FIX Make cross-validation figures less inexact #765
Merged
+110
−52
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
|
Could we order the label into: 1. training, 2. validation (reserved for hyperparameters evaluation), 3. testing (reserved for final or ... evaluation). |
Validation sets are not reserved, but actually used in the given cv iteration. In such case there is no big advantage on factorizing the legend labels as 1., 2. and 3. |
glemaitre
approved these changes
May 17, 2024
github-actions bot
pushed a commit
that referenced
this pull request
May 17, 2024
Co-authored-by: ArturoAmorQ <[email protected]> 9a9e74f
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Outdated suggestions cannot be applied.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.
Some people has mentioned in RL that the figures on train-validation-test split and nested cross-validation may be misleading, as they can make the user think the testing samples are used for evaluation in each cv iteration.
Instead of remaking the figures, this PR proposes a more conservative (but still somewhat inexact) solution by changing the legend labels.Edit: This PR now does change the figures to better show the re-train process done by default by the grid search.
cc @lesteve and @tuscland