git add UQ_imbalance.py

uq_ml_models_FS/scriptfsycm.py

@@ -27,22 +27,56 @@ from sklearn.model_selection import train_test_split, cross_validate, cross_val_
 # Metric
 from sklearn.metrics import mean_squared_error, make_scorer, roc_auc_score, f1_score, matthews_corrcoef, accuracy_score, balanced_accuracy_score, confusion_matrix, classification_report
 
-def run_all_ML(input_pd, target_label):
+#def run_all_ML(input_pd, target_label, bts_input, bts_target, var_type):
+def run_all_ML(input_pd, target_label, preprocess = True, var_type = 'numerical'):
+
     #y = input_pd[target_label]
     #X = input_pd.drop(target_label,axis=1)
     y = target_label
     X = input_pd
+    # determine categorical and numerical features
+    numerical_ix = input_df.select_dtypes(include=['int64', 'float64']).columns
+    numerical_ix
+    categorical_ix = input_df.select_dtypes(include=['object', 'bool']).columns
+    categorical_ix    
+
+    # Determine preprocessing steps ~ var_type
+    if var_type == 'numerical':
+        t = [('num', MinMaxScaler(), numerical_ix)]
+
+    if var_type == 'categorical':
+        t = [('cat', OneHotEncoder(), categorical_ix)]
     
+    if var_type == 'mixed':
+        t = [('num', MinMaxScaler(), numerical_ix)
+              , ('cat', OneHotEncoder(), categorical_ix)]
+        
+    col_transform = ColumnTransformer(transformers = t
+                                       , remainder='passthrough')
     result_pd = pd.DataFrame()
     for name, algorithm in all_estimators(type_filter="classifier"):
         try:
             estmator = algorithm()
             temp_pd = pd.DataFrame()
             temp_cm = pd.DataFrame()
-            
+
+            # orig
             pipe = Pipeline([
-                ("model", algorithm())
+                ("model"    , algorithm())
             ])
+            
+            # turn on and off preprocessing
+            if preprocess == True:
+                pipe = Pipeline([
+                    ('prep'     , col_transform),
+                    ("model"    , algorithm()) 
+                    ])
+            else:   
+                pipe = Pipeline([
+                    ("model"    , algorithm())
+                ])
+                
+            
             y_pred = cross_val_predict(pipe, X, y, cv = 10, n_jobs=10)
             _mcc = round(matthews_corrcoef(y_pred, y), 3)
             _bacc = round(balanced_accuracy_score(y_pred, y), 3)