Update app.py

app.py

@@ -6,6 +6,7 @@ import pandas as pd
 
 app = FastAPI(title="Food Surplus Predictor API")
 
+# Download model
 model_path = hf_hub_download(
     repo_id="BeeBasic/food-for-all",
     filename="best_model.joblib",
@@ -13,7 +14,7 @@ model_path = hf_hub_download(
 )
 model = joblib.load(model_path)
 
-# Define raw input schema
+# Define schema
 class CanteenInput(BaseModel):
     canteen_id: str
     canteen_name: str
@@ -31,26 +32,22 @@ def home():
 
 @app.post("/predict")
 def predict_surplus(request: RequestBody):
+    # Convert input to DataFrame
     df = pd.DataFrame([canteen.dict() for canteen in request.data])
 
-    # One-hot encode based on training columns
-    all_columns = [
-        'day','month','year','day_of_week',
-        'canteen_id_C002','canteen_id_C003','canteen_id_C004',
-        'canteen_id_C005','canteen_id_C006','canteen_id_C010',
-        'canteen_name_Anna University Mess','canteen_name_Buhari Hotel Canteen',
-        'canteen_name_Crescent College Cafeteria','canteen_name_IIT Madras Hostel Mess',
-        'canteen_name_Murugan Idli Shop','canteen_name_SRM Campus Canteen',
-        'canteen_name_Sangeetha Veg Restaurant','canteen_name_The Marina Café',
-        'canteen_name_VIT University Main Canteen'
-    ]
-
-    encoded = pd.get_dummies(df, columns=["canteen_id","canteen_name"])
-    for col in all_columns:
-        if col not in encoded.columns:
-            encoded[col] = 0
-    encoded = encoded[all_columns]
-
-    predictions = model.predict(encoded)
+    # One-hot encode categorical columns
+    df_encoded = pd.get_dummies(df, columns=["canteen_id", "canteen_name"])
+
+    # Align columns with model’s expected input
+    model_features = model.feature_names_ if hasattr(model, "feature_names_") else None
+    if model_features:
+        for col in model_features:
+            if col not in df_encoded.columns:
+                df_encoded[col] = 0
+        df_encoded = df_encoded[model_features]
+
+    # Run prediction
+    predictions = model.predict(df_encoded)
     df["predicted_surplus"] = predictions
+
     return df.to_dict(orient="records")