🔥 Deploy SuperKart Streamlit UI

streamlit_app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+import pandas as pd
+import requests
+import os
+
+# Page config
+st.set_page_config(page_title="SuperKart Forecast", layout="centered")
+st.title("🛒 SuperKart Quarterly Sales Forecast")
+st.write("Fill in the product and store details below, then click 🔮 Predict.")
+
+# Backend URL
+BACKEND_URL = os.getenv("BACKEND_URL", "$BACKEND_URL")
+
+# Input form
+with st.form("forecast_form"):
+    c1, c2 = st.columns(2)
+    with c1:
+        pw   = st.number_input("Product Weight (kg)", 0.0, 100.0, 12.5, 0.1)
+        pa   = st.number_input("Allocated Area Ratio", 0.0, 1.0, 0.08, 0.005)
+        mrp  = st.number_input("Product MRP (₹)", 0.0, 1000.0, 50.0, 1.0)
+        year = st.number_input("Store Established Year", 1900, 2025, 2015, 1)
+        size = st.selectbox("Store Size", ["low", "medium", "high"])
+    with c2:
+        city   = st.selectbox("City Tier", ["Tier 1", "Tier 2", "Tier 3"])
+        stype  = st.selectbox("Store Type", [
+            "Departmental Store", "Supermarket Type 1",
+            "Supermarket Type 2", "Food Mart"
+        ])
+        prefix = st.text_input("Product Prefix", "FD")
+        pnum   = st.number_input("Product Numeric ID", 0, 100000, 6114, 1)
+        age    = st.number_input("Store Age (yrs)", 0, 50, int(pd.Timestamp.now().year - year), 1)
+    submitted = st.form_submit_button("🔮 Predict")
+
+if submitted:
+    payload = {"data": [{
+        "Product_Weight": pw,
+        "Product_Allocated_Area": pa,
+        "Product_MRP": mrp,
+        "Store_Establishment_Year": year,
+        "Store_Size": size,
+        "Store_Location_City_Type": city,
+        "Store_Type": stype,
+        "Product_Prefix": prefix,
+        "Product_Num": pnum,
+        "Store_Age": age
+    }]}
+    try:
+        resp = requests.post(f"{BACKEND_URL}/predict", json=payload, timeout=10)
+        resp.raise_for_status()
+        pred = resp.json()["predictions"][0]
+        st.success(f"🚀 Forecasted Sales: ₹{pred:,.2f}")
+    except Exception as e:
+        st.error(f"❌ Prediction error: {e}")