-
Notifications
You must be signed in to change notification settings - Fork 407
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
Add control features to metric plots #668
Comments
…766) With a slight delay (originally targeted for April) I'm finally removing the `FairlearnDashboard` since a newer version already exists in `raiwidgets`. The documentation is updated to instead use the plots @MiroDudik created with a single line directly from the `MetricFrame`. In the future we want to add more kinds of plots as already mentioned in #758 #666 and #668 . Specifically, the model comparison plots do not yet have a replacement yet. Note that the "example" added to the `examples` directory is not shown under "Example notebooks" on the webpage, which is intentional since it's technically not a notebook. This also makes #561 mostly redundant, which I'll close shortly. #667 is also directly addressed with this PR as the examples illustrate. Signed-off-by: Roman Lutz <rolutz@microsoft.com>
Hi @romanlutz, I would like to pick this up |
Sure thing, @bram49 ! To be quite honest, I'm not entirely sure where this will lead. You can play around with the samples we have in the documentation https://fairlearn.org/main/user_guide/assessment.html#plotting-grouped-metrics and see if there's a good way to showcase the control features. You can basically do the same thing with control features as with sensitive features since the |
Is your feature request related to a problem? Please describe.
The metric plotting functionality mentioned in the docs does not mention
control_features
Describe the solution you'd like
Add an example where
control_features
are used. In the same example we could useage
as a control feature. However, whenever #793 is completed we should switch to the synthetic dataset. After all, it's not ideal to use a real dataset for an abstract purpose of showing this functionality.Bonus
Ideally, a separator line between the control groups or a new line for each set of subgroups within a control group would be nice. Right now they're all treated as equal groups in the plots.
The text was updated successfully, but these errors were encountered: