renamed UQ_LR_FS.py to UQ_LR_FS_p1.py

UQ_LR_FS_p1.py

@@ -230,19 +230,20 @@ print(confusion_matrix(y_bts, test_predict))
 # ADD that within the loop
 # https://towardsdatascience.com/5-feature-selection-method-from-scikit-learn-you-should-know-ed4d116e4172
 #####################
-from sklearn.feature_selection import RFE
+from sklearn.feature_selection import RFECV
 from sklearn.linear_model import LogisticRegression
 from sklearn.feature_selection import SelectFromModel
 from sklearn.feature_selection import SequentialFeatureSelector
 
 # RFE: ~ model coef or feature_importance
-rfe_selector = RFE(estimator = LogisticRegression(**rs
+rfe_selector = RFECV(estimator = LogisticRegression(**rs
                                                   , penalty='l1'
                                                   , solver='saga'
                                                   , max_iter = 100
                                                   , C= 1.0)
-                   , n_features_to_select = None # median by default
+                   #, n_features_to_select = None # median by default
-                   , step = 1)
+                   , step = 1
+                   , cv = 10)
 rfe_selector.fit(X, y)
 rfe_fs = X.columns[rfe_selector.get_support()]
 print('\nFeatures selected from Recursive Feature Elimination:', len(rfe_fs)

UQ_pnca_ML.py

@@ -13,6 +13,8 @@ import numpy as np
 import pprint as pp
 from copy import deepcopy
 from sklearn import linear_model
+from sklearn import datasets
+
 from sklearn.linear_model import LogisticRegression, LinearRegression
 from sklearn.naive_bayes import BernoulliNB
 from sklearn.neighbors import KNeighborsClassifier
@@ -70,15 +72,15 @@ print(np.__version__)
 print(pd.__version__)
 from statistics import mean, stdev, median, mode
 
-#from imblearn.over_sampling import RandomOverSampler
+from imblearn.over_sampling import RandomOverSampler
-#from imblearn.over_sampling import SMOTE
+from imblearn.over_sampling import SMOTE
-#from imblearn.pipeline import Pipeline
+from imblearn.pipeline import Pipeline
-#from sklearn.datasets import make_classification
+from sklearn.datasets import make_classification
 from sklearn.model_selection import cross_validate, cross_val_score
 from sklearn.model_selection import RepeatedStratifiedKFold
 from sklearn.ensemble import AdaBoostClassifier
-#from imblearn.combine import SMOTEENN
+from imblearn.combine import SMOTEENN
-#from imblearn.under_sampling import EditedNearestNeighbours
+from imblearn.under_sampling import EditedNearestNeighbours
 
 from sklearn.model_selection import GridSearchCV
 from sklearn.base import BaseEstimator
@@ -86,9 +88,9 @@ from sklearn.base import BaseEstimator
 scoring_fn =  ({'accuracy'      : make_scorer(accuracy_score)
                  , 'fscore'     : make_scorer(f1_score)
                  , 'mcc'        : make_scorer(matthews_corrcoef)
-                 ,  'precision' : make_scorer(precision_score)
+                 , 'precision'  : make_scorer(precision_score)
-                 ,  'recall'    : make_scorer(recall_score)
+                 , 'recall'     : make_scorer(recall_score)
-                 ,  'roc_auc'   : make_scorer(roc_auc_score)
+                 , 'roc_auc'    : make_scorer(roc_auc_score)
                  , 'jcc'        : make_scorer(jaccard_score)
             }) 
   
@@ -105,7 +107,7 @@ rskf_cv = RepeatedStratifiedKFold(n_splits = 10
                                  ,**rs)
 
 mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
-
+jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
 #%%
 homedir = os.path.expanduser("~")
 os.chdir(homedir + "/git/ML_AI_training/")