[BUG] Fix residual scale estimation in DoubleResidual #503
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
…dd a warning for t dist df<3 trafo=squared, where we observe poor performance.
…n base and residual.
fkiraly
reviewed
Dec 10, 2024
There was a problem hiding this comment.
Nice!
Would you like a review right now, or is this still a work-in-progress draft?
Some comments:
- we should not change the core interface in the same pull request as changes to estimators. Your idea of adding a
sample_weightarg is great, but we should deal with this separately, to avoid interaction between the changes! - changes to the residual estimator look good and sensible. I will have to sit down and work out the math to check, but superficially fine.
fkiraly
reviewed
Dec 10, 2024
| @@ -72,7 +72,7 @@ def __rmul__(self, other): | |||
| else: | |||
| return NotImplemented | |||
|
|
|||
| def fit(self, X, y, C=None): | |||
| def fit(self, X, y, C=None, sample_weight=None): | |||
There was a problem hiding this comment.
as said, good idea, but should be in a separate PR. Could you also open an issue to track adding sample weights?
What we should do (please copy this recommendation in an issue):
- add a tag
capability:sample_weightthat tells the user whether the weights are used non-trivially - add tests in
TestAllRegressorsthat actually passes sample weights, to see that nothing breaks. In particular, nothing should break for any estimator when passed, the current boilerplate would lead to most estimators breaking, as the argument is passed on to_fit! - in particular, the boilerplate should check the tag, and pass
sample_weighton to_fitonly if the tag has valueTrue. - in the tests, we should check that
_fitdoes have the argsample_weightif the tag is setTrue.
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.
Reference Issues/PRs
Fixes #492
What does this implement/fix? Explain your changes.
Changes to ResidualDouble:
Does your contribution introduce a new dependency? If yes, which one?
no
What should a reviewer concentrate their feedback on?
Did you add any tests for the change?
Added tests to confirm uniform quantiles for held out data when the model is correctly specified.