House Price Prediction CI/CD Pipeline

Table of Contents

• Introduction
• CI/CD Pipeline Overview
• Branch Strategy
• Workflows
• API Documentation
• Installation
• Usage
• Docker Deployment
• Dependencies
• Contributing
• Contact

Introduction

This project is a machine learning-powered web application that predicts house prices using a RandomForest regression model. The project implements a comprehensive CI/CD pipeline using GitHub Actions, ensuring code quality, automated testing, and seamless deployment to Docker Hub.

CI/CD Pipeline Overview

Pipeline Architecture

The CI/CD pipeline follows a three-branch strategy with automated workflows:

┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│     dev     │───▶│    test     │───▶│    main     │───▶│ Docker Hub  │
│             │    │             │    │             │    │             │
│ Code Quality│    │ Unit Testing│    │ Deployment  │    │ Container   │
│ Check       │    │ Coverage    │    │ Email Alert │    │ Registry    │
└─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘

Branch Strategy

1. Development Branch (dev)

• Purpose: Feature development and initial code validation
• Triggers:
  • Code quality checks with flake8
  • Security scanning with bandit
  • PEP 8 compliance verification
• Protection: Requires admin approval for merges

2. Test Branch (test)

• Purpose: Comprehensive testing and validation
• Triggers:
  • Automated unit tests
  • Integration tests
  • Code coverage analysis
• Protection: Requires successful test completion

3. Main Branch (main)

• Purpose: Production-ready code
• Triggers:
  • Docker image build and push to Docker Hub
  • Email notifications to administrators
  • Security scanning of container images

Workflows

1. Code Quality Workflow (.github/workflows/code-quality.yml)

Trigger: Push to dev branch or PR to dev

Features:

• Python syntax validation
• flake8 linting with PEP 8 compliance
• Security vulnerability scanning with bandit
• Code complexity analysis

2. Testing Workflow (.github/workflows/testing.yml)

Trigger: Push to test branch or PR to test

Features:

• Comprehensive unit test execution
• Code coverage reporting
• API endpoint validation
• Flask application startup testing

3. Deployment Workflow (.github/workflows/deploy.yml)

Trigger: Push to main branch or merged PR to main

Features:

• Docker image building and optimization
• Multi-tag versioning (latest, branch, SHA)
• Push to Docker Hub registry
• Container security scanning
• Email notifications to administrators

API Documentation

The Flask application provides the following REST API endpoints:

Base URL: http://localhost:5000

1. Health Check

• Endpoint: GET /health
• Description: Check API status and model availability
• Response:

{
  "status": "healthy",
  "model_loaded": true
}

2. Model Information

• Endpoint: GET /model/info
• Description: Get trained model details
• Response:

{
  "model_type": "RandomForestRegressor",
  "features_count": 12,
  "status": "trained"
}

3. Feature Information

• Endpoint: GET /features
• Description: Get list of required input features
• Response:

{
  "features": ["area", "bedrooms", "bathrooms", ...],
  "numerical": ["area", "bedrooms", "bathrooms", ...],
  "categorical": ["mainroad", "guestroom", ...],
  "total_features": 12
}

4. Price Prediction

• Endpoint: POST /predict
• Description: Predict house price based on features
• Request Body:

{
  "features": {
    "area": 1500,
    "bedrooms": 3,
    "bathrooms": 2,
    "stories": 2,
    "mainroad": "yes",
    "guestroom": "no",
    "basement": "no",
    "hotwaterheating": "no",
    "airconditioning": "yes",
    "parking": 2,
    "prefarea": "yes",
    "furnishingstatus": "furnished"
  }
}

• Response:

{
  "prediction": 4500000.0,
  "status": "success"
}

5. Model Retraining

• Endpoint: POST /retrain
• Description: Retrain the model with current dataset
• Response:

{
  "status": "Model retrained successfully",
  "metrics": {
    "mae": 123.45,
    "mse": 456.78,
    "r2": 0.89,
    "r2_percentage": 89.0
  }
}

Installation

Local Development Setup

1. Clone the repository:

   git clone https://github.com/Rayyan9477/House-Price-Prediction-Model.git
   cd House-Price-Prediction-Model

2. Switch to development branch:

   git checkout dev

3. Create virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

4. Install dependencies:

   pip install -r requirements.txt

5. Run the application:

   python app.py

Testing Setup

1. Run unit tests:

   pytest tests/ -v

2. Run tests with coverage:

   pytest tests/ --cov=app --cov-report=html

Docker Deployment

Building Docker Image

docker build -t house-price-prediction .

Running Container

docker run -p 5000:5000 house-price-prediction

Using Docker Compose (Optional)

Create docker-compose.yml:

version: '3.8'
services:
  app:
    build: .
    ports:
      - "5000:5000"
    environment:
      - FLASK_ENV=production

Run with:

docker-compose up

Dependencies

Core Dependencies

• Flask 2.3.3: Web framework for API development
• pandas 2.0.3: Data manipulation and analysis
• numpy 1.24.3: Numerical computing
• scikit-learn 1.3.0: Machine learning algorithms
• matplotlib 3.7.2: Data visualization
• seaborn 0.12.2: Statistical data visualization

Development Dependencies

• pytest 7.4.0: Testing framework
• flake8 6.0.0: Code linting and style checking
• pytest-cov: Code coverage reporting

Contributing

Development Workflow

1. Fork the repository

2. Create feature branch from dev:

   git checkout dev
   git checkout -b feature/your-feature-name

3. Make changes and commit:

   git add .
   git commit -m "feat: add your feature description"

4. Push changes:

   git push origin feature/your-feature-name

5. Create Pull Request to dev branch

Pull Request Process

1. dev → test: Feature completion, triggers testing workflow
2. test → master: Testing success, triggers deployment workflow
3. Admin approval required for all merges

Code Standards

• Follow PEP 8 style guidelines
• Maintain code coverage above 80%
• Add unit tests for new features
• Update documentation for API changes

Required GitHub Secrets

Configure the following secrets in your GitHub repository:

Secret Name	Description	Example
DOCKER_HUB_USERNAME	Docker Hub username	rayyan9477
DOCKER_HUB_ACCESS_TOKEN	Docker Hub access token	dckr_pat_...
EMAIL_USERNAME	SMTP email username	[email protected]
EMAIL_PASSWORD	SMTP email app password	app-specific-password

Project Structure

House-Price-Prediction-Model/
├── .github/
│   └── workflows/
│       ├── code-quality.yml
│       ├── testing.yml
│       └── deploy.yml
├── tests/
│   ├── __init__.py
│   └── test_app.py
├── app.py                 # Flask application
├── House_dataset.csv      # Training dataset
├── requirements.txt       # Python dependencies
├── Dockerfile            # Container configuration
├── .dockerignore         # Docker ignore rules
├── Readme.md            # Project documentation
└── LICENSE              # License file

Video Demonstration

Watch the video demonstration of the project:

Click the link to watch demo.

Contact

• Email: [email protected]
• GitHub: Rayyan9477
• LinkedIn: Rayyan Ahmed

License

This project is licensed under the MIT License - see the LICENSE file for details.