Delete train_and_save_model.py

train_and_save_model.py

@@ -1,115 +0,0 @@
-import pandas as pd
-import numpy as np
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import StandardScaler, LabelEncoder
-from sklearn.ensemble import RandomForestClassifier
-import joblib
-import json
-
-print("Chargement et préparation des données...")
-
-# Chargement des données
-df = pd.read_csv('/mnt/c/Users/david/Desktop/AIA 2025/BLOC_3_AUTOMATIC_FRAUD_DETECTION/fraudTest.csv', index_col=0)
-
-# Feature Engineering
-data = df.copy()
-data['trans_date_trans_time'] = pd.to_datetime(data['trans_date_trans_time'])
-data['hour'] = data['trans_date_trans_time'].dt.hour
-data['day_of_week'] = data['trans_date_trans_time'].dt.dayofweek
-data['day'] = data['trans_date_trans_time'].dt.day
-data['month'] = data['trans_date_trans_time'].dt.month
-
-data['dob'] = pd.to_datetime(data['dob'])
-data['age'] = (data['trans_date_trans_time'] - data['dob']).dt.days // 365
-
-data['distance'] = np.sqrt(
-    (data['lat'] - data['merch_lat'])**2 + 
-    (data['long'] - data['merch_long'])**2
-) * 111
-
-# Encodage
-le_category = LabelEncoder()
-le_gender = LabelEncoder()
-le_state = LabelEncoder()
-
-data['category_encoded'] = le_category.fit_transform(data['category'])
-data['gender_encoded'] = le_gender.fit_transform(data['gender'])
-data['state_encoded'] = le_state.fit_transform(data['state'])
-
-# Statistiques par client
-client_stats = data.groupby('cc_num').agg({
-    'amt': ['mean', 'std', 'count'],
-    'is_fraud': 'sum'
-}).reset_index()
-client_stats.columns = ['cc_num', 'avg_amt', 'std_amt', 'nb_trans', 'nb_fraud']
-client_stats['std_amt'] = client_stats['std_amt'].fillna(0)
-data = data.merge(client_stats, on='cc_num', how='left')
-
-# Préparation des features
-features = [
-    'amt', 'hour', 'day_of_week', 'day', 'month', 'age',
-    'category_encoded', 'gender_encoded', 'state_encoded',
-    'lat', 'long', 'city_pop', 'distance',
-    'avg_amt', 'std_amt', 'nb_trans'
-]
-
-X = data[features].fillna(0)
-y = data['is_fraud']
-
-# Split et entraînement
-X_train, X_test, y_train, y_test = train_test_split(
-    X, y, test_size=0.3, random_state=42, stratify=y
-)
-
-print("Entraînement du Random Forest...")
-model = RandomForestClassifier(
-    n_estimators=100, 
-    max_depth=10, 
-    random_state=42, 
-    n_jobs=-1
-)
-model.fit(X_train, y_train)
-
-# Évaluation
-from sklearn.metrics import roc_auc_score, classification_report
-y_pred_proba = model.predict_proba(X_test)[:, 1]
-auc = roc_auc_score(y_test, y_pred_proba)
-print(f"\nAUC-ROC: {auc:.4f}")
-
-# Sauvegarde du modèle et des encodeurs
-print("\nSauvegarde du modèle et des encodeurs...")
-joblib.dump(model, 'fraud_model.pkl')
-joblib.dump(le_category, 'le_category.pkl')
-joblib.dump(le_gender, 'le_gender.pkl')
-joblib.dump(le_state, 'le_state.pkl')
-
-# Sauvegarde des mappings pour l'API
-category_mapping = dict(zip(le_category.classes_, le_category.transform(le_category.classes_)))
-gender_mapping = dict(zip(le_gender.classes_, le_gender.transform(le_gender.classes_)))
-state_mapping = dict(zip(le_state.classes_, le_state.transform(le_state.classes_)))
-
-mappings = {
-    'categories': category_mapping,
-    'genders': gender_mapping,
-    'states': state_mapping,
-    'features': features
-}
-
-def convert(o):
-    if isinstance(o, np.integer):
-        return int(o)
-    elif isinstance(o, np.floating):
-        return float(o)
-    elif isinstance(o, np.ndarray):
-        return o.tolist()
-    else:
-        return o
-
-with open('mappings.json', 'w') as f:
-    json.dump(mappings, f, indent=2, default=convert)
-
-print("\n✅ Modèle sauvegardé avec succès!")
-print("Fichiers créés:")
-print("  - fraud_model.pkl")
-print("  - le_category.pkl, le_gender.pkl, le_state.pkl")
-print("  - mappings.json")