app.py

import streamlit as st
import pandas as pd
import requests

st.set_page_config(page_title="SuperKart Forecaster", layout="wide")
st.title("🚀 SuperKart Quarterly Sales Forecaster")

st.markdown("""
Use this interactive app to get **real‐time sales forecasts** for products or entire store uploads.
Powered by a Dockerized Flask API on Hugging Face Spaces.
""")

# === Single Product Forecast ===
st.header("🔍 Single Product Forecast")

weight = st.number_input("Product Weight (kg)", min_value=0.1, value=12.65, step=0.1)
sugar = st.selectbox("Sugar Content", ["Low Sugar", "Regular", "No Sugar", "Unknown"])
area = st.number_input("Allocated Display Area (fraction)", min_value=0.001, max_value=1.0, value=0.0688, step=0.001)
p_type = st.text_input("Product Type", value="Fruits and Vegetables")
mrp = st.number_input("Product MRP (₹)", min_value=0.0, value=147.03, step=1.0)
est_year = st.number_input("Store Establishment Year", min_value=1980, max_value=2025, value=2009, step=1)
store_size = st.selectbox("Store Size", ["Low", "Medium", "High"])
city_tier = st.selectbox("City Tier", ["Tier 1", "Tier 2", "Tier 3"])
store_type = st.selectbox("Store Type", ["Departmental Store", "Supermarket Type 1", "Supermarket Type 2", "Food Mart"])

if st.button("Predict Sales"):
    payload = {
        "Product_Weight": weight,
        "Product_Sugar_Content": sugar,
        "Product_Allocated_Area": area,
        "Product_Type": p_type,
        "Product_MRP": mrp,
        "Store_Establishment_Year": est_year,
        "Store_Size": store_size,
        "Store_Location_City_Type": city_tier,
        "Store_Type": store_type
    }

    API_URL = "https://ansh91--superkartpredictionbackend.hf.space/v1/forecast"
    res = requests.post(API_URL, json=payload)
    if res.status_code == 200:
        result = res.json()
        st.success(f"🛒 Predicted Quarterly Sales: ₹{result['Predicted_Sales']}")
    else:
        st.error(f"API Error {res.status_code}: {res.text}")