Repository navigation
Add quantile-quantile plot to wandb custom charts - #539
Merged
Merged
Conversation
Contributor
Author
|
lm2612
marked this pull request as ready for review
August 17, 2026 12:29
lm2612
marked this pull request as draft
August 17, 2026 12:32
Contributor
Author
lm2612
marked this pull request as ready for review
August 18, 2026 14:04
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pull Request
Description
Addresses issue #538
It would be useful to compare p-levels as well as the median on W&B. We can do this using a quantile-quantile plot, which would show the target p-level on the x-axis against the fraction of validation data that falls below that p-level on the y-axis. The ideal model would line up along the y=x line.
To do this I have used the existing line plotting function that plots the MAE at different horizons. This involves storing the fraction of the validation data below each level in a wandb table. I've extended the function wandb_line_plot() to also include the option to show the identity line where y=x as a dashed line.
How Has This Been Tested?
The test run was extended to include quantile regression.
Checklist: