2024-10-25 –, Workshop Class #1
Language: English
One of the challenges for a machine learning project is to deploy it. Fast API provides a fast and easy way to deploy a prototype with less software development expertise and yet allow it to be developed into a professional web service. We will look at how to do it.
In this workshop, we will go deeper into how to prototype a machine-learning project with Fast API. Fast API allows the creation API server with very little effort, it is easy to deploy a pre-trained model, but for models that require re-training, the challenge of when and how to retrain a model and update for a service in use becomes complicated. We will cover the aspect of delivering a pre-trained model and the design of re-training the model. This workshop will also provide suggestions for deploying the machine learning project so it can migrate from a prototype to a functional service in production.
Goal
The workshop aims to equip a data science team capability to convert their machine learning project into a prototype service using Fast API, at the end of the workshop, they will not just be able to deliver API calls to a pre-trained model, but they will also be able to design when to re-train and update the model and be ready to migrate the prototype into production.
Target audience
Data scientists who have little or no experience using Fast API or putting a machine learning model into production. This workshop will assume the audience already knows how to build and train a basic machine learning model (e.g. using Sci-kit learn).
Prerequisite
This workshop assumes that you have experience code in Python and have knowledge using some of the data science and machine learning libraries such as pandas, Scikit-learn and Keras. Details explaining the usage of those libraries will be skipped in this workshop
Preflight check
Please make sure you are using Python 3.12, this is the Python version that we will be using. You may try using other versions of Python but we will not guarantee all exercises will work the same.
If you want to complete part 3 of the workshop, you will need to be able to deploy docker containers locally.
Installation
Requirements are in the file requirements.txt here, we recommend using uv to create a new environment and install dependencies.
We also recommend installing Docker Desktop for part 3 of the workshop.
Outline
Part 1 - Introduction to Fast APi and prediction on demand (25 mins)
- Understand the basics of Fast API (5 mins)
- Using a pre-trained model for prediction with API calls (10 mins)
- Validating the query parameters (10 mins)
Part 2 - Re-train and update models (55 mins)
- Background tasks (15 mins)
- Lifespan events (15 mins)
- Re-training with new data with Fast API (15 mins)
- Problem with updating model: Race conditions (10 mins)
Part 3 - Machine learning model in production (10 mins)
- Fast API in docker containers (10 mins)
After having a career in Data Scientist and Developer Relations, Cheuk dedicated her work to the open-source community and founded CMD Limes, a Python consultants cooperation. She has also co-founded Humble Data, a beginner Python workshop that has been happening around the world. She has served the EuroPython Society board for two years and is now a fellow and director of the Python Software Foundation.