app.py

import streamlit as st
import pandas as pd
import requests
import numpy as np

# Set the title of the Streamlit app
st.title("Superkart Sales Prediction")

# Section for online prediction
st.subheader("Online Prediction")

# Collect user input for sales features
Product_Weight = st.number_input("Product_Weight", min_value=1.0, max_value=100.0, value=12.66)
Product_Sugar_Content = st.selectbox("Product_Sugar_Content", ["Low Sugar", "Regular", "No Sugar"], index=0) # Corrected available options
Product_Allocated_Area = st.number_input("Product_Allocated_Area", min_value=0.0, max_value=1.0, value=0.027)
Product_Type = st.selectbox("Product_Type", ["Frozen Foods", "Dairy", "Canned", "Baking Goods", "Health and Hygiene", "Household", "Meat", "Others", "Seafood", "Snack Foods", "Soft Drinks", "Starchy Foods", "Fruits and Vegetables", "Hard Drinks", "Breakfast"], index=0)
Product_MRP = st.number_input("Product_MRP", min_value=1.0, max_value=1000.0, value=117.08)
Store_Age = st.number_input("Store_Age", min_value=1, max_value=100, value=16)
Store_Type = st.selectbox("Store_Type", ["Supermarket Type1", "Supermarket Type2", "Food Mart", 'Departmental Store'], index=1)
Store_Location_City_Type = st.selectbox("Store_Location_City_Type",  ["Tier 1", "Tier 2", "Tier 3"], index=1)
Store_Size = st.selectbox("Store_Size", ["Small", "Medium", "High"], index=1)


# Convert user input into a DataFrame
input_data = pd.DataFrame([{
    'Product_Weight': Product_Weight,
    'Product_Sugar_Content': Product_Sugar_Content,
    'Product_Type': Product_Type,
    'Product_Allocated_Area': Product_Allocated_Area,
    'Product_MRP': Product_MRP,
    'Store_Age': Store_Age,
    'Store_Type': Store_Type,
    'Store_Location_City_Type': Store_Location_City_Type,
    'Store_Size': Store_Size
}])

# Make prediction when the "Predict" button is clicked
if st.button("Predict", type="primary"):
    # Correct the endpoint URL to match the Flask API
    # The Flask API is running on port 7860 inside the Docker container
    # and exposed externally.
    response = requests.post("https://rajoria007-backendsales.hf.space/v1/sales", json=input_data.to_dict(orient='records')[0])
    if response.status_code == 200:
        # The API now returns the actual sales prediction
        prediction = response.json()['predicted_sales']
        st.success(f"Predicted Sales: {prediction:.2f}") # Display prediction with 2 decimal places
    else:
        st.error(f"Error making prediction. Status Code: {response.status_code}")
        try:
            st.error(f"Error Details: {response.json()}")
        except:
            st.error(f"Error Details: {response.text}")