fixing small details, getting ready to run script

training_models/hyperparam_tuning.py

@@ -30,28 +30,28 @@ def read_data():
     import numpy as np
 
     # Load test data
-    X_test_pre = np.load('./gen_train_data/data/output/pre/X_test_pre.npy', allow_pickle=True)
-    y_test_pre = np.load('./gen_train_data/data/output/pre/y_test_pre.npy', allow_pickle=True)
-    X_test_post = np.load('./gen_train_data/data/output/post/X_test_post.npy', allow_pickle=True)
-    y_test_post = np.load('./gen_train_data/data/output/post/y_test_post.npy', allow_pickle=True)
+    X_test_pre = np.load('../gen_train_data/data/output/pre/X_test_pre.npy', allow_pickle=True)
+    y_test_pre = np.load('../gen_train_data/data/output/pre/y_test_pre.npy', allow_pickle=True)
+    X_test_post = np.load('../gen_train_data/data/output/post/X_test_post.npy', allow_pickle=True)
+    y_test_post = np.load('../gen_train_data/data/output/post/y_test_post.npy', allow_pickle=True)
 
     # Load ORIGINAL training data
-    X_train_pre = np.load('./gen_train_data/data/output/pre/X_train_pre.npy', allow_pickle=True)
-    y_train_pre = np.load('./gen_train_data/data/output/pre/y_train_pre.npy', allow_pickle=True)
-    X_train_post = np.load('./gen_train_data/data/output/post/X_train_post.npy', allow_pickle=True)
-    y_train_post = np.load('./gen_train_data/data/output/post/y_train_post.npy', allow_pickle=True)
+    X_train_pre = np.load('../gen_train_data/data/output/pre/X_train_pre.npy', allow_pickle=True)
+    y_train_pre = np.load('../gen_train_data/data/output/pre/y_train_pre.npy', allow_pickle=True)
+    X_train_post = np.load('../gen_train_data/data/output/post/X_train_post.npy', allow_pickle=True)
+    y_train_post = np.load('../gen_train_data/data/output/post/y_train_post.npy', allow_pickle=True)
 
     # Load oversampled training data
-    X_train_over_pre = np.load('./gen_train_data/data/output/pre/X_train_over_pre.npy', allow_pickle=True)
-    y_train_over_pre = np.load('./gen_train_data/data/output/pre/y_train_over_pre.npy', allow_pickle=True)
-    X_train_over_post = np.load('./gen_train_data/data/output/post/X_train_over_post.npy', allow_pickle=True)
-    y_train_over_post = np.load('./gen_train_data/data/output/post/y_train_over_post.npy', allow_pickle=True)
+    X_train_over_pre = np.load('../gen_train_data/data/output/pre/X_train_over_pre.npy', allow_pickle=True)
+    y_train_over_pre = np.load('../gen_train_data/data/output/pre/y_train_over_pre.npy', allow_pickle=True)
+    X_train_over_post = np.load('../gen_train_data/data/output/post/X_train_over_post.npy', allow_pickle=True)
+    y_train_over_post = np.load('../gen_train_data/data/output/post/y_train_over_post.npy', allow_pickle=True)
 
     # Load undersampled training data
-    X_train_under_pre = np.load('./gen_train_data/data/output/pre/X_train_under_pre.npy', allow_pickle=True)
-    y_train_under_pre = np.load('./gen_train_data/data/output/pre/y_train_under_pre.npy', allow_pickle=True)
-    X_train_under_post = np.load('./gen_train_data/data/output/post/X_train_under_post.npy', allow_pickle=True)
-    y_train_under_post = np.load('./gen_train_data/data/output/post/y_train_under_post.npy', allow_pickle=True)
+    X_train_under_pre = np.load('../gen_train_data/data/output/pre/X_train_under_pre.npy', allow_pickle=True)
+    y_train_under_pre = np.load('../gen_train_data/data/output/pre/y_train_under_pre.npy', allow_pickle=True)
+    X_train_under_post = np.load('../gen_train_data/data/output/post/X_train_under_post.npy', allow_pickle=True)
+    y_train_under_post = np.load('../gen_train_data/data/output/post/y_train_under_post.npy', allow_pickle=True)
 
     data_dic = {
         "X_test_pre": X_test_pre,
@@ -84,26 +84,26 @@ if __name__ == "__main__":
     # --------------------------------------------------------------------------------------------------------
     # 1. No class weight
     models_1 = {"DT" : DecisionTreeClassifier(), 
-            # "RF" : RandomForestClassifier(n_estimators=50), 
-            # "Bagging" : BaggingClassifier(),
-            # "AB" : AdaBoostClassifier(), 
-            # "XGB": XGBClassifier(),
-            # "LR" : LogisticRegression(max_iter=1000), 
-            # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'), 
-            # "SVM" : SVC(probability=True), 
-            # "MLP" : MLPClassifier(max_iter=500),
+            "RF" : RandomForestClassifier(), 
+            "Bagging" : BaggingClassifier(),
+            "AB" : AdaBoostClassifier(), 
+            "XGB": XGBClassifier(),
+            "LR" : LogisticRegression(max_iter=1000), 
+            "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'), 
+            "SVM" : SVC(probability=True), 
+            "MLP" : MLPClassifier(max_iter=500)
             }
     
-    # 2. Class weight 
+    # 2. Class weight: cost-sensitive learning
     models_2 = {"DT" : DecisionTreeClassifier(class_weight='balanced'), 
-            # "RF" : RandomForestClassifier(n_estimators=50, class_weight='balanced'), 
-            # "Bagging" : BaggingClassifier(), # <-
-            # "AB" : AdaBoostClassifier(),  # <-
+            "RF" : RandomForestClassifier(class_weight='balanced'), 
+            "Bagging" : BaggingClassifier(estimator= DecisionTreeClassifier(class_weight='balanced')),
+            "AB" : AdaBoostClassifier(estimator= DecisionTreeClassifier(class_weight='balanced')),  
             # "XGB": XGBClassifier(), # <-
-            # "LR" : LogisticRegression(max_iter=1000, class_weight='balanced'), 
-            # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet', class_weight='balanced'), 
-            # "SVM" : SVC(probability=True, class_weight='balanced'), 
-            # "MLP" : MLPClassifier(max_iter=500), # <-
+            "LR" : LogisticRegression(max_iter=1000, class_weight='balanced'), 
+            "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet', class_weight='balanced'), 
+            "SVM" : SVC(probability=True, class_weight='balanced'), 
+            # "MLP" : MLPClassifier(max_iter=500)
             }
 
     # Hyperparameter tuning setup
@@ -152,8 +152,9 @@ if __name__ == "__main__":
     # Store each df as a sheet in an excel file
     sheets_dict = {}
     for i, group in enumerate(['pre', 'post']):
+        print(group, end = ' ')
         for j, method in enumerate(['', '', 'over_', 'under_']):
-            print(f"ITERATION {i+j}")
+            print(method, end = ' ')
             # Get dataset based on group and method
             X = data_dic['X_train_' + method + group]
             y = data_dic['y_train_' + method + group]
@@ -162,6 +163,7 @@ if __name__ == "__main__":
             # Save results: params and best score for each of the mdodels of this method and group
             hyperparam_df = pd.DataFrame(index=list(models.keys()), columns=['Parameters','Score'])
             for model_name, model in models.items():
+                print(model_name + "\n\n")
                 # Find optimal hyperparams for curr model
                 params = hyperparameters[model_name]
                 search = RandomizedSearchCV(model, param_distributions=params, cv=cv, n_jobs=1, scoring='precision')
@@ -174,7 +176,7 @@ if __name__ == "__main__":
             sheets_dict[sheet_name] = hyperparam_df
 
     # Write results to Excel file
-    with pd.ExcelWriter('./training_models/output/hyperparam.xlsx') as writer:
+    with pd.ExcelWriter('./output/hyperparam.xlsx') as writer:
         for sheet_name, data in sheets_dict.items():
             data.to_excel(writer, sheet_name=sheet_name)
     # --------------------------------------------------------------------------------------------------------