src/app.py

import re
import streamlit as st
import pandas as pd
import joblib

# Load trained model
MODEL_PATH = "superkart_sales_prediction_model_v1_0.joblib"
model = joblib.load(MODEL_PATH)

valid_store_ids = ["OUT001", "OUT002", "OUT003", "OUT004"]
store_meta = {
    "OUT001": {"year": 1987, "size": "High",   "city_type": "Tier 2", "store_type": "Supermarket Type1"},
    "OUT002": {"year": 1998, "size": "Small",  "city_type": "Tier 3", "store_type": "Food Mart"},
    "OUT003": {"year": 1999, "size": "Medium", "city_type": "Tier 1", "store_type": "Departmental Store"},
    "OUT004": {"year": 2009, "size": "Medium", "city_type": "Tier 2", "store_type": "Supermarket Type2"},
}

st.title("SmartKart: Product Sales Prediction")
st.subheader("Online Prediction")

# Product ID validation
product_id = st.text_input("Product ID (2 uppercase letters + 4 digits, e.g., FD6114)", max_chars=6)
product_id_valid = bool(re.fullmatch(r"[A-Z]{2}\d{4}", product_id))
if product_id and not product_id_valid:
    st.error("Invalid Product ID format; it must be 2 uppercase letters followed by 4 digits.")
elif product_id_valid:
    st.success("Product ID format is valid.")

# Store selection
store_id = st.selectbox("Store ID", options=valid_store_ids)
meta = store_meta[store_id]
st.text(f"Store Establishment Year: {meta['year']}")
st.text(f"Store Size: {meta['size']}")
st.text(f"Store Location City Type: {meta['city_type']}")
st.text(f"Store Type: {meta['store_type']}")

# Product features
product_weight = st.number_input("Product Weight", min_value=0.0, value=12.0, format="%.2f")
product_sugar_content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
product_allocated_area = st.slider("Product Allocated Area Ratio", min_value=0.0, max_value=1.0, step=0.001, value=0.05)
product_type = st.selectbox("Product Type", [
    "Meat", "Snack Foods", "Hard Drinks", "Dairy", "Canned", "Soft Drinks",
    "Health and Hygiene", "Baking Goods", "Bread", "Breakfast", "Frozen Foods",
    "Fruits and Vegetables", "Household", "Seafood", "Starchy Foods", "Others"
])
product_mrp = st.number_input("Product MRP", min_value=0.0, value=150.0, format="%.2f")

# Prepare dataframe
input_data = pd.DataFrame([{
    "Product_Id": product_id,
    "Product_Weight": product_weight,
    "Product_Sugar_Content": product_sugar_content,
    "Product_Allocated_Area": product_allocated_area,
    "Product_Type": product_type,
    "Product_MRP": product_mrp,
    "Store_Id": store_id,
    "Store_Establishment_Year": meta['year'],
    "Store_Size": meta['size'],
    "Store_Location_City_Type": meta['city_type'],
    "Store_Type": meta['store_type'],
}])

# Prediction
if st.button("Predict"):
    if not product_id_valid:
        st.error("Please fix the Product ID before proceeding.")
    else:
        try:
            prediction = model.predict(input_data)[0]
            st.success(f"Predicted Product Sales: {prediction:.2f}")
        except Exception as e:
            st.error(f"Prediction failed: {e}")