from traning_zone.traitement_data.feature_engeneering.data_clearning import *
from traning_zone.traitement_data.feature_engeneering.feature_Engineering import *
from traning_zone.modele_zone.modeles import *
from traning_zone.modele_zone.modeles_gridsearch import *
from traning_zone.modele_zone.model import *
import time
import yaml

# Charger le contenu du fichier YAML
with open('variables.yml', 'r') as file:
    data = yaml.load(file, Loader=yaml.FullLoader)

hyper_classes = data['hyper_classes']

for hyper_classe in hyper_classes:
    nom = list(hyper_classe.keys())[0]
    classes = hyper_classe[nom][0]['classes']
    liste_classe = []
    for classe in classes :
        liste_classe.append(str(list(classe.values())[0]))

    start_time = time.time()
    data = clearning(*liste_classe)
    
    tv_xtrain, tv_xtest,  Ytrain, Ytest = engineering(data, nom)
    end_time = time.time()
    print(f"Temps d'exécution du pré-traitement est : {end_time - start_time} secondes")
    
    for name in modeles.keys():

         try :
               start_time = time.time()
               trainer(tv_xtrain, Ytrain, tv_xtest, Ytest, modeles[name], name, nom )
               #traning_gridsearch(tv_xtrain, Ytrain, tv_xtest, Ytest, modeles[name], name, nom, cv= 5)
               end_time = time.time()
               print(f"Temps d'exécution du d'apprentissage du modèle {name} est : {end_time - start_time} secondes")
         except :
               print(f"Erreur lors de l'apprentissage du modèle {name}")

    print(f"L'hyper classe {nom} est terminée")