Found optimal hyperparamers and exported, more analysis to be done in different files

model_selection/hyperparam_tuning.py

 """
-    Selecting best models through cross validation and hyperparameter tunning 
-    for each method: 
+    Finding optimal hyperparameters through RandomSearchCV for each group (1. pre - 2. post) 
+    and method: 
         1. Original training dataset
         2. Original training dataset - Cost sensitive
         3. Oversampling
@@ -21,7 +21,6 @@ from sklearn.linear_model import  LogisticRegression
 from sklearn.tree import DecisionTreeClassifier
 from scipy.stats import randint, uniform
 from sklearn.model_selection import RandomizedSearchCV
-import os 
 # --------------------------------------------------------------------------------------------------------
 
 # Function to read training datasets
@@ -73,26 +72,22 @@ if __name__ == "__main__":
     # --------------------------------------------------------------------------------------------------------
     # 1. No class weight
     models_simple = {"DT" : DecisionTreeClassifier(), 
-            "RF" : RandomForestClassifier(), 
-            "Bagging" : BaggingClassifier(),
-            "AB" : AdaBoostClassifier(algorithm='SAMME'), 
-            "XGB": XGBClassifier(),
-            "LR" : LogisticRegression(max_iter=1000), 
-            "SVM" : SVC(probability=True, max_iter=1000), 
-            "MLP" : MLPClassifier(max_iter=500)
-            # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet')
+            # "RF" : RandomForestClassifier(), 
+            # "Bagging" : BaggingClassifier(),
+            # "AB" : AdaBoostClassifier(algorithm='SAMME'), 
+            # "XGB": XGBClassifier(),
+            # "LR" : LogisticRegression(max_iter=1000), 
+            # "SVM" : SVC(probability=True, max_iter=1000), 
+            # "MLP" : MLPClassifier(max_iter=500)
             }
     
     # 2. Class weight: cost-sensitive learning
     models_CS = {"DT" : DecisionTreeClassifier(class_weight='balanced'), 
-            "RF" : RandomForestClassifier(class_weight='balanced'), 
-            "Bagging" : BaggingClassifier(estimator= DecisionTreeClassifier(class_weight='balanced')),
-            "AB" : AdaBoostClassifier(estimator= DecisionTreeClassifier(class_weight='balanced'), algorithm='SAMME'),  
-            "LR" : LogisticRegression(max_iter=1000, class_weight='balanced'), 
-            "SVM" : SVC(probability=True, max_iter = 1000, class_weight='balanced'), 
-            # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet', class_weight='balanced'), 
-            # "XGB": XGBClassifier(), # <-
-            # "MLP" : MLPClassifier(max_iter=500) # <-
+            # "RF" : RandomForestClassifier(class_weight='balanced'), 
+            # "Bagging" : BaggingClassifier(estimator= DecisionTreeClassifier(class_weight='balanced')),
+            # "AB" : AdaBoostClassifier(estimator= DecisionTreeClassifier(class_weight='balanced'), algorithm='SAMME'),  
+            # "LR" : LogisticRegression(max_iter=1000, class_weight='balanced'), 
+            # "SVM" : SVC(probability=True, max_iter = 1000, class_weight='balanced'), 
             }
     # --------------------------------------------------------------------------------------------------------
 
@@ -121,7 +116,6 @@ if __name__ == "__main__":
         "MLP": {'activation': ['identity', 'logistic', 'tanh', 'relu'], 
                 'hidden_layer_sizes': randint(50, 150), 
                 'learning_rate': ['constant', 'invscaling', 'adaptive']}
-        # "ElNet": {'solver': ['lbfgs', 'sag', 'saga']},
     }
     # --------------------------------------------------------------------------------------------------------
 
@@ -148,25 +142,17 @@ if __name__ == "__main__":
             y = data_dic['y_train_' + method + group]
             # Use group of models with class weight if needed
             models = models_CS if j == 1 else models_simple 
-            # Save results: set of optimal hyperpameters -> mean precision and sd for those parameters across folds
-            hyperparam_df = pd.DataFrame(index=list(models.keys()), columns=['Best Parameters','Mean Precision', 'SD'])
+            # Save optimal hyperparameters for each of the models -> metrics will be computed in a different file
+            hyperparam_df = pd.DataFrame(index=list(models.keys()), columns=['Model Name', 'Best Parameters'])
             for model_name, model in models.items():
                 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=10, scoring='precision')
                 search.fit(X,y)
-                # Access the results
-                results = search.cv_results_
-                best_index = search.best_index_
-                # Get sd and mean across folds for best set of hyperpameters
+                # Keep optimal parameters
                 best_params = search.best_params_
-                mean_precision_best = results['mean_test_score'][best_index]
-                std_precision_best = results['std_test_score'][best_index]
-                # Storing these values
                 hyperparam_df.at[model_name, 'Best Parameters'] = best_params
-                hyperparam_df.at[model_name, 'Mean Precision'] = round(mean_precision_best, 4)
-                hyperparam_df.at[model_name, 'SD'] = round(std_precision_best, 4)
             # Store the DataFrame in the dictionary with a unique key for each sheet
             sheet_name = f"{group}_{method_names[j]}"
             sheets_dict[sheet_name] = hyperparam_df
@@ -178,5 +164,3 @@ if __name__ == "__main__":
 
     print("Successful tuning")
     # --------------------------------------------------------------------------------------------------------
\ No newline at end of file
-    
-