tuning post

model_selection/hyperparam_tuning.py

@@ -142,18 +142,17 @@ if __name__ == "__main__":
     # --------------------------------------------------------------------------------------------------------
     # Store each df as a sheet in an excel file
     sheets_dict = {}
-    for i, group in enumerate(['pre']):
-        for j, method in enumerate(['under_']): #['', '', 'over_', 'under_']
+    for i, group in enumerate(['post']):
+        for j, method in enumerate(['', '', 'over_', 'under_']): 
             # Get dataset based on group and method
             X = data_dic['X_train_' + method + group]
             y = data_dic['y_train_' + method + group]
             # Use group of models with class weight if needed
-            # models = models_CS if j == 2 else models_simple 
-            models = models_simple
+            models = models_CS if j == 2 else models_simple 
             # 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(f"{group}-{method_names[3]}-{model_name}")
+                print(f"{group}-{method_names[j]}-{model_name}")
                 # Find optimal hyperparams for curr model
                 params = hyperparameters[model_name]
                 search = RandomizedSearchCV(model, param_distributions=params, cv=cv, n_jobs=8, scoring='precision')
@@ -162,11 +161,11 @@ if __name__ == "__main__":
                 hyperparam_df.at[model_name,'Score']=round(search.best_score_,4)
             
             # Store the DataFrame in the dictionary with a unique key for each sheet
-            sheet_name = f"{group}_{method_names[3]}"
+            sheet_name = f"{group}_{method_names[j]}"
             sheets_dict[sheet_name] = hyperparam_df
 
     # Write results to Excel file
-    with pd.ExcelWriter('./output/hyperparam_pre_UNDER.xlsx') as writer:
+    with pd.ExcelWriter('./output/hyperparam_post.xlsx') as writer:
         for sheet_name, data in sheets_dict.items():
             data.to_excel(writer, sheet_name=sheet_name)