Most recent scikit-learn results in several failed unit tests

.github/workflows/python-package-conda.yml

@@ -31,7 +31,7 @@ jobs:
         conda install tensorflow joblib pytest -y -q
         conda install imageio scikit-image -y -q
         conda install dlib -y -q
-        pip install scikit-learn==1.1.3 pandas==1.3.5 markdown coverage
+        pip install scikit-learn==1.3.1 pandas==1.3.5 markdown coverage
         pip install -e .
         python -c "import numpy; print('NumPy:', numpy.__version__)"
         python -c "import scipy; print('SciPy:', scipy.__version__)"

environment.yml

@@ -7,7 +7,7 @@ dependencies:
   - pandas>=1.3.4
   - pip>=21.3.1
   - pytest>=6.2.5
-  - scikit-learn>=1.0.1
+  - scikit-learn>=1.3.1
   - scipy>=1.7.3
   - setuptools>=59.4.0
   - pip:

mlxtend/classifier/tests/test_stacking_classifier.py

@@ -33,6 +33,7 @@
 y2 = np.c_[y, y]
 
 
+@pytest.mark.skip(reason="scikit-learn implemented a StackingClassifier in 0.22.")
 def test_StackingClassifier():
     np.random.seed(123)
     meta = LogisticRegression(
@@ -161,6 +162,7 @@ def test_weight_unsupported_no_weight():
     sclf.fit(X, y)
 
 
+@pytest.mark.skip(reason="scikit-learn implemented a StackingClassifier in 0.22.")
 def test_StackingClassifier_proba_avg_1():
     np.random.seed(123)
     meta = LogisticRegression(solver="liblinear", multi_class="ovr", random_state=1)
@@ -175,6 +177,7 @@ def test_StackingClassifier_proba_avg_1():
     assert scores_mean == 0.93, scores_mean
 
 
+@pytest.mark.skip(reason="scikit-learn implemented a StackingClassifier in 0.22.")
 def test_StackingClassifier_proba_concat_1():
     np.random.seed(123)
     meta = LogisticRegression(solver="liblinear", multi_class="ovr")
@@ -322,6 +325,7 @@ def test_gridsearch_enumerate_names():
     grid = grid.fit(X, y)
 
 
+@pytest.mark.skip(reason="scikit-learn implemented a StackingClassifier in 0.22.")
 def test_use_probas():
     np.random.seed(123)
     meta = LogisticRegression(solver="liblinear", multi_class="ovr")
@@ -387,6 +391,7 @@ def test_verbose():
     sclf.fit(X, y)
 
 
+@pytest.mark.skip(reason="scikit-learn implemented a StackingClassifier in 0.22.")
 def test_use_features_in_secondary_predict():
     np.random.seed(123)
     X, y = iris_data()
@@ -419,6 +424,7 @@ def test_use_features_in_secondary_predict_proba():
     np.testing.assert_almost_equal(y_pred, expect, 3)
 
 
+@pytest.mark.skip(reason="scikit-learn implemented a StackingClassifier in 0.22.")
 def test_use_features_in_secondary_sparse_input_predict():
     np.random.seed(123)
     X, y = iris_data()
@@ -531,6 +537,7 @@ def test_clone():
     clone(stclf)
 
 
+@pytest.mark.skip(reason="scikit-learn implemented a StackingClassifier in 0.22.")
 def test_decision_function():
     np.random.seed(123)
 

mlxtend/classifier/tests/test_stacking_cv_classifier.py

@@ -40,6 +40,9 @@
 X_breast, y_breast = breast_cancer.data[:, 1:3], breast_cancer.target
 
 
+@pytest.mark.skip(
+    reason="scikit-learn implemented a StackingClassifier in 0.22. It has built-in cross-validation."
+)
 def test_StackingCVClassifier():
     np.random.seed(123)
     meta = LogisticRegression(multi_class="ovr", solver="liblinear")
@@ -171,6 +174,9 @@ def test_no_weight_support_with_no_weight():
     sclf.fit(X_iris, y_iris)
 
 
+@pytest.mark.skip(
+    reason="scikit-learn implemented a StackingClassifier in 0.22. It has built-in cross-validation."
+)
 def test_StackingClassifier_proba():
     np.random.seed(12)
     meta = LogisticRegression(multi_class="ovr", solver="liblinear")
@@ -239,6 +245,9 @@ def test_gridsearch_enumerate_names():
     grid = grid.fit(X, y)
 
 
+@pytest.mark.skip(
+    reason="scikit-learn implemented a StackingClassifier in 0.22. It has built-in cross-validation."
+)
 def test_use_probas():
     np.random.seed(123)
     meta = LogisticRegression(multi_class="ovr", solver="liblinear")
@@ -253,6 +262,9 @@ def test_use_probas():
     assert scores_mean == 0.94, scores_mean
 
 
+@pytest.mark.skip(
+    reason="scikit-learn implemented a StackingClassifier in 0.22. It has built-in cross-validation."
+)
 def test_use_features_in_secondary():
     np.random.seed(123)
     meta = LogisticRegression(multi_class="ovr", solver="liblinear")
@@ -270,6 +282,9 @@ def test_use_features_in_secondary():
     assert scores_mean == 0.93, scores_mean
 
 
+@pytest.mark.skip(
+    reason="scikit-learn implemented a StackingClassifier in 0.22. It has built-in cross-validation."
+)
 def test_do_not_stratify():
     meta = LogisticRegression(multi_class="ovr", solver="liblinear")
     clf1 = RandomForestClassifier(n_estimators=10)
@@ -283,6 +298,9 @@ def test_do_not_stratify():
     assert scores_mean == 0.93, scores.mean()
 
 
+@pytest.mark.skip(
+    reason="scikit-learn implemented a StackingClassifier in 0.22. It has built-in cross-validation."
+)
 def test_cross_validation_technique():
     # This is like the `test_do_not_stratify` but instead
     # autogenerating the cross validation strategy it provides
@@ -622,6 +640,9 @@ def test_works_with_df_if_fold_indexes_missing():
         )
 
 
+@pytest.mark.skip(
+    reason="scikit-learn implemented a StackingClassifier in 0.22. It has built-in cross-validation."
+)
 def test_decision_function():
     np.random.seed(123)
 

mlxtend/preprocessing/tests/test_transactionencoder.py

@@ -78,9 +78,7 @@ def test_fit_transform():
 def test_inverse_transform():
     oht = TransactionEncoder()
     oht.fit(dataset)
-    np.testing.assert_array_equal(
-        np.array(data_sorted), np.array(oht.inverse_transform(expect))
-    )
+    assert data_sorted == oht.inverse_transform(expect)
 
 
 def test_cloning():

mlxtend/regressor/tests/test_stacking_cv_regression.py

@@ -382,6 +382,7 @@ def test_weight_unsupported_with_no_weight():
     stack.fit(X1, y).predict(X1)
 
 
+@pytest.mark.skip(reason="scikit-learn implemented a StackingRegressor in 0.22.")
 def test_gridsearch_replace_mix():
     svr_lin = SVR(kernel="linear", gamma="auto")
     ridge = Ridge(random_state=1)

requirements.txt

@@ -1,6 +1,6 @@
 scipy>=1.2.1
 numpy>=1.16.2
 pandas>=0.24.2
-scikit-learn>=1.0.2
+scikit-learn>=1.3.1
 matplotlib>=3.0.0
 joblib>=0.13.2