testing the script with DT

model_selection/hyperparam_tuning.py

@@ -27,7 +27,6 @@ import os
 # Function to read training datasets
 # --------------------------------------------------------------------------------------------------------
 def read_data():
-    import numpy as np
 
     # Load ORIGINAL training data
     X_train_pre = np.load('../gen_train_data/data/output/pre/X_train_pre.npy', allow_pickle=True)

model_selection/test_models.py

@@ -25,11 +25,41 @@ def read_test_data():
     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)
+
+    # 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)
+
+    # 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)
+
     data_dic = {
         "X_test_pre": X_test_pre,
         "y_test_pre": y_test_pre,
         "X_test_post": X_test_post,
         "y_test_post": y_test_post,
+        "X_train_pre": X_train_pre,
+        "y_train_pre": y_train_pre,
+        "X_train_post": X_train_post,
+        "y_train_post": y_train_post,
+        "X_train_over_pre": X_train_over_pre,
+        "y_train_over_pre": y_train_over_pre,
+        "X_train_over_post": X_train_over_post,
+        "y_train_over_post": y_train_over_post,
+        "X_train_under_pre": X_train_under_pre,
+        "y_train_under_pre": y_train_under_pre,
+        "X_train_under_post": X_train_under_post,
+        "y_train_under_post": y_train_under_post,
     }
 
     return data_dic
@@ -205,24 +235,31 @@ if __name__ == "__main__":
     scores_sheets = {} # To store score dfs as sheets in the same excel file
     for i, group in enumerate(['pre', 'post']):
         # Get test dataset based on group
-        X = data_dic['X_test' + group]
-        y = data_dic['y_test' + group]
+        X_test = data_dic['X_test' + group]
+        y_test = data_dic['y_test' + group]
         for j, method in enumerate(['', '', 'over_', 'under_']):
+            # Get train dataset based on group and method
+            X_train = data_dic['X_train_' + method + group]
+            y_train = data_dic['y_train_' + method + group]
             # Get tuned models for this group and method
             models = get_tuned_models(group_id=i, method_id=j)
             # Scores df
             scores_df = pd.DataFrame(index=models.keys(), columns=scorings.keys())
             # Evaluate each model
             for model_name, model in models.items():
-                # At each of the scores of interest
-                for score_name, scorer in scorings.items():
-                    score_value = scorer(model, X, y)
-                    scores_df.at[model_name, score_name] = score_value
+                # ----------- TEMPORAL -------------
+                if model_name == "DT":
+                    # Train the model (it was just initialized above)
+                    model.fit(X_train, y_train) 
+                    # Evaluate at each of the scores of interest
+                    for score_name, scorer in scorings.items():
+                        score_value = scorer(model, X_test, y_test)
+                        scores_df.at[model_name, score_name] = score_value
             # Store the DataFrame in the dictionary with a unique key for each sheet
             sheet_name = f"{group}_{method_names[j]}"
             scores_sheets[sheet_name] = scores_df
     # Write results to Excel file
-    with pd.ExcelWriter('./training_models/output/testing_tuned_models.xlsx') as writer:
+    with pd.ExcelWriter('./model_selection/test_results/testing_tuned_models.xlsx') as writer:
         for sheet_name, data in scores_sheets.items():
             data.to_excel(writer, sheet_name=sheet_name)
     # --------------------------------------------------------------------------------------------------------