-
-
Notifications
You must be signed in to change notification settings - Fork 25.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[WIP] Allow TruncatedSVD using randomized to automatically reset k < n_features. #17949
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the PR @zachmayer
If we want to raise warnings instead of errors I think we should do it for all transformers that have a n_components
attribute. Also I'm not sure we need a new warning class, a UserWarning should be enough.
Also please update the PR title to something more descriptive ;) |
What's [MRG] mean? What other transformers have a |
WIP = work in progress For transformers, you can check |
Right right, I keep forgetting about git grep
Should I focus on the ones in decomposition? |
I got a buncha tests to fix too |
This is a better list of files:
|
So I am going to change the following files to reset
I'll also update tests for all those classes. Do you think those changes will be ok with all the other sklearn maintainers? One of those files ( Or is |
@NicolasHug Do you think the changes I proposed above will be ok with all the other sklearn maintainers? |
Reference Issues/PRs
Fixes #17916
What does this implement/fix? Explain your changes.
Allows TruncatedSVD using the randomized algorithm to automatically reset k < n_features.
Any other comments?