Anime Recommendation System

Overview

This repository contains the Anime Recommendation System, an AI-powered web application that provides personalized anime recommendations based on user preferences. The system is built using Jenkins for CI/CD, DVC for data versioning, Docker for containerization, and Kubernetes for deployment.

Features

• Hybrid Recommendation Model that combines user preferences and content-based methods to recommend anime.
• Web Application built with Flask.
• CI/CD Pipeline for automated deployment using Jenkins.
• Data Version Control (DVC) to manage datasets efficiently.
• Containerized Deployment using Docker and Kubernetes.
• Google Cloud Platform (GCP) for hosting and orchestration.

Project Architecture

1. Version Control & Data Management
   • Code hosted on GitHub.
   • DVC used to manage datasets and model artifacts.
2. CI/CD Pipeline
   • Jenkins automates testing, building, and deployment.
   • Docker builds an application container.
   • Google Container Registry (GCR) stores the container image.
   • Kubernetes deploys and manages the application.
3. Deployment
   • Kubernetes cluster on GCP for scaling and reliability.

Getting Started

Prerequisites

Ensure you have the following installed:

• Python 3.8+
• Docker
• Kubernetes & kubectl
• Google Cloud SDK
• Jenkins
• DVC

Setup Instructions

1. Clone the Repository

 git clone https://github.com/anirudh6415/anime_recommendation_system.git
 cd anime_recommendation_system

2. Setup Virtual Environment & Install Dependencies

 python -m venv venv
 source venv/bin/activate  # On Windows use: venv\Scripts\activate
 pip install --upgrade pip
 pip install -e .

3. Configure DVC & Pull Data

 dvc pull

4. Run the Web Application

 python application.py

The web app should now be accessible at http://localhost:5000.

CI/CD Pipeline

This repository includes a Jenkins pipeline that automates the deployment:

1. Clone repository from GitHub.
2. Setup virtual environment and install dependencies.
3. Pull datasets and models using DVC.
4. Build & push Docker image to GCR.
5. Deploy application to Kubernetes.

Deployment

To manually deploy using Kubernetes:

 kubectl apply -f deployment.yaml

Contributing

Feel free to contribute by submitting a pull request or opening an issue!

License

This project is licensed under the MIT License.