MAINT drop python 2

doc/conf.py

@@ -278,8 +278,8 @@
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [('index', 'imbalanced-learn', u'imbalanced-learn Documentation',
-              [u'G. Lemaitre, F. Nogueira, D. Oliveira, C. Aridas'], 1)]
+man_pages = [('index', 'imbalanced-learn', 'imbalanced-learn Documentation',
+              ['G. Lemaitre, F. Nogueira, D. Oliveira, C. Aridas'], 1)]
 
 # If true, show URL addresses after external links.
 # man_show_urls = False
@@ -290,8 +290,8 @@
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-    ('index', 'imbalanced-learn', u'imbalanced-learn Documentation',
-     u'G. Lemaitre, F. Nogueira, D. Oliveira, C. Aridas', 'imbalanced-learn',
+    ('index', 'imbalanced-learn', 'imbalanced-learn Documentation',
+     'G. Lemaitre, F. Nogueira, D. Oliveira, C. Aridas', 'imbalanced-learn',
      'Toolbox for imbalanced dataset in machine learning.', 'Miscellaneous'),
 ]
 
@@ -332,6 +332,6 @@ def setup(app):
 
 # The following is used by sphinx.ext.linkcode to provide links to github
 linkcode_resolve = make_linkcode_resolve('imblearn',
-                                         u'https://github.com/scikit-learn-contrib/'
+                                         'https://github.com/scikit-learn-contrib/'
                                          'imbalanced-learn/blob/{revision}/'
                                          '{package}/{path}#L{lineno}')

doc/sphinxext/sphinx_issues.py

@@ -50,11 +50,11 @@ def user_role(name, rawtext, text, lineno,
     if config.issues_user_uri:
         ref = config.issues_user_uri.format(user=target)
     else:
-        ref = 'https://github.com/{0}'.format(target)
+        ref = 'https://github.com/{}'.format(target)
     if has_explicit_title:
         text = title
     else:
-        text = '@{0}'.format(target)
+        text = '@{}'.format(target)
 
     link = nodes.reference(text=text, refuri=ref, **options)
     return [link], []
@@ -66,10 +66,10 @@ def _make_issue_node(issue_no, config, options=None):
         if config.issues_uri:
             ref = config.issues_uri.format(issue=issue_no)
         elif config.issues_github_path:
-            ref = 'https://github.com/{0}/issues/{1}'.format(
+            ref = 'https://github.com/{}/issues/{}'.format(
                 config.issues_github_path, issue_no
             )
-        issue_text = '#{0}'.format(issue_no)
+        issue_text = '#{}'.format(issue_no)
         link = nodes.reference(text=issue_text, refuri=ref, **options)
     else:
         link = None

examples/applications/plot_over_sampling_benchmark_lfw.py

@@ -31,7 +31,7 @@
 RANDOM_STATE = 42
 
 
-class DummySampler(object):
+class DummySampler:
 
     def sample(self, X, y):
         return X, y

examples/model_selection/plot_validation_curve.py

@@ -53,7 +53,7 @@
                 test_scores_mean - test_scores_std, alpha=0.2)
 idx_max = np.argmax(test_scores_mean)
 plt.scatter(param_range[idx_max], test_scores_mean[idx_max],
-            label=r'Cohen Kappa: ${0:.2f}\pm{1:.2f}$'.format(
+            label=r'Cohen Kappa: ${:.2f}\pm{:.2f}$'.format(
                 test_scores_mean[idx_max], test_scores_std[idx_max]))
 
 plt.title("Validation Curve with SMOTE-CART")

examples/under-sampling/plot_illustration_nearmiss.py

@@ -73,7 +73,7 @@ def make_plot_despine(ax):
         ax.plot([X_majority[positive_idx, 0], X_minority[sample_idx, 0]],
                 [X_majority[positive_idx, 1], X_minority[sample_idx, 1]],
                 '--' + color, alpha=0.3,
-                label='Avg. dist.={0:.2f}'.format(distance)
+                label='Avg. dist.={:.2f}'.format(distance)
                 if make_plot == 0 else "")
 ax.set_title('NearMiss-1')
 make_plot_despine(ax)
@@ -108,7 +108,7 @@ def make_plot_despine(ax):
         ax.plot([X_majority[positive_idx, 0], X_minority[sample_idx, 0]],
                 [X_majority[positive_idx, 1], X_minority[sample_idx, 1]],
                 '--' + color, alpha=0.3,
-                label='Avg. dist.={0:.2f}'.format(distance)
+                label='Avg. dist.={:.2f}'.format(distance)
                 if make_plot == 0 else "")
 ax.set_title('NearMiss-2')
 make_plot_despine(ax)
@@ -148,7 +148,7 @@ def make_plot_despine(ax):
         ax.plot([X_majority[positive_idx, 0], X_minority[sample_idx, 0]],
                 [X_majority[positive_idx, 1], X_minority[sample_idx, 1]],
                 '--' + color, alpha=0.3,
-                label='Avg. dist.={0:.2f}'.format(distance)
+                label='Avg. dist.={:.2f}'.format(distance)
                 if make_plot == 0 else "")
 ax.set_title('NearMiss-3')
 make_plot_despine(ax)

imblearn/base.py

@@ -21,7 +21,7 @@
 from .utils.deprecation import deprecate_parameter
 
 
-class SamplerMixin(six.with_metaclass(ABCMeta, BaseEstimator)):
+class SamplerMixin(BaseEstimator, metaclass=ABCMeta):
     """Mixin class for samplers with abstract method.
 
     Warning: This class should not be used directly. Use the derive classes
@@ -225,7 +225,7 @@ class FunctionSampler(BaseSampler):
     _sampling_type = 'bypass'
 
     def __init__(self, func=None, accept_sparse=True, kw_args=None):
-        super(FunctionSampler, self).__init__()
+        super().__init__()
         self.func = func
         self.accept_sparse = accept_sparse
         self.kw_args = kw_args

imblearn/combine/_smote_enn.py

@@ -99,7 +99,7 @@ def __init__(self,
                  enn=None,
                  n_jobs=1,
                  ratio=None):
-        super(SMOTEENN, self).__init__()
+        super().__init__()
         self.sampling_strategy = sampling_strategy
         self.random_state = random_state
         self.smote = smote

imblearn/combine/_smote_tomek.py

@@ -100,7 +100,7 @@ def __init__(self,
                  tomek=None,
                  n_jobs=1,
                  ratio=None):
-        super(SMOTETomek, self).__init__()
+        super().__init__()
         self.sampling_strategy = sampling_strategy
         self.random_state = random_state
         self.smote = smote

imblearn/datasets/_zenodo.py

@@ -47,18 +47,14 @@
 from collections import OrderedDict
 import tarfile
 from io import BytesIO
+from os import makedirs
 from os.path import join, isfile
-try:
-    from urllib2 import urlopen
-except ImportError:
-    from urllib.request import urlopen
+from urllib.request import urlopen
 
 import numpy as np
 
 from sklearn.datasets import get_data_home
 from sklearn.datasets.base import Bunch
-from sklearn.utils.fixes import makedirs
-from sklearn.externals import six
 from sklearn.utils import check_random_state
 
 URL = ('https://zenodo.org/record/61452/files/'
@@ -211,7 +207,7 @@ def fetch_datasets(data_home=None,
         list_data = MAP_NAME_ID.keys()
         filter_data_ = []
         for it in filter_data:
-            if isinstance(it, six.string_types):
+            if isinstance(it, str):
                 if it not in list_data:
                     raise ValueError('{} is not a dataset available. '
                                      'The available datasets are {}'.format(

imblearn/ensemble/_bagging.py

@@ -186,7 +186,7 @@ def __init__(self,
                  verbose=0,
                  ratio=None):
 
-        super(BalancedBaggingClassifier, self).__init__(
+        super().__init__(
             base_estimator,
             n_estimators=n_estimators,
             max_samples=max_samples,
@@ -207,11 +207,11 @@ def _validate_estimator(self, default=DecisionTreeClassifier()):
         `base_estimator_` attribute."""
         if not isinstance(self.n_estimators, (numbers.Integral, np.integer)):
             raise ValueError("n_estimators must be an integer, "
-                             "got {0}.".format(type(self.n_estimators)))
+                             "got {}.".format(type(self.n_estimators)))
 
         if self.n_estimators <= 0:
             raise ValueError("n_estimators must be greater than zero, "
-                             "got {0}.".format(self.n_estimators))
+                             "got {}.".format(self.n_estimators))
 
         if self.base_estimator is not None:
             base_estimator = clone(self.base_estimator)

imblearn/ensemble/_balance_cascade.py

@@ -104,7 +104,7 @@ def __init__(self,
                  n_max_subset=None,
                  estimator=None,
                  ratio=None):
-        super(BalanceCascade, self).__init__(
+        super().__init__(
             sampling_strategy=sampling_strategy, ratio=ratio)
         self.random_state = random_state
         self.return_indices = return_indices

imblearn/ensemble/_easy_ensemble.py

@@ -103,7 +103,7 @@ def __init__(self,
                  replacement=False,
                  n_subsets=10,
                  ratio=None):
-        super(EasyEnsemble, self).__init__(
+        super().__init__(
             sampling_strategy=sampling_strategy, ratio=ratio)
         self.random_state = random_state
         self.return_indices = return_indices
@@ -235,7 +235,7 @@ class EasyEnsembleClassifier(BaggingClassifier):
     def __init__(self, n_estimators=10, base_estimator=None, warm_start=False,
                  sampling_strategy='auto', replacement=False, n_jobs=1,
                  random_state=None, verbose=0):
-        super(EasyEnsembleClassifier, self).__init__(
+        super().__init__(
             base_estimator,
             n_estimators=n_estimators,
             max_samples=1.0,
@@ -255,11 +255,11 @@ def _validate_estimator(self, default=AdaBoostClassifier()):
         `base_estimator_` attribute."""
         if not isinstance(self.n_estimators, (numbers.Integral, np.integer)):
             raise ValueError("n_estimators must be an integer, "
-                             "got {0}.".format(type(self.n_estimators)))
+                             "got {}.".format(type(self.n_estimators)))
 
         if self.n_estimators <= 0:
             raise ValueError("n_estimators must be greater than zero, "
-                             "got {0}.".format(self.n_estimators))
+                             "got {}.".format(self.n_estimators))
 
         if self.base_estimator is not None:
             base_estimator = clone(self.base_estimator)

imblearn/ensemble/_forest.py

@@ -262,7 +262,7 @@ def __init__(self,
                  verbose=0,
                  warm_start=False,
                  class_weight=None):
-        super(BalancedRandomForestClassifier, self).__init__(
+        super().__init__(
             criterion=criterion,
             max_depth=max_depth,
             n_estimators=n_estimators,
@@ -288,11 +288,11 @@ def _validate_estimator(self, default=DecisionTreeClassifier()):
         `base_estimator_` attribute."""
         if not isinstance(self.n_estimators, (numbers.Integral, np.integer)):
             raise ValueError("n_estimators must be an integer, "
-                             "got {0}.".format(type(self.n_estimators)))
+                             "got {}.".format(type(self.n_estimators)))
 
         if self.n_estimators <= 0:
             raise ValueError("n_estimators must be greater than zero, "
-                             "got {0}.".format(self.n_estimators))
+                             "got {}.".format(self.n_estimators))
 
         if self.base_estimator is not None:
             self.base_estimator_ = clone(self.base_estimator)
@@ -309,8 +309,8 @@ def _make_sampler_estimator(self, random_state=None):
         sub-estimators.
         """
         estimator = clone(self.base_estimator_)
-        estimator.set_params(**dict((p, getattr(self, p))
-                                    for p in self.estimator_params))
+        estimator.set_params(**{p: getattr(self, p)
+                                    for p in self.estimator_params})
         sampler = clone(self.base_sampler_)
 
         if random_state is not None:

imblearn/ensemble/_weight_boosting.py

@@ -115,7 +115,7 @@ class RUSBoostClassifier(AdaBoostClassifier):
     def __init__(self, base_estimator=None, n_estimators=50, learning_rate=1.,
                  algorithm='SAMME.R', sampling_strategy='auto',
                  replacement=False, random_state=None):
-        super(RUSBoostClassifier, self).__init__(
+        super().__init__(
             base_estimator=base_estimator,
             n_estimators=n_estimators,
             learning_rate=learning_rate,
@@ -148,19 +148,19 @@ def fit(self, X, y, sample_weight=None):
         """
         self.samplers_ = []
         self.pipelines_ = []
-        super(RUSBoostClassifier, self).fit(X, y, sample_weight)
+        super().fit(X, y, sample_weight)
         return self
 
     def _validate_estimator(self, default=DecisionTreeClassifier()):
         """Check the estimator and the n_estimator attribute, set the
         `base_estimator_` attribute."""
         if not isinstance(self.n_estimators, (numbers.Integral, np.integer)):
             raise ValueError("n_estimators must be an integer, "
-                             "got {0}.".format(type(self.n_estimators)))
+                             "got {}.".format(type(self.n_estimators)))
 
         if self.n_estimators <= 0:
             raise ValueError("n_estimators must be greater than zero, "
-                             "got {0}.".format(self.n_estimators))
+                             "got {}.".format(self.n_estimators))
 
         if self.base_estimator is not None:
             self.base_estimator_ = clone(self.base_estimator)
@@ -177,8 +177,8 @@ def _make_sampler_estimator(self, append=True, random_state=None):
         sub-estimators.
         """
         estimator = clone(self.base_estimator_)
-        estimator.set_params(**dict((p, getattr(self, p))
-                                    for p in self.estimator_params))
+        estimator.set_params(**{p: getattr(self, p)
+                                    for p in self.estimator_params})
         sampler = clone(self.base_sampler_)
 
         if random_state is not None:

imblearn/ensemble/tests/test_bagging.py

@@ -354,8 +354,8 @@ def test_warm_start(random_state=42):
         n_estimators=10, random_state=random_state, warm_start=False)
     clf_no_ws.fit(X, y)
 
-    assert (set([pipe.steps[-1][1].random_state for pipe in clf_ws]) == set(
-        [pipe.steps[-1][1].random_state for pipe in clf_no_ws]))
+    assert ({pipe.steps[-1][1].random_state for pipe in clf_ws} == {
+        pipe.steps[-1][1].random_state for pipe in clf_no_ws})
 
 
 def test_warm_start_smaller_n_estimators():

imblearn/ensemble/tests/test_easy_ensemble.py

@@ -201,8 +201,8 @@ def test_warm_start(random_state=42):
         n_estimators=10, random_state=random_state, warm_start=False)
     clf_no_ws.fit(X, y)
 
-    assert (set([pipe.steps[-1][1].random_state for pipe in clf_ws]) == set(
-        [pipe.steps[-1][1].random_state for pipe in clf_no_ws]))
+    assert ({pipe.steps[-1][1].random_state for pipe in clf_ws} == {
+        pipe.steps[-1][1].random_state for pipe in clf_no_ws})
 
 
 def test_warm_start_smaller_n_estimators():

imblearn/ensemble/tests/test_weight_boosting.py

@@ -50,10 +50,10 @@ def test_rusboost(imbalanced_dataset, algorithm):
     assert len(rusboost.pipelines_) == len(rusboost.samplers_)
 
     # each sampler in the ensemble should have different random state
-    assert (len(set(sampler.random_state for sampler in rusboost.samplers_)) ==
+    assert (len({sampler.random_state for sampler in rusboost.samplers_}) ==
             len(rusboost.samplers_))
     # each estimator in the ensemble should have different random state
-    assert (len(set(est.random_state for est in rusboost.estimators_)) ==
+    assert (len({est.random_state for est in rusboost.estimators_}) ==
             len(rusboost.estimators_))
 
     # check the consistency of the feature importances

imblearn/metrics/_classification.py

@@ -723,8 +723,8 @@ def compute_score(*args, **kwargs):
             # Make the intersection between the parameters
             sel_params = params_sens_spec.intersection(set(tags_scoring_func))
             # Create a sub dictionary
-            tags_scoring_func = dict((k, tags_scoring_func[k])
-                                     for k in sel_params)
+            tags_scoring_func = {k: tags_scoring_func[k]
+                                     for k in sel_params}
             # Check if the metric is the geometric mean
             if scoring_func.__name__ == 'geometric_mean_score':
                 if 'average' in tags_scoring_func:
@@ -883,7 +883,7 @@ class 2       1.00      0.67      1.00      0.80      0.82      0.64\
         for v in (precision[i], recall[i], specificity[i], f1[i], geo_mean[i],
                   iba[i]):
             values += ["{0:0.{1}f}".format(v, digits)]
-        values += ["{0}".format(support[i])]
+        values += ["{}".format(support[i])]
         report += fmt % tuple(values)
 
     report += '\n'
@@ -896,6 +896,6 @@ class 2       1.00      0.67      1.00      0.80      0.82      0.64\
                   geo_mean, weights=support), np.average(iba,
                                                          weights=support)):
         values += ["{0:0.{1}f}".format(v, digits)]
-    values += ['{0}'.format(np.sum(support))]
+    values += ['{}'.format(np.sum(support))]
     report += fmt % tuple(values)
     return report