Update app.py

app.py

@@ -8,7 +8,7 @@ from fastapi.responses import RedirectResponse
 from pydantic import BaseModel, Field
 from sklearn.base import BaseEstimator, TransformerMixin
 
-# --- 1. CLASSE PERSONNALISÉE (CORRECTION DU HASHING) ---
+# --- 1. CLASSE PERSONNALISÉE ---
 class DFToHashedTokens(BaseEstimator, TransformerMixin):
     def __init__(self, columns=None):
         self.columns = columns
@@ -17,29 +17,21 @@ class DFToHashedTokens(BaseEstimator, TransformerMixin):
         return self
     
     def transform(self, X):
-        # On s'assure que X est un DataFrame
         if not isinstance(X, pd.DataFrame):
             X = pd.DataFrame(X)
-        
         X = X.copy()
         cols = getattr(self, 'columns', None)
-        
         if cols is not None:
-            # Pour chaque ligne, on crée une liste de chaînes de caractères
-            # C'est ce que "iterable over iterables of strings" signifie
             return X[cols].astype(str).values.tolist()
         return X.astype(str).values.tolist()
 
-# Injection pour que joblib retrouve la classe
 __main__.DFToHashedTokens = DFToHashedTokens
 
 # --- 2. CHARGEMENT DU MODÈLE ---
 try:
     model = joblib.load('fraud_model_hashing.pkl')
-    print("✅ Modèle chargé avec succès")
 except Exception as e:
     model = None
-    print(f"❌ Erreur critique : {e}")
 
 # --- 3. CONFIGURATION API ---
 app = FastAPI(title="Fraud Detection API")
@@ -67,13 +59,11 @@ def root():
 # --- 4. LOGIQUE DE PRÉPARATION ---
 def prepare_input(data: dict):
     df = pd.DataFrame([data])
-    
-    # Dates & Temps
     dt = pd.to_datetime(df["trans_date_trans_time"], errors='coerce')
     dob = pd.to_datetime(df["dob"], errors='coerce')
     
     if dt.isna().any() or dob.isna().any():
-        raise ValueError("Format de date invalide. Utilisez YYYY-MM-DD HH:MM:SS")
+        raise ValueError("Format de date invalide.")
 
     df["hour"] = dt.dt.hour
     df["day_of_week"] = dt.dt.dayofweek
@@ -81,41 +71,5 @@ def prepare_input(data: dict):
     df["month"] = dt.dt.month
     df["age"] = ((dt - dob).dt.days / 365.25).astype("float32")
     
-    # Distance
     lat1, lon1 = np.radians(df["lat"]), np.radians(df["long"])
-    lat2, lon2 = np.radians(df["merch_lat"]), np.radians(df["merch_long"])
-    d = np.sin((lat2-lat1)/2)**2 + np.cos(lat1)*np.cos(lat2)*np.sin((lon2-lon1)/2)**2
-    df["distance"] = (6371 * 2 * np.arcsin(np.sqrt(d))).astype("float32")
-
-    # Valeurs par défaut pour les agrégats
-    df["avg_amt"] = df["amt"]
-    df["std_amt"] = 0.0
-    df["nb_trans"] = 1.0
-
-    expected_cols = [
-        'amt', 'hour', 'day_of_week', 'day', 'month', 'age', 'lat', 'long', 
-        'city_pop', 'distance', 'avg_amt', 'std_amt', 'nb_trans', 
-        'category', 'gender', 'state', 'merchant', 'job'
-    ]
-    return df[expected_cols]
-
-# --- 5. ENDPOINT ---
-@app.post("/predict")
-def predict(data: Transaction):
-    if model is None:
-        return {"status": "error", "message": "Modèle non chargé."}
-    try:
-        X_processed = prepare_input(data.dict())
-        # Le modèle Pipeline appellera automatiquement DFToHashedTokens.transform()
-        prediction = model.predict(X_processed)
-        return {
-            "prediction": int(prediction[0]),
-            "label": "FRAUDE" if int(prediction[0]) == 1 else "LÉGITIME",
-            "status": "success"
-        }
-    except Exception as e:
-        return {"status": "error", "message": str(e)}
-
-if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    lat2, lon2 = np.radians