2.2. completed model definition

model_selection/test_models.py

@@ -59,7 +59,7 @@ def get_tuned_models(group_id, method_id):
             "RF": RandomForestClassifier(**{'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 118, 'class_weight': 'balanced'}),
             "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'}),
+            "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'}),
             }
         # 1.3) Trained with oversampled training dataset
@@ -103,12 +103,12 @@ def get_tuned_models(group_id, method_id):
         # 2.2) Trained with original dataset and cost-sensitive learning
         elif method_id == 1:
             tuned_models = {
-            # "DT": DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'log2', 'criterion': 'entropy', 'class_weight': 'balanced'}),
-            # "RF": RandomForestClassifier(**{'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 118, 'class_weight': 'balanced'}),
-            # "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'}),
+            "DT": DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'sqrt', 'criterion': 'log_loss', 'class_weight': 'balanced'}),
+            "RF": RandomForestClassifier(**{'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 164, 'class_weight': 'balanced'}),
+            "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'})
             }
         # 2.3) Trained with oversampled training dataset
         elif method_id == 2: