mkrish2025 commited on
Commit
9860176
·
verified ·
1 Parent(s): be03d0a

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. app.py +10 -33
app.py CHANGED
@@ -20,42 +20,19 @@ Store_Type = st.selectbox("Store Type", ["Supermarket Type2","Departmental Store
20
  Product_Weight = st.number_input("Product Weight", min_value=4.0, max_value=22.0)
21
  Product_Sugar_Content = st.selectbox("Product Sugar Content", ["Low Sugar","Regular","No Sugar"])
22
 
23
- # Start with numerical features dictionary
24
- features_dict = {
25
  'Product_Weight': Product_Weight,
26
  'Product_Allocated_Area': Product_Allocated_Area,
27
  'Product_MRP': Product_MRP,
28
- 'Store_Age': Store_Age
29
- }
30
-
31
- # Manual one-hot encoding for categorical features as per after-encoding columns order
32
- # Product_Sugar_Content
33
- for cat in ["Low Sugar", "No Sugar", "Regular"]:
34
- features_dict[f'Product_Sugar_Content_{cat}'] = int(Product_Sugar_Content == cat)
35
-
36
- # Store_Id
37
- for cat in ["OUT001","OUT002","OUT003","OUT004"]:
38
- features_dict[f'Store_Id_{cat}'] = int(Store_Id == cat)
39
-
40
- # Store_Size
41
- for cat in ["High", "Medium", "Small"]:
42
- features_dict[f'Store_Size_{cat}'] = int(Store_Size == cat)
43
-
44
- # Store_Location_City_Type
45
- for cat in ["Tier 1", "Tier 2", "Tier 3"]:
46
- features_dict[f'Store_Location_City_Type_{cat}'] = int(Store_Location_City_Type == cat)
47
-
48
- # Store_Type
49
- for cat in ["Departmental Store","Food Mart","Supermarket Type1","Supermarket Type2"]:
50
- features_dict[f'Store_Type_{cat}'] = int(Store_Type == cat)
51
-
52
- # Product_Group
53
- for cat in ["Non-Food/Household","Packaged/Processed Foods","Perishable Foods"]:
54
- features_dict[f'Product_Group_{cat}'] = int(Product_Group == cat)
55
-
56
- # Create DataFrame with matching columns
57
- input_data = pd.DataFrame([features_dict])
58
-
59
 
60
  # Make prediction when the "Predict" button is clicked
61
  if st.button("Predict"):
 
20
  Product_Weight = st.number_input("Product Weight", min_value=4.0, max_value=22.0)
21
  Product_Sugar_Content = st.selectbox("Product Sugar Content", ["Low Sugar","Regular","No Sugar"])
22
 
23
+ # Convert user input into a DataFrame
24
+ input_data = pd.DataFrame([{
25
  'Product_Weight': Product_Weight,
26
  'Product_Allocated_Area': Product_Allocated_Area,
27
  'Product_MRP': Product_MRP,
28
+ 'Store_Age': Store_Age,
29
+ 'Product_Group': Product_Group,
30
+ 'Product_Sugar_Content': Product_Sugar_Content,
31
+ 'Store_Id': Store_Id,
32
+ 'Store_Size': Store_Size,
33
+ 'Store_Location_City_Type': Store_Location_City_Type,
34
+ 'Store_Type': Store_Type
35
+ }])
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
 
37
  # Make prediction when the "Predict" button is clicked
38
  if st.button("Predict"):