Metrics fixes and cleanup #2325
Merged
Conversation
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
Balandat
approved these changes
Apr 22, 2023
Comment on lines
+130
to
+131
| def test_standardized_mean_squared_error(self): | ||
| self._test_metric(standardized_mean_squared_error) |
There was a problem hiding this comment.
Hmm this is a kind of interesting test in that it only executes the metric code, without really checking what the computation does. Not really in scope for this PR but this should probably do something more reasonable...
There was a problem hiding this comment.
Agreed. Treating this as out of scope for this PR for now, but created an issue for it: #2326 .
Co-authored-by: Max Balandat <[email protected]>
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Outdated suggestions cannot be applied.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.
In a Nutshell
This PR fixes the implementation of the mean standardized log loss to match its definition and adds some documentation.
Detailed
The mean standardized log loss as defined by Rasmussen and Williams (2006) compares the average log loss to a trivial model based off of the training data summary statistics. This standardization was missing in the implementation.
Further I added the standardized mean squared error to allow for better comparison across experiments.