Machine Learning in Production with Python | Feature Engineering & Model Training

Increasingly, a machine learning project is only complete once your code goes into production as part of a data product. To achieve this, you need to think about how to write code that will be robust and performant. These software development techniques are becoming essential skills for machine learning engineers.
In this session, Michelle Conway, Lead Data Scientist at Lloyds Banking Group, will walk you through a simple machine learning example on banking data, including feature engineering, training a model, making predictions, and assessing model performance. Next, you'll see how to adjust the code to make it suitable for use in production.
Key Takeaways:
- Learn about machine learning workflows in Python.
- Learn about the challenges of putting machine learning code into production.
- Learn how to engineer your machine learning code for production.
Resources: bit.ly/3VQO8Cw

[@Nick-yd3rc]

Nice intro, quite appreciated😊 Still, does adding a couple unit tests really make a notebook production ready? It would be great to actually cover some of notorious aspects of models in production environments. In my books, this is just an ordinary dev-time, ad hoc workflow. Looking forward to a follow-up hands-on deploying this to production, if possible.