Upload folder using huggingface_hub

SuperKart_model_v1_0.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6646c64c50003d7be9e910550c26c0a3da5c1007f1b3c5e453864646bbf19c
-size 259782
+oid sha256:a08df3146149137d37d160f03eefa1551eaf5d25846acfb8fe5642cab851026f
+size 260541

app.py

@@ -28,45 +28,29 @@ def predict_sales():
     try:
         # Get the JSON data from the request body
         data = request.get_json()
-
-        # Calculate derived features
-        current_year = datetime.now().year
-        store_age = current_year - data['store_establishment_year']
-        product_density = data['product_weight'] / (data['product_allocated_area'] + 1e-6)
-        price_per_weight = data['product_mrp'] / (data['product_weight'] + 1e-6)
-        product_size = 'Small' if data['product_weight'] <= 10 else ('Medium' if data['product_weight'] <= 15 else 'Large')
-        store_tier_size = f"{data['store_location_city_type']}_{data['store_size']}"
-
-        # Prepare input data
+        
+        # Prepare input data with only the features used in training
         input_data = pd.DataFrame([{
             'Product_Weight': data['product_weight'],
-            'Product_Sugar_Content': data['product_sugar_content'],
             'Product_Allocated_Area': data['product_allocated_area'],
-            'Product_Type': data['product_type'],
             'Product_MRP': data['product_mrp'],
-            'Store_Id': data['store_id'],
             'Store_Establishment_Year': data['store_establishment_year'],
+            '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_Age': store_age,
-            'Product_Density': product_density,
-            'Price_Per_Unit_Weight': price_per_weight,
-            'Product_Size_Category': product_size,
-            'Store_Tier_Size': store_tier_size
+            'Store_Type': data['store_type']
         }])
-
+        
         # Make prediction
         predicted_sales = model.predict(input_data)[0]
-
+        
         # Return the predicted sales
         return jsonify({
             'predicted_sales': round(float(predicted_sales), 2),
-            'store_age': store_age,
-            'product_density': round(product_density, 2),
-            'price_per_weight': round(price_per_weight, 2)
+            'features_used': list(input_data.columns)
         })
-
+        
     except Exception as e:
         return jsonify({'error': str(e)}), 400
 
@@ -81,37 +65,47 @@ def predict_sales_batch():
         # Check if file was uploaded
         if 'file' not in request.files:
             return jsonify({'error': 'No file uploaded'}), 400
-
+            
         file = request.files['file']
-
+        
         # Read CSV file
         input_data = pd.read_csv(file)
-
-        # Calculate derived features
-        current_year = datetime.now().year
-        input_data['Store_Age'] = current_year - input_data['Store_Establishment_Year']
-        input_data['Product_Density'] = input_data['Product_Weight'] / (input_data['Product_Allocated_Area'] + 1e-6)
-        input_data['Price_Per_Unit_Weight'] = input_data['Product_MRP'] / (input_data['Product_Weight'] + 1e-6)
-        input_data['Product_Size_Category'] = input_data['Product_Weight'].apply(
-            lambda x: 'Small' if x <= 10 else ('Medium' if x <= 15 else 'Large'))
-        input_data['Store_Tier_Size'] = input_data['Store_Location_City_Type'] + '_' + input_data['Store_Size']
-
+        
+        # Ensure we only keep the columns used in training
+        required_columns = [
+            'Product_Weight',
+            'Product_Allocated_Area',
+            'Product_MRP',
+            'Store_Establishment_Year',
+            'Product_Sugar_Content',
+            'Product_Type',
+            'Store_Size',
+            'Store_Location_City_Type',
+            'Store_Type'
+        ]
+        
+        # Verify all required columns are present
+        missing_cols = [col for col in required_columns if col not in input_data.columns]
+        if missing_cols:
+            return jsonify({'error': f'Missing required columns: {missing_cols}'}), 400
+        
         # Make predictions
-        predictions = model.predict(input_data)
-
+        predictions = model.predict(input_data[required_columns])
+        
         # Prepare results
         results = []
         for i, row in input_data.iterrows():
             results.append({
-                'product_id': row['Product_Id'],
-                'store_id': row['Store_Id'],
                 'predicted_sales': round(float(predictions[i]), 2),
                 'product_type': row['Product_Type'],
                 'store_type': row['Store_Type']
             })
-
-        return jsonify({'predictions': results})
-
+            
+        return jsonify({
+            'predictions': results,
+            'features_used': required_columns
+        })
+        
     except Exception as e:
         return jsonify({'error': str(e)}), 400