Frontend with Streamlit + Docker

Dockerfile

@@ -11,6 +11,6 @@ COPY . .
 RUN pip3 install -r requirements.txt
 
 # Define the command to run the Streamlit app on port 8501 and make it accessible externally
-CMD ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
+CMD ["streamlit", "run", "streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
 
 # NOTE: Disable XSRF protection for easier external access in order to make batch predictions

requirements.txt

@@ -1,5 +1,2 @@
 streamlit
-pandas
-numpy
-xgboost
-scikit-learn
+requests

streamlit_app.py

@@ -0,0 +1,50 @@
+import streamlit as st
+import requests
+import numpy as np
+
+st.set_page_config(layout="wide", page_title="SuperKart Sales Predictor")
+
+st.title("SuperKart: Predict Store Sales")
+
+st.markdown("#### Fill in the product and store details:")
+
+with st.form("sales_form"):
+    Store_Size = st.selectbox("Store Size", ["Small", "Medium", "High"])
+    City_Tier = st.selectbox("City Tier", ["Tier 1", "Tier 2", "Tier 3"])
+    Sugar_Content = st.selectbox("Sugar Content", ["low sugar", "no sugar", "regular"])
+    Product_Type = st.selectbox("Product Type (Encoded)", list(range(10)))  # simplified
+    Store_Id = st.selectbox("Store ID (Encoded)", list(range(5)))
+    Store_Type = st.selectbox("Store Type (Encoded)", list(range(4)))
+    Product_Weight = st.number_input("Product Weight (Scaled)", -3.0, 3.0, 0.0)
+    Product_MRP = st.number_input("Product MRP (Scaled)", -3.0, 3.0, 0.0)
+    Allocated_Area = st.number_input("Product Allocated Area (Scaled)", -3.0, 3.0, 0.0)
+    Store_Age = st.number_input("Store Age (Scaled)", -3.0, 3.0, 0.0)
+
+    submitted = st.form_submit_button("Predict")
+
+if submitted:
+    # Encode manually
+    size_map = {"Small": 0, "Medium": 1, "High": 2}
+    tier_map = {"Tier 1": 0, "Tier 2": 1, "Tier 3": 2}
+    sugar_map = {"low sugar": 0, "no sugar": 1, "regular": 2}
+
+    input_data = [
+        size_map[Store_Size],
+        tier_map[City_Tier],
+        sugar_map[Sugar_Content],
+        Product_Type,
+        Store_Id,
+        Store_Type,
+        Product_Weight,
+        Product_MRP,
+        Allocated_Area,
+        Store_Age
+    ]
+
+    backend_url = "https://omm7-superkart-backend.hf.space/predict"
+    try:
+        response = requests.post(backend_url, json={"data": [input_data]})
+        prediction = response.json()["prediction"][0]
+        st.success(f"Predicted Sales: ₹ {prediction:,.2f}")
+    except Exception as e:
+        st.error(f"Something went wrong: {e}")