scikit-learn · thomasjpfan · Apr 6, 2023 · Apr 6, 2023 · Apr 6, 2023 · Apr 6, 2023
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -6,7 +6,7 @@ repos:
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
 -   repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 23.3.0
     hooks:
     -   id: black
 -   repo: https://github.com/pycqa/flake8

diff --git a/benchmarks/bench_20newsgroups.py b/benchmarks/bench_20newsgroups.py
@@ -28,7 +28,6 @@
 # Data
 
 if __name__ == "__main__":
-
     parser = argparse.ArgumentParser()
     parser.add_argument(
         "-e", "--estimators", nargs="+", required=True, choices=ESTIMATORS

diff --git a/benchmarks/bench_feature_expansions.py b/benchmarks/bench_feature_expansions.py
@@ -35,7 +35,6 @@
 
 fig, axes = plt.subplots(nrows=len(densities), ncols=1, figsize=(8, 10))
 for density, ax in zip(densities, axes):
-
     ax.plot(
         dimensionalities,
         csr_times[density] / trials,

diff --git a/benchmarks/bench_glm.py b/benchmarks/bench_glm.py
@@ -10,7 +10,6 @@
 
 
 if __name__ == "__main__":
-
     import matplotlib.pyplot as plt
 
     n_iter = 40
@@ -22,7 +21,6 @@
     dimensions = 500 * np.arange(1, n_iter + 1)
 
     for i in range(n_iter):
-
         print("Iteration %s of %s" % (i, n_iter))
 
         n_samples, n_features = 10 * i + 3, 10 * i + 3

diff --git a/benchmarks/bench_isolation_forest.py b/benchmarks/bench_isolation_forest.py
@@ -52,7 +52,6 @@ def print_outlier_ratio(y):
 
 # Loop over all datasets for fitting and scoring the estimator:
 for dat in datasets:
-
     # Loading and vectorizing the data:
     print("====== %s ======" % dat)
     print("--- Fetching data...")

diff --git a/benchmarks/bench_kernel_pca_solvers_time_vs_n_components.py b/benchmarks/bench_kernel_pca_solvers_time_vs_n_components.py
@@ -82,7 +82,6 @@
 r_time = np.empty((len(n_compo_range), n_iter)) * np.nan
 # loop
 for j, n_components in enumerate(n_compo_range):
-
     n_components = int(n_components)
     print("Performing kPCA with n_components = %i" % n_components)
 

diff --git a/benchmarks/bench_kernel_pca_solvers_time_vs_n_samples.py b/benchmarks/bench_kernel_pca_solvers_time_vs_n_samples.py
@@ -83,7 +83,6 @@
 
 # loop
 for j, n_samples in enumerate(n_samples_range):
-
     n_samples = int(n_samples)
     print("Performing kPCA with n_samples = %i" % n_samples)
 

diff --git a/benchmarks/bench_mnist.py b/benchmarks/bench_mnist.py
@@ -223,7 +223,6 @@ def load_data(dtype=np.float32, order="F"):
     )
     print("-" * 60)
     for name in sorted(args["classifiers"], key=error.get):
-
         print(
             "{0: <23} {1: >10.2f}s {2: >10.2f}s {3: >12.4f}".format(
                 name, train_time[name], test_time[name], error[name]

diff --git a/benchmarks/bench_online_ocsvm.py b/benchmarks/bench_online_ocsvm.py
@@ -65,7 +65,6 @@ def print_outlier_ratio(y):
 results_online = np.empty((len(datasets), n_axis + 5))
 
 for dat, dataset_name in enumerate(datasets):
-
     print(dataset_name)
 
     # Loading datasets
@@ -133,7 +132,6 @@ def print_outlier_ratio(y):
     gamma = 1 / n_features  # OCSVM default parameter
 
     for random_state in random_states:
-
         print("random state: %s" % random_state)
 
         X, y = shuffle(X, y, random_state=random_state)

diff --git a/benchmarks/bench_plot_fastkmeans.py b/benchmarks/bench_plot_fastkmeans.py
@@ -8,7 +8,6 @@
 
 
 def compute_bench(samples_range, features_range):
-
     it = 0
     results = defaultdict(lambda: [])
     chunk = 100

diff --git a/benchmarks/bench_plot_hierarchical.py b/benchmarks/bench_plot_hierarchical.py
@@ -8,7 +8,6 @@
 
 
 def compute_bench(samples_range, features_range):
-
     it = 0
     results = defaultdict(lambda: [])
 

diff --git a/benchmarks/bench_plot_lasso_path.py b/benchmarks/bench_plot_lasso_path.py
@@ -15,7 +15,6 @@
 
 
 def compute_bench(samples_range, features_range):
-
     it = 0
 
     results = defaultdict(lambda: [])

diff --git a/benchmarks/bench_plot_omp_lars.py b/benchmarks/bench_plot_omp_lars.py
@@ -14,7 +14,6 @@
 
 
 def compute_bench(samples_range, features_range):
-
     it = 0
 
     results = dict()

diff --git a/benchmarks/bench_plot_randomized_svd.py b/benchmarks/bench_plot_randomized_svd.py
@@ -342,7 +342,6 @@ def scalable_frobenius_norm_discrepancy(X, U, s, V):
 
 
 def bench_a(X, dataset_name, power_iter, n_oversamples, n_comps):
-
     all_time = defaultdict(list)
     if enable_spectral_norm:
         all_spectral = defaultdict(list)
@@ -398,7 +397,6 @@ def bench_a(X, dataset_name, power_iter, n_oversamples, n_comps):
 
 
 def bench_b(power_list):
-
     n_samples, n_features = 1000, 10000
     data_params = {
         "n_samples": n_samples,

diff --git a/benchmarks/bench_plot_svd.py b/benchmarks/bench_plot_svd.py
@@ -13,7 +13,6 @@
 
 
 def compute_bench(samples_range, features_range, n_iter=3, rank=50):
-
     it = 0
 
     results = defaultdict(lambda: [])

diff --git a/benchmarks/bench_sample_without_replacement.py b/benchmarks/bench_sample_without_replacement.py
@@ -105,47 +105,53 @@ def bench_sample(sampling, n_population, n_samples):
 
     ###########################################################################
     # Set Python core input
-    sampling_algorithm[
-        "python-core-sample"
-    ] = lambda n_population, n_sample: random.sample(range(n_population), n_sample)
+    sampling_algorithm["python-core-sample"] = (
+        lambda n_population, n_sample: random.sample(range(n_population), n_sample)
+    )
 
     ###########################################################################
     # Set custom automatic method selection
-    sampling_algorithm[
-        "custom-auto"
-    ] = lambda n_population, n_samples, random_state=None: sample_without_replacement(
-        n_population, n_samples, method="auto", random_state=random_state
+    sampling_algorithm["custom-auto"] = (
+        lambda n_population, n_samples, random_state=None: sample_without_replacement(
+            n_population, n_samples, method="auto", random_state=random_state
+        )
     )
 
     ###########################################################################
     # Set custom tracking based method
-    sampling_algorithm[
-        "custom-tracking-selection"
-    ] = lambda n_population, n_samples, random_state=None: sample_without_replacement(
-        n_population, n_samples, method="tracking_selection", random_state=random_state
+    sampling_algorithm["custom-tracking-selection"] = (
+        lambda n_population, n_samples, random_state=None: sample_without_replacement(
+            n_population,
+            n_samples,
+            method="tracking_selection",
+            random_state=random_state,
+        )
     )
 
     ###########################################################################
     # Set custom reservoir based method
-    sampling_algorithm[
-        "custom-reservoir-sampling"
-    ] = lambda n_population, n_samples, random_state=None: sample_without_replacement(
-        n_population, n_samples, method="reservoir_sampling", random_state=random_state
+    sampling_algorithm["custom-reservoir-sampling"] = (
+        lambda n_population, n_samples, random_state=None: sample_without_replacement(
+            n_population,
+            n_samples,
+            method="reservoir_sampling",
+            random_state=random_state,
+        )
     )
 
     ###########################################################################
     # Set custom reservoir based method
-    sampling_algorithm[
-        "custom-pool"
-    ] = lambda n_population, n_samples, random_state=None: sample_without_replacement(
-        n_population, n_samples, method="pool", random_state=random_state
+    sampling_algorithm["custom-pool"] = (
+        lambda n_population, n_samples, random_state=None: sample_without_replacement(
+            n_population, n_samples, method="pool", random_state=random_state
+        )
     )
 
     ###########################################################################
     # Numpy permutation based
-    sampling_algorithm[
-        "numpy-permutation"
-    ] = lambda n_population, n_sample: np.random.permutation(n_population)[:n_sample]
+    sampling_algorithm["numpy-permutation"] = (
+        lambda n_population, n_sample: np.random.permutation(n_population)[:n_sample]
+    )
 
     ###########################################################################
     # Remove unspecified algorithm

diff --git a/benchmarks/bench_text_vectorizers.py b/benchmarks/bench_text_vectorizers.py
@@ -45,7 +45,6 @@ def f():
     [CountVectorizer, TfidfVectorizer, HashingVectorizer],
     [("word", (1, 1)), ("word", (1, 2)), ("char", (4, 4)), ("char_wb", (4, 4))],
 ):
-
     bench = {"vectorizer": Vectorizer.__name__}
     params = {"analyzer": analyzer, "ngram_range": ngram_range}
     bench.update(params)

diff --git a/benchmarks/bench_tree.py b/benchmarks/bench_tree.py
@@ -60,7 +60,6 @@ def bench_scikit_tree_regressor(X, Y):
 
 
 if __name__ == "__main__":
-
     print("============================================")
     print("Warning: this is going to take a looong time")
     print("============================================")

diff --git a/benchmarks/bench_tsne_mnist.py b/benchmarks/bench_tsne_mnist.py
@@ -129,8 +129,7 @@ def sanitize(filename):
         try:
             from bhtsne.bhtsne import run_bh_tsne
         except ImportError as e:
-            raise ImportError(
-                """\
+            raise ImportError("""\
 If you want comparison with the reference implementation, build the
 binary from source (https://github.com/lvdmaaten/bhtsne) in the folder
 benchmarks/bhtsne and add an empty `__init__.py` file in the folder:
@@ -140,8 +139,7 @@ def sanitize(filename):
 $ g++ sptree.cpp tsne.cpp tsne_main.cpp -o bh_tsne -O2
 $ touch __init__.py
 $ cd ..
-"""
-            ) from e
+""") from e
 
         def bhtsne(X):
             """Wrapper for the reference lvdmaaten/bhtsne implementation."""
@@ -160,7 +158,6 @@ def bhtsne(X):
         methods.append(("lvdmaaten/bhtsne", bhtsne))
 
     if args.profile:
-
         try:
             from memory_profiler import profile
         except ImportError as e:

diff --git a/build_tools/generate_authors_table.py b/build_tools/generate_authors_table.py
@@ -172,7 +172,6 @@ def generate_list(contributors):
 
 
 if __name__ == "__main__":
-
     (
         core_devs,
         emeritus,
-Original file line number
+Diff line change
@@ Expand Up / @@ -83,7 +83,6 @@ @@
     # loop
     for j, n_samples in enumerate(n_samples_range):
         n_samples = int(n_samples)
         print("Performing kPCA with n_samples = %i" % n_samples)
@@ Expand Down @@
Original file line number	Diff line number	Diff line change
Expand Up		@@ -8,7 +8,6 @@


		def compute_bench(samples_range, features_range):

		it = 0
		results = defaultdict(lambda: [])

Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -15,7 +15,6 @@


		def compute_bench(samples_range, features_range):

		it = 0

		results = defaultdict(lambda: [])
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -14,7 +14,6 @@


		def compute_bench(samples_range, features_range):

		it = 0

		results = dict()
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -13,7 +13,6 @@


		def compute_bench(samples_range, features_range, n_iter=3, rank=50):

		it = 0

		results = defaultdict(lambda: [])
Expand Down