scikit-learn · thomasjpfan · Jun 17, 2021 · Jun 17, 2021 · Jun 17, 2021 · glemaitre
diff --git a/pyproject.toml b/pyproject.toml
@@ -19,6 +19,7 @@ requires = [
 
 [tool.black]
 line-length = 88
+target_version = ['py37', 'py38', 'py39']
 exclude = '''
 /(
     \.eggs         # exclude a few common directories in the

diff --git a/setup.py b/setup.py
@@ -280,7 +280,7 @@ def setup_package():
         python_requires=">=3.7",
         install_requires=min_deps.tag_to_packages["install"],
         package_data={"": ["*.pxd"]},
-        **extra_setuptools_args
+        **extra_setuptools_args,
     )
 
     commands = [arg for arg in sys.argv[1:] if not arg.startswith("-")]

diff --git a/sklearn/cluster/_affinity_propagation.py b/sklearn/cluster/_affinity_propagation.py
@@ -42,7 +42,7 @@ def affinity_propagation(
     copy=True,
     verbose=False,
     return_n_iter=False,
-    random_state=None
+    random_state=None,
 ):
     """Perform Affinity Propagation Clustering of data.
 
@@ -385,7 +385,7 @@ def __init__(
         preference=None,
         affinity="euclidean",
         verbose=False,
-        random_state=None
+        random_state=None,
     ):
 
         self.damping = damping

diff --git a/sklearn/cluster/_agglomerative.py b/sklearn/cluster/_agglomerative.py
@@ -853,7 +853,7 @@ def __init__(
         compute_full_tree="auto",
         linkage="ward",
         distance_threshold=None,
-        compute_distances=False
+        compute_distances=False,
     ):
         self.n_clusters = n_clusters
         self.distance_threshold = distance_threshold
@@ -953,7 +953,7 @@ def fit(self, X, y=None):
             connectivity=connectivity,
             n_clusters=n_clusters,
             return_distance=return_distance,
-            **kwargs
+            **kwargs,
         )
         (self.children_, self.n_connected_components_, self.n_leaves_, parents) = out[
             :4
@@ -1141,7 +1141,7 @@ def __init__(
         linkage="ward",
         pooling_func=np.mean,
         distance_threshold=None,
-        compute_distances=False
+        compute_distances=False,
     ):
         super().__init__(
             n_clusters=n_clusters,

diff --git a/sklearn/cluster/_bicluster.py b/sklearn/cluster/_bicluster.py
@@ -309,7 +309,7 @@ def __init__(
         mini_batch=False,
         init="k-means++",
         n_init=10,
-        random_state=None
+        random_state=None,
     ):
         super().__init__(
             n_clusters, svd_method, n_svd_vecs, mini_batch, init, n_init, random_state
@@ -461,7 +461,7 @@ def __init__(
         mini_batch=False,
         init="k-means++",
         n_init=10,
-        random_state=None
+        random_state=None,
     ):
         super().__init__(
             n_clusters, svd_method, n_svd_vecs, mini_batch, init, n_init, random_state

diff --git a/sklearn/cluster/_birch.py b/sklearn/cluster/_birch.py
@@ -463,7 +463,7 @@ def __init__(
         branching_factor=50,
         n_clusters=3,
         compute_labels=True,
-        copy=True
+        copy=True,
     ):
         self.threshold = threshold
         self.branching_factor = branching_factor

diff --git a/sklearn/cluster/_dbscan.py b/sklearn/cluster/_dbscan.py
@@ -31,7 +31,7 @@ def dbscan(
     leaf_size=30,
     p=2,
     sample_weight=None,
-    n_jobs=None
+    n_jobs=None,
 ):
     """Perform DBSCAN clustering from vector array or distance matrix.
 
@@ -301,7 +301,7 @@ def __init__(
         algorithm="auto",
         leaf_size=30,
         p=None,
-        n_jobs=None
+        n_jobs=None,
     ):
         self.eps = eps
         self.min_samples = min_samples

diff --git a/sklearn/cluster/_mean_shift.py b/sklearn/cluster/_mean_shift.py
@@ -116,7 +116,7 @@ def mean_shift(
     min_bin_freq=1,
     cluster_all=True,
     max_iter=300,
-    n_jobs=None
+    n_jobs=None,
 ):
     """Perform mean shift clustering of data using a flat kernel.
 
@@ -380,7 +380,7 @@ def __init__(
         min_bin_freq=1,
         cluster_all=True,
         n_jobs=None,
-        max_iter=300
+        max_iter=300,
     ):
         self.bandwidth = bandwidth
         self.seeds = seeds

diff --git a/sklearn/compose/_target.py b/sklearn/compose/_target.py
@@ -122,7 +122,7 @@ def __init__(
         transformer=None,
         func=None,
         inverse_func=None,
-        check_inverse=True
+        check_inverse=True,
     ):
         self.regressor = regressor
         self.transformer = transformer

diff --git a/sklearn/covariance/_elliptic_envelope.py b/sklearn/covariance/_elliptic_envelope.py
@@ -132,7 +132,7 @@ def __init__(
         assume_centered=False,
         support_fraction=None,
         contamination=0.1,
-        random_state=None
+        random_state=None,
     ):
         super().__init__(
             store_precision=store_precision,

diff --git a/sklearn/covariance/_graph_lasso.py b/sklearn/covariance/_graph_lasso.py
@@ -87,7 +87,7 @@ def graphical_lasso(
     verbose=False,
     return_costs=False,
     eps=np.finfo(np.float64).eps,
-    return_n_iter=False
+    return_n_iter=False,
 ):
     """l1-penalized covariance estimator
 
@@ -408,7 +408,7 @@ def __init__(
         enet_tol=1e-4,
         max_iter=100,
         verbose=False,
-        assume_centered=False
+        assume_centered=False,
     ):
         super().__init__(assume_centered=assume_centered)
         self.alpha = alpha
@@ -758,7 +758,7 @@ def __init__(
         mode="cd",
         n_jobs=None,
         verbose=False,
-        assume_centered=False
+        assume_centered=False,
     ):
         super().__init__(
             mode=mode,

diff --git a/sklearn/covariance/_robust_covariance.py b/sklearn/covariance/_robust_covariance.py
@@ -687,7 +687,7 @@ def __init__(
         store_precision=True,
         assume_centered=False,
         support_fraction=None,
-        random_state=None
+        random_state=None,
     ):
         self.store_precision = store_precision
         self.assume_centered = assume_centered

diff --git a/sklearn/datasets/_base.py b/sklearn/datasets/_base.py
@@ -93,7 +93,7 @@ def load_files(
     shuffle=True,
     encoding=None,
     decode_error="strict",
-    random_state=0
+    random_state=0,
 ):
     """Load text files with categories as subfolder names.
 

diff --git a/sklearn/datasets/_lfw.py b/sklearn/datasets/_lfw.py
@@ -232,7 +232,7 @@ def fetch_lfw_people(
     color=False,
     slice_=(slice(70, 195), slice(78, 172)),
     download_if_missing=True,
-    return_X_y=False
+    return_X_y=False,
 ):
     """Load the Labeled Faces in the Wild (LFW) people dataset \
 (classification).
@@ -413,7 +413,7 @@ def fetch_lfw_pairs(
     resize=0.5,
     color=False,
     slice_=(slice(70, 195), slice(78, 172)),
-    download_if_missing=True
+    download_if_missing=True,
 ):
     """Load the Labeled Faces in the Wild (LFW) pairs dataset (classification).
 

diff --git a/sklearn/datasets/_olivetti_faces.py b/sklearn/datasets/_olivetti_faces.py
@@ -41,7 +41,7 @@ def fetch_olivetti_faces(
     shuffle=False,
     random_state=0,
     download_if_missing=True,
-    return_X_y=False
+    return_X_y=False,
 ):
     """Load the Olivetti faces data-set from AT&T (classification).
 

@@ -551,7 +551,7 @@ def _download_data_to_bunch(
     data_columns: List[int],
     target_columns: List,
     shape: Optional[Tuple[int, int]],
-    md5_checksum: str
+    md5_checksum: str,
 ):
     """Download OpenML ARFF and convert to Bunch of data"""
     # NB: this function is long in order to handle retry for any failure
@@ -724,7 +724,7 @@ def fetch_openml(
     target_column: Optional[Union[str, List]] = "default-target",
     cache: bool = True,
     return_X_y: bool = False,
-    as_frame: Union[str, bool] = "auto"
+    as_frame: Union[str, bool] = "auto",
 ):
     """Fetch dataset from openml by name or dataset id.
 

diff --git a/sklearn/datasets/_rcv1.py b/sklearn/datasets/_rcv1.py
@@ -92,7 +92,7 @@ def fetch_rcv1(
     download_if_missing=True,
     random_state=None,
     shuffle=False,
-    return_X_y=False
+    return_X_y=False,
 ):
     """Load the RCV1 multilabel dataset (classification).
 

diff --git a/sklearn/datasets/_svmlight_format_io.py b/sklearn/datasets/_svmlight_format_io.py
@@ -48,7 +48,7 @@ def load_svmlight_file(
     zero_based="auto",
     query_id=False,
     offset=0,
-    length=-1
+    length=-1,
 ):
     """Load datasets in the svmlight / libsvm format into sparse CSR matrix
 
@@ -225,7 +225,7 @@ def load_svmlight_files(
     zero_based="auto",
     query_id=False,
     offset=0,
-    length=-1
+    length=-1,
 ):
     """Load dataset from multiple files in SVMlight format
 

diff --git a/sklearn/decomposition/_factor_analysis.py b/sklearn/decomposition/_factor_analysis.py
@@ -164,7 +164,7 @@ def __init__(
         svd_method="randomized",
         iterated_power=3,
         rotation=None,
-        random_state=0
+        random_state=0,
     ):
         self.n_components = n_components
         self.copy = copy

diff --git a/sklearn/decomposition/_fastica.py b/sklearn/decomposition/_fastica.py
@@ -161,7 +161,7 @@ def fastica(
     random_state=None,
     return_X_mean=False,
     compute_sources=True,
-    return_n_iter=False
+    return_n_iter=False,
 ):
     """Perform Fast Independent Component Analysis.
 
@@ -426,7 +426,7 @@ def __init__(
         max_iter=200,
         tol=1e-4,
         w_init=None,
-        random_state=None
+        random_state=None,
     ):
         super().__init__()
         if max_iter < 1:

diff --git a/sklearn/decomposition/_lda.py b/sklearn/decomposition/_lda.py
@@ -325,7 +325,7 @@ def __init__(
         max_doc_update_iter=100,
         n_jobs=None,
         verbose=0,
-        random_state=None
+        random_state=None,
     ):
         self.n_components = n_components
         self.doc_topic_prior = doc_topic_prior

diff --git a/sklearn/decomposition/_nmf.py b/sklearn/decomposition/_nmf.py
@@ -918,7 +918,7 @@ def non_negative_factorization(
     regularization=None,
     random_state=None,
     verbose=0,
-    shuffle=False
+    shuffle=False,
 ):
     """Compute Non-negative Matrix Factorization (NMF).
 
@@ -1292,7 +1292,7 @@ def __init__(
         l1_ratio=0.0,
         verbose=0,
         shuffle=False,
-        regularization="both"
+        regularization="both",
     ):
         self.n_components = n_components
         self.init = init

diff --git a/sklearn/decomposition/_pca.py b/sklearn/decomposition/_pca.py
@@ -345,7 +345,7 @@ def __init__(
         svd_solver="auto",
         tol=0.0,
         iterated_power="auto",
-        random_state=None
+        random_state=None,
     ):
         self.n_components = n_components
         self.copy = copy

diff --git a/sklearn/decomposition/_sparse_pca.py b/sklearn/decomposition/_sparse_pca.py
@@ -129,7 +129,7 @@ def __init__(
         U_init=None,
         V_init=None,
         verbose=False,
-        random_state=None
+        random_state=None,
     ):
         self.n_components = n_components
         self.alpha = alpha
@@ -342,7 +342,7 @@ def __init__(
         shuffle=True,
         n_jobs=None,
         method="lars",
-        random_state=None
+        random_state=None,
     ):
         super().__init__(
             n_components=n_components,

diff --git a/sklearn/decomposition/_truncated_svd.py b/sklearn/decomposition/_truncated_svd.py
@@ -134,7 +134,7 @@ def __init__(
         algorithm="randomized",
         n_iter=5,
         random_state=None,
-        tol=0.0
+        tol=0.0,
     ):
         self.algorithm = algorithm
         self.n_components = n_components

diff --git a/sklearn/ensemble/_bagging.py b/sklearn/ensemble/_bagging.py
@@ -220,7 +220,7 @@ def __init__(
         warm_start=False,
         n_jobs=None,
         random_state=None,
-        verbose=0
+        verbose=0,
     ):
         super().__init__(base_estimator=base_estimator, n_estimators=n_estimators)
 
@@ -648,7 +648,7 @@ def __init__(
         warm_start=False,
         n_jobs=None,
         random_state=None,
-        verbose=0
+        verbose=0,
     ):
 
         super().__init__(
@@ -1062,7 +1062,7 @@ def __init__(
         warm_start=False,
         n_jobs=None,
         random_state=None,
-        verbose=0
+        verbose=0,
     ):
         super().__init__(
             base_estimator,