import numpy as np
from sklearn.model_selection import cross_validate

numeric_transformer= Pipeline(
                                [
                                    ('imputer_num', SimpleImputer(strategy='median')),
                                    ('scaler', StandardScaler())
                                ]
                             )
preprocessor=ColumnTransformer(
                                [
                                    ('numericals', numeric_transformer, numerical_features)
                                ], remainder='drop'
                              )
#Choix du modèle
pipeline_log= Pipeline(
                        [
                            ('preprocessing', preprocessor)
                        ]
                      )
X_train_pip=pipeline_log.fit_transform(X_train_ech, y_train_ech)
#X_train_pip=pipeline_log.fit_transform(X_train, y_train)
log_reg=LogisticRegression()

#Définition du scorer 
scorer_1 = make_scorer( metrics.roc_auc_score, needs_proba=True) #param need_proba à mettre à true pour que ça corresponde à 'roc_auc' car ces métricss utilisent les proba
scorer_2 = make_scorer( metrics.average_precision_score, needs_proba=True)
scoring = {'roc_auc':scorer_1, 'average_precision':scorer_2} 

cv_results = cross_validate(log_reg, X_train_pip, y_train_ech, cv=5,scoring=scoring)
res=sum(cv_results["fit_time"])
print(cv_results["fit_time"],res)

from sklearn.model_selection import RandomizedSearchCV
numeric_transformer= Pipeline(
                                [
                                    ('imputer_num', SimpleImputer(strategy='median')),
                                    ('scaler', StandardScaler())
                                ]
                             )
preprocessor=ColumnTransformer(
                                [
                                    ('numericals', numeric_transformer, numerical_features)
                                ], remainder='drop'
                              )
#Choix du modèle
pipeline_log= Pipeline(
                        [
                            ('preprocessing', preprocessor)
                        ]
                      )

#Définition des différents paramètres à tester 
params={'class_weight': ['balanced'],
        'C' : np.logspace(-4, 4, 20),
        'solver' : ['liblinear'],
        'max_iter' : [100], #1000
        'penalty' : ['l1', 'l2'] #l1
    }
#Définition du scorer 
scorer_1 = make_scorer( metrics.roc_auc_score, needs_proba=True) #param need_proba à mettre à true pour que ça corresponde à 'roc_auc' car ces métricss utilisent les proba
scorer_2 = make_scorer( metrics.average_precision_score, needs_proba=True)
scoring = {'roc_auc':scorer_1, 'average_precision':scorer_2} 

#Ajout du SMOTE au pipeline
X_train_pip=pipeline_log.fit_transform(X_train_ech, y_train_ech)
#X_train_pip=pipeline_log.fit_transform(X_train, y_train)
log_reg=LogisticRegression(max_iter=100,solver='liblinear',class_weight='balanced')

#Définition de gridsearch 
clf_log_w = RandomizedSearchCV(log_reg, distributions, cv=5 ,scoring=scoring, refit='average_precision', n_iter=10)
grid_result_log_w=clf_log_w.fit(X_train_pip, y_train_ech)
#grid_result_log_w=clf_log_w.fit(X_train_pip, y_train)
#clf_log_w.fit(X_train_pip, y_train)
score_w_log = grid_result_log_w.best_score_

print("Best: %f using %s" % (grid_result_log_w.best_score_, grid_result_log_w.best_params_), "\n")