MAINT Run pyupgrade following Python2 deprecation (scikit-learn#12997)

Author: rth

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)
 

benchmarks/bench_plot_nmf.py

@@ -202,7 +202,7 @@ 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)

benchmarks/bench_sample_without_replacement.py

@@ -130,9 +130,9 @@ 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

doc/conf.py

@@ -288,7 +288,7 @@ 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}')
 

doc/tutorial/machine_learning_map/parse_path.py

@@ -28,7 +28,7 @@ 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

doc/tutorial/text_analytics/data/languages/fetch_data.py

@@ -12,23 +12,23 @@
 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
 
 
@@ -88,7 +88,7 @@
         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))

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]))

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]))

examples/applications/plot_out_of_core_classification.py

@@ -220,7 +220,7 @@ 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):

examples/applications/svm_gui.py

@@ -39,7 +39,7 @@
 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.
@@ -71,7 +71,7 @@ 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()
@@ -134,7 +134,7 @@ def refit(self):
             self.fit()
 
 
-class View(object):
+class View:
     """Test docstring. """
     def __init__(self, root, controller):
         f = Figure()
@@ -240,7 +240,7 @@ 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)