Improve robustness of model classifier tests#4447
Merged
alejoe91 merged 6 commits intoSpikeInterface:mainfrom Mar 16, 2026
Merged
Improve robustness of model classifier tests#4447alejoe91 merged 6 commits intoSpikeInterface:mainfrom
alejoe91 merged 6 commits intoSpikeInterface:mainfrom
Conversation
chrishalcrow
added
curation
chrishalcrow
changed the title
alejoe91
reviewed
Mar 16, 2026
alejoe91
approved these changes
Mar 16, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Our model based curation tests are flakey, leading to annoying test failures (e.g. #4443).
This PR makes the tests more robust by training the curation model on data which should be easy to classify: ten good units and ten junk units.
EDIT: it's difficult to seed this fully, because of the hyperparameter search in the model training. I've run the tests 1000 times and they pass. At the very least, this is easier to make even more robust in the future if we keep having problems...