app.py

import streamlit as st
import pandas as pd
import requests

st.title("🛒 SuperKart Sales Forecast App")

st.markdown("""
Use this interactive interface to forecast product-level sales for SuperKart stores based on store and product attributes.
""")

API_URL = "https://jkng77433-Backend.hf.space/v1/forecast/single"

st.header("Single Prediction")

col1, col2 = st.columns(2)
with col1:
    product_id = st.text_input("Product ID", "FD6114")
    product_type = st.selectbox("Product Type", ["Frozen Foods", "Dairy", "Canned", "Snack Foods"])
    sugar_content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
    product_weight = st.number_input("Product Weight", min_value=0.1, value=12.66)
    product_mrp = st.number_input("Product MRP", min_value=0.0, value=117.08)

with col2:
    store_id = st.text_input("Store ID", "OUT004")
    store_type = st.selectbox("Store Type", ["Supermarket Type1", "Supermarket Type2", "Departmental Store", "Food Mart"])
    store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
    store_location = st.selectbox("Store Location City Type", ["Tier 1", "Tier 2", "Tier 3"])
    est_year = st.number_input("Store Establishment Year", min_value=1980, max_value=2025, value=2009)
    allocated_area = st.number_input("Product Allocated Area", min_value=0.0, max_value=1.0, value=0.027, format="%.3f")

if st.button("Predict Sales"):
    payload = {
        "Product_Id": product_id,
        "Product_Type": product_type,
        "Product_Sugar_Content": sugar_content,
        "Product_Weight": product_weight,
        "Product_MRP": product_mrp,
        "Store_Id": store_id,
        "Store_Type": store_type,
        "Store_Size": store_size,
        "Store_Location_City_Type": store_location,
        "Store_Establishment_Year": est_year,
        "Product_Allocated_Area": allocated_area
    }
    response = requests.post(API_URL, json=payload)
    if response.status_code == 200:
        result = response.json()
        st.success(f"Predicted Sales: **${result['Predicted_Product_Store_Sales_Total']:.2f}**")
    else:
        st.error("Prediction failed — check input values or backend availability.")