Upload folder using huggingface_hub

app.py

@@ -23,11 +23,11 @@ def predict_product_sales_price():
     sample = {
         'Product_Weight': product_data['Product_Weight'],
         'Product_Sugar_Content': product_data['Product_Sugar_Content'],
-        'Product_Allocated_Area': product_data['Product_Allocated_Area'],
+        #'Product_Allocated_Area': product_data['Product_Allocated_Area'],
         'Product_Type': product_data['Product_Type'],
         'Product_MRP': product_data['Product_MRP'],
         'Store_Id': product_data['Store_Id'],
-        'Store_Establishment_Year': product_data['Store_Establishment_Year'],
+        'Store_Age': datetime.now().year - product_data['Store_Establishment_Year'],
         'Store_Size': product_data['Store_Size'],
         'Store_Location_City_Type': product_data['Store_Location_City_Type'],
         'Store_Type': product_data['Store_Type']
@@ -49,16 +49,22 @@ def predict_product_batch():
     file = request.files['file']
 
     # Read the file into a DataFrame
-    input_data = pd.read_csv(file)
+    data = pd.read_csv(file)
+
+    input_data = data.copy()
+    input_data['Store_Age'] = datetime.now().year - input_data['Store_Establishment_Year']
+    input_data = input_data.drop(['Product_Id','Store_Establishment_Year','Product_Allocated_Area'],axis=1)
+
+    
 
     # Make predictions for the batch data
     predictions = model.predict(input_data).tolist()
 
     # Add predictions to the DataFrame
-    input_data['Predicted_Product_Sales'] = predictions
+    data['Predicted_Product_Sales'] = predictions
 
     # Convert results to dictionary
-    result = input_data.to_dict(orient="records")
+    result = data.to_dict(orient="records")
 
     return jsonify(result)