Update app.py

app.py

@@ -1,4 +1,5 @@
 from fastapi import FastAPI
+from fastapi import HTTPException
 from pydantic import BaseModel
 import mlflow.pyfunc
 import pandas as pd
@@ -97,20 +98,20 @@ def load_model_on_startup():
         logger.exception("Impossible de charger le modèle au démarrage")
         model = None
 
-class RentalFeatures(BaseModel):
+class PredictionFeatures(BaseModel):
     model_key: str
     mileage: int
     engine_power: int
     fuel: str
     paint_color: str
     car_type: str
-    private_parking_available: int
-    has_gps: int
-    has_air_conditioning: int
-    automatic_car: int
-    has_getaround_connect: int
-    has_speed_regulator: int
-    winter_tires: int
+    private_parking_available: bool
+    has_gps: bool
+    has_air_conditioning: bool
+    automatic_car: bool
+    has_getaround_connect: bool
+    has_speed_regulator: bool
+    winter_tires: bool
 
 
 @app.get("/", tags=["Introduction Endpoints"])
@@ -150,10 +151,10 @@ async def predict(predictionFeatures: RentalFeatures):
     #     predictionFeatures.winter_tires or 0,
     # ]
     try:
-        car_caracteristic = pd.DataFrame(predictionFeatures.model_dump())
+        payload = predictionFeatures.model_dump()
+        car_caracteristic = pd.DataFrame([payload])
         #car_caracteristic = pd.DataFrame({"Car": pf})
-        # Log model from mlflow
-        logger.info(f"Input  : {car_caracteristic}")  
+        # Log model from mlflow 
         BOOL_COLS = [
             "private_parking_available",
             "has_gps",
@@ -166,18 +167,21 @@ async def predict(predictionFeatures: RentalFeatures):
         # Conversion explicite des colonnes booléennes
         for col in BOOL_COLS:
             car_caracteristic[col] = car_caracteristic[col].astype(bool)
-        car_caracteristic=[car_caracteristic]
-        logger.info(f"Input  : {car_caracteristic}")    
+
+        
+        logger.info("Payload reçu: %s", payload)
+        logger.info("dtypes:\n%s", car_characteristic.dtypes)
+
         # Prediction from previously loaded model as a PyFuncModel.
         prediction = model.predict(car_caracteristic)
         logger.info(f"Output  : {prediction}")  
         # Format response
         response = {
-            "prediction": prediction[0],
+            "prediction":  float(prediction[0]),
             "detail": "Prédiction du tarif journalier (nul si aucun modèle : model.pkl).",
         }
         return response
     except Exception as e:
         logger.exception("Erreur dans /predict")
-        raise Exception(status_code=500, detail=str(e))
+        raise HTTPException(status_code=500, detail=str(e))