trying under and oversampling

UQ_pnca_ML.py

@@ -36,7 +36,8 @@ from sklearn.gaussian_process.kernels import WhiteKernel
 from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
 from sklearn.neural_network import MLPClassifier
 
-from sklearn.linear_model import RidgeClassifier
+from sklearn.linear_model import RidgeClassifier, SGDClassifier, PassiveAggressiveClassifier
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
 from sklearn.svm import SVC
 from xgboost import XGBClassifier
 from sklearn.naive_bayes import MultinomialNB
@@ -72,6 +73,7 @@ print(pd.__version__)
 from statistics import mean, stdev, median, mode
 
 from imblearn.over_sampling import RandomOverSampler
+from imblearn.under_sampling import RandomUnderSampler
 from imblearn.over_sampling import SMOTE
 from imblearn.pipeline import Pipeline
 from sklearn.datasets import make_classification
@@ -81,6 +83,7 @@ from sklearn.ensemble import AdaBoostClassifier
 from imblearn.combine import SMOTEENN
 from imblearn.under_sampling import EditedNearestNeighbours
 
+
 from sklearn.model_selection import GridSearchCV
 from sklearn.base import BaseEstimator
 import json
@@ -119,6 +122,10 @@ from MultClassPipe3 import MultClassPipeSKFCV
 gene = 'pncA'
 drug = 'pyrazinamide'
 
+#gene = 'katG'
+#drug = 'isoniazid'
+
+
 #==============
 # directories
 #==============
@@ -234,13 +241,13 @@ numerical_FN = common_cols_stabiltyN + foldX_cols + X_strFN + X_evolFN + X_genom
 
 #categorical feature names
 categorical_FN = ['ss_class'
-             , 'wt_prop_water'
+#             , 'wt_prop_water'
             # , 'lineage_labels' # misleading if using merged_df3
-             , 'mut_prop_water'
-             , 'wt_prop_polarity'
-             , 'mut_prop_polarity'
-             , 'wt_calcprop'
-             , 'mut_calcprop'
+#             , 'mut_prop_water'
+#             , 'wt_prop_polarity'
+#             , 'mut_prop_polarity'
+#             , 'wt_calcprop'
+#             , 'mut_calcprop'
              #, 'active_aa_pos'
              ]
 
@@ -278,9 +285,9 @@ all_df_wtgt.shape
 #------
 # X
 #------
-X     = all_df_wtgt[numerical_FN + categorical_FN] # training data ALL
+#X     = all_df_wtgt[numerical_FN + categorical_FN] # training data ALL
 X_bts = blind_test_df[numerical_FN + categorical_FN] # blind test data ALL
-#X = all_df_wtgt[numerical_FN] # training numerical only
+X = all_df_wtgt[numerical_FN] # training numerical only
 #X_bts = blind_test_df[numerical_FN] # blind test data numerical
 
 #------