app.py

import streamlit as st
import pandas as pd
import requests

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

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

# ---------------------------- User Input Section ----------------------------

# Get product weight from user
product_weight = st.number_input(
    "Product Weight (in grams)",
    min_value=0.0, value=100.0, step=0.1,
    help="Weight of each product"
)

# Get sugar content category
product_sugar_content = st.selectbox(
    "Product Sugar Content",
    ["Low Sugar", "Regular", "No Sugar"],
    help="Sugar content of each product"
)

# Get allocated display area ratio
product_allocated_area = st.number_input(
    "Product Allocated Area (0 to 1)",
    min_value=0.0, max_value=1.0, value=0.2, step=0.01,
    help="Ratio of the product's allocated display area to total display area in the store"
)

# Select product type
product_type = st.selectbox(
    "Product Type",
    [
        "Meat", "Snack Foods", "Hard Drinks", "Dairy", "Canned", "Soft Drinks",
        "Health and Hygiene", "Baking Goods", "Bread", "Breakfast", "Frozen Foods",
        "Fruits and Vegetables", "Household", "Seafood", "Starchy Foods", "Others"
    ],
    help="Broad category for the product"
)

# Set maximum retail price
product_mrp = st.number_input(
    "Product MRP (in ₹)",
    min_value=1.0, value=100.0, step=1.0,
    help="Maximum retail price of each product"
)

# Unique store identifier
store_id = st.text_input(
    "Store ID",
    value="S101",
    help="Unique identifier of the store"
)

# Year of store establishment
store_establishment_year = st.number_input(
    "Store Establishment Year",
    min_value=1900, max_value=2025, value=2010, step=1,
    help="Year the store was established"
)

# Select store size
store_size = st.selectbox(
    "Store Size",
    ["High", "Medium", "Small"],
    help="Size of the store in square feet"
)

# Choose city type for store location
store_location_city_type = st.selectbox(
    "Store Location City Type",
    ["Tier 1", "Tier 2", "Tier 3"],
    help="City type where store is located"
)

# Choose store type
store_type = st.selectbox(
    "Store Type",
    ["Departmental Store", "Supermarket Type 1", "Supermarket Type 2", "Food Mart"],
    help="Type of store based on products sold"
)

# ---------------------------- Create DataFrame ----------------------------

# Collect all the input features into a DataFrame for API call
input_data = pd.DataFrame([{
    '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
}])

# ---------------------------- Online Prediction ----------------------------

# Call the backend model API when the user clicks the "Predict" button
if st.button("Predict"):
    response = requests.post(
        "https://SudeendraMG-SuperKartProductTotalSalesPredictionBackend.hf.space/v1/totalsales",  # Updated endpoint
        json=input_data.to_dict(orient='records')[0]
    )
    
    # Check the response and show the prediction
    if response.status_code == 200:
        prediction = response.json()['Predicted Product Store Sales Total']
        st.success(f"Predicted Product Store Sales Total: {prediction}")
    else:
        st.error("Error making prediction.")  # Show error if API call fails

# ---------------------------- Batch Prediction Section ----------------------------

# Subtitle for batch predictions
st.subheader("Batch Prediction")

# Let user upload CSV file for batch prediction
uploaded_file = st.file_uploader("Upload CSV file for batch prediction", type=["csv"])

# If file is uploaded and user clicks the "Predict Batch" button
if uploaded_file is not None:
    if st.button("Predict Batch"):
        # Send file to the backend batch prediction endpoint
        response = requests.post(
            "https://SudeendraMG-SuperKartProductTotalSalesPredictionBackend.hf.space/v1/totalsalesbatch",  # Updated endpoint
            files={"file": uploaded_file}
        )
        
        # Display batch predictions or error
        if response.status_code == 200:
            predictions = response.json()
            st.success("Batch predictions completed!")
            st.write(predictions)
        else:
            st.error("Error making batch prediction.")