Add "Absolute Average Fold Error" and "Balanced Average Precision" to the metrics

[zhu0619]

Changelogs

• Add metric Balanced average precision from sklearn
• Add metric Absolute Average Fold Error implementation from https://pubs.acs.org/doi/10.1021/acs.chemrestox.3c00305

---

Checklist:

• Add tests to cover the fixed bug(s) or the newly introduced feature(s) (if appropriate).
• Update the API documentation if a new function is added, or an existing one is deleted.
• Write concise and explanatory changelogs above.
• If possible, assign one of the following labels to the PR: feature, fix or test (or ask a maintainer to do it for you).

---

discussion related to that PR

[cwognum]

Thanks, @zhu0619

For this to be merged, there needs to be a similar PR on the Hub side as well that adds support for these new metrics. Is this something you would feel comfortable doing, @zhu0619 ? If not, I can look into it!

[cwognum]

Ah I see you created https://github.com/polaris-hub/polaris-hub/issues/317.

[cwognum]

Could we add some test cases? Especially for the multi-class one, this sounds like something that could fail.

[zhu0619]

Thanks, @zhu0619

For this to be merged, there needs to be a similar PR on the Hub side as well that adds support for these new metrics. Is this something you would feel comfortable doing, @zhu0619 ? If not, I can look into it!

I will do it.

[cwognum]

Hey @zhu0619 , this is probably a bigger change than you anticipated by now! Sorry. Think we're almost there! Let me know if you need help. Happy to jump in.

[cwognum]

Hey @zhu0619, I had one big question I would be curious to hear your thoughts on. Other than that, just some small comments.

[cwognum]

Thanks @zhu0619 ! This is turning into a nice feature that will make the metric system more flexible moving forward.

[cwognum]

Thanks, @zhu0619 ! Looks great!