J535D165 · J535D165 · Jul 12, 2019 · Mar 24, 2019 · Mar 24, 2019 · Mar 24, 2019
diff --git a/.travis.yml b/.travis.yml
@@ -5,7 +5,6 @@ python:
 dist: xenial
 
 python:
-  - "2.7"
   - "3.5"
   - "3.6"
 

diff --git a/README.rst b/README.rst
@@ -136,12 +136,16 @@ share, let us know.
 Dependencies, installation and license
 --------------------------------------
 
-Install the Python Record Linkage Toolkit easily with pip
+The Python Record linkage Toolkit requires Python 3.5 or higher (since version
+>= 0.14). Install the package easily with pip
 
 .. code:: sh
 
     pip install recordlinkage
 
+Python 2.7 users can use version <= 0.13, but it is advised to use Python >=
+3.5.
+
 The toolkit depends on Pandas_ (>=18.0), Numpy_, `Scikit-learn`_, Scipy_ and
 Jellyfish_. You probably have most of them already installed. The package
 ``jellyfish`` is used for approximate string comparing and string encoding.

diff --git a/docs/installation.rst b/docs/installation.rst
@@ -14,12 +14,15 @@ documentation_.
 Installation
 ============
 
-The easiest way of installing the Python Record Linkage Toolkit is using
-``pip``. It is as easy as typing:
+The Python Record linkage Toolkit requires Python 3.5 or higher (since version
+>= 0.14). Install the package easily with pip
 
 .. code:: sh
 
-	pip install --user recordlinkage
+    pip install recordlinkage
+
+Python 2.7 users can use version <= 0.13, but it is advised to use Python >=
+3.5.
 
 You can also clone the project on Github. The license of this record linkage
 package is BSD-3-Clause.

diff --git a/recordlinkage/algorithms/string.py b/recordlinkage/algorithms/string.py
@@ -1,6 +1,3 @@
-from __future__ import division
-from __future__ import unicode_literals
-
 import warnings
 
 import jellyfish

diff --git a/recordlinkage/base.py b/recordlinkage/base.py
@@ -14,8 +14,6 @@
 
 import pandas
 
-import six
-
 from recordlinkage import rl_logging as logging
 import recordlinkage.config as cf
 from recordlinkage.utils import (listify,
@@ -28,7 +26,6 @@
 from recordlinkage.types import (is_numpy_like,
                                  is_pandas_2d_multiindex)
 from recordlinkage.measures import max_pairs
-
 from recordlinkage.utils import DeprecationHelper, LearningError
 
 
@@ -874,7 +871,7 @@ def clear_memory(self):
         raise AttributeError("this method was removed in version 0.12.0")
 
 
-class BaseClassifier(six.with_metaclass(ABCMeta)):
+class BaseClassifier(metaclass=ABCMeta):
     """Base class for classification of records pairs.
 
     This class contains methods for training the classifier.

diff --git a/recordlinkage/compare.py b/recordlinkage/compare.py
@@ -1,6 +1,3 @@
-from __future__ import division
-from __future__ import unicode_literals
-
 from functools import partial
 
 import numpy

diff --git a/recordlinkage/datasets/external.py b/recordlinkage/datasets/external.py
@@ -1,10 +1,10 @@
-import os
+from io import BytesIO
+from pathlib import Path
+from urllib.request import urlopen
 import zipfile
 
 import pandas
 
-from six import BytesIO
-from six.moves.urllib.request import urlopen
 
 
 def load_krebsregister(block=[1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
@@ -68,10 +68,13 @@ def load_krebsregister(block=[1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
     # If the data is not found, download it.
     for i in range(1, 11):
 
-        filepath = os.path.join(os.path.dirname(__file__),
-                                'krebsregister', 'block_{}.zip'.format(i))
+        filepath = Path(
+            Path(__file__).parent,
+            'krebsregister', 
+            'block_{}.zip'.format(i)
+        )
 
-        if not os.path.exists(filepath):
+        if not filepath.is_file():
             _download_krebsregister()
             break
 
@@ -105,7 +108,7 @@ def _download_krebsregister():
 
         # unzip the content and put it in the krebsregister folder
         z = zipfile.ZipFile(BytesIO(r))
-        z.extractall(os.path.join(os.path.dirname(__file__), 'krebsregister'))
+        z.extractall(str(Path(Path(__file__).parent, 'krebsregister')))
 
         print("Data download succesfull.")
 
@@ -120,8 +123,11 @@ def _krebsregister_block(block):
             "Argument 'block' has to be integer in "
             "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10] or list of integers.")
 
-    fp_i = os.path.join(os.path.dirname(__file__),
-                        'krebsregister', 'block_{}.zip'.format(block))
+    fp_i = Path(
+        Path(__file__).parent,
+        'krebsregister', 
+        'block_{}.zip'.format(block)
+    )
 
     data_block = pandas.read_csv(
         fp_i,

diff --git a/recordlinkage/datasets/febrl.py b/recordlinkage/datasets/febrl.py
@@ -1,4 +1,4 @@
-import os
+from pathlib import Path
 
 import pandas
 import numpy
@@ -7,7 +7,11 @@
 def _febrl_load_data(filename):
     # Internal function for loading febrl data
 
-    filepath = os.path.join(os.path.dirname(__file__), 'febrl', filename)
+    filepath = Path(
+        Path(__file__).parent,
+        'febrl', 
+        filename
+    )
 
     febrl_data = pandas.read_csv(filepath,
                                  index_col="rec_id",

diff --git a/recordlinkage/index.py b/recordlinkage/index.py
@@ -1,5 +1,3 @@
-from __future__ import division
-
 import warnings
 
 import numpy

diff --git a/recordlinkage/measures.py b/recordlinkage/measures.py
@@ -1,7 +1,5 @@
 # measures.py
 
-from __future__ import division
-
 import numpy
 
 import pandas

diff --git a/recordlinkage/preprocessing/cleaning.py b/recordlinkage/preprocessing/cleaning.py
@@ -1,7 +1,3 @@
-from __future__ import absolute_import
-from __future__ import division
-# from __future__ import unicode_literals
-
 import sys
 
 from sklearn.feature_extraction.text import strip_accents_ascii, \

diff --git a/recordlinkage/types.py b/recordlinkage/types.py
@@ -14,27 +14,24 @@
 
 import pandas
 
-from six import binary_type, string_types, text_type
-
-string_and_binary_types = (string_types,) + (binary_type,)
+string_and_binary_types = (str, bytes)
 
 
 def is_number(obj):
     return isinstance(obj, (Number, numpy.number))
 
 
 def is_string_like(obj):
-    return isinstance(obj, (text_type, string_types))
+    return isinstance(obj, str)
 
 
 def _iterable_not_string(x):
     return (isinstance(x, collections.Iterable) and
-            not isinstance(x, string_types))
+            not isinstance(x, str))
 
 
 def is_iterator(obj):
-    # python 3 generators have __next__ instead of next
-    return hasattr(obj, 'next') or hasattr(obj, '__next__')
+    return hasattr(obj, '__next__')
 
 
 def is_re(obj):

diff --git a/setup.cfg b/setup.cfg
@@ -1,7 +1,4 @@
 
-[bdist_wheel]
-universal = 1
-
 [versioneer]
 VCS = git
 style = pep440

diff --git a/setup.py b/setup.py
@@ -28,8 +28,8 @@ def read(fname):
     # Github
     url="https://github.com/J535D165/recordlinkage",
 
+    python_requires=">=3.5",
     install_requires=[
-        "six>=1.10.0",
         "jellyfish>=0.5.4",
         "numpy>=1.13.0",
         "pandas>=0.18.0",

diff --git a/tests/test_indexing.py b/tests/test_indexing.py
@@ -1,8 +1,6 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-from __future__ import print_function
-
 import os
 import tempfile
 import shutil

diff --git a/tox.ini b/tox.ini
@@ -1,5 +1,5 @@
 [tox]
-envlist = py{27,35,36}-pandas{018,019,020,021,022,latest},flake8,docs
+envlist = py{35,36}-pandas{018,019,020,021,022,latest},flake8,docs
 
 [testenv]
 deps=
-Original file line number
+Diff line change
@@ Expand Up / @@ -5,7 +5,6 @@ python: @@
     dist: xenial
     python:
-      - "2.7"
       - "3.5"
       - "3.6"
@@ Expand Down @@