This repo contains the scenario notebooks and pipelines. Content is arranged as follows:
- 1-data_exploration Used by students to explore and process the dataset, and to setup the feature store.
- 2-dev_datascience Used by students to build a simple model to explore inference on the dataset.
- 3-prod_datascience Used by students to build production ready processes and workflows for continuous training, validation, and inference.
- 99-data_prep Used for pre-preparation of the raw data. Not used in delivery of the lab but can be used by instructor prior to running the lab to refresh the dataset.