Release v0.1.11 (#17)

* bump to v0.1.11

docs/source/api_reference.rst

@@ -303,3 +303,12 @@ Variable types
     Ordinal
     Boolean
     Text
+
+
+Feature Selection
+------------------
+.. currentmodule:: featuretools.selection
+.. autosummary::
+    :toctree: generated/
+
+    remove_low_information_features

docs/source/changelog.rst

@@ -3,6 +3,17 @@
 Changelog
 ---------
 
+**v0.1.11** October 31, 2017
+    * Package linting (:pr:`7`)
+    * Custom primitive creation functions (:pr:`13`)
+    * Split requirements to separate files and pin to latest versions (:pr:`15`)
+    * Select low information features (:pr:`18`)
+    * Fix docs typos (:pr:`19`)
+    * Fixed Diff primitive for rare nan case (:pr:`21`)
+    * added some mising doc strings (:pr:`23`)
+    * Trend fix (:pr:`22`)
+    * Remove as_dir=False option from EntitySet.to_pickle() (:pr:`20`)
+    * Entity Normalization Preserves Types of Copy & Additional Variables (:pr:`25`)
 
 **v0.1.10** October 12, 2017
     * NumTrue primitive added and docstring of other primitives updated (:pr:`11`)
@@ -47,3 +58,6 @@ Changelog
 **v0.1.2** July 3rd, 2017
 
     * Initial release
+
+.. command
+.. git log --pretty=oneline --abbrev-commit

featuretools/__init__.py

@@ -11,4 +11,4 @@
 from .utils.pickle_utils import *
 import featuretools.demo
 
-__version__ = '0.1.10'
+__version__ = '0.1.11'

featuretools/selection/api.py

@@ -1,2 +1,2 @@
 # flake8: noqa
-from .variance_selection import *
+from .selection import *

featuretools/selection/selection.py

@@ -0,0 +1,18 @@
+def remove_low_information_features(feature_matrix, features=None):
+    '''
+    Select features that have at least 2 unique values and that are not all null
+    Args:
+        feature_matrix (:class:`pd.DataFrame`): DataFrame whose columns are
+            feature names and rows are instances
+        features (list[:class:`featuretools.PrimitiveBase`] or list[str], optional):
+            List of features to select
+    '''
+    keep = [c for c in feature_matrix
+            if (feature_matrix[c].nunique(dropna=False) > 1 and
+                feature_matrix[c].dropna().shape[0] > 0)]
+    feature_matrix = feature_matrix[keep]
+    if features is not None:
+        features = [f for f in features
+                    if f.get_name() in feature_matrix.columns]
+        return feature_matrix, features
+    return feature_matrix

featuretools/tests/selection/test_selection.py

@@ -0,0 +1,44 @@
+from featuretools.selection import remove_low_information_features
+from featuretools.tests.testing_utils import make_ecommerce_entityset
+from featuretools import Feature
+import numpy as np
+import pandas as pd
+import pytest
+
+
+@pytest.fixture(scope='module')
+def feature_matrix():
+    feature_matrix = pd.DataFrame({'test': [0, 1, 2],
+                                   'no_null': [np.nan, 0, 0],
+                                   'some_null': [np.nan, 0, 0],
+                                   'all_null': [np.nan, np.nan, np.nan],
+                                   'many_value': [1, 2, 3],
+                                   'dup_value': [1, 1, 2],
+                                   'one_value': [1, 1, 1]})
+    return feature_matrix
+
+
+@pytest.fixture(scope='module')
+def es(feature_matrix):
+    es = make_ecommerce_entityset()
+    es.entity_from_dataframe('test', feature_matrix, index='test')
+    return es
+
+
+def test_remove_low_information_feature_names(feature_matrix):
+    feature_matrix = remove_low_information_features(feature_matrix)
+    assert feature_matrix.shape == (3, 5)
+    assert 'one_value' not in feature_matrix.columns
+    assert 'all_null' not in feature_matrix.columns
+
+
+def test_remove_low_information_features(es, feature_matrix):
+    features = [Feature(v) for v in es['test'].variables]
+    feature_matrix, features = remove_low_information_features(feature_matrix,
+                                                               features)
+    assert feature_matrix.shape == (3, 5)
+    assert len(features) == 5
+    for f in features:
+        assert f.get_name() in feature_matrix.columns
+    assert 'one_value' not in feature_matrix.columns
+    assert 'all_null' not in feature_matrix.columns

setup.py

@@ -15,7 +15,7 @@ def finalize_options(self):
 
 setup(
     name='featuretools',
-    version='0.1.10',
+    version='0.1.11',
     packages=find_packages(),
     description='a framework for automated feature engineering',
     url='http://featuretools.com',