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

# --- Configuration ---
# Replace with your deployed backend API URL
API_URL = "https://austinsd-backendKart.hf.space/predict" 
# Median Product_Allocated_Area from training data for handling zero values
MEDIAN_ALLOCATED_AREA = 0.056  # This value was derived from df['Product_Allocated_Area'].median()

st.title('SuperKart Sales Prediction')
st.markdown('Enter product and store details to predict sales total.')

# --- Input Fields ---
st.header('Product Details')
product_weight = st.number_input('Product Weight (e.g., 12.66)', min_value=0.1, max_value=30.0, value=12.66, step=0.01)
product_allocated_area = st.number_input('Product Allocated Area (e.g., 0.027, if 0 will be replaced by median)', min_value=0.0, max_value=0.3, value=0.027, step=0.001)
product_mrp = st.number_input('Product MRP (e.g., 117.08)', min_value=0.0, max_value=300.0, value=117.08, step=0.01)
product_sugar_content = st.selectbox(
    'Product Sugar Content',
    ['Low Sugar', 'Regular', 'No Sugar']
)
product_type = st.selectbox(
    'Product Type',
    ['Fruits and Vegetables', 'Snack Foods', 'Household', 'Frozen Foods', 'Dairy', 'Canned', 'Baking Goods',
     'Health and Hygiene', 'Soft Drinks', 'Meat', 'Breads', 'Hard Drinks', 'Breakfast', 'Starchy Foods', 'Seafood', 'Others']
)

st.header('Store Details')
store_establishment_year = st.number_input('Store Establishment Year (e.g., 2009)', min_value=1950, max_value=2023, value=2009, step=1)
store_id = st.selectbox(
    'Store ID',
    ['OUT001', 'OUT003', 'OUT009', 'OUT005', 'OUT004', 'OUT010', 'OUT006', 'OUT007', 'OUT002', 'OUT008']
)
store_size = st.selectbox(
    'Store Size',
    ['High', 'Medium', 'Small']
)
store_location_city_type = st.selectbox(
    'Store Location City Type',
    ['Tier 1', 'Tier 2', 'Tier 3']
)
store_type = st.selectbox(
    'Store Type',
    ['Supermarket Type1', 'Food Mart', 'Supermarket Type2', 'Departmental Store']
)

# --- Prediction Logic ---
if st.button('Predict Sales'):
    # Preprocess inputs to match model's expected features
    store_age = 2024 - store_establishment_year
    product_visibility = product_allocated_area if product_allocated_area != 0 else MEDIAN_ALLOCATED_AREA

    input_data = {
        'Product_Weight': product_weight,
        'Product_Allocated_Area': product_allocated_area, # Keep original for consistency with training data columns
        'Product_MRP': product_mrp,
        'Store_Age': store_age,
        'Product_Visibility': product_visibility,
        'Product_Sugar_Content': product_sugar_content,
        'Product_Type': product_type,
        'Store_Id': store_id,
        'Store_Size': store_size,
        'Store_Location_City_Type': store_location_city_type,
        'Store_Type': store_type
    }
    
    # Wrap input_data in a list because the backend expects a list of records
    payload = [input_data]

    try:
        response = requests.post(API_URL, json=payload)
        if response.status_code == 200:
            prediction = response.json().get('prediction')
            if prediction:
                st.success(f"Predicted Product Store Sales Total: ${prediction[0]:,.2f}")
            else:
                st.error("Prediction not found in response.")
        else:
            st.error(f"Error from API: {response.status_code} - {response.text}")
    except requests.exceptions.ConnectionError:
        st.error("Could not connect to the API. Please ensure the backend is running and the API_URL is correct.")
    except Exception as e:
        st.error(f"An unexpected error occurred: {e}")