import streamlit as st
import pandas as pd
import requests

# Streamlit UI for Customer Churn Prediction
st.title("Sales Prediction App")
st.write("This tool predicts SupeKaet Sales. Enter the required information below.")

# Model Choice
model_choice = st.selectbox(
    "Select Model",
    options=["dt", "xgb"],
    format_func=lambda x: "Decision Tree" if x == "dt" else "XGBoost"
)

# Collect user input based on dataset columns

product_weight = st.number_input("Product Weight", min_value=0.0)
sugar = st.selectbox("Sugar Content", [0, 1, 2])
area = st.number_input("Allocated Area", min_value=0.0)
product_type = st.number_input("Product Type Code", min_value=0)
mrp = st.number_input("Product MRP", min_value=0.0)
store_size = st.selectbox("Store Size Code", [0, 1, 2])
city = st.selectbox("City Type Code", [0, 1, 2])
store_type = st.number_input("Store Type Code", min_value=0)
store_age = st.number_input("Store Age", min_value=0)

# Convert categorical inputs to match model training
sample = {
    "model": model_choice,
    "Product_Weight": product_weight,
    "Product_Sugar_Content": sugar,
    "Product_Allocated_Area": area,
    "Product_Type": product_type,
    "Product_MRP": mrp,
    "Store_Size": store_size,
    "Store_Location_City_Type": city,
    "Store_Type": store_type,
    "Store_Age": store_age

}

if st.button("Predict", type='primary'):
    response = requests.post("https://Lokiiparihar-Sample.hf.space/predict", json=sample)    # enter user name and space name before running the cell
    if response.status_code == 200:
        result = response.json()
        sales_prediction = result["Prediction"]  # Extract only the value
        st.write(f"Based on the information provided, the sale is likely to {sales_prediction}.")
    else:
        st.error("Error in API request")

# Run the Flask app in debug mode
if __name__ == '__main__':
    app.run(debug=True)