explicitly require Python 3.6 and drop six dependency

.travis.yml

@@ -17,7 +17,7 @@ install:
   # Useful for debugging any issues with conda
   - conda info -a
 
-  - conda create -q -n test-environment python=$PYTHON_VERSION numpy scipy pytest cython scikit-learn six joblib
+  - conda create -q -n test-environment python=$PYTHON_VERSION numpy scipy pytest cython scikit-learn joblib
   - source activate test-environment
   - make all
 

README.rst

@@ -17,9 +17,9 @@ ranking in Python.
 
 Highlights:
 
-- follows the `scikit-learn <http://scikit-learn.org>`_ API conventions
+- follows the `scikit-learn <https://scikit-learn.org>`_ API conventions
 - supports natively both dense and sparse data representations
-- computationally demanding parts implemented in `Cython <http://cython.org>`_
+- computationally demanding parts implemented in `Cython <https://cython.org>`_
 
 Solvers supported:
 
@@ -66,8 +66,8 @@ penalty on the News20 dataset (c.f., `Blondel et al. 2013
 Dependencies
 ------------
 
-lightning requires Python >= 2.7, setuptools, Numpy >= 1.3, SciPy >= 0.7 and
-scikit-learn >= 0.15. Building from source also requires Cython and a working C/C++ compiler. To run the tests you will also need pytest.
+lightning requires Python >= 3.6, setuptools, Numpy >= 1.12, SciPy >= 0.19 and
+scikit-learn >= 0.19. Building from source also requires Cython and a working C/C++ compiler. To run the tests you will also need pytest.
 
 Installation
 ------------
@@ -93,7 +93,7 @@ Documentation
 
 http://contrib.scikit-learn.org/lightning/
 
-On Github
+On GitHub
 ---------
 
 https://github.com/scikit-learn-contrib/lightning

appveyor.yml

@@ -1,6 +1,5 @@
 # AppVeyor.com is a Continuous Integration service to build and run tests under
 # Windows
-# https://ci.appveyor.com/project/fabianp/lightning-bpc6r
 
 image: Visual Studio 2019
 
@@ -52,7 +51,7 @@ install:
   - "python -c \"import struct; print(struct.calcsize('P') * 8)\""
   - "python -m pip --version"
 
-  - "python -m pip install --timeout=60 numpy scipy cython pytest scikit-learn wheel six joblib"
+  - "python -m pip install --timeout=60 numpy scipy cython pytest scikit-learn wheel joblib"
   - "python setup.py bdist_wheel bdist_wininst"
 
   - ps: "ls dist"

build_tools/move-conda-package.py

@@ -5,7 +5,7 @@
 import shutil
 from conda_build.config import config
 
-with open(os.path.join(sys.argv[1], 'meta.yaml')) as f:
+with open(os.path.join(sys.argv[1], 'meta.yaml'), encoding='utf-8') as f:
     name = yaml.load(f)['package']['name']
 
 binary_package_glob = os.path.join(

doc/sphinxext/gen_rst.py

@@ -7,7 +7,6 @@
 Files that generate images should start with 'plot'
 
 """
-from __future__ import division, print_function
 from time import time
 import ast
 import os
@@ -20,37 +19,19 @@
 import posixpath
 import subprocess
 import warnings
-import six
 
+from io import StringIO
+import pickle
+import urllib.request
+import urllib.error
+import urllib.parse
+from urllib.error import HTTPError, URLError
 
-# Try Python 2 first, otherwise load from Python 3
-try:
-    from StringIO import StringIO
-    import cPickle as pickle
-    import urllib2 as urllib
-    from urllib2 import HTTPError, URLError
-except ImportError:
-    from io import StringIO
-    import pickle
-    import urllib.request
-    import urllib.error
-    import urllib.parse
-    from urllib.error import HTTPError, URLError
-
-
-try:
-    # Python 2 built-in
-    execfile
-except NameError:
-    def execfile(filename, global_vars=None, local_vars=None):
-        with open(filename, encoding='utf-8') as f:
-            code = compile(f.read(), filename, 'exec')
-            exec(code, global_vars, local_vars)
 
-try:
-    basestring
-except NameError:
-    basestring = str
+def execfile(filename, global_vars=None, local_vars=None):
+    with open(filename, encoding='utf-8') as f:
+        code = compile(f.read(), filename, 'exec')
+        exec(code, global_vars, local_vars)
 
 import token
 import tokenize
@@ -93,13 +74,8 @@ def flush(self):
 def _get_data(url):
     """Helper function to get data over http or from a local file"""
     if url.startswith('http://'):
-        # Try Python 2, use Python 3 on exception
-        try:
-            resp = urllib.urlopen(url)
-            encoding = resp.headers.dict.get('content-encoding', 'plain')
-        except AttributeError:
-            resp = urllib.request.urlopen(url)
-            encoding = resp.headers.get('content-encoding', 'plain')
+        resp = urllib.request.urlopen(url)
+        encoding = resp.headers.get('content-encoding', 'plain')
         data = resp.read()
         if encoding == 'plain':
             pass
@@ -427,10 +403,8 @@ def resolve(self, cobj, this_url):
 def extract_docstring(filename, ignore_heading=False):
     """ Extract a module-level docstring, if any
     """
-    if six.PY2:
-        lines = open(filename).readlines()
-    else:
-        lines = open(filename, encoding='utf-8').readlines()
+    with open(filename, encoding='utf-8') as f:
+        lines = f.readlines()
     start_row = 0
     if lines[0].startswith('#!'):
         lines.pop(0)
@@ -526,10 +500,8 @@ def generate_example_rst(app):
 def extract_line_count(filename, target_dir):
     # Extract the line count of a file
     example_file = os.path.join(target_dir, filename)
-    if six.PY2:
-        lines = open(example_file).readlines()
-    else:
-        lines = open(example_file, encoding='utf-8').readlines()
+    with open(example_file, encoding='utf-8') as f:
+        lines = f.readlines()
     start_row = 0
     if lines and lines[0].startswith('#!'):
         lines.pop(0)
@@ -620,7 +592,7 @@ def generate_dir_rst(directory, fhindex, example_dir, root_dir, plot_gallery, se
 %s
 
 
-""" % open(os.path.join(src_dir, 'README.txt')).read())
+""" % open(os.path.join(src_dir, 'README.txt'), encoding='utf-8').read())
     if not os.path.exists(target_dir):
         os.makedirs(target_dir)
     sorted_listdir = line_count_sort(os.listdir(src_dir),
@@ -676,8 +648,8 @@ def make_thumbnail(in_fname, out_fname, width, height):
         import Image
     img = Image.open(in_fname)
     width_in, height_in = img.size
-    scale_w = width / float(width_in)
-    scale_h = height / float(height_in)
+    scale_w = width / width_in
+    scale_h = height / height_in
 
     if height_in * scale_w <= height:
         scale = scale_w
@@ -727,7 +699,7 @@ class NameFinder(ast.NodeVisitor):
     """
 
     def __init__(self):
-        super(NameFinder, self).__init__()
+        super().__init__()
         self.imported_names = {}
         self.accessed_names = set()
 
@@ -964,11 +936,8 @@ def generate_file_rst(fname, target_dir, src_dir, root_dir, plot_gallery):
     f.flush()
 
     # save variables so we can later add links to the documentation
-    if six.PY2:
-        example_code_obj = identify_names(open(example_file).read())
-    else:
-        example_code_obj = \
-            identify_names(open(example_file, encoding='utf-8').read())
+    with open(example_file, encoding='utf-8') as f:
+        example_code_obj = identify_names(f.read())
     if example_code_obj:
         codeobj_fname = example_file[:-3] + '_codeobj.pickle'
         with open(codeobj_fname, 'wb') as fid:

doc/sphinxext/numpy_ext/docscrape.py

@@ -7,11 +7,7 @@
 import re
 import pydoc
 from warnings import warn
-# Try Python 2 first, otherwise load from Python 3
-try:
-    from StringIO import StringIO
-except:
-    from io import StringIO
+from io import StringIO
 
 
 class Reader(object):
@@ -466,7 +462,7 @@ def __str__(self):
             out += '.. %s:: %s\n    \n\n' % (roles.get(self._role, ''),
                                              func_name)
 
-        out += super(FunctionDoc, self).__str__(func_role=self._role)
+        out += super().__str__(func_role=self._role)
         return out
 
 

doc/sphinxext/numpy_ext/docscrape_sphinx.py

@@ -117,7 +117,7 @@ def _str_section(self, name):
     def _str_see_also(self, func_role):
         out = []
         if self['See Also']:
-            see_also = super(SphinxDocString, self)._str_see_also(func_role)
+            see_also = super()._str_see_also(func_role)
             out = ['.. seealso::', '']
             out += self._str_indent(see_also[2:])
         return out

doc/sphinxext/numpy_ext/numpydoc.py

@@ -17,9 +17,6 @@
 
 """
 
-from __future__ import unicode_literals
-
-import sys # Only needed to check Python version
 import os
 import re
 import pydoc
@@ -41,10 +38,7 @@ def mangle_docstrings(app, what, name, obj, options, lines,
         lines[:] = title_re.sub('', "\n".join(lines)).split("\n")
     else:
         doc = get_doc_object(obj, what, "\n".join(lines), config=cfg)
-        if sys.version_info[0] < 3:
-            lines[:] = unicode(doc).splitlines()
-        else:
-            lines[:] = str(doc).splitlines()
+        lines[:] = str(doc).splitlines()
 
     if app.config.numpydoc_edit_link and hasattr(obj, '__name__') and \
            obj.__name__:
@@ -104,12 +98,8 @@ def setup(app, get_doc_object_=get_doc_object):
     global get_doc_object
     get_doc_object = get_doc_object_
 
-    if sys.version_info[0] < 3:
-        app.connect(b'autodoc-process-docstring', mangle_docstrings)
-        app.connect(b'autodoc-process-signature', mangle_signature)
-    else:
-        app.connect('autodoc-process-docstring', mangle_docstrings)
-        app.connect('autodoc-process-signature', mangle_signature)
+    app.connect('autodoc-process-docstring', mangle_docstrings)
+    app.connect('autodoc-process-signature', mangle_signature)
     app.add_config_value('numpydoc_edit_link', None, False)
     app.add_config_value('numpydoc_use_plots', None, False)
     app.add_config_value('numpydoc_show_class_members', True, True)
@@ -135,7 +125,7 @@ class ManglingDomainBase(object):
     directive_mangling_map = {}
 
     def __init__(self, *a, **kw):
-        super(ManglingDomainBase, self).__init__(*a, **kw)
+        super().__init__(*a, **kw)
         self.wrap_mangling_directives()
 
     def wrap_mangling_directives(self):

examples/plot_sparse_non_linear.py

@@ -33,20 +33,20 @@ class SparseNonlinearClassifier(CDClassifier):
 
     def __init__(self, gamma=1e-2, C=1, alpha=1):
         self.gamma = gamma
-        super(SparseNonlinearClassifier, self).__init__(C=C,
-                                                        alpha=alpha,
-                                                        loss="squared_hinge",
-                                                        penalty="l1")
+        super().__init__(C=C,
+                         alpha=alpha,
+                         loss="squared_hinge",
+                         penalty="l1")
 
     def fit(self, X, y):
         K = rbf_kernel(X, gamma=self.gamma)
         self.X_train_ = X
-        super(SparseNonlinearClassifier, self).fit(K, y)
+        super().fit(K, y)
         return self
 
     def decision_function(self, X):
         K = rbf_kernel(X, self.X_train_, gamma=self.gamma)
-        return super(SparseNonlinearClassifier, self).decision_function(K)
+        return super().decision_function(K)
 
 
 def gen_non_lin_separable_data():

lightning/impl/adagrad.py

@@ -4,7 +4,6 @@
 import numpy as np
 
 from sklearn.utils import check_random_state
-from six.moves import xrange
 
 from .base import BaseClassifier, BaseRegressor
 from .dataset_fast import get_dataset
@@ -38,7 +37,7 @@ def _fit(self, X, Y):
         loss = self._get_loss()
         n_calls = n_samples if self.n_calls is None else self.n_calls
 
-        for i in xrange(n_vectors):
+        for i in range(n_vectors):
             _adagrad_fit(self, ds, Y[:, i], self.coef_[i], self.g_sum_[i],
                          self.g_norms_[i], loss, self.eta, delta, alpha1,
                          alpha2, self.n_iter, self.shuffle, self.callback,

lightning/impl/adagrad_fast.pyx

@@ -26,7 +26,7 @@ cdef double _pred(double* data,
     cdef int j, jj
     cdef double dot = 0
 
-    for jj in xrange(n_nz):
+    for jj in range(n_nz):
         j = indices[jj]
         dot += w[j] * data[jj]
 
@@ -64,7 +64,7 @@ cpdef _proj_elastic_all(double eta,
                         np.ndarray[double, ndim=1] w):
     cdef int n_features = w.shape[0]
     cdef int j
-    for j in xrange(n_features):
+    for j in range(n_features):
         if g_norms[j] != 0:
             w[j] = _proj_elastic(eta, t, g_sum[j], g_norms[j], alpha1, alpha2,
                                  delta)
@@ -107,21 +107,21 @@ def _adagrad_fit(self,
     cdef double* w = <double*>coef.data
 
     t = 1
-    for it in xrange(n_iter):
+    for it in range(n_iter):
 
         # Shuffle sample indices.
         if shuffle:
             rng.shuffle(sindices)
 
-        for ii in xrange(n_samples):
+        for ii in range(n_samples):
             i = sindices[ii]
 
             # Retrieve sample i.
             X.get_row_ptr(i, &indices, &data, &n_nz)
 
             # Update w lazily.
             if t > 1:
-                for jj in xrange(n_nz):
+                for jj in range(n_nz):
                     j = indices[jj]
                     if g_norms[j] != 0:
                         w[j] = _proj_elastic(eta, t - 1, g_sum[j], g_norms[j],
@@ -135,14 +135,14 @@ def _adagrad_fit(self,
 
             # Update g_sum and g_norms.
             if scale != 0:
-                for jj in xrange(n_nz):
+                for jj in range(n_nz):
                     j = indices[jj]
                     tmp = scale * data[jj]
                     g_sum[j] += tmp
                     g_norms[j] += tmp * tmp
 
             # Update w by naive implementation: very slow.
-            # for j in xrange(n_features):
+            # for j in range(n_features):
             #    w[j] = _proj_elastic(eta, t, g_sum[j], g_norms[j], alpha1,
             #                         alpha2, delta)
 

lightning/impl/base.py

@@ -30,9 +30,9 @@ def n_nonzero(self, percentage=False):
         if percentage:
             if hasattr(self, "support_vectors_") and \
                self.support_vectors_ is not None:
-                n_nz /= float(self.n_samples_)
+                n_nz /= self.n_samples_
             else:
-                n_nz /= float(coef.shape[1])
+                n_nz /= coef.shape[1]
 
         return n_nz