Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+# Use a minimal base image with Python 3.9 installed
+FROM python:3.9-slim
+
+# Set the working directory inside the container to /app
+WORKDIR /app
+
+# Copy all files from the current directory on the host to the container's /app directory
+COPY . .
+
+# Install Python dependencies listed in requirements.txt
+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", "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

app.py

@@ -0,0 +1,125 @@
+import streamlit as st
+import pandas as pd
+import requests
+from datetime import datetime
+
+# -------------------------
+# SuperKart - Sales Forecast Streamlit App (Online Prediction only)
+# -------------------------
+st.set_page_config(page_title="SuperKart Sales Forecast", layout="wide")
+st.title("SuperKart — Outlet Sales Forecasting")
+st.markdown(
+    "Use this app to get **online** sales forecasts for a product at a specific store."
+)
+
+# ----- Online prediction -----
+st.subheader("Online Prediction (single product-store pair)")
+
+# Product fields
+with st.expander("Product details", expanded=True):
+    product_id = st.text_input("Product_Id (e.g. PR123)", value="PR1001")
+    product_weight = st.number_input("Product_Weight (numeric)", min_value=0.0, value=250.0, format="%.3f")
+    product_sugar_content = st.selectbox(
+        "Product_Sugar_Content",
+        ["Low Sugar", "Regular", "No Sugar"]
+    )
+    product_allocated_area = st.number_input(
+        "Product_Allocated_Area (ratio 0-1)",
+        min_value=0.0, max_value=1.0, value=0.05, format="%.4f"
+    )
+    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"
+        ]
+    )
+    product_mrp = st.number_input("Product_MRP (maximum retail price)", min_value=0.0, value=99.0, format="%.2f")
+
+# Store fields
+with st.expander("Store details", expanded=True):
+    store_id = st.text_input("Store_Id (e.g. ST100)", value="ST100")
+    store_est_year = st.number_input(
+        "Store_Establishment_Year",
+        min_value=1900,
+        max_value=datetime.now().year,
+        value=2015,
+        step=1
+    )
+    store_size = st.selectbox("Store_Size", ["Low", "Medium", "High"])
+    store_location_city_type = st.selectbox("Store_Location_City_Type", ["Tier 1", "Tier 2", "Tier 3"])
+    store_type = st.selectbox("Store_Type", ["Departmental Store", "Supermarket Type 1", "Supermarket Type 2", "Food Mart"])
+
+# Prepare input dataframe
+input_data = pd.DataFrame([{
+    "Product_Id": product_id,
+    "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": int(store_est_year),
+    "Store_Size": store_size,
+    "Store_Location_City_Type": store_location_city_type,
+    "Store_Type": store_type
+}])
+
+st.markdown("**Preview of the input that will be sent to the model endpoint:**")
+st.dataframe(input_data)
+
+# -------------------------
+# Configure your backend endpoint here
+# -------------------------
+PREDICTION_API_URL = "https://viveksardey-superkartsalesrevpredictionbackend.hf.space/v1/forecast"  # single-record prediction (POST JSON)
+
+# Make prediction when the "Predict" button is clicked
+if st.button("Predict Sales (Online)"):
+    try:
+        payload = input_data.to_dict(orient="records")[0]
+        response = requests.post(PREDICTION_API_URL, json=payload, timeout=30)
+        if response.status_code == 200:
+            try:
+                resp_json = response.json()
+            except ValueError:
+                st.success(f"Prediction response (non-JSON): {response.text}")
+                st.stop()
+
+            # common keys to search for in response
+            predicted = None
+            for key in ("predicted_sales", "Predicted Sales", "Predicted_Sales", "prediction", "sales", "predicted"):
+                if key in resp_json:
+                    predicted = resp_json[key]
+                    break
+
+            # fallback handling
+            if predicted is None:
+                if isinstance(resp_json, (int, float, str)):
+                    predicted = resp_json
+                elif isinstance(resp_json, dict) and len(resp_json) == 1:
+                    predicted = list(resp_json.values())[0]
+
+            if predicted is not None:
+                st.success(f"Predicted Sales Revenue for the quarter: {predicted}")
+            else:
+                st.write(resp_json)
+                st.info("Couldn't find a standard 'predicted_sales' field — raw response shown above.")
+        else:
+            st.error(f"Prediction API returned status {response.status_code}")
+            try:
+                st.write(response.json())
+            except Exception:
+                st.write(response.text)
+    except requests.exceptions.RequestException as e:
+        st.error(f"Error connecting to prediction API: {e}")
+
+# ----- Helpful notes -----
+st.markdown("---")
+st.markdown(
+    "**Notes & tips:**\n\n"
+    "- Replace `PREDICTION_API_URL` with your deployed model endpoint.\n"
+    "- Ensure your backend accepts the same column names and formats as used in this frontend.\n"
+    "- For production, secure your endpoint (authentication, TLS) and validate inputs on the backend.\n"
+    "- Common backend response format: `{\"predicted_sales\": <number>}`.\n"
+)

requirements.txt

@@ -0,0 +1,3 @@
+pandas==2.2.2
+requests==2.28.1
+streamlit==1.43.2