Quick Example of ML pipeline with dbt-python and Github Actions
This is a quick overview of taking a basic #ML pipeline using #dbt-python and #Snowflake and adding a quick #CI test with #Github-Actions.
Note:
This is a toy example (as always)
I've done nothing around model performance, fairness, drift, etc, e.g., the actual hard stuff in ML
But if you're a data scientist who thinks "hey, if I adopted more software engineering practices I might get more models deployed", this should help build some intuition around basic concepts (and we're very thankful that these types of people reach out to us Continual)
Also, given that dbt-python uses #snowpark to run all of the compute in Snowflake, the default Github Actions compute instance works really well (because I don't need lots of storage and compute on the CI/CD server as everything is just happening in Snowflake). This is at least as feasible as spinning up huge K8s cluster to handle all your ML training/inferencing (and much easier).
Watch video Quick Example of ML pipeline with dbt-python and Github Actions online without registration, duration hours minute second in high quality. This video was added by user Gus Cavanaugh 02 November 2022, don't forget to share it with your friends and acquaintances, it has been viewed on our site 698 once and liked it 11 people.