import streamlit as st
import requests
import json
import pandas as pd

# --- Configuration ---
# IMPORTANT: Replace this with the URL of your deployed Flask API
# It should look like: https://your-username-your-space-name.hf.space/predict
API_URL = "https://kritish205/supercart-backend/predict" 

# --- UI Layout ---
st.set_page_config(page_title="SuperKart Sales Predictor", layout="wide")
st.title("🛒 SuperKart Sales Predictor")

st.markdown("""
This app predicts the total sales for a product in a given store. 
Please provide the details of the product and the store below.
""")

# Create columns for a cleaner layout
col1, col2 = st.columns(2)

# --- Input Fields ---

with col1:
    st.header("📦 Product Details")
    product_weight = st.number_input("Product Weight (kg)", min_value=0.0, max_value=30.0, value=10.0, step=0.1)
    product_mrp = st.number_input("Product MRP ($)", min_value=0.0, max_value=300.0, value=150.0)
    product_sugar_content = st.selectbox("Product Sugar Content", ["No Sugar", "Low Sugar", "Regular"])
    product_allocated_area = st.slider("Product Allocated Area (Ratio)", 0.0, 0.3, 0.05)
    
    # This list should match the categories from the original dataset
    product_type_options = [
        'Snack Foods', 'Household', 'Frozen Foods', 'Fruits and Vegetables', 
        'Health and Hygiene', 'Dairy', 'Baking Goods', 'Canned', 'Meat', 
        'Soft Drinks', 'Breads', 'Hard Drinks', 'Starchy Foods', 'Breakfast', 
        'Seafood', 'Others'
    ]
    product_type = st.selectbox("Product Type", product_type_options)

with col2:
    st.header("🏪 Store Details")
    store_age = st.number_input("Store Age (Years)", min_value=0, max_value=50, value=15)
    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"])

# --- Prediction Logic ---
if st.button("Predict Sales", type="primary"):
    if "YOUR_BACKEND_API_URL_HERE" in API_URL:
        st.error("Please update the `API_URL` in the `app.py` script with your backend's URL.")
    else:
        # Create a dictionary payload for the API
        # The keys must EXACTLY match the column names the model was trained on
        payload = {
            "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_Size": store_size,
            "Store_Location_City_Type": store_location_city_type,
            "Store_Type": store_type,
            "Store_Age": store_age
        }
        
        try:
            # Send the data to the Flask API
            with st.spinner('Getting prediction...'):
                response = requests.post(API_URL, json=payload)
                response.raise_for_status() # Raise an exception for bad status codes
                
                result = response.json()
                predicted_sales = result['predicted_sales']
                
                st.success(f"**Predicted Sales:** ${predicted_sales:,.2f}")

        except requests.exceptions.RequestException as e:
            st.error(f"Error connecting to the API: {e}")
        except KeyError:
            st.error("Received an unexpected response from the API. Check the backend logs.")