Roman Lutz
Roman Lutz
@MiroDudik this sounds like a question for you.
I agree with @MiroDudik on replacing clone with deepcopy, but curious what @adrinjalali thinks as well. Adding a bit to what @MiroDudik wrote regarding the code. Perhaps we can resolve...
It's great feedback, thanks for being so responsive and providing a sample that is easy to reproduce. @fairlearn/fairlearn-maintainers this is a good reminder to make our requirements of estimators more...
@yavuzs of course. Let us know if you questions!
Yes, go ahead!
> Are there any reasonable plots you generate for the relaxed version? Answering my own question here: I saw the relaxation plot (below on the right side) in the paper....
> Regarding the plot, I can add that exact plotting function from Figure 9 as implemented [here](https://github.com/socialfoundations/error-parity/blob/main/error_parity/threshold_optimizer.py#L387). > > For now, I wanted to get the core working and ready...
@fairlearn/fairlearn-maintainers does anyone feel like there's a required follow-up on this? @riedgar-ms outlined a pretty comprehensive set of things that the docs for `MetricFrame` should include and I believe it...
Thanks, @afsilva, for opening this issue. We're aware that PyRIT currently supports only Python 3.10 and will add support for newer versions in the near future. I'll update when I...
This has partially been addressed through #241 #364 #424 and #443 but could use a little more work to make it intuitive what these functions actually do.