MAINT: bump the version of scikit-learn 0.20rc1

Author: glemaitre

Diff for: .travis.yml

@@ -33,11 +33,11 @@ matrix:
     - env: DISTRIB="ubuntu"
     # Latest release
     - env: DISTRIB="conda" PYTHON_VERSION="2.7"
-           NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.19.0"
-    - env: DISTRIB="conda" PYTHON_VERSION="3.5"
-           NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.19.0"
+           NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.20rc"
     - env: DISTRIB="conda" PYTHON_VERSION="3.6"
-           NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.19.0"
+           NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.20rc"
+    - env: DISTRIB="conda" PYTHON_VERSION="3.7"
+           NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.20rc"
     - env: DISTRIB="conda" PYTHON_VERSION="3.7"
            NUMPY_VERSION="*" SCIPY_VERSION="*" SKLEARN_VERSION="master"
   allow_failures:

Diff for: CONTRIBUTING.md

@@ -98,8 +98,8 @@ tools:
 
 -  Code with good unittest coverage (at least 80%), check with:
 
-        $ pip install nose coverage
-        $ nosetests --with-coverage path/to/tests_for_package
+        $ pip install pytest pytest-cov
+        $ pytest --cov=imblearn imblearn
 
 -  No pyflakes warnings, check with:
 

Diff for: Makefile

@@ -13,14 +13,14 @@ clean:
 	rm -rf examples/.ipynb_checkpoints
 
 test-code:
-	py.test imblearn
+	pytest imblearn
 
 test-doc:
-	py.test doc/*.rst
+	pytest doc/*.rst
 
 test-coverage:
 	rm -rf coverage .coverage
-	py.test --cov=imblearn imblearn
+	pytest --cov=imblearn imblearn
 
 test: test-coverage test-doc
 

Diff for: README.rst

@@ -49,18 +49,20 @@ Installation
 Dependencies
 ~~~~~~~~~~~~
 
-imbalanced-learn is tested to work under Python 2.7 and Python 3.5, and
-3.6. The dependency requirements are based on the last scikit-learn release:
+imbalanced-learn is tested to work under Python 2.7 and Python 3.6, and
+3.7. The dependency requirements are based on the last scikit-learn release:
 
 * scipy(>=0.13.3)
 * numpy(>=1.8.2)
-* scikit-learn(>=0.19.0)
+* scikit-learn(>=0.20)
 * keras 2 (optional)
 * tensorflow (optional)
 
 Additionally, to run the examples, you need matplotlib(>=2.0.0) and
 pandas(>=0.22).
 
+**imbalanced-learn 0.4 is the last version to support Python 2.7**
+
 Installation
 ~~~~~~~~~~~~
 
@@ -87,7 +89,7 @@ Or install using pip and GitHub::
 Testing
 ~~~~~~~
 
-After installation, you can use `nose` to run the test suite::
+After installation, you can use `pytest` to run the test suite::
 
   make coverage
 

Diff for: appveyor.yml

@@ -8,27 +8,27 @@ environment:
   # We use miniconda versions of Python provided by appveyor windows images
   matrix:
     - PYTHON: "C:\\Miniconda-x64"
-      PYTHON_VERSION: "2.7.x"
+      PYTHON_VERSION: "2.7"
       PYTHON_ARCH: "64"
       OPTIONAL_DEP: "pandas"
 
     - PYTHON: "C:\\Miniconda"
-      PYTHON_VERSION: "2.7.x"
+      PYTHON_VERSION: "2.7"
       PYTHON_ARCH: "32"
       OPTIONAL_DEP: "pandas"
 
-    - PYTHON: "C:\\Miniconda35-x64"
-      PYTHON_VERSION: "3.5.x"
+    - PYTHON: "C:\\Miniconda36-x64"
+      PYTHON_VERSION: "3.6"
       PYTHON_ARCH: "64"
       OPTIONAL_DEP: "pandas keras tensorflow"
 
     - PYTHON: "C:\\Miniconda36-x64"
-      PYTHON_VERSION: "3.6.x"
+      PYTHON_VERSION: "3.7"
       PYTHON_ARCH: "64"
-      OPTIONAL_DEP: "pandas keras tensorflow"
+      OPTIONAL_DEP: "pandas"
 
     - PYTHON: "C:\\Miniconda36"
-      PYTHON_VERSION: "3.6.x"
+      PYTHON_VERSION: "3.7"
       PYTHON_ARCH: "32"
       OPTIONAL_DEP: "pandas"
 
@@ -37,11 +37,14 @@ install:
   # Add Library/bin directory to fix issue
   # https://github.com/conda/conda/issues/1753
   - "SET PATH=%PYTHON%;%PYTHON%\\Scripts;%PYTHON%\\Library\\bin;%PATH%"
-  - conda install pip scipy numpy scikit-learn=0.19 -y -q
+  - conda update conda -y -q
+  - conda create -n testenv --yes python=%PYTHON_VERSION% pip
+  - activate testenv
+  - conda install scipy numpy -y -q
+  - pip install --pre scikit-learn
   - "conda install %OPTIONAL_DEP% -y -q"
   - conda install pytest pytest-cov -y -q
   - pip install codecov
-  - conda install nose -y -q  # FIXME: remove this line when using sklearn > 0.19
   - pip install .
 
 test_script:

Diff for: build_tools/circle/build_doc.sh

@@ -92,7 +92,7 @@ conda create -n $CONDA_ENV_NAME --yes --quiet python=3
 source activate $CONDA_ENV_NAME
 
 conda install --yes pip numpy scipy scikit-learn pillow matplotlib sphinx \
-      sphinx_rtd_theme numpydoc pandas keras nose
+      sphinx_rtd_theme numpydoc pandas keras
 pip install -U git+https://github.com/sphinx-gallery/sphinx-gallery.git
 
 # Build and install imbalanced-learn in dev mode

Diff for: build_tools/travis/after_success.sh

@@ -7,7 +7,7 @@
 set -e
 
 # Need to run covdecov from a git checkout, so we copy .coverage
-# from TEST_DIR where nosetests has been run
+# from TEST_DIR where pytest has been run
 cd $TRAVIS_BUILD_DIR
 # Ignore covdecov failures as the covdecov server is not
 # very reliable but we don't want travis to report a failure

Diff for: build_tools/travis/install.sh

@@ -40,7 +40,7 @@ if [[ "$DISTRIB" == "conda" ]]; then
     source activate testenv
     conda install --yes numpy=$NUMPY_VERSION scipy=$SCIPY_VERSION
 
-    if [[ $PYTHON_VERSION == "3.6" ]]; then
+    if [[ $PYTHON_VERSION == "3.7" ]]; then
         conda install --yes pandas
         conda install --yes -c conda-forge keras
         KERAS_BACKEND=tensorflow
@@ -52,12 +52,11 @@ if [[ "$DISTRIB" == "conda" ]]; then
         conda install --yes cython
         pip install -U git+https://github.com/scikit-learn/scikit-learn.git
     else
-        conda install --yes scikit-learn=$SKLEARN_VERSION
+        conda install --yes scikit-learn=$SKLEARN_VERSION -c conda-forge/label/rc -c conda-forge
     fi
 
-    conda install --yes nose pytest pytest-cov
-    # Install nose-timer via pip
-    pip install nose-timer codecov
+    conda install --yes pytest pytest-cov
+    pip install codecov
 
 elif [[ "$DISTRIB" == "ubuntu" ]]; then
     # At the time of writing numpy 1.9.1 is included in the travis
@@ -67,9 +66,10 @@ elif [[ "$DISTRIB" == "ubuntu" ]]; then
     # Create a new virtualenv using system site packages for python, numpy
     virtualenv --system-site-packages testvenv
     source testvenv/bin/activate
-    pip install scikit-learn
+
+    pip install --pre scikit-learn
     pip install pandas keras tensorflow
-    pip install nose nose-timer pytest pytest-cov codecov sphinx numpydoc
+    pip install pytest pytest-cov codecov sphinx numpydoc
 
 fi
 

Diff for: build_tools/travis/test_script.sh

@@ -12,7 +12,7 @@ run_tests(){
     # Get into a temp directory to run test from the installed scikit learn and
     # check if we do not leave artifacts
     mkdir -p $TEST_DIR
-    # We need the setup.cfg for the nose settings
+    # We need the setup.cfg for the pytest settings
     cp setup.cfg $TEST_DIR
     cd $TEST_DIR
 
@@ -21,7 +21,7 @@ run_tests(){
     python -c "import scipy; print('scipy %s' % scipy.__version__)"
     python -c "import multiprocessing as mp; print('%d CPUs' % mp.cpu_count())"
 
-    py.test --cov=$MODULE -r sx --pyargs $MODULE
+    pytest --cov=$MODULE -r sx --pyargs $MODULE
 
     # Test doc
     cd $OLDPWD

Diff for: doc/install.rst

@@ -9,12 +9,13 @@ The imbalanced-learn package requires the following dependencies:
 
 * numpy (>=1.8.2)
 * scipy (>=0.13.3)
-* scikit-learn (>=0.19.0)
+* scikit-learn (>=0.20)
 * keras 2 (optional)
 * tensorflow (optional)
 
 Our release policy is to follow the scikit-learn releases in order to
-synchronize the new feature.
+synchronize the new feature. **imbalanced-learn 0.4 is the last version to
+support Python 2.7**
 
 Install
 =======
@@ -50,6 +51,10 @@ You wish to test the coverage of your version::
 
   $ make coverage
 
+You can also use `pytest`::
+
+  $ pytest imblearn -v
+
 Contribute
 ==========
 

Diff for: doc/whats_new/v0.0.4.rst

@@ -81,7 +81,7 @@ Bug fixes
   samples.
   :issue:`450` by :user:`Guillaume Lemaitre <glemaitre>`.
 
-- Add the option to pass a ``Memory`` object to :func:`make_pipeline` like 
+- Add the option to pass a ``Memory`` object to :func:`make_pipeline` like
   in :class:`pipeline.Pipeline` class.
   :issue:`458` by :user:`Christos Aridas <chkoar>`.
 
@@ -94,6 +94,9 @@ Maintenance
 - Make some modules private.
   :issue:`452` by :user:`Guillaume Lemaitre <glemaitre>`.
 
+- Upgrade requirements to scikit-learn 0.20.
+  :issue:`379` by :user:`Guillaume Lemaitre <glemaitre>`.
+
 Documentation
 .............
 

Diff for: imblearn/base.py

@@ -6,7 +6,6 @@
 
 from __future__ import division
 
-import logging
 import warnings
 from abc import ABCMeta, abstractmethod
 
@@ -132,7 +131,6 @@ def __init__(self, sampling_strategy='auto', ratio=None):
         self.sampling_strategy = sampling_strategy
         # FIXME: remove in 0.6
         self.ratio = ratio
-        self.logger = logging.getLogger(self.__module__)
 
     @staticmethod
     def _check_X_y(X, y):
@@ -154,18 +152,6 @@ def _deprecate_ratio(self):
             deprecate_parameter(self, '0.4', 'ratio', 'sampling_strategy')
             self.sampling_strategy = self.ratio
 
-    def __getstate__(self):
-        """Prevent logger from being pickled."""
-        object_dictionary = self.__dict__.copy()
-        del object_dictionary['logger']
-        return object_dictionary
-
-    def __setstate__(self, dict):
-        """Re-open the logger."""
-        logger = logging.getLogger(self.__module__)
-        self.__dict__.update(dict)
-        self.logger = logger
-
 
 def _identity(X, y):
     return X, y
@@ -241,7 +227,6 @@ def __init__(self, func=None, accept_sparse=True, kw_args=None):
         self.func = func
         self.accept_sparse = accept_sparse
         self.kw_args = kw_args
-        self.logger = logging.getLogger(__name__)
 
     def _fit_resample(self, X, y):
         X, y = check_X_y(X, y, accept_sparse=['csr', 'csc']

Diff for: imblearn/combine/_smote_enn.py

@@ -6,8 +6,6 @@
 
 from __future__ import division
 
-import logging
-
 from sklearn.base import clone
 from sklearn.utils import check_X_y
 
@@ -98,7 +96,6 @@ def __init__(self,
         self.smote = smote
         self.enn = enn
         self.ratio = ratio
-        self.logger = logging.getLogger(__name__)
 
     def _validate_estimator(self):
         "Private function to validate SMOTE and ENN objects"

Diff for: imblearn/combine/_smote_tomek.py

@@ -7,8 +7,6 @@
 
 from __future__ import division
 
-import logging
-
 from sklearn.base import clone
 from sklearn.utils import check_X_y
 
@@ -106,7 +104,6 @@ def __init__(self,
         self.smote = smote
         self.tomek = tomek
         self.ratio = ratio
-        self.logger = logging.getLogger(__name__)
 
     def _validate_estimator(self):
         "Private function to validate SMOTE and ENN objects"

Diff for: imblearn/datasets/_imbalance.py

@@ -5,7 +5,6 @@
 #          Christos Aridas
 # License: MIT
 
-import logging
 import warnings
 from collections import Counter
 
@@ -14,14 +13,13 @@
 from ..under_sampling import RandomUnderSampler
 from ..utils import check_sampling_strategy
 
-LOGGER = logging.getLogger(__name__)
-
 
 def make_imbalance(X,
                    y,
                    sampling_strategy=None,
                    ratio=None,
                    random_state=None,
+                   verbose=False,
                    **kwargs):
     """Turns a dataset into an imbalanced dataset at specific ratio.
 
@@ -60,6 +58,9 @@ def make_imbalance(X,
         If None, the random number generator is the RandomState instance used
         by np.random.
 
+    verbose : bool, optional (default=False)
+        Show information regarding the sampling.
+
     kwargs : dict, optional
         Dictionary of additional keyword arguments to pass to
         ``sampling_strategy``.
@@ -115,13 +116,15 @@ def make_imbalance(X,
                          "function returning a dictionary. Got {} instead."
                          .format(type(sampling_strategy)))
 
-    LOGGER.info('The original target distribution in the dataset is: %s',
-                target_stats)
+    if verbose:
+        print('The original target distribution in the dataset is: %s',
+              target_stats)
     rus = RandomUnderSampler(
         sampling_strategy=sampling_strategy_,
         replacement=False,
         random_state=random_state)
     X_resampled, y_resampled = rus.fit_resample(X, y)
-    LOGGER.info('Make the dataset imbalanced: %s', Counter(y_resampled))
+    if verbose:
+        print('Make the dataset imbalanced: %s', Counter(y_resampled))
 
     return X_resampled, y_resampled