search

alan-turing-institute / learning-machines-drift

A Python package for monitoring dataset drift in secure environments
4 stars 2 forks source link

Capturing model explainability, predictions and uncertainty within monitor #18

Closed sgreenbury closed 2 years ago

sgreenbury commented 2 years ago

Consider how to capture model meta-features (like feature importances) as part of the monitor.

sgreenbury commented 2 years ago

Update hypothesis_tests.py to also run single-feature tests on labels and latents.

sgreenbury commented 2 years ago

Closes with #21. New issue for future work with more latents and other feature types.