MNT add isort to ruff's rules (#26649)

scikit-learn · Jun 21, 2023 · 42173fd · 42173fd
1 parent 4a8b4f9
commit 42173fd
Show file tree

Hide file tree

Showing 771 changed files with 5,515 additions and 5,563 deletions.
diff --git a/.github/scripts/label_title_regex.py b/.github/scripts/label_title_regex.py
@@ -1,10 +1,11 @@
 """Labels PRs based on title. Must be run in a github action with the
 pull_request_target event."""
-from github import Github
-import os
 import json
+import os
 import re
 
+from github import Github
+
 context_dict = json.loads(os.getenv("CONTEXT_GITHUB"))
 
 repo = context_dict["repository"]

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -14,6 +14,7 @@ repos:
     rev: v0.0.272
     hooks:
     -   id: ruff
+        args: ["--fix", "--show-source"]
 -   repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.3.0
     hooks:

diff --git a/asv_benchmarks/benchmarks/cluster.py b/asv_benchmarks/benchmarks/cluster.py
@@ -1,7 +1,7 @@
 from sklearn.cluster import KMeans, MiniBatchKMeans
 
 from .common import Benchmark, Estimator, Predictor, Transformer
-from .datasets import _blobs_dataset, _20newsgroups_highdim_dataset
+from .datasets import _20newsgroups_highdim_dataset, _blobs_dataset
 from .utils import neg_mean_inertia
 
 

diff --git a/asv_benchmarks/benchmarks/common.py b/asv_benchmarks/benchmarks/common.py
@@ -1,11 +1,11 @@
-import os
+import itertools
 import json
-import timeit
+import os
 import pickle
-import itertools
+import timeit
 from abc import ABC, abstractmethod
-from pathlib import Path
 from multiprocessing import cpu_count
+from pathlib import Path
 
 import numpy as np
 

diff --git a/asv_benchmarks/benchmarks/datasets.py b/asv_benchmarks/benchmarks/datasets.py
@@ -1,21 +1,22 @@
+from pathlib import Path
+
 import numpy as np
 import scipy.sparse as sp
 from joblib import Memory
-from pathlib import Path
 
-from sklearn.decomposition import TruncatedSVD
 from sklearn.datasets import (
-    make_blobs,
     fetch_20newsgroups,
+    fetch_olivetti_faces,
     fetch_openml,
     load_digits,
-    make_regression,
+    make_blobs,
     make_classification,
-    fetch_olivetti_faces,
+    make_regression,
 )
-from sklearn.preprocessing import MaxAbsScaler, StandardScaler
+from sklearn.decomposition import TruncatedSVD
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import MaxAbsScaler, StandardScaler
 
 # memory location for caching datasets
 M = Memory(location=str(Path(__file__).resolve().parent / "cache"))

diff --git a/asv_benchmarks/benchmarks/decomposition.py b/asv_benchmarks/benchmarks/decomposition.py
@@ -1,8 +1,8 @@
 from sklearn.decomposition import PCA, DictionaryLearning, MiniBatchDictionaryLearning
 
 from .common import Benchmark, Estimator, Transformer
-from .datasets import _olivetti_faces_dataset, _mnist_dataset
-from .utils import make_pca_scorers, make_dict_learning_scorers
+from .datasets import _mnist_dataset, _olivetti_faces_dataset
+from .utils import make_dict_learning_scorers, make_pca_scorers
 
 
 class PCABenchmark(Transformer, Estimator, Benchmark):

diff --git a/asv_benchmarks/benchmarks/ensemble.py b/asv_benchmarks/benchmarks/ensemble.py
@@ -1,7 +1,7 @@
 from sklearn.ensemble import (
-    RandomForestClassifier,
     GradientBoostingClassifier,
     HistGradientBoostingClassifier,
+    RandomForestClassifier,
 )
 
 from .common import Benchmark, Estimator, Predictor

diff --git a/asv_benchmarks/benchmarks/linear_model.py b/asv_benchmarks/benchmarks/linear_model.py
@@ -1,9 +1,9 @@
 from sklearn.linear_model import (
-    LogisticRegression,
-    Ridge,
     ElasticNet,
     Lasso,
     LinearRegression,
+    LogisticRegression,
+    Ridge,
     SGDRegressor,
 )
 

diff --git a/benchmarks/bench_20newsgroups.py b/benchmarks/bench_20newsgroups.py
@@ -1,18 +1,19 @@
-from time import time
 import argparse
-import numpy as np
+from time import time
 
-from sklearn.dummy import DummyClassifier
+import numpy as np
 
 from sklearn.datasets import fetch_20newsgroups_vectorized
-from sklearn.metrics import accuracy_score
-from sklearn.utils.validation import check_array
-
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.ensemble import ExtraTreesClassifier
-from sklearn.ensemble import AdaBoostClassifier
+from sklearn.dummy import DummyClassifier
+from sklearn.ensemble import (
+    AdaBoostClassifier,
+    ExtraTreesClassifier,
+    RandomForestClassifier,
+)
 from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score
 from sklearn.naive_bayes import MultinomialNB
+from sklearn.utils.validation import check_array
 
 ESTIMATORS = {
     "dummy": DummyClassifier(),

diff --git a/benchmarks/bench_covertype.py b/benchmarks/bench_covertype.py
@@ -45,20 +45,24 @@
 #         Arnaud Joly <[email protected]>
 # License: BSD 3 clause
 
+import argparse
 import os
 from time import time
-import argparse
+
 import numpy as np
 from joblib import Memory
 
 from sklearn.datasets import fetch_covtype, get_data_home
-from sklearn.svm import LinearSVC
-from sklearn.linear_model import SGDClassifier, LogisticRegression
+from sklearn.ensemble import (
+    ExtraTreesClassifier,
+    GradientBoostingClassifier,
+    RandomForestClassifier,
+)
+from sklearn.linear_model import LogisticRegression, SGDClassifier
+from sklearn.metrics import zero_one_loss
 from sklearn.naive_bayes import GaussianNB
+from sklearn.svm import LinearSVC
 from sklearn.tree import DecisionTreeClassifier
-from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
-from sklearn.ensemble import GradientBoostingClassifier
-from sklearn.metrics import zero_one_loss
 from sklearn.utils import check_array
 
 # Memoize the data extraction and memory map the resulting

diff --git a/benchmarks/bench_feature_expansions.py b/benchmarks/bench_feature_expansions.py
@@ -1,8 +1,10 @@
+from time import time
+
 import matplotlib.pyplot as plt
 import numpy as np
 import scipy.sparse as sparse
+
 from sklearn.preprocessing import PolynomialFeatures
-from time import time
 
 degree = 2
 trials = 3

diff --git a/benchmarks/bench_glm.py b/benchmarks/bench_glm.py
@@ -5,9 +5,10 @@
 
 """
 from datetime import datetime
+
 import numpy as np
-from sklearn import linear_model
 
+from sklearn import linear_model
 
 if __name__ == "__main__":
     import matplotlib.pyplot as plt

diff --git a/benchmarks/bench_glmnet.py b/benchmarks/bench_glmnet.py
@@ -16,9 +16,11 @@
 
 In both cases, only 10% of the features are informative.
 """
-import numpy as np
 import gc
 from time import time
+
+import numpy as np
+
 from sklearn.datasets import make_regression
 
 alpha = 0.1
@@ -45,11 +47,11 @@ def bench(factory, X, Y, X_test, Y_test, ref_coef):
 
 
 if __name__ == "__main__":
-    from glmnet.elastic_net import Lasso as GlmnetLasso
-    from sklearn.linear_model import Lasso as ScikitLasso
-
     # Delayed import of matplotlib.pyplot
     import matplotlib.pyplot as plt
+    from glmnet.elastic_net import Lasso as GlmnetLasso
+
+    from sklearn.linear_model import Lasso as ScikitLasso
 
     scikit_results = []
     glmnet_results = []

diff --git a/benchmarks/bench_hist_gradient_boosting.py b/benchmarks/bench_hist_gradient_boosting.py
@@ -1,15 +1,16 @@
-from time import time
 import argparse
+from time import time
 
 import matplotlib.pyplot as plt
 import numpy as np
-from sklearn.model_selection import train_test_split
-from sklearn.ensemble import HistGradientBoostingRegressor
-from sklearn.ensemble import HistGradientBoostingClassifier
-from sklearn.datasets import make_classification
-from sklearn.datasets import make_regression
-from sklearn.ensemble._hist_gradient_boosting.utils import get_equivalent_estimator
 
+from sklearn.datasets import make_classification, make_regression
+from sklearn.ensemble import (
+    HistGradientBoostingClassifier,
+    HistGradientBoostingRegressor,
+)
+from sklearn.ensemble._hist_gradient_boosting.utils import get_equivalent_estimator
+from sklearn.model_selection import train_test_split
 
 parser = argparse.ArgumentParser()
 parser.add_argument("--n-leaf-nodes", type=int, default=31)

diff --git a/benchmarks/bench_hist_gradient_boosting_adult.py b/benchmarks/bench_hist_gradient_boosting_adult.py
@@ -4,15 +4,14 @@
 import numpy as np
 import pandas as pd
 
-from sklearn.model_selection import train_test_split
-from sklearn.compose import make_column_transformer, make_column_selector
+from sklearn.compose import make_column_selector, make_column_transformer
 from sklearn.datasets import fetch_openml
-from sklearn.metrics import accuracy_score, roc_auc_score
 from sklearn.ensemble import HistGradientBoostingClassifier
 from sklearn.ensemble._hist_gradient_boosting.utils import get_equivalent_estimator
+from sklearn.metrics import accuracy_score, roc_auc_score
+from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import OrdinalEncoder
 
-
 parser = argparse.ArgumentParser()
 parser.add_argument("--n-leaf-nodes", type=int, default=31)
 parser.add_argument("--n-trees", type=int, default=100)

diff --git a/benchmarks/bench_hist_gradient_boosting_categorical_only.py b/benchmarks/bench_hist_gradient_boosting_categorical_only.py
@@ -1,11 +1,10 @@
 import argparse
 from time import time
 
-from sklearn.preprocessing import KBinsDiscretizer
 from sklearn.datasets import make_classification
 from sklearn.ensemble import HistGradientBoostingClassifier
 from sklearn.ensemble._hist_gradient_boosting.utils import get_equivalent_estimator
-
+from sklearn.preprocessing import KBinsDiscretizer
 
 parser = argparse.ArgumentParser()
 parser.add_argument("--n-leaf-nodes", type=int, default=31)

diff --git a/benchmarks/bench_hist_gradient_boosting_higgsboson.py b/benchmarks/bench_hist_gradient_boosting_higgsboson.py
@@ -1,17 +1,17 @@
-from urllib.request import urlretrieve
+import argparse
 import os
 from gzip import GzipFile
 from time import time
-import argparse
+from urllib.request import urlretrieve
 
 import numpy as np
 import pandas as pd
 from joblib import Memory
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score, roc_auc_score
+
 from sklearn.ensemble import HistGradientBoostingClassifier
 from sklearn.ensemble._hist_gradient_boosting.utils import get_equivalent_estimator
-
+from sklearn.metrics import accuracy_score, roc_auc_score
+from sklearn.model_selection import train_test_split
 
 parser = argparse.ArgumentParser()
 parser.add_argument("--n-leaf-nodes", type=int, default=31)

diff --git a/benchmarks/bench_hist_gradient_boosting_threading.py b/benchmarks/bench_hist_gradient_boosting_threading.py
@@ -1,18 +1,19 @@
-from time import time
 import argparse
 import os
 from pprint import pprint
+from time import time
 
 import numpy as np
 from threadpoolctl import threadpool_limits
+
 import sklearn
-from sklearn.model_selection import train_test_split
-from sklearn.ensemble import HistGradientBoostingRegressor
-from sklearn.ensemble import HistGradientBoostingClassifier
-from sklearn.datasets import make_classification
-from sklearn.datasets import make_regression
+from sklearn.datasets import make_classification, make_regression
+from sklearn.ensemble import (
+    HistGradientBoostingClassifier,
+    HistGradientBoostingRegressor,
+)
 from sklearn.ensemble._hist_gradient_boosting.utils import get_equivalent_estimator
-
+from sklearn.model_selection import train_test_split
 
 parser = argparse.ArgumentParser()
 parser.add_argument("--n-leaf-nodes", type=int, default=31)
@@ -290,8 +291,8 @@ def one_run(n_threads, n_samples):
 
 
 if args.plot or args.plot_filename:
-    import matplotlib.pyplot as plt
     import matplotlib
+    import matplotlib.pyplot as plt
 
     fig, axs = plt.subplots(2, figsize=(12, 12))
 

diff --git a/benchmarks/bench_isolation_forest.py b/benchmarks/bench_isolation_forest.py
@@ -17,12 +17,13 @@
 """
 
 from time import time
-import numpy as np
+
 import matplotlib.pyplot as plt
+import numpy as np
 
+from sklearn.datasets import fetch_covtype, fetch_kddcup99, fetch_openml
 from sklearn.ensemble import IsolationForest
-from sklearn.metrics import roc_curve, auc
-from sklearn.datasets import fetch_kddcup99, fetch_covtype, fetch_openml
+from sklearn.metrics import auc, roc_curve
 from sklearn.preprocessing import LabelBinarizer
 from sklearn.utils import shuffle as sh
 

diff --git a/benchmarks/bench_isotonic.py b/benchmarks/bench_isotonic.py
@@ -10,13 +10,15 @@
 This allows the scaling of the algorithm with the problem size to be
 visualized and understood.
 """
-import numpy as np
+import argparse
 import gc
 from datetime import datetime
-from sklearn.isotonic import isotonic_regression
-from scipy.special import expit
+
 import matplotlib.pyplot as plt
-import argparse
+import numpy as np
+from scipy.special import expit
+
+from sklearn.isotonic import isotonic_regression
 
 
 def generate_perturbed_logarithm_dataset(size):

diff --git a/benchmarks/bench_kernel_pca_solvers_time_vs_n_components.py b/benchmarks/bench_kernel_pca_solvers_time_vs_n_components.py
@@ -39,13 +39,12 @@
 
 import time
 
-import numpy as np
 import matplotlib.pyplot as plt
-
+import numpy as np
 from numpy.testing import assert_array_almost_equal
-from sklearn.decomposition import KernelPCA
-from sklearn.datasets import make_circles
 
+from sklearn.datasets import make_circles
+from sklearn.decomposition import KernelPCA
 
 print(__doc__)