Skip to content

C
covid_analysis
Commit cbf63f20 authored by Joaquin Torres's avatar Joaquin Torres
Browse files
Options

Completed description of tuned models for PRE from excel files

parent a1b725f9
Show whitespace changes
Inline Side-by-side
Showing with 43 additions and 80 deletions
model_selection/test_models.py
View file @ cbf63f20
......@@ -43,109 +43,72 @@ def get_tuned_models(group_id, method_id):
# 1.1) Trained with original dataset
if method_id == 0:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
"DT" : DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'sqrt', 'criterion': 'gini'}),
"RF" : RandomForestClassifier(**{'criterion': 'gini', 'max_features': 'sqrt', 'n_estimators': 117}),
"Bagging" : BaggingClassifier(**{'max_features': 1.0, 'max_samples': 1.0, 'n_estimators': 23, 'warm_start': True}),
"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}),
"MLP" : MLPClassifier(**{'activation': 'identity', 'hidden_layer_sizes': 122, 'learning_rate': 'invscaling', 'max_iter':500})
}
# 1.2) Trained with original dataset and cost-sensitive learning
elif method_id == 1:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
"DT" : DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'log2', 'criterion': 'log_loss', '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}, estimator= DecisionTreeClassifier(class_weight='balanced'), algorithm='SAMME'),
"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
elif method_id == 2:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
"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}),
"MLP" : MLPClassifier(**{'activation': 'relu', 'hidden_layer_sizes': 116, 'learning_rate': 'invscaling', 'max_iter':500})
}
# 1. 4) Trained with undersampled training dataset
# 1.4) Trained with undersampled training dataset
elif method_id == 3:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
"DT" : DecisionTreeClassifier(**{'splitter': 'best', 'max_features': 'sqrt', 'criterion': 'gini'}),
"RF" : RandomForestClassifier(**{'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 104}),
"Bagging" : BaggingClassifier(**{'max_features': 1.0, 'max_samples': 1.0, 'n_estimators': 38, 'warm_start': True}),
"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}),
"MLP" : MLPClassifier(**{'activation': 'relu', 'hidden_layer_sizes': 131, 'learning_rate': 'constant', 'max_iter':500})
}
# 2. POST
else:
# 2.1) Trained with original dataset
if method_id == 0:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
"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}),
"MLP" : MLPClassifier(**{'activation': 'logistic', 'hidden_layer_sizes': 112, 'learning_rate': 'constant', 'max_iter':500})
}
# 2.2) Trained with original dataset and cost-sensitive learning
elif method_id == 1:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
...
# 2.3) Trained with oversampled training dataset
elif method_id == 2:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
...
# 2.4) Trained with undersampled training dataset
elif method_id == 3:
tuned_models = {
"DT" : DecisionTreeClassifier(),
"RF" : RandomForestClassifier(),
"Bagging" : BaggingClassifier(),
"AB" : AdaBoostClassifier(),
"XGB": XGBClassifier(),
"LR" : LogisticRegression(max_iter=1000),
"ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'),
"SVM" : SVC(probability=True),
"MLP" : MLPClassifier(max_iter=500)
}
...
return tuned_models
# --------------------------------------------------------------------------------------------------------
......@@ -201,8 +164,8 @@ if __name__ == "__main__":
'FN':FN_scorer,
'FP':FP_scorer,
'TP':TP_scorer
# AUROC and AUPRC (plot?)
}
# AUROC and AUPRC (plot?)
method_names = {
0: "ORIG",
1: "ORIG_CW",
......
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