copy of ML dir to an FS-only version

UQ_FS_eg.py

@@ -49,8 +49,7 @@ clf2.best_estimator_.named_steps['selector'].n_features_in_
 clf2.best_estimator_ #n of best features
 clf2.best_params_ 
 clf2.best_estimator_.get_params
-clf2.get_feature_names()
-
+clf2.get_feature_names(
 
 
 clf3 = clf2.best_estimator_ # 
@@ -62,4 +61,37 @@ clf3._final_estimator.solver
 fs_bmod = clf2.best_estimator_
 print('\nbest model with feature selection:', fs_bmod)
 
+#########################################################
+# my data
+
+pipe = Pipeline([
+    ('pre', MinMaxScaler())
+    ('selector', RFECV(LogisticRegression(**rs), cv = skf_cv, scoring = 'matthews_corrcoef'))
+    , ('classifier',  LogisticRegression(**rs))])
+
+search_space = [{'selector__min_features_to_select': [1,2]},
+                {'classifier': [LogisticRegression()],
+                 #'classifier__C': np.logspace(0, 4, 10),
+                 'classifier__C': [2, 2.8],
+                 'classifier__max_iter': [100],
+                 'classifier__penalty': ['l1', 'l2'],
+                 'classifier__solver': ['saga']
+                 }] #,
+                #{'classifier': [RandomForestClassifier(n_estimators=100)],
+                # 'classifier__max_depth': [5, 10, None]},
+                #{'classifier': [KNeighborsClassifier()],
+                # 'classifier__n_neighbors': [3, 7, 11],
+                # 'classifier__weights': ['uniform', 'distance']
+                #}]
+
+clf = GridSearchCV(pipe, search_space, cv=skf_cv, scoring = mcc_score_fn, refit = 'mcc',  verbose=0)
+
+clf.fit(X, y)
+clf.best_params_
+clf.best_score_
+
+tp = clf.predict(X_bts)
+print('\nMCC on Blind test:'     , round(matthews_corrcoef(y_bts, tp),2))
+print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, tp),2))
+