FIX RuntimeWarning division by zero in check_classifiers_one_label #19690
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
….com/mbatoul/scikit-learn into fix_test_check_classifiers_one_label
|
With only 1 class, scikit-learn/sklearn/discriminant_analysis.py Line 479 in 302106b Maybe we can do something like if self._max_components == 0:
self.explained_variance_ratio = np.empty((0,), dtype=S.dtype)
else:
self.explained_variance_ratio = ... |
|
Thank you for your help, @jeremiedbb! It makes total sense, I missed that I will work on it tonight. |
…n max components is zero
lorentzenchr
approved these changes
Mar 16, 2021
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Outdated suggestions cannot be applied.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
See issue #19334.
What does this implement/fix? Explain your changes.
The warning stems from the LDA's fit method. There is a division by zero in the
LinearDiscriminantAnalysis#_solve_svdmethod, when computing the explained variance ratio:self.explained_variance_ratio_ = (S**2 / np.sum(S**2))[:self._max_components]. Here,Sis zero because it's the singular values vector of the zero matrixXgiven byX = np.dot(((np.sqrt((n_samples * self.priors_) * fac)) * (self.means_ - self.xbar_).T).T, scalings). Here, we haveself.means_ == self.xbar_because we are testing the LDA classifier with only one class (seey = np.ones(10)).Any other comments?
I am still trying to figure out the right way to solve this problem.