Skip to content

MAINT: More logistic regression deselections due to numerical issues #2798

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
david-cortes-intel wants to merge 3 commits into
base: main
Choose a base branch
from
Open

MAINT: More logistic regression deselections due to numerical issues #2798

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0ba5f0f
more deselections due to numeric issues
david-cortes-intel Nov 25, 2025
e0eff6c
Merge branch 'main' into desel_logreg_tol
david-cortes-intel Nov 26, 2025
9a5e7b7
Merge branch 'main' into desel_logreg_tol
david-cortes-intel Nov 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions deselected_tests.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -376,6 +376,10 @@ deselected_tests:
- model_selection/tests/test_search.py::test_search_cv_sample_weight_equivalence[estimator0]
- tests/test_common.py::test_estimators[StackingClassifier(estimators=[('est1',LogisticRegression(C=0.1)),('est2',LogisticRegression(C=1))])-check_sample_weights_invariance(kind=ones)] <1.1
- tests/test_common.py::test_estimators[StackingClassifier(estimators=[('est1',LogisticRegression(C=0.1)),('est2',LogisticRegression(C=1))])-check_sample_weights_invariance(kind=zeros)] <1.1
# Here it doesn't reach convergence under the default maximum iterations, and the test
# turns the convergence warning into an error. Note that it has numeric differences w.r.t.
# the original sklearn, so it's not guaranteed to reach the same optimality after each iteration.
Copy link
Contributor

@avolkov-intel avolkov-intel Nov 26, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is it possible to suppress warnings for this particular test instead of removing it? What are the further steps? Do we want to leave it as deselected forever or some modification to logistic regression is planned?

Copy link
Contributor Author

@david-cortes-intel david-cortes-intel Nov 26, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The test is explicitly checking that no warning is issued.

- linear_model/tests/test_logistic.py::test_multinomial_identifiability_on_iris[42-False-newton-cg]

# Scikit-learn does not constraint multinomial logistic intercepts to sum to zero.
# Softmax function is invariant to additions by a constant, so even though the numbers
Expand Down
Loading