Learn the best practices to bring your machine learning models into production
This practical 2-day training prepares you to bring your machine learning models into production by using best practices. For example, you will learn how software engineers manage their code and the advanced Python features that can make your life easier. You will also learn how to go from notebooks to packages, and much more.
This training is for you if…
- You want to move your code from an experimental Jupyter notebook to a mature Python package.
- You want to enhance the quality of your code and apply the current industry-standard tooling.
- You want to be able to collaborate better on projects with your colleagues.
This training is not for you if…
- You are comfortable just experimenting in Jupyter notebooks and not interested in evolving your projects so they can bring value to the organisation.
- You are looking to enhance your machine learning knowledge (check out the Advanced Data Science with Python training instead).
- You want to go in-depth about data pipelines or deploying on specific cloud environments.
Clients we've helped
What you'll learn
- Python version management, package managers, and virtual environments.
- Characteristics of high-quality and maintainable code.
- Automatic linting and code formatting with black, flake8, isort
- Ensure quality checks on every commit with pre-commit
- Type hinting and type checking with mypy.
Quality Python packaging
- What to test in a data science project with pytest.
- Effective logging and monitoring with logging.
- Build beautiful documentation with Sphinx and MyST.
- Create a command-line interface to your package with typer.
- Build an API with the modern, fast high-performance web-framework FastAPI.
- What makes a project ‘production-ready’?
- From notebook to Python package.
- How to enhance the quality and robustness of your code.
- OOP in Python.
- Iterators, generators, decorators, and other advanced features.
- Design patterns and anti-patterns.
- Using documentation as code to keep your documentation and code synchronised.
- How to set up logging and testing for your package.
- Build interfaces to serve your code as a CLI or as a RESTful API.
After the training you will be able to:
- Create a high-quality Python package for your machine learning project that is easy to share, collaborate on, and deploy.
- Write robust Python code that is easy to extend, debug, monitor and test.
- Understand the importance of and what it means for a project to be production-ready.
- Serve your models with an API or command-line interface.
Data Science Learning Journey
Julian de RuiterMachine learning engineer
Structured, to-the-point, good combination of theory and practical examples, very knowledgeable trainer who can explain concepts very well
It was a hands-on and tangible course. We could apply what we learned in a matter of minutes. The trainer did a great job of answering ad-hoc questions that complemented the material. We appreciated the fact that we could apply what we were taught directly to our company.
I liked every aspect of this training and would like to thank the trainers. They did an excellent job of explaining how to use Spark for data science. This is the fourth GoDataDriven training I’ve followed. All were great, but this was the best one so far.
Climbing a steep Python and Machine Learning curve in three days. This would have taken me months on my own.