: BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model',
|
|
BaggingClassifier(n_jobs=10, oob_score=True,
|
|
random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.15212679 0.16374302 0.16546059 0.16883278 0.16681457 0.056422
|
|
0.16603708 0.15502191 0.15446663 0.04659557]
|
|
|
|
mean value: 0.13955209255218506
|
|
|
|
key: score_time
|
|
value: [0.03932214 0.03972292 0.04102039 0.03985643 0.04061651 0.0379293
|
|
0.03316736 0.03227663 0.03358197 0.03551793]
|
|
|
|
mean value: 0.037301158905029295
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 0.97590007 1. 0.95235327 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9903863095531827
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 0.98780488 1. 0.97560976 1.
|
|
1. 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9951068955133996
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 0.98795181 1. 0.97619048 1.
|
|
1. 1. 0.98765432 1. ]
|
|
|
|
mean value: 0.9951796604407046
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 0.97619048 1. 0.95348837 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9905288604381061
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 0.98780488 1. 0.97560976 1.
|
|
1. 1. 0.98780488 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
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. 0.97619048 1. 0.95348837 1.
|
|
1. 1. 0.97560976 1. ]
|
|
|
|
mean value: 0.9905288604381061
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test:/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Gaussian Process
|
|
Model func: GaussianProcessClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GaussianProcessClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.23483968 0.2919898 0.28060555 0.40334725 0.45062828 0.42588902
|
|
0.36511922 0.29585052 0.51436138 0.32489538]
|
|
|
|
mean value: 0.35875260829925537
|
|
|
|
key: score_time
|
|
value: [0.01855564 0.01846242 0.03192854 0.03131938 0.03152657 0.03708315
|
|
0.01892447 0.03142667 0.01882124 0.03217816]
|
|
|
|
mean value: 0.027022624015808107
|
|
|
|
key: test_mcc
|
|
value: [1. 0.97590007 1. 1. 1. 1.
|
|
1. 0.97590007 1. 1. ]
|
|
|
|
mean value: 0.9951800145897066
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 0.99728629 1. 1. ]
|
|
|
|
mean value: 0.9997286290790893
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.98780488 1. 1. 1. 1.
|
|
1. 0.98780488 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1.
|
|
0.9986413 1. 1. ]
|
|
|
|
mean value: 0.9998641304347826
|
|
|
|
key: test_fscore
|
|
value: [1. 0.98795181 1. 1. 1. 1.
|
|
1. 0.98795181 1. 1. ]
|
|
|
|
mean value: 0.9975903614457832
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 0.99864315 1. 1. ]
|
|
|
|
mean value: 0.999864314789688
|
|
|
|
key: test_precision
|
|
value: [1. 0.97619048 1. 1. 1. 1.
|
|
1. 0.97619048 1. 1. ]
|
|
|
|
mean value: 0.9952380952380953
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 0.99728997 1. 1. ]
|
|
|
|
mean value: 0.9997289972899729
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.98780488 1. 1. 1. 1.
|
|
1. 0.98780488 1. 1. ]
|
|
|
|
mean value: 0.9975609756097561
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1.
|
|
0.9986413 1. 1. ]
|
|
|
|
mean value: 0.9998641304347826
|
|
|
|
key: test_jcc
|
|
value: [1. 0.97619048 1. 1. 1. 1.
|
|
1. 0.97619048 1. 1. ]
|
|
|
|
mean value: 0.9952380952380953
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1.
|
|
1. 0.99728997 1. 1. ]
|
|
|
|
mean value: 0.9997289972899729
|
|
|
|
MCC on Blind test: -0.01
|
|
|
|
Accuracy on Blind test: 0.63
|
|
|
|
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: /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/discriminant_analysis.py:887: UserWarning: Variables are collinear
|
|
warnings.warn("Variables are collinear")
|
|
/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/metrics/_classification.py:1327: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
_warn_prf(average, modifier, msg_start, len(result))
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', GradientBoostingClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.37295341 0.58469367 0.35287929 0.59070086 0.34697008 0.57370162
|
|
0.57505512 0.58783317 0.58660769 0.58256197]
|
|
|
|
mean value: 0.5153956890106202
|
|
|
|
key: score_time
|
|
value: [0.01013303 0.00937486 0.0092721 0.00929713 0.00996041 0.00939012
|
|
0.00961304 0.00950384 0.00951195 0.00951266]
|
|
|
|
mean value: 0.009556913375854492
|
|
|
|
key: test_mcc
|
|
value: [0.97590007 1. 0.97590007 1. 0.95235327 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.99041534123828
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [0.98780488 1. 0.98780488 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [0.98795181 1. 0.98795181 1. 0.97619048 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9952094090648308
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [0.97619048 1. 0.97619048 1. 0.95348837 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9905869324473976
|
|
|
|
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: [0.98780488 1. 0.98780488 1. 0.97560976 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9951219512195122
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [0.97619048 1. 0.97619048 1. 0.95348837 1.
|
|
1. 1. 1. 1. ]
|
|
|
|
mean value: 0.9905869324473976
|
|
|
|
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: 0.64
|
|
|
|
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: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', QuadraticDiscriminantAnalysis())])
|
|
|
|
key: fit_time
|
|
value: [0.03872991 0.03791022 0.03865004 0.03827381 0.04180598 0.04633164
|
|
0.038692 0.0389986 0.04175949 0.04024053]
|
|
|
|
mean value: 0.04013922214508057
|
|
|
|
key: score_time
|
|
value: [0.02073717 0.01299286 0.01280546 0.01337028 0.01272225 0.01557684
|
|
0.01273084 0.01278329 0.017133 0.01732206]
|
|
|
|
mean value: 0.014817404747009277
|
|
|
|
key: test_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_mcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_accuracy
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_fscore
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_precision
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_roc_auc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_jcc
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
MCC on Blind test: 0.0
|
|
|
|
Accuracy on Blind test: 0.64
|
|
|
|
Model_name: Ridge Classifier
|
|
Model func: RidgeClassifier(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
|
|
colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
|
|
gamma=0, gpu_id=-1, importance_type=None,
|
|
interaction_constraints='', learning_rate=0.300000012,
|
|
max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
|
|
monotone_constraints='()', n_estimators=100, n_jobs=12,
|
|
num_parallel_tree=1, predictor='auto', random_state=42,
|
|
reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
|
|
tree_method='exact', use_label_encoder=False,
|
|
validate_parameters=1, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', RidgeClassifier(random_state=42))])
|
|
|
|
key: fit_time
|
|
value: [0.02562404 0.01709557 0.01693654 0.017066 0.03375077 0.0413425
|
|
0.04174829 0.04163456 0.0395155 0.04287601]
|
|
|
|
mean value: 0.03175897598266601
|
|
|
|
key: score_time
|
|
value: [0.01889253 0.01219988 0.01222539 0.01215148 0.01892686 0.01885581
|
|
0.02128983 0.02113318 0.01900244 0.01880312]
|
|
|
|
mean value: 0.017348051071166992
|
|
|
|
key: test_mcc
|
|
value: [1. 0.97590007 1. 0.97590007 1. 1.
|
|
0.95235327 1. 0.97560976 0.95174259]
|
|
|
|
mean value: 0.983150575630985
|
|
|
|
key: train_mcc
|
|
value: [0.99728629 0.99728629 0.99457991 0.99457991 0.99728629 0.99728629
|
|
0.99728629 0.99728629 0.99458719 0.99728997]
|
|
|
|
mean value: 0.9964754720077219
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.98780488 1. 0.98780488 1. 1.
|
|
0.97560976 1. 0.98765432 0.97530864]
|
|
|
|
mean value: 0.9914182475158084
|
|
|
|
key: train_accuracy
|
|
value: [0.9986413 0.9986413 0.99728261 0.99728261 0.9986413 0.9986413
|
|
0.9986413 0.9986413 0.9972863 0.99864315]
|
|
|
|
mean value: 0.9982342487168898
|
|
|
|
key: test_fscore
|
|
value: [1. 0.98795181 1. 0.98795181 1. 1.
|
|
0.97619048 1. 0.98765432 0.97619048]
|
|
|
|
mean value: 0.9915938887826438
|
|
|
|
key: train_fscore
|
|
value: [0.99864315 0.99864315 0.99728997 0.99728997 0.99864315 0.99864315
|
|
0.99864315 0.99864315 0.9972973 0.99864315]
|
|
|
|
mean value: 0.9982379278374909
|
|
|
|
key: test_precision
|
|
value: [1. 0.97619048 1. 0.97619048 1. 1.
|
|
0.95348837 1. 0.97560976 0.95348837]
|
|
|
|
mean value: 0.983496745266456
|
|
|
|
key: train_precision
|
|
value: [0.99728997 0.99728997 0.99459459 0.99459459 0.99728997 0.99728997
|
|
0.99728997 0.99728997 0.99460916 0.99728997]
|
|
|
|
mean value: 0.9964828163907777
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.98780488 1. 0.98780488 1. 1.
|
|
0.97560976 1. 0.98780488 0.975 ]
|
|
|
|
mean value: 0.9914024390243903
|
|
|
|
key: train_roc_auc
|
|
value: [0.9986413 0.9986413 0.99728261 0.99728261 0.9986413 0.9986413
|
|
0.9986413 0.9986413 0.99728261 0.99864499]
|
|
|
|
mean value: 0.9982340638623778
|
|
|
|
key: test_jcc
|
|
value: [1. 0.97619048 1. 0.97619048 1. 1.
|
|
0.95348837 1. 0.97560976 0.95348837]
|
|
|
|
mean value: 0.983496745266456
|
|
|
|
key: train_jcc
|
|
value: [0.99728997 0.99728997 0.99459459 0.99459459 0.99728997 0.99728997
|
|
0.99728997 0.99728997 0.99460916 0.99728997]
|
|
|
|
mean value: 0.9964828163907777
|
|
|
|
MCC on Blind test: 0.15
|
|
|
|
Accuracy on Blind test: 0.66
|
|
|
|
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: /home/tanu/git/LSHTM_analysis/scripts/ml/./gid_rt.py:155: SettingWithCopyWarning:
|
|
A value is trying to be set on a copy of a slice from a DataFrame
|
|
|
|
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
|
|
ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_rt.py:158: 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)
|
|
Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', RidgeClassifierCV(cv=10))])
|
|
|
|
key: fit_time
|
|
value: [0.25911665 0.39674997 0.37813807 0.31950808 0.33281422 0.39413953
|
|
0.32855153 0.34012485 0.31728721 0.34709024]
|
|
|
|
mean value: 0.3413520336151123
|
|
|
|
key: score_time
|
|
value: [0.01918983 0.01939535 0.0202353 0.01941204 0.01946306 0.01990223
|
|
0.02010703 0.01912546 0.01892161 0.01906776]
|
|
|
|
mean value: 0.019481968879699708
|
|
|
|
key: test_mcc
|
|
value: [1. 0.97590007 1. 1. 1. 1.
|
|
0.95235327 1. 0.97560976 0.95174259]
|
|
|
|
mean value: 0.9855605683361317
|
|
|
|
key: train_mcc
|
|
value: [0.99457991 0.99728629 0.99457991 0.99457991 0.99457991 0.99457991
|
|
0.99728629 0.99457991 0.99458719 0.99728997]
|
|
|
|
mean value: 0.9953929180451583
|
|
|
|
key: test_accuracy
|
|
value: [1. 0.98780488 1. 1. 1. 1.
|
|
0.97560976 1. 0.98765432 0.97530864]
|
|
|
|
mean value: 0.9926377597109304
|
|
|
|
key: train_accuracy
|
|
value: [0.99728261 0.9986413 0.99728261 0.99728261 0.99728261 0.99728261
|
|
0.9986413 0.99728261 0.9972863 0.99864315]
|
|
|
|
mean value: 0.9976907704560203
|
|
|
|
key: test_fscore
|
|
value: [1. 0.98795181 1. 1. 1. 1.
|
|
0.97619048 1. 0.98765432 0.97619048]
|
|
|
|
mean value: 0.9927987080597522
|
|
|
|
key: train_fscore
|
|
value: [0.99728997 0.99864315 0.99728997 0.99728997 0.99728997 0.99728997
|
|
0.99864315 0.99728997 0.9972973 0.99864315]
|
|
|
|
mean value: 0.9976966578386308
|
|
|
|
key: test_precision
|
|
value: [1. 0.97619048 1. 1. 1. 1.
|
|
0.95348837 1. 0.97560976 0.95348837]
|
|
|
|
mean value: 0.9858776976474084
|
|
|
|
key: train_precision
|
|
value: [0.99459459 0.99728997 0.99459459 0.99459459 0.99459459 0.99459459
|
|
0.99728997 0.99459459 0.99460916 0.99728997]
|
|
|
|
mean value: 0.995404665068724
|
|
|
|
key: test_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: train_recall
|
|
value: [1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
|
|
|
|
mean value: 1.0
|
|
|
|
key: test_roc_auc
|
|
value: [1. 0.98780488 1. 1. 1. 1.
|
|
0.97560976 1. 0.98780488 0.975 ]
|
|
|
|
mean value: 0.9926219512195122
|
|
|
|
key: train_roc_auc
|
|
value: [0.99728261 0.9986413 0.99728261 0.99728261 0.99728261 0.99728261
|
|
0.9986413 0.99728261 0.99728261 0.99864499]
|
|
|
|
mean value: 0.9976905856015081
|
|
|
|
key: test_jcc
|
|
value: [1. 0.97619048 1. 1. 1. 1.
|
|
0.95348837 1. 0.97560976 0.95348837]
|
|
|
|
mean value: 0.9858776976474084
|
|
|
|
key: train_jcc
|
|
value: [0.99459459 0.99728997 0.99459459 0.99459459 0.99459459 0.99459459
|
|
0.99728997 0.99459459 0.99460916 0.99728997]
|
|
|
|
mean value: 0.995404665068724
|
|
|
|
MCC on Blind test: 0.15
|
|
|
|
Accuracy on Blind test: 0.66
|
|
|
|
Model_name: Logistic Regression
|
|
Model func: LogisticRegression(random_state=42)
|
|
List of models: [('Logistic Regression', LogisticRegression(random_state=42)), ('Logistic RegressionCV', LogisticRegressionCV(random_state=42)), ('Gaussian NB', GaussianNB()), ('Naive Bayes', BernoulliNB()), ('K-Nearest Neighbors', KNeighborsClassifier()), ('SVM', SVC(random_state=42)), ('MLP', MLPClassifier(max_iter=500, random_state=42)), ('Decision Tree', DecisionTreeClassifier(random_state=42)), ('Extra Trees', ExtraTreesClassifier(random_state=42)), ('Extra Tree', ExtraTreeClassifier(random_state=42)), ('Random Forest', RandomForestClassifier(n_estimators=1000, random_state=42)), ('Random Forest2', RandomForestClassifier(max_features='auto', min_samples_leaf=5,
|
|
n_estimators=1000, n_jobs=10, oob_score=True,
|
|
random_state=42)), ('Naive Bayes', BernoulliNB()), ('XGBoost', XGBClassifier(base_score=None, booster=None, colsample_bylevel=None,
|
|
colsample_bynode=None, colsample_bytree=None,
|
|
enable_categorical=False, gamma=None, gpu_id=None,
|
|
importance_type=None, interaction_constraints=None,
|
|
learning_rate=None, max_delta_step=None, max_depth=None,
|
|
min_child_weight=None, missing=nan, monotone_constraints=None,
|
|
n_estimators=100, n_jobs=None, num_parallel_tree=None,
|
|
predictor=None, random_state=42, reg_alpha=None, reg_lambda=None,
|
|
scale_pos_weight=None, subsample=None, tree_method=None,
|
|
use_label_encoder=False, validate_parameters=None, verbosity=0)), ('LDA', LinearDiscriminantAnalysis()), ('Multinomial', MultinomialNB()), ('Passive Aggresive', PassiveAggressiveClassifier(n_jobs=10, random_state=42)), ('Stochastic GDescent', SGDClassifier(n_jobs=10, random_state=42)), ('AdaBoost Classifier', AdaBoostClassifier(random_state=42)), ('Bagging Classifier', BaggingClassifier(n_jobs=10, oob_score=True, random_state=42)), ('Gaussian Process', GaussianProcessClassifier(random_state=42)), ('Gradient Boosting', GradientBoostingClassifier(random_state=42)), ('QDA', QuadraticDiscriminantAnalysis()), ('Ridge Classifier', RidgeClassifier(random_state=42)), ('Ridge ClassifierCV', RidgeClassifierCV(cv=10))]
|
|
Running model pipeline: Pipeline(steps=[('prep',
|
|
ColumnTransformer(remainder='passthrough',
|
|
transformers=[('num', MinMaxScaler(),
|
|
Index(['ligand_distance', 'ligand_affinity_change', 'duet_stability_change',
|
|
'ddg_foldx', 'deepddg', 'ddg_dynamut2', 'mmcsm_lig', 'contacts',
|
|
'mcsm_na_affinity', 'rsa',
|
|
...
|
|
'VENM980101', 'VOGG950101', 'WEIL970101', 'WEIL970102', 'ZHAC000101',
|
|
'ZHAC000102', 'ZHAC000103', 'ZHAC000104', 'ZHAC000105', 'ZHAC000106'],
|
|
dtype='object', length=167)),
|
|
('cat', OneHotEncoder(),
|
|
Index(['ss_class', 'aa_prop_change', 'electrostatics_change',
|
|
'polarity_change', 'water_change', 'drtype_mode_labels', 'active_site'],
|
|
dtype='object'))])),
|
|
('model', LogisticRegression(random_state=42))])
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/joblib/parallel.py", line 822, in dispatch_one_batch
|
|
tasks = self._ready_batches.get(block=False)
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/queue.py", line 168, in get
|
|
raise Empty
|
|
_queue.Empty
|
|
|
|
During handling of the above exception, another exception occurred:
|
|
|
|
Traceback (most recent call last):
|
|
File "/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_rt.py", line 165, in <module>
|
|
mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
|
|
File "/home/tanu/git/LSHTM_analysis/scripts/ml/MultModelsCl.py", line 218, in MultModelsCl
|
|
skf_cv_mod = cross_validate(model_pipeline
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 266, in cross_validate
|
|
results = parallel(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/joblib/parallel.py", line 1043, in __call__
|
|
if self.dispatch_one_batch(iterator):
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/joblib/parallel.py", line 833, in dispatch_one_batch
|
|
islice = list(itertools.islice(iterator, big_batch_size))
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_validation.py", line 266, in <genexpr>
|
|
results = parallel(
|
|
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 333, in split
|
|
raise ValueError(
|
|
ValueError: Cannot have number of splits n_splits=10 greater than the number of samples: n_samples=6.
|