Upload folder using huggingface_hub

Dockerfile

@@ -1,20 +1,16 @@
-FROM python:3.13.5-slim
+# 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
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY requirements.txt ./
-COPY src/ ./src/
+# 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
 
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+# 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"]
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# NOTE: Disable XSRF protection for easier external access in order to make batch predictions

app.py

@@ -0,0 +1,85 @@
+import streamlit as st
+import requests
+import pandas as pd
+import numpy as np
+
+# --- Configuration ---
+# Replace with your deployed backend API URL
+API_URL = "https://<YOUR_HF_USERNAME>-<YOUR_HF_SPACE_NAME>.hf.space/predict" 
+# Median Product_Allocated_Area from training data for handling zero values
+MEDIAN_ALLOCATED_AREA = 0.056  # This value was derived from df['Product_Allocated_Area'].median()
+
+st.title('SuperKart Sales Prediction')
+st.markdown('Enter product and store details to predict sales total.')
+
+# --- Input Fields ---
+st.header('Product Details')
+product_weight = st.number_input('Product Weight (e.g., 12.66)', min_value=0.1, max_value=30.0, value=12.66, step=0.01)
+product_allocated_area = st.number_input('Product Allocated Area (e.g., 0.027, if 0 will be replaced by median)', min_value=0.0, max_value=0.3, value=0.027, step=0.001)
+product_mrp = st.number_input('Product MRP (e.g., 117.08)', min_value=0.0, max_value=300.0, value=117.08, step=0.01)
+product_sugar_content = st.selectbox(
+    'Product Sugar Content',
+    ['Low Sugar', 'Regular', 'No Sugar']
+)
+product_type = st.selectbox(
+    'Product Type',
+    ['Fruits and Vegetables', 'Snack Foods', 'Household', 'Frozen Foods', 'Dairy', 'Canned', 'Baking Goods',
+     'Health and Hygiene', 'Soft Drinks', 'Meat', 'Breads', 'Hard Drinks', 'Breakfast', 'Starchy Foods', 'Seafood', 'Others']
+)
+
+st.header('Store Details')
+store_establishment_year = st.number_input('Store Establishment Year (e.g., 2009)', min_value=1950, max_value=2023, value=2009, step=1)
+store_id = st.selectbox(
+    'Store ID',
+    ['OUT001', 'OUT003', 'OUT009', 'OUT005', 'OUT004', 'OUT010', 'OUT006', 'OUT007', 'OUT002', 'OUT008']
+)
+store_size = st.selectbox(
+    'Store Size',
+    ['High', 'Medium', 'Small']
+)
+store_location_city_type = st.selectbox(
+    'Store Location City Type',
+    ['Tier 1', 'Tier 2', 'Tier 3']
+)
+store_type = st.selectbox(
+    'Store Type',
+    ['Supermarket Type1', 'Food Mart', 'Supermarket Type2', 'Departmental Store']
+)
+
+# --- Prediction Logic ---
+if st.button('Predict Sales'):
+    # Preprocess inputs to match model's expected features
+    store_age = 2024 - store_establishment_year
+    product_visibility = product_allocated_area if product_allocated_area != 0 else MEDIAN_ALLOCATED_AREA
+
+    input_data = {
+        'Product_Weight': product_weight,
+        'Product_Allocated_Area': product_allocated_area, # Keep original for consistency with training data columns
+        'Product_MRP': product_mrp,
+        'Store_Age': store_age,
+        'Product_Visibility': product_visibility,
+        'Product_Sugar_Content': product_sugar_content,
+        'Product_Type': product_type,
+        'Store_Id': store_id,
+        'Store_Size': store_size,
+        'Store_Location_City_Type': store_location_city_type,
+        'Store_Type': store_type
+    }
+    
+    # Wrap input_data in a list because the backend expects a list of records
+    payload = [input_data]
+
+    try:
+        response = requests.post(API_URL, json=payload)
+        if response.status_code == 200:
+            prediction = response.json().get('prediction')
+            if prediction:
+                st.success(f"Predicted Product Store Sales Total: ${prediction[0]:,.2f}")
+            else:
+                st.error("Prediction not found in response.")
+        else:
+            st.error(f"Error from API: {response.status_code} - {response.text}")
+    except requests.exceptions.ConnectionError:
+        st.error("Could not connect to the API. Please ensure the backend is running and the API_URL is correct.")
+    except Exception as e:
+        st.error(f"An unexpected error occurred: {e}")

requirements.txt

@@ -1,3 +1,4 @@
-altair
+streamlit
+requests
 pandas
-streamlit
+numpy