[MRG+2] median_absolute_error multioutput #14732
Conversation
|
Not sure why Azure pipeline tests fail |
|
Regarding the failure, you need to add |
|
Thanks @glemaitre . Any thoughts regarding |
|
I would say to implement it in another PR. I am also not sure how to apply some weight during the computation of the median such that it is meaningful. You would need to sort |
|
Conflicts with master resolved. Any willing reviewers? :) |
|
ping @rth @jeremiedbb |
sklearn/metrics/regression.py
Outdated
| if y_type == 'continuous-multioutput': | ||
| raise ValueError("Multioutput not supported in median_absolute_error") | ||
| return np.median(np.abs(y_pred - y_true)) | ||
| _, y_true, y_pred, _ = _check_reg_targets(y_true, y_pred, None) |
There was a problem hiding this comment.
We need to pass multioutput
this should be y_type, y_true, y_pred, multioutput = _check_reg_targets(y_true, y_pred, multioutput)
There was a problem hiding this comment.
Well spotted.
Fixed.
sklearn/metrics/regression.py
Outdated
| if y_type == 'continuous-multioutput': | ||
| raise ValueError("Multioutput not supported in median_absolute_error") | ||
| return np.median(np.abs(y_pred - y_true)) | ||
| _, y_true, y_pred, _ = _check_reg_targets(y_true, y_pred, multioutput) |
There was a problem hiding this comment.
Let's use y_type, y_true, y_pred, multioutput = _check_reg_targets(y_true, y_pred, multioutput) here. This will be more consistent. (Actually since we call check_array in _check_reg_targets, multioutput will sometimes be modified.)
There was a problem hiding this comment.
Good point, thanks. Now fixed.
|
Let's merge then. Thanks @agamemnonc!!! |
Reference Issues/PRs
Closes #14728.
What does this implement/fix? Explain your changes.
Implements
multioutputformedian_absolute_error.Any other comments?
Shall we also include support for
sample_weightin this PR? See also #6217.