ready to retune

model_selection/hyperparam_tuning.py

@@ -79,7 +79,7 @@ if __name__ == "__main__":
             "AB" : AdaBoostClassifier(algorithm='SAMME'), 
             "XGB": XGBClassifier(),
             "LR" : LogisticRegression(max_iter=1000), 
-            "SVM" : SVC(max_iter=1000), 
+            "SVM" : SVC(probability=True, max_iter=1000), 
             "MLP" : MLPClassifier(max_iter=500)
             # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet')
             }
@@ -90,7 +90,7 @@ if __name__ == "__main__":
             "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(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) # <-
@@ -142,18 +142,17 @@ if __name__ == "__main__":
     # --------------------------------------------------------------------------------------------------------
     # Store each df as a sheet in an excel file
     sheets_dict = {}
-    for i, group in enumerate(['post']):
-        for j, method in enumerate(['']): #['', '', 'over_', 'under_']
+    for i, group in enumerate(['pre', '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 == 1 else models_simple 
-            models = models_CS
+            models = models_CS if j == 1 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[1]}-{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[1]}"
+            sheet_name = f"{group}_{method_names[j]}"
             sheets_dict[sheet_name] = hyperparam_df
 
     # Write results to Excel file
-    with pd.ExcelWriter('./output/hyperparam_post_ORIG_CS.xlsx') as writer:
+    with pd.ExcelWriter('./output/hyperparamers_pre_and_post') as writer:
         for sheet_name, data in sheets_dict.items():
             data.to_excel(writer, sheet_name=sheet_name)
 

model_selection/test_models.py

@@ -49,7 +49,7 @@ def get_tuned_models(group_id, method_id):
             "AB" : AdaBoostClassifier(**{'learning_rate': 1.9189147333140566, 'n_estimators': 131, 'algorithm': 'SAMME'}), 
             "XGB": XGBClassifier(**{'learning_rate': 0.22870029177880222, 'max_depth': 8, 'n_estimators': 909}),
             "LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': None, 'max_iter': 1000}), 
-            #"SVM" : SVC(**{'C': 0.9872682949695772, 'kernel': 'linear', 'max_iter':1000}), 
+            #"SVM" : SVC(**{'C': 0.9872682949695772, 'kernel': 'linear', 'max_iter':1000, 'probability': True}), 
             "MLP" : MLPClassifier(**{'activation': 'identity', 'hidden_layer_sizes': 122, 'learning_rate': 'invscaling', 'max_iter':500})
             }
         # 1.2) Trained with original dataset and cost-sensitive learning
@@ -60,7 +60,7 @@ def get_tuned_models(group_id, method_id):
             "Bagging": BaggingClassifier(**{'max_features': 1.0, 'max_samples': 1.0, 'n_estimators': 15, 'warm_start': False, 'estimator': DecisionTreeClassifier(class_weight='balanced')}),
             "AB": AdaBoostClassifier(**{'learning_rate': 0.8159074545140872, 'n_estimators': 121, 'algorithm': 'SAMME', 'estimator': DecisionTreeClassifier(class_weight='balanced')}),
             "LR": LogisticRegression(**{'solver': 'lbfgs', 'penalty': None, 'max_iter': 1000, 'class_weight': 'balanced'}),
-            #"SVM": SVC(**{'C': 1.5550524351360953, 'kernel': 'linear', 'max_iter': 1000, 'class_weight': 'balanced'}),
+            #"SVM": SVC(**{'C': 1.5550524351360953, 'kernel': 'linear', 'max_iter': 1000, 'class_weight': 'balanced', 'probability': True}),
             }
         # 1.3) Trained with oversampled training dataset
         elif method_id == 2:
@@ -71,7 +71,7 @@ def get_tuned_models(group_id, method_id):
             "AB" : AdaBoostClassifier(**{'learning_rate': 1.6590924545876917, 'n_estimators': 141, 'algorithm': 'SAMME'}), 
             "XGB": XGBClassifier(**{'learning_rate': 0.26946295284728783, 'max_depth': 7, 'n_estimators': 893}),
             "LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': 'l2', 'max_iter': 1000}), 
-            #"SVM" : SVC(**{'C': 1.676419306008229, 'kernel': 'poly', 'max_iter':1000}), 
+            #"SVM" : SVC(**{'C': 1.676419306008229, 'kernel': 'poly', 'max_iter':1000, 'probability': True}), 
             "MLP" : MLPClassifier(**{'activation': 'relu', 'hidden_layer_sizes': 116, 'learning_rate': 'invscaling', 'max_iter':500})
             }
         # 1.4) Trained with undersampled training dataset
@@ -83,7 +83,7 @@ def get_tuned_models(group_id, method_id):
             "AB" : AdaBoostClassifier(**{'learning_rate': 1.6996764264041269, 'n_estimators': 93, 'algorithm': 'SAMME'}), 
             "XGB": XGBClassifier(**{'learning_rate': 0.26480707899668926, 'max_depth': 7, 'n_estimators': 959}),
             "LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': None, 'max_iter': 1000}), 
-            #"SVM" : SVC(**{'C': 1.1996501173654208, 'kernel': 'poly', 'max_iter':1000}), 
+            #"SVM" : SVC(**{'C': 1.1996501173654208, 'kernel': 'poly', 'max_iter':1000, 'probability': True}), 
             "MLP" : MLPClassifier(**{'activation': 'relu', 'hidden_layer_sizes': 131, 'learning_rate': 'constant', 'max_iter':500})
             }
     # 2. POST
@@ -97,7 +97,7 @@ def get_tuned_models(group_id, method_id):
             "AB" : AdaBoostClassifier(**{'learning_rate': 1.7806904141367559, 'n_estimators': 66, 'algorithm': 'SAMME'}), 
             "XGB": XGBClassifier(**{'learning_rate': 0.21889089898592098, 'max_depth': 6, 'n_estimators': 856}),
             "LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': None, 'max_iter': 1000}), 
-            #"SVM" : SVC(**{'C': 1.9890638540240584, 'kernel': 'linear', 'max_iter':1000}), 
+            #"SVM" : SVC(**{'C': 1.9890638540240584, 'kernel': 'linear', 'max_iter':1000, 'probability': True}), 
             "MLP" : MLPClassifier(**{'activation': 'logistic', 'hidden_layer_sizes': 112, 'learning_rate': 'constant', 'max_iter':500})
             }
         # 2.2) Trained with original dataset and cost-sensitive learning
@@ -108,7 +108,7 @@ def get_tuned_models(group_id, method_id):
             "Bagging": BaggingClassifier(**{'max_features': 1.0, 'max_samples': 0.8, 'n_estimators': 11, 'warm_start': True, 'estimator': DecisionTreeClassifier(class_weight='balanced')}),
             "AB": AdaBoostClassifier(**{'learning_rate': 1.7102248217141944, 'n_estimators': 108, 'algorithm': 'SAMME', 'estimator': DecisionTreeClassifier(class_weight='balanced')}),
             "LR": LogisticRegression(**{'solver': 'lbfgs', 'penalty': None, 'max_iter': 1000, 'class_weight': 'balanced'}),
-            #"SVM": SVC(**{'C': 1.1313840454519628, 'kernel': 'sigmoid', 'max_iter': 1000, 'class_weight': 'balanced'})
+            #"SVM": SVC(**{'C': 1.1313840454519628, 'kernel': 'sigmoid', 'max_iter': 1000, 'class_weight': 'balanced', 'probability': True})
             }
         # 2.3) Trained with oversampled training dataset
         elif method_id == 2:
@@ -119,7 +119,7 @@ def get_tuned_models(group_id, method_id):
             # "AB" : AdaBoostClassifier(**{'learning_rate': 1.6590924545876917, 'n_estimators': 141, 'algorithm': 'SAMME'}), 
             # "XGB": XGBClassifier(**{'learning_rate': 0.26946295284728783, 'max_depth': 7, 'n_estimators': 893}),
             # "LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': 'l2', 'max_iter': 1000}), 
-            # "SVM" : SVC(**{'C': 1.676419306008229, 'kernel': 'poly', 'max_iter':1000}), 
+            # "SVM" : SVC(**{'C': 1.676419306008229, 'kernel': 'poly', 'max_iter':1000, 'probability': True}), 
             # "MLP" : MLPClassifier(**{'activation': 'relu', 'hidden_layer_sizes': 116, 'learning_rate': 'invscaling', 'max_iter':500})
             }
         # 2.4) Trained with undersampled training dataset
@@ -131,7 +131,7 @@ def get_tuned_models(group_id, method_id):
             "AB" : AdaBoostClassifier(**{'learning_rate': 1.836659462701278, 'n_estimators': 138, 'algorithm': 'SAMME'}), 
             "XGB": XGBClassifier(**{'learning_rate': 0.2517946893282251, 'max_depth': 4, 'n_estimators': 646}),
             "LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': 'l2', 'max_iter': 1000}), 
-            #"SVM" : SVC(**{'C': 1.8414678085000697, 'kernel': 'linear', 'max_iter':1000}), 
+            #"SVM" : SVC(**{'C': 1.8414678085000697, 'kernel': 'linear', 'max_iter':1000, 'probability': True}), 
             "MLP" : MLPClassifier(**{'activation': 'relu', 'hidden_layer_sizes': 76, 'learning_rate': 'constant', 'max_iter':500})
             }
     return tuned_models