Upload folder using huggingface_hub

Dockerfile

@@ -6,11 +6,8 @@ WORKDIR /app
 # Copy all files from the current directory to the container's working directory
 COPY . .
 
-# Install dependencies from the requirements file without using cache to reduce image size
+# Install dependencies
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-# 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`)
+# Start with Gunicorn
 CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:super_kart_api"]

app.py

@@ -1,14 +1,13 @@
-# 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
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
 
 # Initialize the Flask application
 super_kart_api = Flask("Super Kart Price Predictor")
 
-# Load the trained machine learning model (updated path to match deployment structure)
-model_path = "super_kart_model_v1_0.joblib"
+# Load the trained machine learning model
+model_path = "backend_files/super_kart_model_v1_0.joblib"
 try:
     model = joblib.load(model_path)
     print(f"Model loaded successfully from {model_path}")
@@ -36,7 +35,6 @@ def predict_sales():
     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': input_data['Product_Weight'],
         'Product_Sugar_Content': input_data['Product_Sugar_Content'],
@@ -48,13 +46,14 @@ def predict_sales():
         'Store_Location_City_Type': input_data['Store_Location_City_Type'],
         'Store_Type': input_data['Store_Type']
     }
-    # Convert the extracted data into a Pandas DataFrame
+    
+    # Convert to DataFrame
     features_df = pd.DataFrame([sample])
     
-    # Apply one-hot encoding for nominal columns (matching training)
+    # Apply one-hot encoding
     features_df = pd.get_dummies(features_df, columns=['Product_Type', 'Store_Type'], drop_first=True)
     
-    # Apply ordinal encoding (based on provided orders)
+    # Apply ordinal encoding
     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}
@@ -63,19 +62,96 @@ def predict_sales():
     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)
+    # Make prediction
     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})
 
-# Run the app (for testing locally; remove or adjust for production)
+# Run the app (for testing locally)
 if __name__ == '__main__':
     super_kart_api.run(debug=True)
+
+# %%writefile backend_files/app.py
+# # 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
+
+# # Initialize the Flask application
+# super_kart_api = Flask("Super Kart Price Predictor")
+
+# # 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.")
+
+# # 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!"
+
+# # 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': 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 the extracted data into a Pandas DataFrame
+#     features_df = pd.DataFrame([sample])
+    
+#     # 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 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})
+
+# # Run the app (for testing locally; remove or adjust for production)
+# if __name__ == '__main__':
+#     super_kart_api.run(debug=True)

requirements.txt

@@ -7,5 +7,3 @@ Werkzeug==3.1.3
 flask==3.1.1
 gunicorn==20.1.0
 requests==2.28.1
-uvicorn[standard]
-streamlit==1.43.2