import streamlit as st
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression

# Streamlit page config
st.set_page_config(page_title="BigMart Sales Predictor", page_icon="🛒", layout="centered")

st.title("🛒 BigMart Sales Prediction")
st.markdown("Enter item details below to predict sales:")

# Input fields
project_name = st.text_input("📦 Project Name")
item_weight = st.number_input("⚖️ Item Weight (kg)", min_value=0.0, step=0.1)
item_visibility = st.slider("👀 Item Visibility", 0.0, 1.0, 0.1)
item_mrp = st.number_input("💰 Item MRP (Max Retail Price)", min_value=0.0, step=1.0)

# Predict button
if st.button("Predict Sales"):
    if not project_name:
        st.warning("Please enter a project name.")
    else:
        # Dummy ML Model: Replace with your actual trained model
        X_train = np.array([
            [9.3, 0.016, 249.8],
            [5.92, 0.019, 48.27],
            [17.5, 0.016, 141.62],
            [19.2, 0.0075, 182.095],
        ])
        y_train = np.array([3735.14, 443.42, 2233.6, 3612.47])  # example sales

        model = LinearRegression()
        model.fit(X_train, y_train)

        # Prepare input
        user_input = np.array([[item_weight, item_visibility, item_mrp]])
        prediction = model.predict(user_input)[0]

        st.success(f"📈 Predicted Sales for '{project_name}': ₹{prediction:,.2f}")

# Sidebar info
st.sidebar.title("📌 About")
st.sidebar.markdown(
    """
    This app uses a simple ML model to estimate sales based on:
    - Item weight
    - Item visibility
    - Item MRP

    Replace with a trained BigMart dataset model for production use.
    """
)