scikit-learn · ogrisel · Dec 14, 2018 · Sep 4, 2018 · Dec 8, 2018 · Dec 9, 2018
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -1,13 +1,18 @@
 version: 2
 
 jobs:
-  python3:
+  doc-min-dependencies:
     docker:
       - image: circleci/python:3.6.1
     environment:
       - MINICONDA_PATH: ~/miniconda
       - CONDA_ENV_NAME: testenv
-      - PYTHON_VERSION: 3
+      - PYTHON_VERSION: 3.5
+      - NUMPY_VERSION: 1.11.0
+      - SCIPY_VERSION: 0.17.0
+      - PANDAS_VERSION: 0.18.0
+      - MATPLOTLIB_VERSION: 1.5.1
+      - SCIKIT_IMAGE_VERSION: 0.12.3
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
@@ -30,31 +35,21 @@ jobs:
           root: doc/_build/html
           paths: .
 
-
-  python2:
+  doc:
     docker:
-      # We use the python 3 docker image for simplicity. Python is installed
-      # through conda and the python version actually used is set via the
-      # PYTHON_VERSION environment variable.
       - image: circleci/python:3.6.1
     environment:
-      # Test examples run with minimal dependencies
       - MINICONDA_PATH: ~/miniconda
       - CONDA_ENV_NAME: testenv
-      - PYTHON_VERSION: "2"
-      - NUMPY_VERSION: "1.10"
-      - SCIPY_VERSION: "0.16"
-      - MATPLOTLIB_VERSION: "1.4"
-      - SCIKIT_IMAGE_VERSION: "0.11"
-      - PANDAS_VERSION: "0.17.1"
+      - PYTHON_VERSION: 3
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
       - restore_cache:
-          key: v1-datasets-{{ .Branch }}-python2
+          key: v1-datasets-{{ .Branch }}
       - run: ./build_tools/circle/build_doc.sh
       - save_cache:
-          key: v1-datasets-{{ .Branch }}-python2
+          key: v1-datasets-{{ .Branch }}
           paths:
             - ~/scikit_learn_data
       - store_artifacts:
@@ -63,6 +58,11 @@ jobs:
       - store_artifacts:
           path: ~/log.txt
           destination: log.txt
+      # Persists generated documentation so that it can be attached and deployed
+      # in the 'deploy' step.
+      - persist_to_workspace:
+          root: doc/_build/html
+          paths: .
 
   lint:
     docker:
@@ -114,8 +114,8 @@ workflows:
   version: 2
   build-doc-and-deploy:
     jobs:
-      - python3
-      - python2
+      - doc
+      - doc-min-dependencies
       - lint
       - pypy3:
           filters:

diff --git a/.travis.yml b/.travis.yml
@@ -9,7 +9,7 @@ cache:
   - $HOME/.cache/pip
   - $HOME/.ccache
 
-dist: trusty
+dist: xenial
 
 env:
   global:
@@ -21,26 +21,29 @@ env:
 matrix:
   include:
     # This environment tests that scikit-learn can be built against
-    # versions of numpy, scipy with ATLAS that comes with Ubuntu Trusty 14.04
-    # i.e. numpy 1.8.2 and scipy 0.13.3
-    - env: DISTRIB="ubuntu" PYTHON_VERSION="2.7" CYTHON_VERSION="0.23.5"
-           COVERAGE=true
+    # versions of numpy, scipy with ATLAS that comes with Ubuntu Xenial 16.04
+    # i.e. numpy 1.11 and scipy 0.17
+    - env: DISTRIB="ubuntu" PYTHON_VERSION="3.5" CYTHON_VERSION="0.28.6"
+           NUMPY_VERSION="1.11.0" SCIPY_VERSION="0.17.0"
+           PILLOW_VERSION="4.0.0" COVERAGE=true
+           SKLEARN_SITE_JOBLIB=1 JOBLIB_VERSION="0.11"
       if: type != cron
       addons:
         apt:
           packages:
             # these only required by the DISTRIB="ubuntu" builds:
-            - python-scipy
+            - python3-scipy
             - libatlas3-base
+            - libatlas-base-dev
             - libatlas-dev
-    # Python 3.4 build
-    - env: DISTRIB="conda" PYTHON_VERSION="3.4" INSTALL_MKL="false"
-           NUMPY_VERSION="1.10.4" SCIPY_VERSION="0.16.1" CYTHON_VERSION="0.25.2"
+    # Python 3.5 build without SITE_JOBLIB
+    - env: DISTRIB="conda" PYTHON_VERSION="3.5" INSTALL_MKL="false"
+           NUMPY_VERSION="1.11.0" SCIPY_VERSION="0.17.0" CYTHON_VERSION="0.25.2"
            PILLOW_VERSION="4.0.0" COVERAGE=true
       if: type != cron
     # Python 3.5 build
     - env: DISTRIB="conda" PYTHON_VERSION="3.5" INSTALL_MKL="false"
-           NUMPY_VERSION="1.10.4" SCIPY_VERSION="0.16.1" CYTHON_VERSION="0.25.2"
+           NUMPY_VERSION="1.11.0" SCIPY_VERSION="0.17.0" CYTHON_VERSION="0.25.2"
            PILLOW_VERSION="4.0.0" COVERAGE=true
            SKLEARN_SITE_JOBLIB=1 JOBLIB_VERSION="0.11"
       if: type != cron
@@ -57,7 +60,7 @@ matrix:
     # This environment tests scikit-learn against numpy and scipy master
     # installed from their CI wheels in a virtualenv with the Python
     # interpreter provided by travis.
-    -  python: 3.6
+    -  python: 3.7
        env: DISTRIB="scipy-dev" CHECK_WARNINGS="true"
        if: type = cron OR commit_message =~ /\[scipy-dev\]/
 

diff --git a/appveyor.yml b/appveyor.yml
@@ -22,11 +22,10 @@ environment:
       PYTHON_ARCH: "64"
       CHECK_WARNINGS: "true"
 
-    - PYTHON: "C:\\Python27"
-      PYTHON_VERSION: "2.7.8"
+    - PYTHON: "C:\\Python35"
+      PYTHON_VERSION: "3.5.6"
       PYTHON_ARCH: "32"
 
-
 # Because we only have a single worker, we don't want to waste precious
 # appveyor CI time and make other PRs wait for repeated failures in a failing
 # PR. The following option cancels pending jobs in a given PR after the first

diff --git a/build_tools/travis/install.sh b/build_tools/travis/install.sh
@@ -70,21 +70,16 @@ if [[ "$DISTRIB" == "conda" ]]; then
     fi
 	  make_conda $TO_INSTALL
 
-    # for python 3.4, conda does not have recent pytest packages
-    if [[ "$PYTHON_VERSION" == "3.4" ]]; then
-        pip install pytest==3.5
-    fi
-
 elif [[ "$DISTRIB" == "ubuntu" ]]; then
     # At the time of writing numpy 1.9.1 is included in the travis
     # virtualenv but we want to use the numpy installed through apt-get
     # install.
     deactivate
     # Create a new virtualenv using system site packages for python, numpy
     # and scipy
-    virtualenv --system-site-packages testvenv
+    virtualenv --system-site-packages --python=python3 testvenv
     source testvenv/bin/activate
-    pip install pytest pytest-cov cython==$CYTHON_VERSION
+    pip install pytest pytest-cov cython==$CYTHON_VERSION joblib==$JOBLIB_VERSION
 
 elif [[ "$DISTRIB" == "scipy-dev" ]]; then
     make_conda python=3.7

diff --git a/conftest.py b/conftest.py
@@ -11,8 +11,6 @@
 import pytest
 from _pytest.doctest import DoctestItem
 
-from sklearn.utils.fixes import PY3_OR_LATER
-
 PYTEST_MIN_VERSION = '3.3.0'
 
 if LooseVersion(pytest.__version__) < PYTEST_MIN_VERSION:
@@ -47,11 +45,8 @@ def pytest_collection_modifyitems(config, items):
                 item.add_marker(skip_network)
 
     # numpy changed the str/repr formatting of numpy arrays in 1.14. We want to
-    # run doctests only for numpy >= 1.14. We want to skip the doctest for
-    # python 2 due to unicode.
+    # run doctests only for numpy >= 1.14.
     skip_doctests = False
-    if not PY3_OR_LATER:
-        skip_doctests = True
     try:
         import numpy as np
         if LooseVersion(np.__version__) < LooseVersion('1.14'):

diff --git a/examples/model_selection/plot_precision_recall.py b/examples/model_selection/plot_precision_recall.py
@@ -137,7 +137,7 @@
 # ................................
 from sklearn.metrics import precision_recall_curve
 import matplotlib.pyplot as plt
-from sklearn.utils.fixes import signature
+from inspect import signature
 
 precision, recall, _ = precision_recall_curve(y_test, y_score)
 

diff --git a/setup.py b/setup.py
@@ -11,11 +11,7 @@
 from distutils.command.clean import clean as Clean
 from pkg_resources import parse_version
 import traceback
-
-if sys.version_info[0] < 3:
-    import __builtin__ as builtins
-else:
-    import builtins
+import builtins
 
 # This is a bit (!) hackish: we are setting a global variable so that the main
 # sklearn __init__ can detect if it is being loaded by the setup routine, to
@@ -45,8 +41,8 @@
     SCIPY_MIN_VERSION = '1.1.0'
     NUMPY_MIN_VERSION = '1.14.0'
 else:
-    SCIPY_MIN_VERSION = '0.13.3'
-    NUMPY_MIN_VERSION = '1.8.2'
+    SCIPY_MIN_VERSION = '0.17.0'
+    NUMPY_MIN_VERSION = '1.11.0'
 
 
 # Optional setuptools features
@@ -183,10 +179,7 @@ def setup_package():
                                  'Operating System :: POSIX',
                                  'Operating System :: Unix',
                                  'Operating System :: MacOS',
-                                 'Programming Language :: Python :: 2',
-                                 'Programming Language :: Python :: 2.7',
                                  'Programming Language :: Python :: 3',
-                                 'Programming Language :: Python :: 3.4',
                                  'Programming Language :: Python :: 3.5',
                                  'Programming Language :: Python :: 3.6',
                                  'Programming Language :: Python :: 3.7',

diff --git a/sklearn/base.py b/sklearn/base.py
@@ -6,11 +6,11 @@
 import copy
 import warnings
 from collections import defaultdict
+from inspect import signature
 
 import numpy as np
 from scipy import sparse
 from .externals import six
-from .utils.fixes import signature
 from . import __version__
 
 

diff --git a/sklearn/calibration.py b/sklearn/calibration.py
@@ -9,6 +9,7 @@
 
 from __future__ import division
 import warnings
+from inspect import signature
 
 from math import log
 import numpy as np
@@ -20,7 +21,6 @@
 from .preprocessing import label_binarize, LabelBinarizer
 from .utils import check_X_y, check_array, indexable, column_or_1d
 from .utils.validation import check_is_fitted, check_consistent_length
-from .utils.fixes import signature
 from .isotonic import IsotonicRegression
 from .svm import LinearSVC
 from .model_selection import check_cv

diff --git a/sklearn/cluster/tests/test_k_means.py b/sklearn/cluster/tests/test_k_means.py
@@ -237,10 +237,6 @@ def test_k_means_new_centers():
 
 @if_safe_multiprocessing_with_blas
 def test_k_means_plus_plus_init_2_jobs():
-    if sys.version_info[:2] < (3, 4):
-        raise SkipTest(
-            "Possible multi-process bug with some BLAS under Python < 3.4")
-
     km = KMeans(init="k-means++", n_clusters=n_clusters, n_jobs=2,
                 random_state=42).fit(X)
     _check_fitted_model(km)

diff --git a/sklearn/datasets/covtype.py b/sklearn/datasets/covtype.py
@@ -17,7 +17,7 @@
 from gzip import GzipFile
 import logging
 from os.path import dirname, exists, join
-from os import remove
+from os import remove, makedirs
 
 import numpy as np
 
@@ -26,7 +26,6 @@
 from .base import RemoteFileMetadata
 from ..utils import Bunch
 from .base import _pkl_filepath
-from ..utils.fixes import makedirs
 from ..utils import _joblib
 from ..utils import check_random_state
 

diff --git a/sklearn/datasets/kddcup99.py b/sklearn/datasets/kddcup99.py
@@ -205,14 +205,7 @@ def _fetch_brute_kddcup99(data_home=None,
     """
 
     data_home = get_data_home(data_home=data_home)
-    if sys.version_info[0] == 3:
-        # The zlib compression format use by joblib is not compatible when
-        # switching from Python 2 to Python 3, let us use a separate folder
-        # under Python 3:
-        dir_suffix = "-py3"
-    else:
-        # Backward compat for Python 2 users
-        dir_suffix = ""
+    dir_suffix = "-py3"
 
     if percent10:
         kddcup_dir = join(data_home, "kddcup99_10" + dir_suffix)

diff --git a/sklearn/datasets/mldata.py b/sklearn/datasets/mldata.py
@@ -7,16 +7,9 @@
 from os.path import join, exists
 import re
 import numbers
-try:
-    # Python 2
-    from urllib2 import HTTPError
-    from urllib2 import quote
-    from urllib2 import urlopen
-except ImportError:
-    # Python 3+
-    from urllib.error import HTTPError
-    from urllib.parse import quote
-    from urllib.request import urlopen
+from urllib.error import HTTPError
+from urllib.parse import quote
+from urllib.request import urlopen
 
 import numpy as np
 import scipy as sp

diff --git a/sklearn/datasets/openml.py b/sklearn/datasets/openml.py
@@ -7,20 +7,14 @@
 from contextlib import closing
 from functools import wraps
 
-try:
-    # Python 3+
-    from urllib.request import urlopen, Request
-except ImportError:
-    # Python 2
-    from urllib2 import urlopen, Request
-
+from urllib.request import urlopen, Request
 
 import numpy as np
 import scipy.sparse
 
 from sklearn.externals import _arff
 from .base import get_data_home
-from ..externals.six import string_types, PY2, BytesIO
+from ..externals.six import string_types
 from ..externals.six.moves.urllib.error import HTTPError
 from ..utils import Bunch
 
@@ -89,8 +83,6 @@ def is_gzip(_fsrc):
     if data_home is None:
         fsrc = urlopen(req)
         if is_gzip(fsrc):
-            if PY2:
-                fsrc = BytesIO(fsrc.read())
             return gzip.GzipFile(fileobj=fsrc, mode='rb')
         return fsrc
 
@@ -357,16 +349,9 @@ def _arff_load():
             else:
                 return_type = _arff.DENSE
 
-            if PY2:
-                arff_file = _arff.load(
-                    response.read(),
-                    encode_nominal=encode_nominal,
-                    return_type=return_type,
-                )
-            else:
-                arff_file = _arff.loads(response.read().decode('utf-8'),
-                                        encode_nominal=encode_nominal,
-                                        return_type=return_type)
+            arff_file = _arff.loads(response.read().decode('utf-8'),
+                                    encode_nominal=encode_nominal,
+                                    return_type=return_type)
         return arff_file
 
     return _arff_load()