Migrate assert_raises_regex to pytest.raises

Author: Joan Massich

imblearn/combine/tests/test_smote_enn.py

@@ -7,7 +7,7 @@
 
 import numpy as np
 from sklearn.utils.testing import assert_allclose, assert_array_equal
-from sklearn.utils.testing import assert_raises_regex
+from pytest import raises
 
 from imblearn.combine import SMOTEENN
 from imblearn.under_sampling import EditedNearestNeighbours
@@ -113,8 +113,8 @@ def test_error_wrong_object():
     smote = 'rnd'
     enn = 'rnd'
     smt = SMOTEENN(smote=smote, random_state=RND_SEED)
-    assert_raises_regex(ValueError, "smote needs to be a SMOTE",
-                        smt.fit_sample, X, Y)
+    with raises(ValueError, match="smote needs to be a SMOTE"):
+        smt.fit_sample(X, Y)
     smt = SMOTEENN(enn=enn, random_state=RND_SEED)
-    assert_raises_regex(ValueError, "enn needs to be an ",
-                        smt.fit_sample, X, Y)
+    with raises(ValueError, match="enn needs to be an "):
+        smt.fit_sample(X, Y)

imblearn/combine/tests/test_smote_tomek.py

@@ -7,7 +7,7 @@
 
 import numpy as np
 from sklearn.utils.testing import assert_allclose, assert_array_equal
-from sklearn.utils.testing import assert_raises_regex
+from pytest import raises
 
 from imblearn.combine import SMOTETomek
 from imblearn.over_sampling import SMOTE
@@ -156,8 +156,8 @@ def test_error_wrong_object():
     smote = 'rnd'
     tomek = 'rnd'
     smt = SMOTETomek(smote=smote, random_state=RND_SEED)
-    assert_raises_regex(ValueError, "smote needs to be a SMOTE",
-                        smt.fit_sample, X, Y)
+    with raises(ValueError, match="smote needs to be a SMOTE"):
+        smt.fit_sample(X, Y)
     smt = SMOTETomek(tomek=tomek, random_state=RND_SEED)
-    assert_raises_regex(ValueError, "tomek needs to be a TomekLinks",
-                        smt.fit_sample, X, Y)
+    with raises(ValueError, match="tomek needs to be a TomekLinks"):
+        smt.fit_sample(X, Y)

imblearn/datasets/tests/test_imbalance.py

@@ -11,8 +11,8 @@
 import numpy as np
 
 from sklearn.datasets import load_iris
-from sklearn.utils.testing import assert_raises_regex
 from sklearn.utils.testing import assert_warns_message
+from pytest import raises
 
 from imblearn.datasets import make_imbalance
 
@@ -24,18 +24,18 @@ def test_make_imbalance_error():
     # we are reusing part of utils.check_ratio, however this is not cover in
     # the common tests so we will repeat it here
     ratio = {0: -100, 1: 50, 2: 50}
-    assert_raises_regex(ValueError, "in a class cannot be negative",
-                        make_imbalance, X, Y, ratio)
+    with raises(ValueError, match="in a class cannot be negative"):
+        make_imbalance(X, Y, ratio)
     ratio = {0: 10, 1: 70}
-    assert_raises_regex(ValueError, "should be less or equal to the original",
-                        make_imbalance, X, Y, ratio)
+    with raises(ValueError, match="should be less or equal to the original"):
+        make_imbalance(X, Y, ratio)
     y_ = np.zeros((X.shape[0], ))
     ratio = {0: 10}
-    assert_raises_regex(ValueError, "needs to have more than 1 class.",
-                        make_imbalance, X, y_, ratio)
+    with raises(ValueError, match="needs to have more than 1 class."):
+        make_imbalance(X, y_, ratio)
     ratio = 'random-string'
-    assert_raises_regex(ValueError, "has to be a dictionary or a function",
-                        make_imbalance, X, Y, ratio)
+    with raises(ValueError, match="has to be a dictionary or a function"):
+        make_imbalance(X, Y, ratio)
 
 
 # FIXME: to be removed in 0.4 due to deprecation

imblearn/datasets/tests/test_zenodo.py

@@ -8,7 +8,8 @@
 
 from imblearn.datasets import fetch_datasets
 from sklearn.utils.testing import SkipTest, assert_allclose
-from sklearn.utils.testing import assert_raises_regex
+
+from pytest import raises
 
 DATASET_SHAPE = {'ecoli': (336, 7),
                  'optical_digits': (5620, 64),
@@ -84,11 +85,11 @@ def test_fetch_filter():
 
 
 def test_fetch_error():
-    assert_raises_regex(ValueError, 'is not a dataset available.',
-                        fetch_datasets, filter_data=tuple(['rnd']))
-    assert_raises_regex(ValueError, 'dataset with the ID=',
-                        fetch_datasets, filter_data=tuple([-1]))
-    assert_raises_regex(ValueError, 'dataset with the ID=',
-                        fetch_datasets, filter_data=tuple([100]))
-    assert_raises_regex(ValueError, 'value in the tuple',
-                        fetch_datasets, filter_data=tuple([1.00]))
+    with raises(ValueError, match='is not a dataset available.'):
+        fetch_datasets(filter_data=tuple(['rnd']))
+    with raises(ValueError, match='dataset with the ID='):
+        fetch_datasets(filter_data=tuple([-1]))
+    with raises(ValueError, match='dataset with the ID='):
+        fetch_datasets(filter_data=tuple([100]))
+    with raises(ValueError, match='value in the tuple'):
+        fetch_datasets(filter_data=tuple([1.00]))

imblearn/ensemble/tests/test_balance_cascade.py

@@ -7,7 +7,7 @@
 
 import numpy as np
 from sklearn.utils.testing import assert_array_equal
-from sklearn.utils.testing import assert_raises_regex
+
 from sklearn.ensemble import RandomForestClassifier
 
 from imblearn.ensemble import BalanceCascade
@@ -365,5 +365,5 @@ def test_give_classifier_wrong_obj():
     classifier = 2
     bc = BalanceCascade(ratio=ratio, random_state=RND_SEED,
                         return_indices=True, estimator=classifier)
-    assert_raises_regex(ValueError, "Invalid parameter `estimator`",
-                        bc.fit_sample, X, Y)
+    with raises(ValueError, match="Invalid parameter `estimator`"):
+        bc.fit_sample(X, Y)

imblearn/over_sampling/tests/test_adasyn.py

@@ -7,11 +7,12 @@
 
 import numpy as np
 from sklearn.utils.testing import assert_allclose, assert_array_equal
-from sklearn.utils.testing import assert_raises_regex
 from sklearn.neighbors import NearestNeighbors
 
 from imblearn.over_sampling import ADASYN
 
+from pytest import raises
+
 RND_SEED = 0
 X = np.array([[0.11622591, -0.0317206], [0.77481731, 0.60935141],
               [1.25192108, -0.22367336], [0.53366841, -0.30312976],
@@ -141,5 +142,5 @@ def test_ada_fit_sample_nn_obj():
 def test_ada_wrong_nn_obj():
     nn = 'rnd'
     ada = ADASYN(random_state=RND_SEED, n_neighbors=nn)
-    assert_raises_regex(ValueError, "has to be one of",
-                        ada.fit_sample, X, Y)
+    with raises(ValueError, match="has to be one of"):
+        ada.fit_sample(X, Y)

imblearn/over_sampling/tests/test_smote.py

@@ -7,12 +7,13 @@
 
 import numpy as np
 from sklearn.utils.testing import assert_allclose, assert_array_equal
-from sklearn.utils.testing import assert_raises_regex
 from sklearn.neighbors import NearestNeighbors
 from sklearn.svm import SVC
 
 from imblearn.over_sampling import SMOTE
 
+from pytest import raises
+
 RND_SEED = 0
 X = np.array([[0.11622591, -0.0317206], [0.77481731, 0.60935141],
               [1.25192108, -0.22367336], [0.53366841, -0.30312976],
@@ -31,8 +32,8 @@
 def test_smote_wrong_kind():
     kind = 'rnd'
     smote = SMOTE(kind=kind, random_state=RND_SEED)
-    assert_raises_regex(ValueError, "Unknown kind for SMOTE",
-                        smote.fit_sample, X, Y)
+    with raises(ValueError, match="Unknown kind for SMOTE"):
+        smote.fit_sample(X, Y)
 
 
 def test_sample_regular():
@@ -203,19 +204,19 @@ def test_wrong_nn():
     nn_k = NearestNeighbors(n_neighbors=6)
     smote = SMOTE(
         random_state=RND_SEED, kind=kind, k_neighbors=nn_k, m_neighbors=nn_m)
-    assert_raises_regex(ValueError, "has to be one of",
-                        smote.fit_sample, X, Y)
+    with raises(ValueError, match="has to be one of"):
+        smote.fit_sample(X, Y)
     nn_k = 'rnd'
     nn_m = NearestNeighbors(n_neighbors=10)
     smote = SMOTE(
         random_state=RND_SEED, kind=kind, k_neighbors=nn_k, m_neighbors=nn_m)
-    assert_raises_regex(ValueError, "has to be one of",
-                        smote.fit_sample, X, Y)
+    with raises(ValueError, match="has to be one of"):
+        smote.fit_sample(X, Y)
     kind = 'regular'
     nn_k = 'rnd'
     smote = SMOTE(random_state=RND_SEED, kind=kind, k_neighbors=nn_k)
-    assert_raises_regex(ValueError, "has to be one of",
-                        smote.fit_sample, X, Y)
+    with raises(ValueError, match="has to be one of"):
+        smote.fit_sample(X, Y)
 
 
 def test_sample_regular_with_nn_svm():
@@ -250,5 +251,5 @@ def test_sample_regular_wrong_svm():
     smote = SMOTE(
         random_state=RND_SEED, kind=kind, k_neighbors=nn_k, svm_estimator=svm)
 
-    assert_raises_regex(ValueError, "has to be one of",
-                        smote.fit_sample, X, Y)
+    with raises(ValueError, match="has to be one of"):
+        smote.fit_sample(X, Y)

imblearn/tests/test_exceptions.py

@@ -4,12 +4,12 @@
 # License: MIT
 
 
-from sklearn.utils.testing import assert_raises_regex
-
 from imblearn.exceptions import raise_isinstance_error
 
+from pytest import raises
+
 
 def test_raise_isinstance_error():
     var = 10.0
-    assert_raises_regex(ValueError, "has to be one of",
-                        raise_isinstance_error, 'var', [int], var)
+    with raises(ValueError, match="has to be one of"):
+        raise_isinstance_error('var', [int], var)

imblearn/tests/test_pipeline.py

@@ -11,7 +11,6 @@
 import time
 
 import numpy as np
-from sklearn.utils.testing import assert_raises_regex
 from sklearn.utils.testing import assert_raise_message
 from sklearn.utils.testing import assert_array_equal
 from sklearn.utils.testing import assert_array_almost_equal
@@ -181,10 +180,9 @@ def test_pipeline_init():
         Pipeline()
     # Check that we can't instantiate pipelines with objects without fit
     # method
-    assert_raises_regex(TypeError,
-                        'Last step of Pipeline should implement fit. '
-                        '.*NoFit.*',
-                        Pipeline, [('clf', NoFit())])
+    error_regex = 'Last step of Pipeline should implement fit. .*NoFit.*'
+    with raises(TypeError, match=error_regex):
+        Pipeline([('clf', NoFit())])
     # Smoke test with only an estimator
     clf = NoTrans()
     pipe = Pipeline([('svc', clf)])
@@ -206,9 +204,9 @@ def test_pipeline_init():
 
     # Check that we can't instantiate with non-transformers on the way
     # Note that NoTrans implements fit, but not transform
-    assert_raises_regex(TypeError,
-                        'implement fit and transform or sample',
-                        Pipeline, [('t', NoTrans()), ('svc', clf)])
+    error_regex = 'implement fit and transform or sample'
+    with raises(TypeError, match=error_regex):
+        Pipeline([('t', NoTrans()), ('svc', clf)])
 
     # Check that params are set
     pipe.set_params(svc__C=0.1)
@@ -400,9 +398,9 @@ def test_fit_predict_on_pipeline_without_fit_predict():
     scaler = StandardScaler()
     pca = PCA(svd_solver='full')
     pipe = Pipeline([('scaler', scaler), ('pca', pca)])
-    assert_raises_regex(AttributeError,
-                        "'PCA' object has no attribute 'fit_predict'",
-                        getattr, pipe, 'fit_predict')
+    error_regex = "'PCA' object has no attribute 'fit_predict'"
+    with raises(AttributeError, match=error_regex):
+        getattr(pipe, 'fit_predict')
 
 
 def test_fit_predict_with_intermediate_fit_params():
@@ -620,9 +618,10 @@ def test_pipeline_wrong_memory():
     memory = 1
     cached_pipe = Pipeline([('transf', DummyTransf()), ('svc', SVC())],
                            memory=memory)
-    assert_raises_regex(ValueError, "'memory' should either be a string or a"
-                        " joblib.Memory instance, got 'memory=1' instead.",
-                        cached_pipe.fit, X, y)
+    error_regex = ("'memory' should either be a string or a joblib.Memory"
+                   " instance, got 'memory=1' instead.")
+    with raises(ValueError, match=error_regex):
+        cached_pipe.fit(X, y)
 
 
 def test_pipeline_memory_transformer():

imblearn/under_sampling/prototype_generation/tests/test_cluster_centroids.py

@@ -6,7 +6,8 @@
 import numpy as np
 from sklearn.utils.testing import assert_allclose
 from sklearn.utils.testing import assert_array_equal
-from sklearn.utils.testing import assert_raises_regex
+from pytest import raises
+
 from sklearn.cluster import KMeans
 
 from imblearn.under_sampling import ClusterCentroids
@@ -79,5 +80,5 @@ def test_fit_sample_wrong_object():
     cluster = 'rnd'
     cc = ClusterCentroids(
         ratio=ratio, random_state=RND_SEED, estimator=cluster)
-    assert_raises_regex(ValueError, "has to be a KMeans clustering",
-                        cc.fit_sample, X, Y)
+    with raises(ValueError, match="has to be a KMeans clustering"):
+        cc.fit_sample(X, Y)

imblearn/under_sampling/prototype_selection/tests/test_condensed_nearest_neighbour.py

@@ -7,7 +7,7 @@
 
 import numpy as np
 from sklearn.utils.testing import assert_array_equal
-from sklearn.utils.testing import assert_raises_regex
+from pytest import raises
 
 from sklearn.neighbors import KNeighborsClassifier
 
@@ -87,5 +87,5 @@ def test_cnn_fit_sample_with_object():
 def test_cnn_fit_sample_with_wrong_object():
     knn = 'rnd'
     cnn = CondensedNearestNeighbour(random_state=RND_SEED, n_neighbors=knn)
-    assert_raises_regex(ValueError, "has to be a int or an ",
-                        cnn.fit_sample, X, Y)
+    with raises(ValueError, match="has to be a int or an "):
+        cnn.fit_sample(X, Y)

imblearn/under_sampling/prototype_selection/tests/test_edited_nearest_neighbours.py

@@ -7,7 +7,7 @@
 
 import numpy as np
 from sklearn.utils.testing import assert_array_equal
-from sklearn.utils.testing import assert_raises_regex
+from pytest import raises
 
 from sklearn.neighbors import NearestNeighbors
 
@@ -102,5 +102,5 @@ def test_enn_not_good_object():
     nn = 'rnd'
     enn = EditedNearestNeighbours(
         n_neighbors=nn, random_state=RND_SEED, kind_sel='mode')
-    assert_raises_regex(ValueError, "has to be one of",
-                        enn.fit_sample, X, Y)
+    with raises(ValueError, match="has to be one of"):
+        enn.fit_sample(X, Y)

imblearn/under_sampling/prototype_selection/tests/test_instance_hardness_threshold.py

@@ -8,6 +8,7 @@
 import numpy as np
 from sklearn.utils.testing import assert_array_equal
 from sklearn.ensemble import GradientBoostingClassifier
+from pytest import raises
 
 from imblearn.under_sampling import InstanceHardnessThreshold
 
@@ -273,5 +274,5 @@ def test_iht_fit_sample_wrong_class_obj():
     from sklearn.cluster import KMeans
     est = KMeans()
     iht = InstanceHardnessThreshold(estimator=est, random_state=RND_SEED)
-    assert_raises_regex(ValueError, "Invalid parameter `estimator`",
-                        iht.fit_sample, X, Y)
+    with raises(ValueError, match="Invalid parameter `estimator`"):
+        iht.fit_sample(X, Y)

imblearn/under_sampling/prototype_selection/tests/test_nearmiss.py

@@ -7,8 +7,8 @@
 
 import numpy as np
 from sklearn.utils.testing import assert_array_equal, assert_warns
-from sklearn.utils.testing import assert_raises_regex
 from sklearn.neighbors import NearestNeighbors
+from pytest import raises
 
 from imblearn.under_sampling import NearMiss
 
@@ -42,8 +42,8 @@ def test_nearmiss_deprecation():
 def test_nearmiss_wrong_version():
     version = 1000
     nm = NearMiss(version=version, random_state=RND_SEED)
-    assert_raises_regex(ValueError, "must be 1, 2 or 3",
-                        nm.fit_sample, X, Y)
+    with raises(ValueError, match="must be 1, 2 or 3"):
+        nm.fit_sample(X, Y)
 
 
 def test_nm_wrong_nn_obj():
@@ -53,15 +53,15 @@ def test_nm_wrong_nn_obj():
                   version=VERSION_NEARMISS,
                   return_indices=True,
                   n_neighbors=nn)
-    assert_raises_regex(ValueError, "has to be one of",
-                        nm.fit_sample, X, Y)
+    with raises(ValueError, match="has to be one of"):
+        nm.fit_sample(X, Y)
     nn3 = 'rnd'
     nn = NearestNeighbors(n_neighbors=3)
     nm3 = NearMiss(ratio=ratio, random_state=RND_SEED,
                    version=3, return_indices=True,
                    n_neighbors=nn, n_neighbors_ver3=nn3)
-    assert_raises_regex(ValueError, "has to be one of",
-                        nm3.fit_sample, X, Y)
+    with raises(ValueError, match="has to be one of"):
+        nm3.fit_sample(X, Y)
 
 
 def test_nm_fit_sample_auto():