Upload folder using huggingface_hub

Dockerfile

@@ -1,15 +1,16 @@
 FROM python:3.11.13
 
-# Set the working directory inside the container to /app
+# Set the working directory inside the container
 WORKDIR /app
 
-# Copy all files from the current directory on the host to the container's /app directory
+# Copy all files from the current directory to the container's working directory
 COPY . .
 
-# Install Python dependencies listed in requirements.txt
-RUN pip3 install -r requirements.txt
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -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
+# Define the command to start the application using Gunicorn with 4 worker processes
+# - `-w 4`: Uses 4 worker processes for handling requests
+# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
+# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:super_kart_api"]

app.py

@@ -1,81 +1,81 @@
-
-import streamlit as st
-import pandas as pd
-import joblib
+# Import necessary libraries
 import numpy as np
+import joblib  # For loading the serialized model
+import pandas as pd  # For data manipulation
+from flask import Flask, request, jsonify  # For creating the Flask API
 
-# Load the trained model
-@st.cache_resource
-def load_model():
-    return joblib.load("super_kart_model_v1_0.joblib")
-
-model = load_model()
-
-# Streamlit UI for Super Kart Sales Prediction
-st.title("Super Kart Product Sales Prediction App")
-st.write("This tool predicts the total sales for a product based on store and product details.")
+# Initialize the Flask application
+super_kart_api = Flask("Super Kart Price Predictor")
 
-st.subheader("Enter the product and store details:")
+# Load the trained machine learning model (updated path to match deployment structure)
+model_path = "super_kart_model_v1_0.joblib"
+try:
+    model = joblib.load(model_path)
+    print(f"Model loaded successfully from {model_path}")
+except FileNotFoundError:
+    raise FileNotFoundError(f"Model file not found at {model_path}. Ensure it's included in the deployment.")
 
-# Collect user input (matching Super Kart features)
-product_weight = st.number_input("Product Weight", min_value=0.0, value=10.0, step=0.1)
-product_sugar_content = st.selectbox("Product Sugar Content", ["No Sugar", "Low Sugar", "Regular"])
-product_allocated_area = st.number_input("Product Allocated Area (sq ft)", min_value=0.0, value=500.0, step=1.0)
-product_type = st.selectbox("Product Type", ["Dairy", "Soft Drinks", "Meat", "Fruits and Vegetables", "Snack Foods", "Household", "Frozen Foods", "Baking Goods", "Canned", "Health and Hygiene", "Hard Drinks", "Breads", "Starchy Foods", "Breakfast", "Seafood", "Others"])  # Add actual types from your data
-product_mrp = st.number_input("Product MRP (price)", min_value=0.0, value=100.0, step=1.0)
-store_establishment_year = st.number_input("Store Establishment Year", min_value=1900, max_value=2025, value=2000, step=1)
-store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
-store_location_city_type = st.selectbox("Store Location City Type", ["Tier 3", "Tier 2", "Tier 1"])
-store_type = st.selectbox("Store Type", ["Grocery Store", "Supermarket Type1", "Supermarket Type2", "Supermarket Type3"])  # Add actual types from your data
+# Define a route for the home page (GET request)
+@super_kart_api.get('/')
+def home():
+    """
+    This function handles GET requests to the root URL ('/') of the API.
+    It returns a simple welcome message.
+    """
+    return "Welcome to the Super Kart Price Prediction API!"
 
-# Predict button
-if st.button("Predict"):
-    # Create input dictionary
+# Define an endpoint for single product sales prediction (POST request)
+@super_kart_api.post('/v1/sales')
+def predict_sales():
+    """
+    This function handles POST requests to the '/v1/sales' endpoint.
+    It expects a JSON payload containing product and store details and returns
+    the predicted sales total as a JSON response.
+    """
+    # Get the JSON data from the request body
+    input_data = request.get_json()
+    
+    # Extract relevant features from the JSON data
+    # Note: Exclude Product_Id and Store_Id if they are not used in prediction
     sample = {
-        '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_Establishment_Year': store_establishment_year,
-        'Store_Size': store_size,
-        'Store_Location_City_Type': store_location_city_type,
-        'Store_Type': store_type
+        'Product_Weight': input_data['Product_Weight'],
+        'Product_Sugar_Content': input_data['Product_Sugar_Content'],
+        'Product_Allocated_Area': input_data['Product_Allocated_Area'],
+        'Product_Type': input_data['Product_Type'],
+        'Product_MRP': input_data['Product_MRP'],
+        'Store_Establishment_Year': input_data['Store_Establishment_Year'],
+        'Store_Size': input_data['Store_Size'],
+        'Store_Location_City_Type': input_data['Store_Location_City_Type'],
+        'Store_Type': input_data['Store_Type']
     }
-
-    # Convert to DataFrame
+    # Convert the extracted data into a Pandas DataFrame
     features_df = pd.DataFrame([sample])
-
-    # Apply one-hot encoding for nominal columns (matching backend)
+    
+    # Apply one-hot encoding for nominal columns (matching training)
     features_df = pd.get_dummies(features_df, columns=['Product_Type', 'Store_Type'], drop_first=True)
-
-    # Apply ordinal encoding (based on backend mappings)
+    
+    # Apply ordinal encoding (based on provided orders)
     sugar_mapping = {'No Sugar': 0, 'Low Sugar': 1, 'Regular': 2}
     size_mapping = {'Small': 0, 'Medium': 1, 'High': 2}
     city_mapping = {'Tier 3': 0, 'Tier 2': 1, 'Tier 1': 2}
-
+    
     features_df['Product_Sugar_Content'] = features_df['Product_Sugar_Content'].map(sugar_mapping)
     features_df['Store_Size'] = features_df['Store_Size'].map(size_mapping)
     features_df['Store_Location_City_Type'] = features_df['Store_Location_City_Type'].map(city_mapping)
+    
+    # Make prediction (assuming direct sales prediction; adjust if log-transformed)
+    predicted_sales = model.predict(features_df)[0]
+    
+    # If your model predicts log(sales), uncomment and use this instead:
+    # predicted_log_sales = model.predict(features_df)[0]
+    # predicted_sales = np.exp(predicted_log_sales)
+    
+    # Convert to Python float and round to 2 decimals
+    predicted_sales = round(float(predicted_sales), 2)
+    
+    # Return the predicted sales total
+    return jsonify({'Predicted Sales Total (in dollars)': predicted_sales})
 
-    # Option 1: Predict locally (if model is loaded)
-    # predicted_sales = model.predict(features_df)[0]
-    # predicted_sales = round(float(predicted_sales), 2)  # Or np.exp if log-transformed
-
-    # Option 2: Call the backend Flask API (recommended if backend is hosted separately)
-    # Replace with your actual backend URL (e.g., from Hugging Face Space)
-    backend_url = "https://Hugo014/TotalSalesPredictionBackend.hf.space/v1/sales"  # Update with real URL
-    try:
-        response = requests.post(backend_url, json=sample)
-        if response.status_code == 200:
-            result = response.json()
-            predicted_sales = result['Predicted Sales Total (in dollars)']
-        else:
-            st.error(f"Backend error: {response.status_code} - {response.text}")
-            predicted_sales = None
-    except Exception as e:
-        st.error(f"Error calling backend: {str(e)}")
-        predicted_sales = None
-
-    if predicted_sales is not None:
-        st.write(f"The predicted sales total for the product is ${predicted_sales:.2f}.")
+# Run the app (for testing locally; remove or adjust for production)
+if __name__ == '__main__':
+    super_kart_api.run(debug=True)

requirements.txt

@@ -1,3 +1,11 @@
 pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==3.0.4
+joblib==1.5.1
+Werkzeug==3.1.3
+flask==3.1.1
+gunicorn==20.1.0
 requests==2.28.1
-streamlit==1.48.1
+uvicorn[standard]
+streamlit==1.43.2