streamlit_app.py

# import requests
# import streamlit as st
# import numpy as np

# st.title("SuperKart Sales Forecast")

# inputs = [st.number_input(f"Enter {name}", value=0.0) for name in [
#     "Product_Weight", "Product_Allocated_Area", "Product_MRP", "Store_Establishment_Year"
# ]]

# if st.button("Predict Sales"):
#     try:
#         response = requests.post("http://localhost:5000/predict", json={"features": inputs})
#         st.success(f"Predicted Sales: {response.json()['prediction']}")
#     except Exception as e:
#         st.error(f"Error: {e}")

import os
os.environ["XDG_CONFIG_HOME"] = "/tmp"

import streamlit as st
import joblib
import numpy as np

st.set_page_config(page_title="SuperKart Forecast", layout="centered")
st.title("🛒 SuperKart Sales Forecast")

# Load the trained model
model = joblib.load("random_forest_best_model.pkl")

# Input fields
st.subheader("Enter Product & Store Details")
feature_names = ['Product_Weight', 'Product_Allocated_Area', 'Product_MRP', 'Store_Establishment_Year']
inputs = [st.number_input(f"{feature}", value=0.0, step=0.01) for feature in feature_names]

# Prediction
if st.button("📈 Predict Sales"):
    features = np.array(inputs).reshape(1, -1)
    prediction = model.predict(features)
    st.success(f"📊 Predicted Sales Revenue: ₹{prediction[0]:,.2f}")