Update R2 score to handle single sample computation #2235
Merged
Conversation
This file contains 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
arnavgarg1
changed the title
justinxzhao
reviewed
Jul 6, 2022
tgaddair
approved these changes
Jul 6, 2022
justinxzhao
approved these changes
Jul 6, 2022
arnavgarg1
added a commit
that referenced
this pull request
Aug 2, 2022
* Update R2 scores to handle single sample computation
arnavgarg1
added a commit
that referenced
this pull request
Aug 2, 2022
* Update R2 scores to handle single sample computation
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Outdated suggestions cannot be applied.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.
One of the users in Ludwig's OSS reported an issue with R2 computation in v0.5 where R2 scores can't be computed if the sample size during prediction is just 1 row. The error
torchmetricsreturns is logically correct because R2 scores can't be calculated for just one sample.This PR updates the implementation of R2 to return
NaNwhen one sample is used for R2 computation and logs a user-facing warning to use two or more samples for non NaN R2 score calculation.