Fix sklearn 1.7+ compatibility: BaseEstimator type detection for ensemble

.github/copilot-instructions.md

@@ -135,6 +135,7 @@ The repository uses pre-commit hooks for:
 - Ensure all tests pass before requesting review
 - Update documentation if adding new features
 - Follow the PR template in `.github/PULL_REQUEST_TEMPLATE.md`
+- ALWAYS run `pre-commit run --all-files` before each commit to avoid formatting issues
 
 ## Project Structure
 

flaml/automl/model.py

@@ -26,6 +26,13 @@
 from sklearn.svm import LinearSVC
 from xgboost import __version__ as xgboost_version
 
+try:
+    from sklearn.utils._tags import ClassifierTags, RegressorTags
+
+    SKLEARN_TAGS_AVAILABLE = True
+except ImportError:
+    SKLEARN_TAGS_AVAILABLE = False
+
 from flaml import tune
 from flaml.automl.data import group_counts
 from flaml.automl.spark import ERROR as SPARK_ERROR
@@ -148,6 +155,25 @@ def get_params(self, deep=False):
             params["_estimator_type"] = self._estimator_type
         return params
 
+    def __sklearn_tags__(self):
+        """Override sklearn tags to respect the _estimator_type attribute.
+
+        This is needed for sklearn 1.7+ which uses get_tags() instead of
+        checking _estimator_type directly. Since BaseEstimator inherits from
+        ClassifierMixin, it would otherwise always be tagged as a classifier.
+        """
+        tags = super().__sklearn_tags__()
+        if hasattr(self, "_estimator_type") and SKLEARN_TAGS_AVAILABLE:
+            if self._estimator_type == "regressor":
+                tags.estimator_type = "regressor"
+                tags.regressor_tags = RegressorTags()
+                tags.classifier_tags = None
+            elif self._estimator_type == "classifier":
+                tags.estimator_type = "classifier"
+                tags.classifier_tags = ClassifierTags()
+                tags.regressor_tags = None
+        return tags
+
     @property
     def classes_(self):
         return self._model.classes_

test/automl/test_sklearn_17_compat.py

@@ -0,0 +1,89 @@
+"""Test sklearn 1.7+ compatibility for estimator type detection.
+
+This test ensures that FLAML estimators are properly recognized as
+regressors or classifiers by sklearn's is_regressor() and is_classifier()
+functions, which is required for sklearn 1.7+ ensemble methods.
+"""
+
+import pytest
+from sklearn.base import is_classifier, is_regressor
+
+from flaml.automl.model import (
+    ExtraTreesEstimator,
+    LGBMEstimator,
+    RandomForestEstimator,
+    XGBoostSklearnEstimator,
+)
+
+
+def test_extra_trees_regressor_type():
+    """Test that ExtraTreesEstimator with regression task is recognized as regressor."""
+    est = ExtraTreesEstimator(task="regression")
+    assert is_regressor(est), "ExtraTreesEstimator(task='regression') should be recognized as a regressor"
+    assert not is_classifier(est), "ExtraTreesEstimator(task='regression') should not be recognized as a classifier"
+
+
+def test_extra_trees_classifier_type():
+    """Test that ExtraTreesEstimator with classification task is recognized as classifier."""
+    est = ExtraTreesEstimator(task="binary")
+    assert is_classifier(est), "ExtraTreesEstimator(task='binary') should be recognized as a classifier"
+    assert not is_regressor(est), "ExtraTreesEstimator(task='binary') should not be recognized as a regressor"
+
+    est = ExtraTreesEstimator(task="multiclass")
+    assert is_classifier(est), "ExtraTreesEstimator(task='multiclass') should be recognized as a classifier"
+    assert not is_regressor(est), "ExtraTreesEstimator(task='multiclass') should not be recognized as a regressor"
+
+
+def test_random_forest_regressor_type():
+    """Test that RandomForestEstimator with regression task is recognized as regressor."""
+    est = RandomForestEstimator(task="regression")
+    assert is_regressor(est), "RandomForestEstimator(task='regression') should be recognized as a regressor"
+    assert not is_classifier(est), "RandomForestEstimator(task='regression') should not be recognized as a classifier"
+
+
+def test_random_forest_classifier_type():
+    """Test that RandomForestEstimator with classification task is recognized as classifier."""
+    est = RandomForestEstimator(task="binary")
+    assert is_classifier(est), "RandomForestEstimator(task='binary') should be recognized as a classifier"
+    assert not is_regressor(est), "RandomForestEstimator(task='binary') should not be recognized as a regressor"
+
+
+def test_lgbm_regressor_type():
+    """Test that LGBMEstimator with regression task is recognized as regressor."""
+    est = LGBMEstimator(task="regression")
+    assert is_regressor(est), "LGBMEstimator(task='regression') should be recognized as a regressor"
+    assert not is_classifier(est), "LGBMEstimator(task='regression') should not be recognized as a classifier"
+
+
+def test_lgbm_classifier_type():
+    """Test that LGBMEstimator with classification task is recognized as classifier."""
+    est = LGBMEstimator(task="binary")
+    assert is_classifier(est), "LGBMEstimator(task='binary') should be recognized as a classifier"
+    assert not is_regressor(est), "LGBMEstimator(task='binary') should not be recognized as a regressor"
+
+
+def test_xgboost_regressor_type():
+    """Test that XGBoostSklearnEstimator with regression task is recognized as regressor."""
+    est = XGBoostSklearnEstimator(task="regression")
+    assert is_regressor(est), "XGBoostSklearnEstimator(task='regression') should be recognized as a regressor"
+    assert not is_classifier(est), "XGBoostSklearnEstimator(task='regression') should not be recognized as a classifier"
+
+
+def test_xgboost_classifier_type():
+    """Test that XGBoostSklearnEstimator with classification task is recognized as classifier."""
+    est = XGBoostSklearnEstimator(task="binary")
+    assert is_classifier(est), "XGBoostSklearnEstimator(task='binary') should be recognized as a classifier"
+    assert not is_regressor(est), "XGBoostSklearnEstimator(task='binary') should not be recognized as a regressor"
+
+
+if __name__ == "__main__":
+    # Run all tests
+    test_extra_trees_regressor_type()
+    test_extra_trees_classifier_type()
+    test_random_forest_regressor_type()
+    test_random_forest_classifier_type()
+    test_lgbm_regressor_type()
+    test_lgbm_classifier_type()
+    test_xgboost_regressor_type()
+    test_xgboost_classifier_type()
+    print("All sklearn 1.7+ compatibility tests passed!")