A production-grade machine learning system for predicting house prices using MLflow and ZenML. This project implements various design patterns and best practices for building maintainable and scalable ML pipelines.

• 🏗️ End-to-end ML pipeline implementation
• 📊 Comprehensive data analysis tools
• 🔍 Advanced feature engineering
• 🤖 Model training and evaluation
• 📈 MLflow experiment tracking
• 🚀 Model deployment with MLflow
• ♻️ Continuous deployment pipeline
• 🔄 Real-time inference capabilities

The project follows a modular architecture with clear separation of concerns:

• Data Analysis: Includes univariate, bivariate, and multivariate analysis tools
• Feature Engineering: Implements various transformation strategies
• Model Pipeline: Handles training, evaluation, and deployment
• Deployment: Continuous deployment with MLflow integration

• Python 3.8+
• MLflow
• ZenML
• Required Python packages (see requirements.txt)

1. Clone the repository:

git clone https://github.com/yourusername/properchy.git
cd properchy

2. Create and activate a virtual environment:

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

3. Install dependencies:

pip install -r requirements.txt

To run the training pipeline:

python run_pipeline.py

To deploy the model:

python run_deployment.py

To stop the deployment service:

python run_deployment.py --stop-service

Use the sample prediction script:

python sample_predict.py

properchy/
├── analysis/
│   └── analysis_src/           # Analysis tools
├── pipelines/                  # ML pipeline definitions
├── src/                       # Core source code
├── steps/                     # Pipeline steps
├── data/                      # Data directory
├── requirements.txt           # Project dependencies
└── README.md                 # Project documentation

• Basic Data Inspection
• Univariate Analysis
• Bivariate Analysis
• Multivariate Analysis
• Missing Values Analysis

• Log Transformation
• Standard Scaling
• Min-Max Scaling
• One-Hot Encoding

• Data Ingestion
• Missing Value Handling
• Feature Engineering
• Outlier Detection
• Model Training
• Model Evaluation
• Model Deployment

The project uses configuration files for various settings:

• .zen/config.yaml: ZenML configuration
• config.yaml: Model and pipeline configuration

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

• MLflow for experiment tracking and model deployment
• ZenML for pipeline management
• Scikit-learn for machine learning implementations