small validation fix to remove contains_classifier

Author: jsture

src/scikit_opls/validation.py

@@ -117,20 +117,8 @@ def _permuted_scores(
 
 
 def _contains_classifier(estimator: BaseEstimator) -> bool:
-    """Return whether estimator or a simple wrapped estimator is a classifier."""
-    if is_classifier(estimator):
-        return True
-
-    steps = getattr(estimator, "steps", None)
-    if steps is not None:
-        return any(_contains_classifier(step) for _, step in steps)
-
-    for attr in ("estimator", "base_estimator", "best_estimator_"):
-        inner = getattr(estimator, attr, None)
-        if inner is not None and _contains_classifier(inner):
-            return True
-
-    return False
+    """Return whether estimator is tagged as a classifier."""
+    return is_classifier(estimator)
 
 
 def _resolve_cv(estimator: BaseEstimator, cv: _CVType, y: NDArray[np.float64]):

tests/test_validation.py

@@ -6,8 +6,12 @@
 import pytest
 from sklearn.utils._testing import assert_allclose
 
-from scikit_opls import OPLS
-from scikit_opls.validation import _safe_r2_score, permutation_test
+from scikit_opls import OPLS, OPLSDA
+from scikit_opls.validation import (
+    _contains_classifier,
+    _safe_r2_score,
+    permutation_test,
+)
 
 from ._data import make_regression_data as _regression_data
 
@@ -91,8 +95,6 @@ def test_permutation_test_n_jobs_is_reproducible():
 
 
 def test_permutation_test_non_regression_estimator_raises():
-    from scikit_opls import OPLSDA
-
     X, y = _regression_data(seed=10)
     labels = np.where(y > 0.0, "hi", "lo")
     # OPLSDA is a classifier, raising a clean TypeError immediately
@@ -224,8 +226,6 @@ def test_permutation_test_classifier_wrapped_raises():
     from sklearn.model_selection import GridSearchCV
     from sklearn.pipeline import Pipeline
 
-    from scikit_opls import OPLSDA
-
     X, y = _regression_data(seed=42)
     # 1. Pipeline containing a classifier
     pipe = Pipeline([("clf", OPLSDA())])
@@ -236,3 +236,24 @@ def test_permutation_test_classifier_wrapped_raises():
     gs = GridSearchCV(pipe, {"clf__n_components": [1]})
     with pytest.raises(TypeError, match="classifiers like OPLSDA are not supported"):
         permutation_test(gs, X, y)
+
+
+def test_contains_classifier_detects_oplsda():
+    assert _contains_classifier(OPLSDA())
+    assert not _contains_classifier(OPLS())
+
+
+def test_contains_classifier_detects_pipeline_ending_in_oplsda():
+    from sklearn.pipeline import Pipeline
+
+    assert _contains_classifier(Pipeline([("model", OPLSDA())]))
+    assert not _contains_classifier(Pipeline([("model", OPLS())]))
+
+
+def test_contains_classifier_detects_grid_search_over_oplsda():
+    from sklearn.model_selection import GridSearchCV
+
+    search = GridSearchCV(OPLSDA(), {"n_orthogonal": [0, 1]}, cv=2)
+    assert _contains_classifier(search)
+    other = GridSearchCV(OPLS(), {"n_orthogonal": [0, 1]}, cv=2)
+    assert not _contains_classifier(other)