Upload folder using huggingface_hub

app.py

@@ -10,110 +10,81 @@ superkart_api = Flask("SuperKart Sales Predictor")
 # Load the trained machine learning model
 model = joblib.load("superkart_sales_prediction_model_v1_0.joblib")
 
-# -------------------------------------------------------------------
-# 🧩 Helper: Ensure All Required Columns Are Present
-# -------------------------------------------------------------------
-def preprocess_input(df: pd.DataFrame) -> pd.DataFrame:
-    """
-    Ensures that all features expected by the model exist.
-    Automatically computes missing engineered columns if possible.
-    """
-    df = df.copy()
-
-    # ✅ If Store_Age is missing but Store_Establishment_Year exists
-    if "Store_Age" not in df.columns and "Store_Establishment_Year" in df.columns:
-        current_year = datetime.datetime.now().year
-        df["Store_Age"] = current_year - df["Store_Establishment_Year"]
-
-    # ✅ Fill any completely missing numeric columns with 0 (safety net)
-    for col in ["Product_Weight", "Product_Allocated_Area", "Product_MRP", "Store_Age"]:
-        if col not in df.columns:
-            df[col] = 0.0
-
-    # ✅ For categorical fields missing in CSV, fill with a default
-    cat_defaults = {
-        "Product_Sugar_Content": "Regular",
-        "Product_Type": "Others",
-        "Store_Size": "Medium",
-        "Store_Location_City_Type": "Tier 2",
-        "Store_Type": "Supermarket Type1",
-        "Store_Id": "ST001"
-    }
-    for col, val in cat_defaults.items():
-        if col not in df.columns:
-            df[col] = val
-
-    return df
 
-# -------------------------------------------------------------------
-# 🔹 Home Route
-# -------------------------------------------------------------------
+# Define a route for the home page (GET request)
 @superkart_api.get('/')
 def home():
+    """
+    This function handles GET requests to the root URL ('/') of the API.
+    It returns a simple welcome message.
+    """
     return "Welcome to the SuperKart Sales Prediction API!"
 
-# -------------------------------------------------------------------
-# 🔹 Single Prediction
-# -------------------------------------------------------------------
+
+# Define an endpoint for single property prediction (POST request)
 @superkart_api.post('/v1/sales')
 def predict_sales():
+    """
+    POST endpoint to predict sales for a single product-store combination.
+    Expects JSON input with product and store attributes.
+    """
     try:
+        # Get the JSON data from the request body
         data = request.get_json()
-
+        print("Raw incoming data:", data)
+
+        # Validate expected fields
+        required_fields = [
+            "Product_Weight",
+            "Product_Allocated_Area",
+            "Product_MRP",
+            "Store_Age",
+            "Product_Sugar_Content",
+            "Product_Type",
+            "Store_Size",
+            "Store_Location_City_Type",
+            "Store_Type",
+            "Store_Id"
+        ]
+        missing_fields = [f for f in required_fields if f not in data]
+        if missing_fields:
+            return jsonify({
+                "error": f"Missing required fields: {missing_fields}"
+            }), 400
+
+        # Extract relevant features from the JSON data
         sample = {
-            "Product_Weight": data.get("Product_Weight"),
-            "Product_Allocated_Area": data.get("Product_Allocated_Area"),
-            "Product_MRP": data.get("Product_MRP"),
-            "Store_Age": data.get("Store_Age"),
-            "Product_Sugar_Content": data.get("Product_Sugar_Content"),
-            "Product_Type": data.get("Product_Type"),
-            "Store_Size": data.get("Store_Size"),
-            "Store_Location_City_Type": data.get("Store_Location_City_Type"),
-            "Store_Type": data.get("Store_Type"),
-            "Store_Id": data.get("Store_Id")
+            "Product_Weight": data["Product_Weight"],
+            "Product_Allocated_Area": data["Product_Allocated_Area"],
+            "Product_MRP": data["Product_MRP"],
+            "Store_Age": data["Store_Age"],
+            "Product_Sugar_Content": data["Product_Sugar_Content"],
+            "Product_Type": data["Product_Type"],
+            "Store_Size": data["Store_Size"],
+            "Store_Location_City_Type": data["Store_Location_City_Type"],
+            "Store_Type": data["Store_Type"],
+            "Store_Id": data["Store_Id"]
         }
 
-        input_df = preprocess_input(pd.DataFrame([sample]))
+        # Prepare data for prediction
+        sample = {f: data[f] for f in required_fields}
+        # Convert the extracted data into a Pandas DataFrame
+        input_df = pd.DataFrame([sample])
+
+        # Make prediction
         prediction = model.predict(input_df)[0]
+
+        # Convert predicted_price to Python float
         predicted_sales = round(float(prediction), 2)
 
+        # Return the predicted sales
         return jsonify({"Predicted_Sales_Total": predicted_sales})
 
     except Exception as e:
+        # Catch all errors and return them as JSON
         return jsonify({"error": str(e)}), 500
 
-# -------------------------------------------------------------------
-# 🔹 Batch Prediction
-# -------------------------------------------------------------------
-@superkart_api.post('/v1/salesbatch')
-def predict_sales_batch():
-    """
-    Handles batch prediction from a CSV file.
-    Automatically computes Store_Age and validates columns.
-    """
-    try:
-        file = request.files['file']
-        batch_data = pd.read_csv(file)
-
-        # 🧩 Preprocess to ensure consistency
-        batch_data = preprocess_input(batch_data)
-
-        # Predict
-        predictions = model.predict(batch_data)
-        batch_data["Predicted_Sales_Total"] = np.round(predictions, 2)
-
-        # Return results mapped to Product_Id or index
-        id_col = "Product_Id" if "Product_Id" in batch_data.columns else batch_data.index.astype(str)
-        result_dict = dict(zip(id_col, batch_data["Predicted_Sales_Total"]))
-
-        # Use jsonify to ensure valid JSON serialization
-        return jsonify(result_dict)
-
-    except Exception as e:
-        return jsonify({"error": str(e)}), 500
 
-# -------------------------------------------------------------------
-# 🔹 Run (Local)
-# -------------------------------------------------------------------
+# Run the Flask application in debug mode if this script is executed directly
 if __name__ == '__main__':
     superkart_api.run(debug=True)