Skip to content

Fix kappa #1047

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

Merged
merged 5 commits into from
Feb 11, 2020
Merged

Fix kappa #1047

merged 5 commits into from
Feb 11, 2020

Conversation

AakashKumarNain
Copy link
Member

This PR fixes the problems mentioned in #906

Highlights:

  1. Works with/without keras model.
  2. Can handle sparse labels for multi-class classification.
  3. Can handle the cases where user want to treat the problem as a regression problem

@googlebot
Copy link

We found a Contributor License Agreement for you (the sender of this pull request), but were unable to find agreements for all the commit author(s) or Co-authors. If you authored these, maybe you used a different email address in the git commits than was used to sign the CLA (login here to double check)? If these were authored by someone else, then they will need to sign a CLA as well, and confirm that they're okay with these being contributed to Google.
In order to pass this check, please resolve this problem and then comment @googlebot I fixed it.. If the bot doesn't comment, it means it doesn't think anything has changed.

ℹ️ Googlers: Go here for more info.

@AakashKumarNain
Copy link
Member Author

@facaiy @seanpmorgan @WindQAQ This is the best I could think of to keep things as simple and clean as possible. But if you feel we need to change something, I am open to suggestions.

Copy link
Member

@seanpmorgan seanpmorgan left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mostly LGTM, one edge case I would like to see tested.

As a side note thank you very much for the comprehensive RFC. It made following the issue substantially easier.

@AakashKumarNain
Copy link
Member Author

Thanks @seanpmorgan for the feedback. I have renamed that variable and added more tests to cover all the cases.

Copy link
Member

@seanpmorgan seanpmorgan left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Very nice fix thanks again! LGTM

@seanpmorgan seanpmorgan merged commit 83df531 into tensorflow:master Feb 11, 2020
@seanpmorgan
Copy link
Member

We'll add this to 0.8.2 patch release

@AakashKumarNain
Copy link
Member Author

Cool. Thanks for the valuable feedback

seanpmorgan pushed a commit to seanpmorgan/addons that referenced this pull request Feb 12, 2020
* fix kappa
* add more tests and rename regression variable
* add cross_entropy test for binary class model

(cherry picked from commit 83df531)
@seanpmorgan seanpmorgan mentioned this pull request Feb 12, 2020
gabrieldemarmiesse pushed a commit that referenced this pull request Feb 12, 2020
* Fix kappa (#1047)

* fix kappa
* add more tests and rename regression variable
* add cross_entropy test for binary class model

(cherry picked from commit 83df531)

* Typo in type #1067 (#1069)
(cherry picked from commit 99352d0)

* Bump to 0.8.2

* Add CI to release branches

Co-authored-by: Aakash Kumar Nain <[email protected]>
Co-authored-by: failure-to-thrive <[email protected]>
jrruijli pushed a commit to jrruijli/addons that referenced this pull request Dec 23, 2020
* fix kappa
* add more tests and rename regression variable
* add cross_entropy test for binary class model
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants