Fix bug with encode_features and features that create multiple columns (

#622) * fix indent * tests for duplicate columns * update changelog * Update changelog.rst
alteryx · Jul 2, 2019 · 7203f2d · 7203f2d
1 parent 0257f52
commit 7203f2d
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 2 deletions.
diff --git a/docs/source/changelog.rst b/docs/source/changelog.rst
@@ -12,6 +12,8 @@ Changelog
         * Filter dataframes through forward relationships (:pr:`625`)
         * Specify Dask version in requirements for python 2 (:pr:`627`)
         * Keep dataframe sorted by time during feature calculation (:pr:`626`)
+        * Fix bug in encode_features that created duplicate columns of
+          features with multiple outputs (:pr:`622`)
     * Changes
         * Remove unused variance_selection.py file (:pr:`613`)
         * Remove Timedelta data param (:pr:`619`)

diff --git a/featuretools/synthesis/encode_features.py b/featuretools/synthesis/encode_features.py
@@ -74,7 +74,7 @@ def encode_features(feature_matrix, features, top_n=10, include_unknown=True,
             assert fname in X.columns, (
                 "Feature %s not found in feature matrix" % (fname)
             )
-        feature_names.append(fname)
+            feature_names.append(fname)
 
     extra_columns = [col for col in X.columns if col not in feature_names]
 

diff --git a/featuretools/tests/synthesis/test_encode_features.py b/featuretools/tests/synthesis/test_encode_features.py
@@ -135,6 +135,7 @@ def test_encode_features_topn(es):
     features_enc, feature_defs_enc = encode_features(features,
                                                      feature_defs,
                                                      include_unknown=True)
-    assert topn.hash() in [feat.hash() for feat in feature_defs_enc]
+    assert topn.unique_name() in [feat.unique_name() for feat in feature_defs_enc]
     for name in topn.get_feature_names():
         assert name in features_enc.columns
+        assert features_enc.columns.tolist().count(name) == 1