scikit-learn · qinhanmin2014 · Feb 8, 2019 · Jan 10, 2019 · Jan 16, 2019 · Jan 16, 2019
diff --git a/benchmarks/bench_plot_neighbors.py b/benchmarks/bench_plot_neighbors.py
@@ -38,10 +38,10 @@ def barplot_neighbors(Nrange=2 ** np.arange(1, 11),
 
     #------------------------------------------------------------
     # varying N
-    N_results_build = dict([(alg, np.zeros(len(Nrange)))
-                            for alg in algorithms])
-    N_results_query = dict([(alg, np.zeros(len(Nrange)))
-                            for alg in algorithms])
+    N_results_build = {alg: np.zeros(len(Nrange))
+                       for alg in algorithms}
+    N_results_query = {alg: np.zeros(len(Nrange))
+                       for alg in algorithms}
 
     for i, NN in enumerate(Nrange):
         print("N = %i (%i out of %i)" % (NN, i + 1, len(Nrange)))
@@ -61,10 +61,10 @@ def barplot_neighbors(Nrange=2 ** np.arange(1, 11),
 
     #------------------------------------------------------------
     # varying D
-    D_results_build = dict([(alg, np.zeros(len(Drange)))
-                            for alg in algorithms])
-    D_results_query = dict([(alg, np.zeros(len(Drange)))
-                            for alg in algorithms])
+    D_results_build = {alg: np.zeros(len(Drange))
+                       for alg in algorithms}
+    D_results_query = {alg: np.zeros(len(Drange))
+                       for alg in algorithms}
 
     for i, DD in enumerate(Drange):
         print("D = %i (%i out of %i)" % (DD, i + 1, len(Drange)))
@@ -84,10 +84,10 @@ def barplot_neighbors(Nrange=2 ** np.arange(1, 11),
 
     #------------------------------------------------------------
     # varying k
-    k_results_build = dict([(alg, np.zeros(len(krange)))
-                            for alg in algorithms])
-    k_results_query = dict([(alg, np.zeros(len(krange)))
-                            for alg in algorithms])
+    k_results_build = {alg: np.zeros(len(krange))
+                       for alg in algorithms}
+    k_results_query = {alg: np.zeros(len(krange))
+                       for alg in algorithms}
 
     X = get_data(N, DD, dataset)
 

diff --git a/benchmarks/bench_plot_nmf.py b/benchmarks/bench_plot_nmf.py
@@ -203,7 +203,7 @@ class _PGNMF(NMF):
     def __init__(self, n_components=None, solver='pg', init=None,
                  tol=1e-4, max_iter=200, random_state=None,
                  alpha=0., l1_ratio=0., nls_max_iter=10):
-        super(_PGNMF, self).__init__(
+        super().__init__(
             n_components=n_components, init=init, solver=solver, tol=tol,
             max_iter=max_iter, random_state=random_state, alpha=alpha,
             l1_ratio=l1_ratio)

diff --git a/benchmarks/bench_sample_without_replacement.py b/benchmarks/bench_sample_without_replacement.py
@@ -133,9 +133,9 @@ def bench_sample(sampling, n_population, n_samples):
 
     ###########################################################################
     # Remove unspecified algorithm
-    sampling_algorithm = dict((key, value)
-                              for key, value in sampling_algorithm.items()
-                              if key in selected_algorithm)
+    sampling_algorithm = {key: value
+                          for key, value in sampling_algorithm.items()
+                          if key in selected_algorithm}
 
     ###########################################################################
     # Perform benchmark

diff --git a/doc/conf.py b/doc/conf.py
@@ -288,6 +288,6 @@ def setup(app):
 
 # The following is used by sphinx.ext.linkcode to provide links to github
 linkcode_resolve = make_linkcode_resolve('sklearn',
-                                         u'https://github.com/scikit-learn/'
+                                         'https://github.com/scikit-learn/'
                                          'scikit-learn/blob/{revision}/'
                                          '{package}/{path}#L{lineno}')
diff --git a/doc/tutorial/machine_learning_map/parse_path.py b/doc/tutorial/machine_learning_map/parse_path.py
@@ -29,7 +29,7 @@ class CaselessPreservingLiteral(CaselessLiteral):
         instead of as defined.
     """
     def __init__( self, matchString ):
-        super(CaselessPreservingLiteral,self).__init__( matchString.upper() )
+        super().__init__(matchString.upper())
         self.name = "'%s'" % matchString
         self.errmsg = "Expected " + self.name
         self.myException.msg = self.errmsg

diff --git a/doc/tutorial/text_analytics/data/languages/fetch_data.py b/doc/tutorial/text_analytics/data/languages/fetch_data.py
@@ -17,23 +17,23 @@
 import codecs
 
 pages = {
-    u'ar': u'http://ar.wikipedia.org/wiki/%D9%88%D9%8A%D9%83%D9%8A%D8%A8%D9%8A%D8%AF%D9%8A%D8%A7',
-    u'de': u'http://de.wikipedia.org/wiki/Wikipedia',
-    u'en': u'https://en.wikipedia.org/wiki/Wikipedia',
-    u'es': u'http://es.wikipedia.org/wiki/Wikipedia',
-    u'fr': u'http://fr.wikipedia.org/wiki/Wikip%C3%A9dia',
-    u'it': u'http://it.wikipedia.org/wiki/Wikipedia',
-    u'ja': u'http://ja.wikipedia.org/wiki/Wikipedia',
-    u'nl': u'http://nl.wikipedia.org/wiki/Wikipedia',
-    u'pl': u'http://pl.wikipedia.org/wiki/Wikipedia',
-    u'pt': u'http://pt.wikipedia.org/wiki/Wikip%C3%A9dia',
-    u'ru': u'http://ru.wikipedia.org/wiki/%D0%92%D0%B8%D0%BA%D0%B8%D0%BF%D0%B5%D0%B4%D0%B8%D1%8F',
+    'ar': 'http://ar.wikipedia.org/wiki/%D9%88%D9%8A%D9%83%D9%8A%D8%A8%D9%8A%D8%AF%D9%8A%D8%A7',   # noqa: E501
+    'de': 'http://de.wikipedia.org/wiki/Wikipedia',
+    'en': 'https://en.wikipedia.org/wiki/Wikipedia',
+    'es': 'http://es.wikipedia.org/wiki/Wikipedia',
+    'fr': 'http://fr.wikipedia.org/wiki/Wikip%C3%A9dia',
+    'it': 'http://it.wikipedia.org/wiki/Wikipedia',
+    'ja': 'http://ja.wikipedia.org/wiki/Wikipedia',
+    'nl': 'http://nl.wikipedia.org/wiki/Wikipedia',
+    'pl': 'http://pl.wikipedia.org/wiki/Wikipedia',
+    'pt': 'http://pt.wikipedia.org/wiki/Wikip%C3%A9dia',
+    'ru': 'http://ru.wikipedia.org/wiki/%D0%92%D0%B8%D0%BA%D0%B8%D0%BF%D0%B5%D0%B4%D0%B8%D1%8F',  # noqa: E501
 #    u'zh': u'http://zh.wikipedia.org/wiki/Wikipedia',
 }
 
-html_folder = u'html'
-text_folder = u'paragraphs'
-short_text_folder = u'short_paragraphs'
+html_folder = 'html'
+text_folder = 'paragraphs'
+short_text_folder = 'short_paragraphs'
 n_words_per_short_text = 5
 
 
@@ -93,7 +93,7 @@
         groups = np.array_split(words, n_groups)
 
         for group in groups:
-            small_content = u" ".join(group)
+            small_content = " ".join(group)
 
             short_text_filename = os.path.join(short_text_lang_folder,
                                                '%s_%04d.txt' % (lang, j))

diff --git a/doc/tutorial/text_analytics/skeletons/exercise_01_language_train_model.py b/doc/tutorial/text_analytics/skeletons/exercise_01_language_train_model.py
@@ -52,11 +52,11 @@
 
 # Predict the result on some short new sentences:
 sentences = [
-    u'This is a language detection test.',
-    u'Ceci est un test de d\xe9tection de la langue.',
-    u'Dies ist ein Test, um die Sprache zu erkennen.',
+    'This is a language detection test.',
+    'Ceci est un test de d\xe9tection de la langue.',
+    'Dies ist ein Test, um die Sprache zu erkennen.',
 ]
 predicted = clf.predict(sentences)
 
 for s, p in zip(sentences, predicted):
-    print(u'The language of "%s" is "%s"' % (s, dataset.target_names[p]))
+    print('The language of "%s" is "%s"' % (s, dataset.target_names[p]))
diff --git a/doc/tutorial/text_analytics/solutions/exercise_01_language_train_model.py b/doc/tutorial/text_analytics/solutions/exercise_01_language_train_model.py
@@ -60,11 +60,11 @@
 
 # Predict the result on some short new sentences:
 sentences = [
-    u'This is a language detection test.',
-    u'Ceci est un test de d\xe9tection de la langue.',
-    u'Dies ist ein Test, um die Sprache zu erkennen.',
+    'This is a language detection test.',
+    'Ceci est un test de d\xe9tection de la langue.',
+    'Dies ist ein Test, um die Sprache zu erkennen.',
 ]
 predicted = clf.predict(sentences)
 
 for s, p in zip(sentences, predicted):
-    print(u'The language of "%s" is "%s"' % (s, dataset.target_names[p]))
+    print('The language of "%s" is "%s"' % (s, dataset.target_names[p]))
diff --git a/examples/applications/plot_out_of_core_classification.py b/examples/applications/plot_out_of_core_classification.py
@@ -221,7 +221,7 @@ def get_minibatch(doc_iter, size, pos_class=positive_class):
     Note: size is before excluding invalid docs with no topics assigned.
 
     """
-    data = [(u'{title}\n\n{body}'.format(**doc), pos_class in doc['topics'])
+    data = [('{title}\n\n{body}'.format(**doc), pos_class in doc['topics'])
             for doc in itertools.islice(doc_iter, size)
             if doc['topics']]
     if not len(data):

diff --git a/examples/applications/svm_gui.py b/examples/applications/svm_gui.py
@@ -44,7 +44,7 @@
 x_min, x_max = -50, 50
 
 
-class Model(object):
+class Model:
     """The Model which hold the data. It implements the
     observable in the observer pattern and notifies the
     registered observers on change event.
@@ -76,7 +76,7 @@ def dump_svmlight_file(self, file):
         dump_svmlight_file(X, y, file)
 
 
-class Controller(object):
+class Controller:
     def __init__(self, model):
         self.model = model
         self.kernel = Tk.IntVar()
@@ -139,7 +139,7 @@ def refit(self):
             self.fit()
 
 
-class View(object):
+class View:
     """Test docstring. """
     def __init__(self, root, controller):
         f = Figure()
@@ -245,7 +245,7 @@ def plot_decision_surface(self, surface, type):
             raise ValueError("surface type unknown")
 
 
-class ControllBar(object):
+class ControllBar:
     def __init__(self, root, controller):
         fm = Tk.Frame(root)
         kernel_group = Tk.Frame(fm)

diff --git a/examples/applications/wikipedia_principal_eigenvector.py b/examples/applications/wikipedia_principal_eigenvector.py
@@ -112,7 +112,7 @@ def get_redirects(redirects_filename):
     for l, source in enumerate(redirects.keys()):
         transitive_target = None
         target = redirects[source]
-        seen = set([source])
+        seen = {source}
         while True:
             transitive_target = target
             target = redirects.get(target)
@@ -172,7 +172,7 @@ def get_adjacency_matrix(redirects_filename, page_links_filename, limit=None):
 # stop after 5M links to make it possible to work in RAM
 X, redirects, index_map = get_adjacency_matrix(
     redirects_filename, page_links_filename, limit=5000000)
-names = dict((i, name) for name, i in index_map.items())
+names = {i: name for name, i in index_map.items()}
 
 print("Computing the principal singular vectors using randomized_svd")
 t0 = time()

diff --git a/examples/gaussian_process/plot_gpr_noisy_targets.py b/examples/gaussian_process/plot_gpr_noisy_targets.py
@@ -63,8 +63,8 @@ def f(x):
 # the MSE
 plt.figure()
 plt.plot(x, f(x), 'r:', label=r'$f(x) = x\,\sin(x)$')
-plt.plot(X, y, 'r.', markersize=10, label=u'Observations')
-plt.plot(x, y_pred, 'b-', label=u'Prediction')
+plt.plot(X, y, 'r.', markersize=10, label='Observations')
+plt.plot(x, y_pred, 'b-', label='Prediction')
 plt.fill(np.concatenate([x, x[::-1]]),
          np.concatenate([y_pred - 1.9600 * sigma,
                         (y_pred + 1.9600 * sigma)[::-1]]),
@@ -99,8 +99,8 @@ def f(x):
 # the MSE
 plt.figure()
 plt.plot(x, f(x), 'r:', label=r'$f(x) = x\,\sin(x)$')
-plt.errorbar(X.ravel(), y, dy, fmt='r.', markersize=10, label=u'Observations')
-plt.plot(x, y_pred, 'b-', label=u'Prediction')
+plt.errorbar(X.ravel(), y, dy, fmt='r.', markersize=10, label='Observations')
+plt.plot(x, y_pred, 'b-', label='Prediction')
 plt.fill(np.concatenate([x, x[::-1]]),
          np.concatenate([y_pred - 1.9600 * sigma,
                         (y_pred + 1.9600 * sigma)[::-1]]),

diff --git a/examples/mixture/plot_gmm_covariances.py b/examples/mixture/plot_gmm_covariances.py
@@ -83,9 +83,9 @@ def make_ellipses(gmm, ax):
 n_classes = len(np.unique(y_train))
 
 # Try GMMs using different types of covariances.
-estimators = dict((cov_type, GaussianMixture(n_components=n_classes,
-                   covariance_type=cov_type, max_iter=20, random_state=0))
-                  for cov_type in ['spherical', 'diag', 'tied', 'full'])
+estimators = {cov_type: GaussianMixture(n_components=n_classes,
+              covariance_type=cov_type, max_iter=20, random_state=0)
+              for cov_type in ['spherical', 'diag', 'tied', 'full']}
 
 n_estimators = len(estimators)
 

diff --git a/examples/model_selection/plot_nested_cross_validation_iris.py b/examples/model_selection/plot_nested_cross_validation_iris.py
@@ -90,7 +90,7 @@
 
 score_difference = non_nested_scores - nested_scores
 
-print("Average difference of {0:6f} with std. dev. of {1:6f}."
+print("Average difference of {:6f} with std. dev. of {:6f}."
       .format(score_difference.mean(), score_difference.std()))
 
 # Plot scores on each trial for nested and non-nested CV

diff --git a/setup.py b/setup.py
@@ -49,12 +49,12 @@
 # We need to import setuptools early, if we want setuptools features,
 # as it monkey-patches the 'setup' function
 # For some commands, use setuptools
-SETUPTOOLS_COMMANDS = set([
+SETUPTOOLS_COMMANDS = {
     'develop', 'release', 'bdist_egg', 'bdist_rpm',
     'bdist_wininst', 'install_egg_info', 'build_sphinx',
     'egg_info', 'easy_install', 'upload', 'bdist_wheel',
     '--single-version-externally-managed',
-])
+}
 if SETUPTOOLS_COMMANDS.intersection(sys.argv):
     import setuptools
 
@@ -63,8 +63,8 @@
         include_package_data=True,
         extras_require={
             'alldeps': (
-                'numpy >= {0}'.format(NUMPY_MIN_VERSION),
-                'scipy >= {0}'.format(SCIPY_MIN_VERSION),
+                'numpy >= {}'.format(NUMPY_MIN_VERSION),
+                'scipy >= {}'.format(SCIPY_MIN_VERSION),
             ),
         },
     )
@@ -111,7 +111,7 @@ def run(self):
 # to PyPI at release time.
 # The URL of the artifact repositories are configured in the setup.cfg file.
 
-WHEELHOUSE_UPLOADER_COMMANDS = set(['fetch_artifacts', 'upload_all'])
+WHEELHOUSE_UPLOADER_COMMANDS = {'fetch_artifacts', 'upload_all'}
 if WHEELHOUSE_UPLOADER_COMMANDS.intersection(sys.argv):
     import wheelhouse_uploader.cmd
 
@@ -190,8 +190,8 @@ def setup_package():
                                  ],
                     cmdclass=cmdclass,
                     install_requires=[
-                        'numpy>={0}'.format(NUMPY_MIN_VERSION),
-                        'scipy>={0}'.format(SCIPY_MIN_VERSION)
+                        'numpy>={}'.format(NUMPY_MIN_VERSION),
+                        'scipy>={}'.format(SCIPY_MIN_VERSION)
                     ],
                     **extra_setuptools_args)
 
@@ -214,7 +214,7 @@ def setup_package():
         metadata['version'] = VERSION
     else:
         numpy_status = get_numpy_status()
-        numpy_req_str = "scikit-learn requires NumPy >= {0}.\n".format(
+        numpy_req_str = "scikit-learn requires NumPy >= {}.\n".format(
             NUMPY_MIN_VERSION)
 
         instructions = ("Installation instructions are available on the "
@@ -224,12 +224,12 @@ def setup_package():
         if numpy_status['up_to_date'] is False:
             if numpy_status['version']:
                 raise ImportError("Your installation of Numerical Python "
-                                  "(NumPy) {0} is out-of-date.\n{1}{2}"
+                                  "(NumPy) {} is out-of-date.\n{}{}"
                                   .format(numpy_status['version'],
                                           numpy_req_str, instructions))
             else:
                 raise ImportError("Numerical Python (NumPy) is not "
-                                  "installed.\n{0}{1}"
+                                  "installed.\n{}{}"
                                   .format(numpy_req_str, instructions))
 
         from numpy.distutils.core import setup