-
Notifications
You must be signed in to change notification settings - Fork 264
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
support multilabel confusion matrix #533
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, added a few small comments!
closing ticks for the code block adding config_name to load
adding config_name="multilabel" to load
formatting file
There was a problem with file formatting, I reformatted it and comitted the new code |
There's an error in tests, I can't understand it, it seems to be unrelated with the code 😅 sorry for inconvenience |
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.
Overall LGTM, but I wonder if it should be a separate metric to keep 1:1 mapping to sklearn
fixing error in test Co-authored-by: Omar Sanseviero <[email protected]>
I'm not sure 100% what is the optimal way, but I think the main idea behind evaluate is to be an abstraction. anyway, if you think if it's better to be in a seperate module I can do it. thank you |
@osanseviero will you accept the request? I've done the suggested edites |
thanks for rerunning the workflow, but I don't understand what's the problem 😬 |
adding `array()` in 2nd example
I fixed the problem in docstring example that causes unit test failure, can you run the test and merge please? @lvwerra |
using sklearn
multilabel_confusion_matrix
sample usage:
output: