BUG: sefault in concat of CategoricalIndex (#16133)

* BUG: sefault in concat of cat-idx * lint
pandas-dev · Apr 25, 2017 · 186957e · 186957e
1 parent 8d122e6
commit 186957e
Show file tree

Hide file tree

Showing 3 changed files with 27 additions and 2 deletions.
diff --git a/doc/source/whatsnew/v0.20.0.txt b/doc/source/whatsnew/v0.20.0.txt
@@ -1629,6 +1629,7 @@ Indexing
 - Bug in the display of ``.info()`` where a qualifier (+) would always be displayed with a ``MultiIndex`` that contains only non-strings (:issue:`15245`)
 - Bug in ``pd.concat()`` where the names of ``MultiIndex`` of resulting ``DataFrame`` are not handled correctly when ``None`` is presented in the names of ``MultiIndex`` of input ``DataFrame`` (:issue:`15787`)
 - Bug in ``DataFrame.sort_index()`` and ``Series.sort_index()`` where ``na_position`` doesn't work with a ``MultiIndex`` (:issue:`14784`, :issue:`16604`)
+ - Bug in in ``pd.concat()`` when combining objects with a ``CategoricalIndex`` (:issue:`16111`)
 
 I/O
 ^^^

diff --git a/pandas/core/indexes/category.py b/pandas/core/indexes/category.py
@@ -12,6 +12,7 @@
     is_scalar)
 from pandas.core.common import _asarray_tuplesafe
 from pandas.core.dtypes.missing import array_equivalent
+from pandas.core.algorithms import take_1d
 
 
 from pandas.util.decorators import Appender, cache_readonly
@@ -470,8 +471,10 @@ def get_indexer(self, target, method=None, limit=None, tolerance=None):
             codes = target.codes
         else:
             if isinstance(target, CategoricalIndex):
-                target = target.categories
-            codes = self.categories.get_indexer(target)
+                code_indexer = self.categories.get_indexer(target.categories)
+                codes = take_1d(code_indexer, target.codes, fill_value=-1)
+            else:
+                codes = self.categories.get_indexer(target)
 
         indexer, _ = self._engine.get_indexer_non_unique(codes)
 

diff --git a/pandas/tests/reshape/test_concat.py b/pandas/tests/reshape/test_concat.py
@@ -1928,6 +1928,27 @@ def test_concat_multiindex_dfs_with_deepcopy(self):
         result_no_copy = pd.concat(example_dict, names=['testname'])
         tm.assert_frame_equal(result_no_copy, expected)
 
+    def test_concat_categoricalindex(self):
+        # GH 16111, categories that aren't lexsorted
+        categories = [9, 0, 1, 2, 3]
+
+        a = pd.Series(1, index=pd.CategoricalIndex([9, 0],
+                                                   categories=categories))
+        b = pd.Series(2, index=pd.CategoricalIndex([0, 1],
+                                                   categories=categories))
+        c = pd.Series(3, index=pd.CategoricalIndex([1, 2],
+                                                   categories=categories))
+
+        result = pd.concat([a, b, c], axis=1)
+
+        exp_idx = pd.CategoricalIndex([0, 1, 2, 9])
+        exp = pd.DataFrame({0: [1, np.nan, np.nan, 1],
+                            1: [2, 2, np.nan, np.nan],
+                            2: [np.nan, 3, 3, np.nan]},
+                           columns=[0, 1, 2],
+                           index=exp_idx)
+        tm.assert_frame_equal(result, exp)
+
 
 @pytest.mark.parametrize('pdt', [pd.Series, pd.DataFrame, pd.Panel])
 @pytest.mark.parametrize('dt', np.sctypes['float'])