Merge pull request #353 from glemaitre/0.3.1

Release 0.3.1

build_tools/circle/build_doc.sh

@@ -93,7 +93,7 @@ source activate $CONDA_ENV_NAME
 
 conda install --yes pip numpy scipy scikit-learn pillow matplotlib sphinx \
       sphinx_rtd_theme numpydoc
-pip install sphinx-gallery
+pip install sphinx-gallery==0.1.11
 
 # Build and install imbalanced-learn in dev mode
 cd "$HOME/$CIRCLE_PROJECT_REPONAME"

conda-recipe/imbalanced-learn/meta.yaml

@@ -1,11 +1,15 @@
 package:
   name: imbalanced-learn
-  version: "0.3.0"
+  version: "0.3.1"
 
 source:
-  git_rev: 0.3.0
+  git_rev: 0.3.1
   git_url: https://github.com/scikit-learn-contrib/imbalanced-learn.git
 
+build:
+  number: 0
+  noarch: python
+
 requirements:
   build:
     - python

doc/combine.rst

@@ -8,19 +8,19 @@ Combination of over- and under-sampling
 
 We previously presented :class:`SMOTE` and showed that this method can generate
 noisy samples by interpolating new points between marginal outliers and
-inliers. This issue can be solved by cleaning the resulted space obtained
-after over-sampling.
+inliers. This issue can be solved by cleaning the space resulting
+from over-sampling.
 
 .. currentmodule:: imblearn.combine
 
 In this regard, Tomek's link and edited nearest-neighbours are the two cleaning
-methods which have been added pipeline after SMOTE over-sampling to obtain a
-cleaner space. Therefore, imbalanced-learn implemented two ready-to-use class
-which pipeline both over- and under-sampling methods: (i) :class:`SMOTETomek`
+methods that have been added to the pipeline after applying SMOTE over-sampling
+to obtain a cleaner space. The two ready-to use classes imbalanced-learn implements
+for combining over- and undersampling methods are: (i) :class:`SMOTETomek`
 and (ii) :class:`SMOTEENN`.
 
-These two classes can be used as any other sampler with identical parameters
-than their former samplers::
+Those two classes can be used like any other sampler with parameters identical 
+to their former samplers::
 
   >>> from collections import Counter
   >>> from sklearn.datasets import make_classification

doc/conf.py

@@ -103,7 +103,7 @@
 # built documents.
 #
 # The short X.Y version.
-__version__ = '0.3.0'
+__version__ = '0.3.1'
 version = __version__
 # The full version, including alpha/beta/rc tags.
 release = __version__

doc/developers_utils.rst

@@ -12,8 +12,8 @@ All the following functions and classes are in the module :mod:`imblearn.utils`.
 
    These utilities are meant to be used internally within the imbalanced-learn
    package. They are not guaranteed to be stable between versions of
-   imbalance-learn. Backports, in particular, will be removed as the
-   imbalance-learn dependencies evolve.
+   imbalanced-learn. Backports, in particular, will be removed as the
+   imbalanced-learn dependencies evolve.
 
 
 Validation Tools
@@ -97,7 +97,7 @@ same information as the deprecation warning as explained above. Use the
      ``k`` was renamed to ``n_clusters`` in version 0.13 and will be removed
      in 0.15.
 
-On the top of all the functionality provided by scikit-learn. Imbalance-learn
+On the top of all the functionality provided by scikit-learn. imbalanced-learn
 provides :func:`deprecate_parameter`: which is used to deprecate a sampler's
 parameter (attribute) by another one.
 

imblearn/under_sampling/prototype_selection/neighbourhood_cleaning_rule.py

@@ -73,6 +73,15 @@ class NeighbourhoodCleaningRule(BaseCleaningSampler):
         :class:`sklearn.neighbors.base.KNeighborsMixin` that will be used to
         find the nearest-neighbors.
 
+    threshold_cleaning : float, optional (default=0.5)
+        Threshold used to whether consider a class or not during the cleaning
+        after applying ENN. A class will be considered during cleaning when:
+
+        Ci > C x T ,
+
+        where Ci and C is the number of samples in the class and the data set,
+        respectively and theta is the threshold.
+
     n_jobs : int, optional (default=1)
         The number of threads to open if possible.
 

imblearn/version.py

@@ -21,7 +21,7 @@
 # Dev branch marker is: 'X.Y.dev' or 'X.Y.devN' where N is an integer.
 # 'X.Y.dev0' is the canonical version of 'X.Y.dev'
 #
-__version__ = '0.3.0'
+__version__ = '0.3.1'
 
 _IMBALANCED_DATASET_INSTALL_MSG = 'See %s for installation information.' % (
     'http://contrib.scikit-learn.org/imbalanced-learn/install.html')

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.0
+current_version = 0.3.1
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<dev>\d+))?
 serialize =