Apply new validation to cuml.covariance

[jcrist]

Fixes #7988.

[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: bfc50093-e10c-4263-9395-ea93044d9dfa

📥 Commits

Reviewing files that changed from the base of the PR and between 9ed5a67 and 6c928d4.

📒 Files selected for processing (2)

• python/cuml/cuml_accel_tests/upstream/scikit-learn/xfail-list.yaml
• python/cuml/tests/test_sklearn_compatibility.py

💤 Files with no reviewable changes (2)

• python/cuml/tests/test_sklearn_compatibility.py
• python/cuml/cuml_accel_tests/upstream/scikit-learn/xfail-list.yaml

---

📝 Walkthrough

Summary by CodeRabbit

• Bug Fixes

  • LedoitWolf: unified input validation/casting, better handling of object-dtype and NaN/Inf inputs, single-sample fit now warns instead of error, and statistical terms correctly scale with feature count.

• Tests

  • Removed expected-failure markers for LedoitWolf compatibility checks so those scenarios are now evaluated normally.

Walkthrough

Replaces per-method input conversion/validation in LedoitWolf with unified check_inputs casting to float32/float64; adjusts feature-count usage and single-sample warning behavior; converts stored arrays via .to_output("cupy"); changes @reflect(reset=...) to reset="type". Removes several LedoitWolf xfail entries from sklearn-compat configs.

Changes

Cohort / File(s)	Summary
LedoitWolf estimator python/cuml/cuml/covariance/ledoit_wolf.py	Replaced input_to_cupy_array + check_features with check_inputs across fit, score, error_norm, mahalanobis, and get_precision. fit now warns for single-sample inputs (no hard error), uses X.shape for feature counts and dtype, updates covariance diagonal indexing accordingly, and converts stored arrays using .to_output("cupy"). Changed @reflect reset from True to "type".
sklearn xfail mappings & tests python/cuml/cuml_accel_tests/upstream/scikit-learn/xfail-list.yaml, python/cuml/tests/test_sklearn_compatibility.py	Removed xfail entries that previously exempted LedoitWolf from checks for object-dtype handling, empty-data error messages, and NaN/Inf validation so those estimator checks will run normally.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related issues

• Update cuml.covariance to new input validation #7988 — Targets the same cuml.covariance input-validation changes for LedoitWolf (migration to check_inputs and related API adjustments).

Possibly related PRs

• Apply new input validation to cuml.multiclass #8017 — Similar migration to centralized check_inputs and @reflect reset semantics.
• Apply new validation to cuml.random_projection #8009 — Applies the same per-method → centralized input-validation refactor and @reflect change.
• Use new input validation infrastructure for cuml.decomposition. #8006 — Migrates estimators to shared input validation (check_inputs/check_array) and updates @reflect reset behavior.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title 'Apply new validation to cuml.covariance' accurately summarizes the main change: updating input validation in the covariance module.
Description check	✅ Passed	The description 'Fixes #7988' is minimal but directly related to the changeset, referencing the linked issue about updating covariance validation.
Linked Issues check	✅ Passed	The PR implements validation updates to cuml.covariance as required by issue #7988, including check_inputs-based validation, input conversion refactoring, and removal of obsolete xfail entries.
Out of Scope Changes check	✅ Passed	All changes are scoped to updating input validation in the LedoitWolf estimator and removing corresponding xfail entries; no unrelated modifications are present.
Docstring Coverage	✅ Passed	Docstring coverage is 85.71% which is sufficient. The required threshold is 80.00%.

_{✏️ 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.}

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@python/cuml/cuml/covariance/ledoit_wolf.py`:
- Around line 255-259: The warnings.warn call inside the X.shape[0] == 1 branch
should include stacklevel=2 so the warning points at the user's caller; update
the warnings.warn(...) invocation in ledoit_wolf.py (the block that checks if
X.shape[0] == 1) to pass stacklevel=2 as an argument to warnings.warn to improve
the warning stack trace.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 1ce11a2e-df76-4657-af87-6f7b50d73e9a

📥 Commits

Reviewing files that changed from the base of the PR and between 42f57b5 and 7b296fc.

📒 Files selected for processing (3)

• python/cuml/cuml/covariance/ledoit_wolf.py
• python/cuml/cuml_accel_tests/upstream/scikit-learn/xfail-list.yaml
• python/cuml/tests/test_sklearn_compatibility.py

💤 Files with no reviewable changes (2)

• python/cuml/tests/test_sklearn_compatibility.py
• python/cuml/cuml_accel_tests/upstream/scikit-learn/xfail-list.yaml

[jcrist]

/merge