Skip to content

C
covid_analysis
Commit cd7aff2a authored by Joaquin Torres's avatar Joaquin Torres
Browse files
Options

completed model definition after tuning manually

parent d57b78fe
Hide whitespace changes
Inline Side-by-side
Showing with 29 additions and 29 deletions
model_selection/test_models.py
View file @ cd7aff2a
......@@ -91,48 +91,48 @@ def get_tuned_models(group_id, method_id):
# 2.1) Trained with original dataset
if method_id == 0:
tuned_models = {
"DT" : DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'log2', 'criterion': 'gini'}),
"RF" : RandomForestClassifier(**{'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 213}),
"Bagging" : BaggingClassifier(**{'max_features': 1.0, 'max_samples': 0.8, 'n_estimators': 32, 'warm_start': True}),
"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, 'probability': True}),
"MLP" : MLPClassifier(**{'activation': 'logistic', 'hidden_layer_sizes': 112, 'learning_rate': 'constant', 'max_iter':500})
"DT" : DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'sqrt', 'criterion': 'log_loss'}),
"RF" : RandomForestClassifier(**{'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 120}),
"Bagging" : BaggingClassifier(**{'max_features': 1.0, 'max_samples': 0.8, 'n_estimators': 38, 'warm_start': True}),
"AB" : AdaBoostClassifier(**{'learning_rate': 1.9069394544838472, 'n_estimators': 121, 'algorithm': 'SAMME'}),
"XGB": XGBClassifier(**{'learning_rate': 0.24787889985627387, 'max_depth': 4, 'n_estimators': 956}),
"LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': 'l2'}),
"SVM" : SVC(**{'C': 1.7965537393241109, 'kernel': 'linear', 'max_iter':1000, 'probability': True}),
"MLP" : MLPClassifier(**{'activation': 'relu', 'hidden_layer_sizes': 147, 'learning_rate': 'invscaling', 'max_iter':500})
}
# 2.2) Trained with original dataset and cost-sensitive learning
elif method_id == 1:
tuned_models = {
"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', 'probability': True})
"DT": DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'sqrt', 'criterion': 'gini', 'class_weight': 'balanced'}),
"RF": RandomForestClassifier(**{'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 138, 'class_weight': 'balanced'}),
"Bagging": BaggingClassifier(**{'max_features': 1.0, 'max_samples': 1.0, 'n_estimators': 66, 'warm_start': True, 'estimator': DecisionTreeClassifier(class_weight='balanced')}),
"AB": AdaBoostClassifier(**{'learning_rate': 1.92541653518023, 'n_estimators': 114, 'algorithm': 'SAMME', 'estimator': DecisionTreeClassifier(class_weight='balanced')}),
"LR": LogisticRegression(**{'solver': 'lbfgs', 'penalty': 'l2', 'max_iter': 1000, 'class_weight': 'balanced'}),
"SVM": SVC(**{'C': 0.8395104850983046, 'kernel': 'linear', 'max_iter': 1000, 'class_weight': 'balanced', 'probability': True})
}
# 2.3) Trained with oversampled training dataset
elif method_id == 2:
tuned_models = {
# "DT" : DecisionTreeClassifier(**{'splitter': 'random', 'max_features': 'sqrt', 'criterion': 'log_loss'}),
# "RF" : RandomForestClassifier(**{'criterion': 'gini', 'max_features': 'sqrt', 'n_estimators': 135}),
# "Bagging" : BaggingClassifier(**{'max_features': 1.0, 'max_samples': 1.0, 'n_estimators': 26, 'warm_start': True}),
# "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, 'probability': True}),
# "MLP" : MLPClassifier(**{'activation': 'relu', 'hidden_layer_sizes': 116, 'learning_rate': 'invscaling', 'max_iter':500})
"DT" : DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'log2', 'criterion': 'entropy'}),
"RF" : RandomForestClassifier(**{'criterion': 'gini', 'max_features': 'sqrt', 'n_estimators': 118}),
"Bagging" : BaggingClassifier(**{'max_features': 1.0, 'max_samples': 1.0, 'n_estimators': 56, 'warm_start': False}),
"AB" : AdaBoostClassifier(**{'learning_rate': 1.5933610622176648, 'n_estimators': 114, 'algorithm': 'SAMME'}),
"XGB": XGBClassifier(**{'learning_rate': 0.059934879882855396, 'max_depth': 9, 'n_estimators': 660}),
"LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': 'l2', 'max_iter': 1000}),
"SVM" : SVC(**{'C': 1.2237930722499044, 'kernel': 'poly', 'max_iter':1000, 'probability': True}),
"MLP" : MLPClassifier(**{'activation': 'identity', 'hidden_layer_sizes': 134, 'learning_rate': 'invscaling', 'max_iter':500})
}
# 2.4) Trained with undersampled training dataset
elif method_id == 3:
tuned_models = {
"DT" : DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'sqrt', 'criterion': 'entropy'}),
"RF" : RandomForestClassifier(**{'criterion': 'gini', 'max_features': 'sqrt', 'n_estimators': 224}),
"Bagging" : BaggingClassifier(**{'max_features': 1.0, 'max_samples': 0.8, 'n_estimators': 13, 'warm_start': True}),
"AB" : AdaBoostClassifier(**{'learning_rate': 1.836659462701278, 'n_estimators': 138, 'algorithm': 'SAMME'}),
"XGB": XGBClassifier(**{'learning_rate': 0.2517946893282251, 'max_depth': 4, 'n_estimators': 646}),
"DT" : DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'log2', 'criterion': 'log_loss'}),
"RF" : RandomForestClassifier(**{'criterion': 'gini', 'max_features': 'sqrt', 'n_estimators': 151}),
"Bagging" : BaggingClassifier(**{'max_features': 1.0, 'max_samples': 1.0, 'n_estimators': 20, 'warm_start': False}),
"AB" : AdaBoostClassifier(**{'learning_rate': 1.6523810056317618, 'n_estimators': 89, 'algorithm': 'SAMME'}),
"XGB": XGBClassifier(**{'learning_rate': 0.18430397856234193, 'max_depth': 4, 'n_estimators': 956}),
"LR" : LogisticRegression(**{'solver': 'lbfgs', 'penalty': 'l2', '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})
"SVM" : SVC(**{'C': 1.1807459108651588, 'kernel': 'linear', 'max_iter':1000, 'probability': True}),
"MLP" : MLPClassifier(**{'activation': 'identity', 'hidden_layer_sizes': 55, 'learning_rate': 'constant', 'max_iter':500})
}
return tuned_models
# --------------------------------------------------------------------------------------------------------
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment