app.py

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

# Load the trained model
@st.cache_resource
def load_model():
    return joblib.load("Superkart_sales_model_v1_0.joblib")

model = load_model()


#Streamlit UI for Price Prediction
#st.set_page_config(page_title="SuperKart Sales Predictor", layout='wide')
st.title("SuperKart Sales Prediction App - By Sriranjan")
st.write("Input the product and store details below. The app will predict the **Product Store Sales Total** using the trained ML model.")

st.subheader("Enter the listing details:")

# Collect user input
# Example options based on your data
product_sugar_content_options = ['Low Sugar', 'Regular', 'No Sugar', 'reg']
product_type_options = [
    'Fruits and Vegetables', 'Snack Foods', 'Frozen Foods', 'Dairy', 'Household',
    'Baking Goods', 'Canned', 'Health and Hygiene', 'Meat', 'Soft Drinks',
    'Breads', 'Hard Drinks', 'Others', 'Starchy Foods', 'Breakfast', 'Seafood'
]
store_id_options = ['OUT004', 'OUT001', 'OUT003', 'OUT002']
store_size_options = ['Medium', 'High', 'Small']
city_type_options = ['Tier 2', 'Tier 1', 'Tier 3']
store_type_options = ['Supermarket Type2', 'Supermarket Type1', 'Departmental Store', 'Food Mart']

# Product Store Sales Total is the target,  not an input, so you may exclude it from user input or display stats elsewhere

# --- Input widgets ---
# Numeric feature inputs with min, max, mean values set as constraints/defaults
product_weight = st.number_input("Product Weight (kg)",min_value=4.0,max_value=22.0, value=4.0,help="Weight of the product in kilograms")

product_allocated_area = st.number_input(
    "Product Allocated Area",
    min_value=0.004,
    max_value=0.298,
    value= 0.004
)

store_establishment_year = st.number_input(
    "Store Establishment Year",
    min_value=1987,
    max_value=2009,
    value=1987,
    help="Year the store was established"
)

product_sugar_content = st.selectbox("Product Sugar Content", product_sugar_content_options)
product_type = st.selectbox("Product Type", product_type_options)
store_id = st.selectbox("Store Id", store_id_options)
store_size = st.selectbox("Store Size", store_size_options)
city_type = st.selectbox("Store Location City Type", city_type_options)
store_type = st.selectbox("Store Type", store_type_options)


# --- Prepare input for prediction ---
input_dict = {
    "Product_Weight": product_weight,
    "Product_Allocated_Area": product_allocated_area,
    "Store_Establishment_Year": store_establishment_year,
    "Product_Sugar_Content": product_sugar_content,
    "Product_Type": product_type,
    "Store_Id": store_id,
    "Store_Size": store_size,
    "Store_Location_City_Type": city_type,
    "Store_Type": store_type
}

input_data = pd.DataFrame([input_dict])

# Add dummy column expected by model
input_data["Product_Store_Sales_Total"] = 0

st.write("### Input Summary")
st.dataframe(input_data)



# --- Prediction ---
if st.button("Predict Sales"):
    prediction = model.predict(input_data)
    st.write(f"The predicted Sales is ${prediction}")

st.markdown("""
---
*Built by the Sriranjan.*
""")