app.py

import streamlit as st
import pandas as pd
import requests

# Set the title of the Streamlit app
st.title("SuperKart Sales Prediction")

# Section for online prediction
st.subheader("Online Prediction")

# Collect user input for product and store features
product_type = st.selectbox("Product Type", [
    "Dairy", "Soft Drinks", "Meat", "Fruits and Vegetables", "Household", 
    "Baking Goods", "Snack Foods", "Frozen Foods", "Breakfast", "Health and Hygiene",
    "Hard Drinks", "Others", "Seafood", "Starchy Foods", "Canned", "Breads"
])
store_id = st.selectbox("Store ID", ["OUT004", "OUT001", "OUT003", "OUT002"])  # Update with actual store IDs

product_sugar_content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
product_weight = st.number_input("Product Weight (grams)", min_value=0.0, step=0.1, value=500.0)
product_mrp = st.number_input("Product MRP (₹)", min_value=0.0, step=0.1, value=100.0)
product_allocated_area = st.number_input("Allocated Shelf Area (sq cm)", min_value=0.0, step=1.0, value=100.0)

store_type = st.selectbox("Store Type", ["Supermarket Type2", "Supermarket Type1", "Departmental Store", "Food Mart"])
store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
store_location_city_type = st.selectbox("Store Location", ["Tier 2", "Tier 1", "Tier 3"])
store_establishment_year = st.number_input("Year of Store Establishment", min_value=1900, max_value=2025, step=1, value=2015)

# Convert user input into a DataFrame
input_data = pd.DataFrame([{
    'Product_Type': product_type,
    'Product_Sugar_Content': product_sugar_content,
    'Product_Weight': product_weight,
    'Product_MRP': product_mrp,
    'Product_Allocated_Area': product_allocated_area,
    'Store_Id': store_id,
    'Store_Type': store_type,
    'Store_Size': store_size,
    'Store_Location_City_Type': store_location_city_type,
    'Store_Establishment_Year': store_establishment_year
}])

# Make prediction when the "Predict" button is clicked
if st.button("Predict"):
    response = requests.post("https://Swetha2031-SuperKartSalesPredictionBackend.hf.space/v1/salestotal", json=input_data.to_dict(orient='records')[0])
    if response.status_code == 200:
        prediction = response.json()['Predicted Sales (₹)']
        st.success(f"Predicted Product Sales: ₹{prediction}")
    else:
        st.error("Error making prediction.")


# Section for batch prediction
st.subheader("Batch Prediction")

# Allow users to upload a CSV file for batch prediction
uploaded_file = st.file_uploader("Upload CSV file for batch prediction", type=["csv"])


if st.button("Predict Batch"):
    response = requests.post("https://Swetha2031-SuperKartSalesPredictionBackend.hf.space/v1/salesbatch", files={"file": uploaded_file})
    if response.status_code == 200:
        predictions = response.json()

        # Convert dictionary to DataFrame
        df_predictions = pd.DataFrame(list(predictions.items()), columns=["Store ID", "Predicted Sales (₹)"])

        # Optional: check for overflow
        if df_predictions["Predicted Sales (₹)"].gt(1e10).any():
            st.warning("Some predictions are extremely large. This may indicate overflow or input scaling issues.")

        st.success("Batch predictions completed!")
        st.write(df_predictions)
    else:
        st.error("Error making batch prediction.")