-
-
Notifications
You must be signed in to change notification settings - Fork 26k
[MRG] MAINT sync/add support sample_weight with liblinear #15038
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
[MRG] MAINT sync/add support sample_weight with liblinear #15038
Conversation
@amueller you might want to have a look at that |
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.
Not a complete review, but looks pretty good.
@adrinjalali any other comments? |
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.
I can confirm the tests fail in master...
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.
nits, otherwise, as far as I can tell, this looks good.
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.
I've checked the C code looks reasonably safe.... and that the tests are valid... I'd do better to compare to upstream, but I'm okay to see this merged.
Just realized this kinda needs a whats_new entry. |
Co-Authored-By: Nicolas Hug <contact@nicolas-hug.com>
Thanks @glemaitre ! |
Sweet! |
Is this functionality in any of the stable sklearn releases? What should I upgrade to? |
Not yet. The new release should be out this week |
Also, would anyone be keen on updating the old docs to mention the fact that |
Since this is a bug, it would be better to backport the fix. But we will probably release tomorrow, not sure that it would be worth. |
With the latest release of sklearn, we have merged scikit-learn#15038 which officially adds support for sample weights to these models. Let's update the docs to reflect this.
With the latest release of sklearn, we have merged scikit-learn#15038 which officially adds support for sample weights to these models. Let's update the docs to reflect this.
Add support for
sample_weight
for the loss/penalty in liblinear.Hopefully it will close:
closes #10873
closes #15018