app.py

import os
import streamlit as st
import requests
import json

st.set_page_config(page_title="SuperKart Sales Prediction", page_icon="🛒")

st.title("SuperKart Sales Prediction")
st.markdown(
    "Provide the product and store details to predict the expected "
    "**Product Total Sales** for that combination."
)

# Backend URL from environment / secrets
BACKEND_URL = os.environ.get("BACKEND_URL")

if BACKEND_URL is None:
    # Try Streamlit secrets as a second option
    try:
        BACKEND_URL = st.secrets["BACKEND_URL"]
    except Exception:
        st.warning(
            "No BACKEND_URL found in secrets or environment. "
            "If you are running locally, provide it below."
        )
        BACKEND_URL = st.text_input(
            "Backend URL",
            value="http://127.0.0.1:7860/v1/predict"
        )

st.subheader("Product information")

Product_Weight = st.number_input(
    "Product Weight",
    min_value=0.0,
    value=12.5,
    step=0.1
)

Product_Sugar_Content = st.selectbox(
    "Product Sugar Content",
    ["Low Sugar", "Regular", "No Sugar"]
)

Product_Allocated_Area = st.number_input(
    "Product Allocated Area (ratio)",
    min_value=0.0,
    max_value=0.4,
    value=0.07,
    step=0.01
)

Product_MRP = st.number_input(
    "Product MRP (Maximum Retail Price)",
    min_value=0.0,
    value=150.0,
    step=1.0
)

Product_Type_Category = st.selectbox(
    "Product Type Category",
    ["Perishables", "Non Perishables"]
)

Product_Id_char = st.text_input(
    "Product ID Prefix(FD(Food), NC(No Consumable), DR(Drinks))",
    value="FD",
    max_chars=2
)

st.subheader("Store information")

Store_Size = st.selectbox(
    "Store Size",
    ["Small", "Medium", "High"]
)

Store_Location_City_Type = st.selectbox(
    "Store Location City Type",
    ["Tier 1", "Tier 2", "Tier 3"]
)

Store_Type = st.selectbox(
    "Store Type",
    ["Supermarket Type1", "Supermarket Type2", "Departmental Store", "Food Mart"]
)

Store_Age_Years = st.number_input(
    "Store Age (years)",
    min_value=0,
    value=10,
    step=1
)

# Build payload matching backend expectations
product_data = {
    "Product_Weight": float(Product_Weight),
    "Product_Sugar_Content": Product_Sugar_Content,
    "Product_Allocated_Area": float(Product_Allocated_Area),
    "Product_MRP": float(Product_MRP),
    "Store_Size": Store_Size,
    "Store_Location_City_Type": Store_Location_City_Type,
    "Store_Type": Store_Type,
    "Product_Id_char": Product_Id_char,
    "Store_Age_Years": int(Store_Age_Years),
    "Product_Type_Category": Product_Type_Category,
}

st.markdown("----")

if st.button("Predict Sales", type="primary"):
    with st.spinner("Calling SuperKart backend..."):
        try:
            response = requests.post(
                BACKEND_URL,
                json=product_data,
                timeout=20
            )
            if response.status_code == 200:
                result = response.json()
                predicted_sales = result.get("Sales", None)

                if predicted_sales is not None:
                    st.success(f"✅ Predicted Total Store Sales: **{predicted_sales:,.2f}**")
                    st.caption("Prediction returned by the tuned Bagging model deployed by Sergio Riveros.")
                else:
                    st.error("The backend did not return a 'Sales' field.")
                    st.code(json.dumps(result, indent=2))
            else:
                st.error(f"Backend error. Status code: {response.status_code}")
                try:
                    st.code(json.dumps(response.json(), indent=2))
                except Exception:
                    st.write(response.text)
        except Exception as e:
            st.error(f"Request failed: {e}")