8000 Test sample_weight in common tests · Issue #5367 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]

Skip to content

Test sample_weight in common tests #5367

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

Closed
arjoly opened this issue Oct 8, 2015 · 7 comments
Closed

Test sample_weight in common tests #5367

arjoly opened this issue Oct 8, 2015 · 7 comments

Comments

@arjoly
Copy link
Member
arjoly commented Oct 8, 2015

As discuss in #2752, it would be nice to test sample weight in common tests.

@MechCoder
Copy link
Member

Wasn't there an issue for this to refactor common tests? I remember someone proposing to refactor warm_start etc under common tests.

@arjoly
Copy link
Member Author
arjoly commented Oct 8, 2015

If it's already somewhere, please close this issue.

@amueller
Copy link
Member
amueller commented Oct 9, 2015

Not that I remember.

@eickenberg
Copy link
Contributor

@MechCoder thanks for making the link to #5444 - I had only heard talk about this being something that needs doing. Hadn't seen the issue. A PR is open, but running into difficulties because general assumptions on effect of sample weights turned out to be pretty weak.

@giorgiop
Copy link
Contributor

+1 to this. See #5526

@cmarmo
Copy link
Contributor
cmarmo commented Dec 9, 2021

Following the thread of the various PRs mentioned here I think this issue can be closed as commented here. Feel free to reopen if this is not the case. (@rth, @amueller)

@cmarmo cmarmo closed this as completed Dec 9, 2021
@ogrisel
Copy link
Member
ogrisel commented Dec 9, 2021

Thanks for the cleanup @cmarmo. Indeed, @rth's #17176 implements 2 kinds of sample weight invariance checks that are run as part of the common test suite.

We could extend this to testing the semantics that multiplying the weigth of some samples by 2.0 is equivalent to duplicating those samples. But this can be tracked in #15657 instead.

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

No branches or pull requests

7 participants
0