Roman Lutz

To merge this we'll also need a few tests, e.g., building on https://github.com/fairlearn/fairlearn/blob/1247b081b5cbdf9373595b7e4627c142ae30ae44/test/unit/metrics/test_disparities.py

@IanEisenberg are you still planning to get back to this? Please feel free to say so. If not, someone else may be interested in continuing the pull request. I'm going...

Welcome @wcheung-code ! This is very exciting and I'm glad to see this topic finally approached in Fairlearn. Regarding the datasets: if you can find them on the internet I...

Thanks for the comprehensive update @wcheung-code ! I see a few challenges here that we need to think about: - Will this be integrated into the website? Assuming the answer...

@kstohr thanks for patiently working through the comments 🙂 In terms of mitigation I would suggest restricting this PR to generating the ROC curves. It will keep growing in scope...

@kstohr do you want to revisit this and perhaps set up some time to talk about testing as we had planned a while back?

> @kstohr do you want to revisit this and perhaps set up some time to talk about testing as we had planned a while back? Ping @kstohr 🙂 I suppose...

I'm not terribly opinionated on this issue, but if we move to something like `MetricFrame(*, metrics, sensitive_features, control_features, sample_params, **shared_sample_params)` then we better have extremely good documentation. Reading this in...

I feel like this discussion could benefit from some concrete examples. Like @riedgar-ms (and @hildeweerts I think) I'm currently struggling to see the benefit of complicating the currently very intuitive...

@MiroDudik we are already on up-for-grabs! I added us there a long time ago: https://github.com/up-for-grabs/up-for-grabs.net/blob/gh-pages/_data/projects/Fairlearn.yml