Upload folder using huggingface_hub

Dockerfile

@@ -1,21 +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
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    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 +1,114 @@
+import streamlit as st
+import pandas as pd
+import joblib
+import numpy as np
+from datetime import datetime
+
+# Load the trained model
+@st.cache_resource
+def load_model():
+    return joblib.load("SuperKart_model_v1_0.joblib")
+
+model = load_model()
+
+# Streamlit UI for Sales Prediction
+st.title("Retail Product Sales Prediction App")
+st.write("This tool predicts the total sales for a product in a retail store based on product and store characteristics.")
+
+st.subheader("Enter the product and store details:")
+
+# Create two columns for better layout
+col1, col2 = st.columns(2)
+
+with col1:
+    # Product Features
+    st.markdown("**Product Details**")
+    product_weight = st.slider("Product Weight (kg)", 4.0, 22.0, 12.66, 0.01)
+    product_sugar = st.selectbox("Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
+    product_area = st.slider("Allocated Area (sqm)", 0.004, 0.3, 0.05, 0.001)
+    product_type = st.selectbox("Product Type", [
+        "Frozen Foods", "Dairy", "Canned", "Baking Goods", 
+        "Health and Hygiene", "Snack Foods", "Meat", "Household"
+    ])
+    product_mrp = st.slider("Product MRP (price)", 31.0, 266.0, 147.0, 0.5)
+
+with col2:
+    # Store Features
+    st.markdown("**Store Details**")
+    store_id = st.selectbox("Store ID", ["OUT001", "OUT002", "OUT003", "OUT004"])
+    current_year = datetime.now().year
+    establishment_year = st.slider("Store Establishment Year", 
+                                1987, current_year, 2002)
+    store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
+    city_type = st.selectbox("City Tier", ["Tier 1", "Tier 2", "Tier 3"])
+    store_type = st.selectbox("Store Type", [
+        "Supermarket Type1", "Supermarket Type2", 
+        "Departmental Store", "Food Mart"
+    ])
+
+# Calculate derived features
+store_age = current_year - establishment_year
+product_density = product_weight / (product_area + 1e-6)
+price_per_weight = product_mrp / (product_weight + 1e-6)
+
+# Convert user input into a DataFrame
+input_data = pd.DataFrame([{
+    'Product_Weight': product_weight,
+    'Product_Sugar_Content': product_sugar,
+    'Product_Allocated_Area': product_area,
+    'Product_Type': product_type,
+    'Product_MRP': product_mrp,
+    'Store_Id': store_id,
+    'Store_Establishment_Year': establishment_year,
+    'Store_Size': store_size,
+    'Store_Location_City_Type': city_type,
+    'Store_Type': store_type,
+    'Store_Age': store_age,
+    'Product_Density': product_density,
+    'Price_Per_Unit_Weight': price_per_weight,
+    'Product_Size_Category': 'Small' if product_weight <= 10 else ('Medium' if product_weight <= 15 else 'Large'),
+    'Store_Tier_Size': f"{city_type}_{store_size}"
+}])
+
+# Predict button
+if st.button("Predict Sales"):
+    try:
+        prediction = model.predict(input_data)
+        st.success(f"Predicted Sales Total: ${prediction[0]:.2f}")
+        
+        # Show some statistics
+        st.subheader("Statistics")
+        st.write(f"Store Age: {store_age} years")
+        st.write(f"Product Density: {product_density:.2f} kg/sqm")
+        st.write(f"Price per Unit Weight: ${price_per_weight:.2f}/kg")
+        
+    except Exception as e:
+        st.error(f"Error in prediction: {str(e)}")
+
+# Add some helpful information
+st.sidebar.markdown("""
+**Data Statistics:**
+- Average Product Weight: 12.65 kg
+- Average Allocated Area: 0.07 sqm
+- Average MRP: $147.03
+- Average Sales: $3464.00
+""")
+
+# Add a sample data button
+if st.sidebar.button("Load Sample Data"):
+    sample_data = {
+        'Product_Weight': 12.66,
+        'Product_Sugar_Content': "Low Sugar",
+        'Product_Allocated_Area': 0.027,
+        'Product_Type': "Frozen Foods",
+        'Product_MRP': 117.08,
+        'Store_Id': "OUT004",
+        'Store_Establishment_Year': 2009,
+        'Store_Size': "Medium",
+        'Store_Location_City_Type': "Tier 2",
+        'Store_Type': "Supermarket Type2"
+    }
+    
+    # Update all widgets with sample data
+    st.experimental_set_query_params(**sample_data)
+    st.experimental_rerun()

requirements.txt

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