import streamlit as st
import requests

st.title("SuperKart-Forecast-Prediction") #Complete the code to define the title of the app.

# Input fields for product and store data (bounds and choices taken from processed_data.csv)

# Numeric ranges from data
# Product_Weight: min=4.00, median=12.66, max=22.00
Product_Weight = st.number_input("Product Weight (kg)", min_value=4.0, max_value=22.0, value=12.66, step=0.01)

# Product_Sugar_Content categories present in data
Product_Sugar_Content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"])

# Product_Allocated_Area: min=0.004, median=0.056, max=0.298
Product_Allocated_Area = st.number_input("Product Allocated Area (fraction of shelf space)",
                                         min_value=0.004, max_value=0.298, value=0.056, step=0.001, format="%.3f")

# Product_MRP: min=31.00, median=146.74, max=266.00 (₹)
Product_MRP = st.number_input("Product MRP (₹)",
                              min_value=31.0, max_value=266.0, value=146.74, step=0.01, format="%.2f")

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

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

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

# Product_Id_char categories (product family code)
Product_Id_char = st.selectbox("Product ID (family code)", ["DR", "FD", "NC"])

# Store_Age_Years: min=16, median=16, max=38
Store_Age_Years = st.number_input("Store Age (years)", min_value=16, max_value=38, value=16, step=1)

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


product_data = {
    "Product_Weight": Product_Weight,
    "Product_Sugar_Content": Product_Sugar_Content,
    "Product_Allocated_Area": Product_Allocated_Area,
    "Product_MRP": 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": Store_Age_Years,
    "Product_Type_Category": Product_Type_Category
}

if st.button("Predict", type='primary'):
    # Replace <your_username> and <your_backend_space> with your actual HF handle and backend space name
    response = requests.post("https://huggingface.co/spaces/VGusMaximus/SuperKart-Model/tree/main", json=product_data)
    if response.status_code == 200:
        result = response.json()
        predicted_sales = result["Sales"]
        st.write(f"Predicted Product Store Sales Total: ₹{predicted_sales:.2f}")
    else:
        st.error("Error in API request")