🚀 Grocery Recommendation System

A system that recommends groceries by identifying related products based on user input and preferences.

Check it out live : grocerypicks.onrender.com

📌 Project Highlights

• Product Recommendation: Developed a machine learning model using Apriori algorithm to suggest products based on customers' purchase histories.

• API Development with Django: Built an API with Django, enabling smooth integration and user-friendly access to the recommendation system.

• Unit Testing & Linting: Implemented unit tests to validate functionality and used Flake8 for effective code linting.

• Containerized Application: Containerized the application using Docker to ensure consistent deployment and performance across multiple environments.

• Automated CI/CD Pipeline: Configured GitHub Actions to automate the integration and deployment processes to maintain code quality and project integrity.

• Efficient Deployment Configuration: Deployed using Gunicorn for performance and Whitenoise for efficient static file handling.

• Live on Render: Successfully deployed the application on Render for easy access and scalability.

🔧 Tech Stack

• 
• 
• 
• 
• 
• 
• 

⚡🧠️ Machine Learning Model Link

github.com/SA-K1B/Grocery_recommendation_model

⚙️ Installation with Docker

1. Clone the repo

   git clone https://github.com/SA-K1B/Django_Grocery_recommendation.git

2. Build Image

   docker compose up --build

⚙️ Installation without Docker

1. Set up a virtual environment

   python -m venv myenv

2. Activate the virtual environment

   On macOS/Linux

   source myenv/bin/activate

   On windows

   myenv\Scripts\activate

3. Upgrade pip

    python -m pip install --upgrade pip

4. Install the required packages

   pip install -r requirements.txt

5. Run database migration

   python manage.py migrate
   

6. Collect static files

   python manage.py collectstatic --noinput

7. Run the development server

   python manage.py runserver

Now, a HTTP server will start up, listening on port 8000. You will see the app running at https://localhost:8000.

🔄 CI/CD Workflow

• Every push triggers automated unit tests to validate functionality.

• Flake8 performs code linting to ensure coding standards.

• The application is built into a Docker container for consistent deployment and pushed to Docker Hub.

• The application is hosted on Render, deployed from Docker Hub.

WhiteNoise: Serving Static Files Efficiently

A Python package for serving static files directly from web application. While Django includes built-in support for handling static files, it's mainly designed for development purposes and is not optimal for use in production environments.

Gunicorn: Efficient Application Server

Gunicorn is a WSGI compliant web server for Python Applications that receives requests sent to the Web Server from a Client and forwards them onto the Python applications or Web Frameworks.