iter

Author: glemaitre

imblearn/tests/test_common.py

@@ -9,8 +9,10 @@
 
 import numpy as np
 import pytest
+import sklearn
 from sklearn.base import clone
 from sklearn.exceptions import ConvergenceWarning
+from sklearn.utils.fixes import parse_version
 from sklearn.utils._testing import ignore_warnings
 from sklearn.utils.estimator_checks import (
     parametrize_with_checks as parametrize_with_checks_sklearn,
@@ -27,9 +29,18 @@
 from imblearn.utils.testing import all_estimators
 from imblearn.utils._test_common.instance_generator import (
     _get_check_estimator_ids,
+    _get_expected_failed_checks,
     _tested_estimators,
 )
 
+sklearn_version = parse_version(parse_version(sklearn.__version__).base_version)
+if sklearn_version >= parse_version("1.6"):
+    kwargs_parametrize_with_checks = {
+        "expected_failed_checks": _get_expected_failed_checks
+    }
+else:
+    kwargs_parametrize_with_checks = {}
+
 
 @pytest.mark.parametrize("name, Estimator", all_estimators())
 def test_all_estimator_no_base_class(name, Estimator):
@@ -38,13 +49,17 @@ def test_all_estimator_no_base_class(name, Estimator):
     assert not name.lower().startswith("base"), msg
 
 
-@parametrize_with_checks_sklearn(list(_tested_estimators()))
+@parametrize_with_checks_sklearn(
+    list(_tested_estimators()), **kwargs_parametrize_with_checks
+)
 def test_estimators_compatibility_sklearn(estimator, check, request):
     _set_checking_parameters(estimator)
     check(estimator)
 
 
-@parametrize_with_checks(list(_tested_estimators()))
+@parametrize_with_checks(
+    list(_tested_estimators()), expected_failed_checks=_get_expected_failed_checks
+)
 def test_estimators_imblearn(estimator, check, request):
     # Common tests for estimator instances
     with ignore_warnings(

imblearn/utils/_test_common/instance_generator.py

@@ -19,6 +19,7 @@
     BalancedBaggingClassifier,
     BalancedRandomForestClassifier,
     EasyEnsembleClassifier,
+    RUSBoostClassifier,
 )
 from imblearn.over_sampling import (
     ADASYN,
@@ -83,7 +84,13 @@
 # same check with multiple instances of the same estimator with different parameters.
 # The special key "*" allows to apply the parameters to all checks.
 # TODO(devtools): allow third-party developers to pass test specific params to checks
-PER_ESTIMATOR_CHECK_PARAMS: dict = {}
+PER_ESTIMATOR_CHECK_PARAMS: dict = {
+    Pipeline: {
+        "check_classifiers_with_encoded_labels": dict(
+            sampler__sampling_strategy={"setosa": 20, "virginica": 20}
+        )
+    }
+}
 
 SKIPPED_ESTIMATORS = [SMOTENC]
 
@@ -187,3 +194,31 @@ def _yield_instances_for_check(check, estimator_orig):
         estimator = clone(estimator_orig)
         estimator.set_params(**params)
         yield estimator
+
+
+PER_ESTIMATOR_XFAIL_CHECKS = {
+    BalancedRandomForestClassifier: {
+        "check_sample_weight_equivalence": "FIXME",
+    },
+    NearMiss: {
+        "check_samplers_fit_resample": "FIXME",
+    },
+    Pipeline: {
+        "check_dont_overwrite_parameters": (
+            "Pipeline changes the `steps` parameter, which it shouldn't."
+            "Therefore this test is x-fail until we fix this."
+        ),
+        "check_estimators_overwrite_params": (
+            "Pipeline changes the `steps` parameter, which it shouldn't."
+            "Therefore this test is x-fail until we fix this."
+        ),
+    },
+    RUSBoostClassifier: {
+        "check_sample_weight_equivalence": "FIXME",
+    },
+}
+
+def _get_expected_failed_checks(estimator):
+    """Get the expected failed checks for all estimators in scikit-learn."""
+    failed_checks = PER_ESTIMATOR_XFAIL_CHECKS.get(type(estimator), {})
+    return failed_checks

imblearn/utils/estimator_checks.py

@@ -668,7 +668,6 @@ def check_classifiers_with_encoded_labels(name, classifier_orig):
             "virginica": 50,
         },
     )
-    classifier.set_params(sampling_strategy={"setosa": 20, "virginica": 20})
     classifier.fit(df, y)
     assert set(classifier.classes_) == set(y.cat.categories.tolist())
     y_pred = classifier.predict(df)