streamlit_app.py

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

# Hugging Face backend endpoint
BACKEND_URL = "https://dhani10-SuperKart-Backend.hf.space/predict"

# Load dropdown values from SuperKart.csv
@st.cache_data
def load_dropdown_data():
    df = pd.read_csv("SuperKart.csv")
    # product_ids = sorted(df['Product_Id'].dropna().unique())
    # store_ids = sorted(df['Store_Id'].dropna().unique())
    # years = sorted(df['Store_Establishment_Year'].dropna().unique())
    product_ids = sorted(df['Product_Id'].dropna().astype(str).unique())
    store_ids = sorted(df['Store_Id'].dropna().astype(str).unique())
    years = sorted(df['Store_Establishment_Year'].dropna().astype(int).unique())

    return product_ids, store_ids, years, df

# Page Title
st.title('SuperKart Sales Forecasting')

# Load CSV data
product_ids, store_ids, est_years, df = load_dropdown_data()

# Input Form
with st.form("prediction_form"):
    st.header("Product & Store Details")

    col1, col2 = st.columns(2)
    with col1:
        product_id = st.selectbox("Product ID", options=product_ids)
        product_weight = st.number_input("Product Weight", min_value=6.0, max_value=500.0)
        sugar_content = st.selectbox("Product Sugar Content", ["No Sugar", "Low Sugar", "Reg", "Regular"])
        allocated_area = st.number_input("Allocated Area Ratio", min_value=0.0, max_value=0.03)
        product_type = st.selectbox("Product Type", [
            "Baking Goods", "Bread", "Breakfast", "Canned", "Dairy", 
            "Frozen Foods", "Fruits and Vegetables", "Hard Drinks", 
            "Health and Hygiene", "Household", "Meat", "Others", 
            "Seafood", "Snack Foods", "Soft Drinks", "Starchy Foods"])
        mrp = st.number_input("MRP ($)", min_value=0.0, value=5.99)

    with col2:
        store_id = st.selectbox("Store ID", options=store_ids)
        establishment_year = st.selectbox("Establishment Year", options=est_years)
        store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
        city_type = st.selectbox("City Type", ["Tier 1", "Tier 2", "Tier 3"])
        store_type = st.selectbox("Store Type", [
            "Departmental Store", "Supermarket Type 1", 
            "Supermarket Type 2", "Food Mart"])

    submit = st.form_submit_button("Predict Sales")

# Prediction logic
if submit:
    # data = {
    #     "Product_Id": product_id,
    #     "Product_Weight": product_weight,
    #     "Product_Sugar_Content": sugar_content,
    #     "Product_Allocated_Area": allocated_area,
    #     "Product_Type": product_type,
    #     "Product_MRP": mrp,
    #     "Store_Id": store_id,
    #     "Store_Establishment_Year": establishment_year,
    #     "Store_Size": store_size,
    #     "Store_Location_City_Type": city_type,
    #     "Store_Type": store_type
    # }
    data = {
    "Product_Id": str(product_id),
    "Product_Weight": float(product_weight),
    "Product_Sugar_Content": str(sugar_content),
    "Product_Allocated_Area": float(allocated_area),
    "Product_Type": str(product_type),
    "Product_MRP": float(mrp),
    "Store_Id": str(store_id),
    "Store_Establishment_Year": int(establishment_year),  # FIXED LINE
    "Store_Size": str(store_size),
    "Store_Location_City_Type": str(city_type),
    "Store_Type": str(store_type)
    }


    try:
        response = requests.post(BACKEND_URL, json=data)
        if response.status_code == 200:
            prediction = response.json().get('prediction')
            if prediction is not None:
                st.success(f"**Predicted Sales:** ${prediction:,.2f}")

                st.subheader("Inventory Recommendations")
                if prediction > 1000:
                    st.info("✅ **High-demand product** - Increase stock by 30%")
                elif prediction > 500:
                    st.info("🔄 **Moderate-demand product** - Maintain current stock levels")
                else:
                    st.info("⚠️ **Low-demand product** - Reduce stock by 20%")
            else:
                st.error("Unexpected response from backend: 'prediction' key missing")
        else:
            st.error(f"Backend error: {response.status_code} - {response.text}")
    except Exception as e:
        st.error(f"Connection error: {str(e)}")

# Business insights section
st.markdown("---")
st.header("Business Insights")
st.write("""
- **Premium products** in Tier 1 cities show 35% higher sales  
- **Health & Hygiene** category growing at 18% YoY  
- **Supermarket Type 1** stores have highest sales/sq.ft  
- Reduce waste by 22% using accurate forecasts  
""")

# Optional: Show sample data
if st.checkbox("Show Product Database"):
    st.dataframe(df[['Product_Id', 'Product_Type', 'Product_Weight', 'Product_MRP']].drop_duplicates().head(10))

if st.checkbox("Show Store Database"):
    st.dataframe(df[['Store_Id', 'Store_Location_City_Type', 'Store_Size', 'Store_Type']].drop_duplicates().head(10))