Remove deprecated sample_weight in naive bayes/sample_weights in hinge_loss

[jcrist]

This removes:

• The deprecated sample_weights alias in hinge_loss
• The deprecated sample_weight arg to discrete naive bayes estimators

Part of #8220.

[jcrist]

The only remaining deprecations to remove this release cycle are probability in SVC/LinearSVC. Since that one requires a larger effort (including letting us delete some C++) I'm splitting it out into a separate PR.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 370b49fa-cd05-47f9-bcec-0c88562a9e6e

📥 Commits

Reviewing files that changed from the base of the PR and between e1b2740 and 6b38f08.

📒 Files selected for processing (5)

• python/cuml/cuml/metrics/hinge_loss.py
• python/cuml/cuml/naive_bayes/naive_bayes.py
• python/cuml/tests/test_metrics.py
• python/cuml/tests/test_naive_bayes.py
• python/cuml/tests/test_sklearn_compatibility.py

💤 Files with no reviewable changes (4)

• python/cuml/tests/test_sklearn_compatibility.py
• python/cuml/cuml/metrics/hinge_loss.py
• python/cuml/tests/test_metrics.py
• python/cuml/tests/test_naive_bayes.py

---

📝 Walkthrough

Summary by CodeRabbit

Breaking Changes

• Removed deprecated sample_weights parameter from hinge_loss() function; use sample_weight instead.
• Removed deprecated sample_weight parameter from Naive Bayes fit() and partial_fit() methods in discrete implementations; sample weighting is no longer supported.

Walkthrough

This PR removes deprecated sample_weight parameter aliases and their associated deprecation-warning logic from the hinge_loss metric function and discrete Naive Bayes estimators. Corresponding tests validating the deprecated behavior are deleted, and sklearn compatibility expected-failure configurations are updated to reflect the removals.

Changes

Deprecation Cleanup for sample_weight Parameters

Layer / File(s)	Summary
Hinge Loss: remove sample_weights deprecation python/cuml/cuml/metrics/hinge_loss.py, python/cuml/tests/test_metrics.py	The sample_weights deprecated alias and its FutureWarning aliasing logic are removed from hinge_loss. The function signature now accepts only sample_weight, the warnings import is deleted, the docstring deprecation section is removed, and the test test_hinge_loss_sample_weights_deprecated is deleted.
Naive Bayes: remove sample_weight deprecation python/cuml/cuml/naive_bayes/naive_bayes.py, python/cuml/tests/test_naive_bayes.py	The deprecated sample_weight parameter is removed from _BaseDiscreteNB.partial_fit, _BaseDiscreteNB.fit, and the internal _BaseDiscreteNB._partial_fit method. The warnings import is deleted, deprecation/unsupported-behavior logic is eliminated, method delegations are adjusted to omit sample_weight, and the test test_sample_weight_deprecated is deleted.
sklearn compatibility: update expected-failure configuration python/cuml/tests/test_sklearn_compatibility.py	The XFAILS mappings for BernoulliNB, CategoricalNB, ComplementNB, and MultinomialNB are updated to remove all sample_weight-related expected-failure checks, leaving only check_estimator_tags_renamed and check_classifier_data_not_an_array.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

Possibly related PRs

• rapidsai/cuml#8060: The earlier PR introduces the deprecated sample_weights alias for hinge_loss and the sample_weight deprecation in Naive Bayes methods, which this PR removes.

Suggested labels

Cython / Python, breaking

Suggested reviewers

• dantegd
• divyegala

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The pull request title clearly and specifically describes the main changes: removing deprecated sample_weight in naive bayes and sample_weights in hinge_loss.
Description check	✅ Passed	The pull request description is directly related to the changeset, listing the deprecated features being removed and referencing the related issue.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[jcrist]

/merge