Skip to content
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.

Sign up for GitHub

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

Jump to bottom

update knn shapely score transformation #1127

Closed
jwmueller opened this issue May 23, 2024 · 0 comments · Fixed by #1142
Closed

update knn shapely score transformation #1127

jwmueller opened this issue May 23, 2024 · 0 comments · Fixed by #1142
Assignees
@elisno
Labels
next release Address by next version release

Comments

@jwmueller
Copy link
Member

jwmueller commented May 23, 2024 •
edited

to be: max(x, 0) , instead of the current transformation: 0.5*(x+1)

Needs property based testing. Test should fail if x is ever negative pre-transformation.

Also update the is_issue threshold to be <= 1e-6
@jwmueller jwmueller added the next release Address by next version release label May 25, 2024
elisno added a commit to elisno/cleanlab that referenced this issue Jun 12, 2024
@elisno
update knn shapely score transformation
721614b 
- Make the _knn_shapley_score function easily testable.
- Adjust hard-coded scores in tests to new transformation.
- Add new test class for property based test that asserts that the raw scores are never negative.

Resolves cleanlab#1127
@elisno elisno mentioned this issue Jun 12, 2024
Merged
elisno added a commit to elisno/cleanlab that referenced this issue Jun 18, 2024
@elisno
update knn shapely score computation
c1c90fb 
Fixes cleanlab#1127
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@elisno elisno

Labels
next release Address by next version release
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Update knn shapely score computation elisno/cleanlab
2 participants
@jwmueller @elisno