front-end / app.py
Anamika123321's picture
Upload folder using huggingface_hub
f6a6042 verified
Raw History Blame Contribute Delete
2.52 kB
# Streamlit Web App for SuperKart Sales Forecasting
import streamlit as st
import requests
import numpy as np
# Add Logo
st.image("https://i.postimg.cc/2yM4LgJM/Superkart-notebook-cover-image.png", width=400)
# App Title
st.title("๐Ÿ›’ SuperKart Sales Forecasting App")
# Instructions
st.markdown("๐Ÿ” Enter product and store attributes to forecast **monthly product sales revenue**.\n\n_All sales are reported in ($) USD._")
# User Inputs
Product_Weight = st.number_input("Product Weight (oz)", min_value=0.0, value=12.66)
Product_Sugar_Content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
Product_Allocated_Area = st.number_input("Product Allocated Area (linear in.)", min_value=0.0, value=100.0)
Product_MRP = st.number_input("Maximum Retail Price (USD)", min_value=0.0, value=150.0)
Store_Size = st.selectbox("Store Size", ["Small", "Medium", "High"])
Store_Location_City_Type = st.selectbox("Store Location City Type", ["Tier 1", "Tier 2", "Tier 3"])
Store_Type = st.selectbox("Store Type", ["Supermarket Type1", "Supermarket Type2", "Departmental Store", "Food Mart"])
Store_Age_Years = st.slider("Store Age (years)", min_value=0, max_value=30, value=10)
Product_Type_Category = st.selectbox("Product Type Category", ["Perishables", "Non Perishables"])
# Apply log1p transform (must match backend model training)
Product_Allocated_Area_Log = np.log1p(Product_Allocated_Area)
# Prepare JSON payload for the backend
product_data = {
"Product_Weight": str(Product_Weight),
"Product_Sugar_Content": Product_Sugar_Content,
"Product_Allocated_Area": str(Product_Allocated_Area),
"Product_MRP": str(Product_MRP),
"Store_Size": Store_Size,
"Store_Location_City_Type": Store_Location_City_Type,
"Store_Type": Store_Type,
"Store_Age_Years": str(Store_Age_Years),
"Product_Type_Category": Product_Type_Category
}
# Trigger Prediction
if st.button("Predict", type='primary'):
try:
response = requests.post(
"https://Anamika123321-superkart-sales-forecast-backend.hf.space/v1/predict",
json=product_data
)
if response.status_code == 200:
result = response.json()
predicted_sales = result["Predicted_Sales"]
st.success(f"๐Ÿ“ˆ Predicted Monthly Sales: **${predicted_sales:,.2f} USD**")
else:
st.error("โŒ API Error: Please verify input values or try again later.")
except Exception as e:
st.error(f"โš ๏ธ Connection error: {e}")