app.py

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

# Load the trained Random Forest pipeline model
try:
    model = joblib.load('random_forest_pipeline.pkl')
except FileNotFoundError:
    st.error("Model file 'random_forest_pipeline.pkl' not found. Please ensure the model is trained and saved.")
    model = None

st.title('SuperKart Sales Prediction App')

if model:
    st.sidebar.header('Input Features')

    # Define input fields for each feature based on your dataset columns
    # Product_Weight
    product_weight = st.sidebar.number_input('Product Weight(kg)', min_value=0.1, max_value=30.0, value=10.0)

    # Product_Sugar_Content
    sugar_content_options = ['Low Sugar', 'Regular', 'No Sugar', 'reg'] # Based on EDA
    product_sugar_content = st.sidebar.selectbox('Product Sugar Content', sugar_content_options)

    # Product_Allocated_Area
    product_allocated_area = st.sidebar.number_input('Product Allocated Area (sq. m)', min_value=0.0, max_value=1.0, value=0.05)

    # Product_Type
    product_type_options = ['Breads', 'Snack Foods', 'Frozen Foods', 'Dairy', 'Seafood', 'Starchy Foods', 'Soft Drinks', 'Meat', 'Hard Drinks', 'Health and Hygiene', 'Baking Goods', 'Breakfast', 'Canned', 'Fruits and Vegetables', 'Household', 'Others'] # Based on EDA
    product_type = st.sidebar.selectbox('Product Type', product_type_options)

    # Product_MRP
    product_mrp = st.sidebar.number_input('Product MRP ($)', min_value=10.0, max_value=300.0, value=150.0)

    # Store_Id - Using an example list, replace with actual Store IDs from your data if possible
    store_id_options = ['OUT027', 'OUT013', 'OUT011', 'OUT010', 'OUT004', 'OUT001', 'OUT002', 'OUT003']
    store_id = st.sidebar.selectbox('Store ID', store_id_options)

    # Store_Establishment_Year
    store_establishment_year = st.sidebar.number_input('Store Establishment Year', min_value=1900, max_value=2024, value=2000)

    # Store_Size
    store_size_options = ['Medium', 'High', 'Low']
    store_size = st.sidebar.selectbox('Store Size', store_size_options)

    # Store_Location_City_Type
    city_type_options = ['Tier 1', 'Tier 2', 'Tier 3']
    store_location_city_type = st.sidebar.selectbox('Store Location City Type', city_type_options)

    # Store_Type
    store_type_options = ['Departmental Store', 'Supermarket Type 1', 'Supermarket Type 2', 'Food Mart']
    store_type = st.sidebar.selectbox('Store Type', store_type_options)

    # Product_Id - Although not used in the model, it's in the original data structure
    # For prediction, we can use a placeholder or a dummy value if not strictly needed by the preprocessor
    product_id = 'dummy_product_id' # Placeholder

    # Create a DataFrame with the input features
    input_data = pd.DataFrame({
        'Product_Id': [product_id],
        '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_Id': [store_id],
        'Store_Establishment_Year': [store_establishment_year],
        'Store_Size': [store_size],
        'Store_Location_City_Type': [store_location_city_type],
        'Store_Type': [store_type]
    })


    st.subheader('Input Data')
    st.write(input_data)

    # Make prediction
    if st.sidebar.button('Predict Sales'):
        try:
            prediction = model.predict(input_data)
            st.subheader('Predicted Product Store Sales Total')
            st.success(f'Predicted Sales: ${prediction[0]:,.2f}')
        except Exception as e:
            st.error(f"An error occurred during prediction: {e}")

else:
    st.warning("Model not loaded. Please ensure the model file exists and the pipeline is correctly defined.")