Testing metric generation

model_selection/cv_metric_gen.py

@@ -81,9 +81,9 @@ def get_tuned_models(group_str, method_str):
     tuned_models = {}
     # Iterate through each row of the DataFrame
     for _, row in tuned_models_df.iterrows():
-        model_name = row[0]
+        model_name = row.iloc[0]
         # Read dictionary
-        parameters = ast.literal_eval(row['Parameters'])
+        parameters = ast.literal_eval(row['Best Parameters'])
         # Add extra parameters 
         if model_name == 'AB':
             parameters['algorithm'] = 'SAMME'
@@ -177,7 +177,7 @@ if __name__ == "__main__":
     scores_sheets = {} # To store score dfs as sheets in the same excel file
     for i, group in enumerate(['pre', 'post']):
         for j, method in enumerate(['', '', 'over_', 'under_']):
-            print(f"{group}-{method_names[j]}")
+            # print(f"{group}-{method_names[j]}")
             # Get train dataset based on group and method
             X_train = data_dic['X_train_' + method + group]
             y_train = data_dic['y_train_' + method + group]
@@ -188,12 +188,13 @@ if __name__ == "__main__":
             scores_df = pd.DataFrame(columns=range(1,11), index=[f"{model_name}_{metric_name}" for model_name in models.keys() for metric_name in scorings.keys()])
             # Metric generation for each model
             for model_name, model in models.items():
-                # Retrieve cv scores for our metrics of interest
-                scores = cross_validate(model, X_train, y_train, scoring=scorings, cv=cv, return_train_score=True, n_jobs=10)
-                # Save results of each fold
-                scores_df.loc[model_name +'_F1']=list(np.around(np.array(scores["test_f1"]),4)) 
-                scores_df.loc[model_name +'_PREC']=list(np.around(np.array(scores["test_precision"]),4))
-                scores_df.loc[model_name +'_REC']=list(np.around(np.array(scores["test_recall"]),4))
+                if model_name == 'DT':
+                    print(f"{group}-{method_names[j]}-{model_name}")
+                    # Retrieve cv scores for our metrics of interest
+                    scores = cross_validate(model, X_train, y_train, scoring=scorings, cv=cv, return_train_score=True, n_jobs=10)
+                    # Save results of each fold
+                    for metric_name in scorings.keys():
+                        scores_df.loc[model_name + f'_{metric_name}']=list(np.around(np.array(scores[f"test_{metric_name}"]),4)) 
             # 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