Skip to content

Conversation

betatim
Copy link

@betatim betatim commented Aug 29, 2025

What does this PR do?

This picks up #2347, which modifies _reduce_dimensionality to use fit_transform when possible. This makes it possible to use nearest neighbor descent with cuML UMAP.

Fixes #2335

Before submitting

  • This PR fixes a typo or improves the docs (if yes, ignore all other checks!).
  • Did you read the contributor guideline?
  • Was this discussed/approved via a Github issue? Please add a link to it if that's the case.
  • Did you write any new necessary tests?

jemather and others added 10 commits April 28, 2025 16:22
Modifying _reduce_dimensionality to use fit_transform, per MaartenGr#2335
trying to diagnose what the other potential error is besides a TypeError that needs to be caught
trying another condition
ensuring fit_transform is available
Remove testing for whether topic_representations_ has been modified - not clear why this is needed here, and creates an unhandled case when using partial_fit
fixing lint whitespace issue
Addressing comments raised by @MaartenGr
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Adding support for cuML's nn-descent with UMAP
2 participants