BUG: reindex would throw when a categorical index was empty pandas-de…

…v#16770
ri938 · Jul 3, 2017 · df5bfcf · df5bfcf
1 parent 664348c
commit df5bfcf
Show file tree

Hide file tree

Showing 3 changed files with 16 additions and 3 deletions.
diff --git a/doc/source/whatsnew/v0.20.3.txt b/doc/source/whatsnew/v0.20.3.txt
@@ -37,7 +37,7 @@ Performance Improvements
 Bug Fixes
 ~~~~~~~~~
 - Fixed issue with dataframe scatter plot for categorical data that reports incorrect column key not found when categorical data is used for plotting (:issue:`16199`)
-
+- Handle reindexing an empty categorical index rather than throwing (:issue:`16770`)
 
 
 

diff --git a/pandas/core/indexes/category.py b/pandas/core/indexes/category.py
@@ -419,7 +419,11 @@ def reindex(self, target, method=None, level=None, limit=None,
             raise ValueError("cannot reindex with a non-unique indexer")
 
         indexer, missing = self.get_indexer_non_unique(np.array(target))
-        new_target = self.take(indexer)
+
+        if len(self.codes):
+            new_target = self.take(indexer)
+        else:
+            new_target = target
 
         # filling in missing if needed
         if len(missing):
@@ -430,7 +434,8 @@ def reindex(self, target, method=None, level=None, limit=None,
                 result = Index(np.array(self), name=self.name)
                 new_target, indexer, _ = result._reindex_non_unique(
                     np.array(target))
-
+                # see GH 16819, indexer needs to be converted to correct type
+                indexer = np.array(indexer, dtype=np.int64)
             else:
 
                 codes = new_target.codes.copy()

diff --git a/pandas/tests/indexes/test_category.py b/pandas/tests/indexes/test_category.py
@@ -420,6 +420,14 @@ def test_reindex_dtype(self):
         tm.assert_numpy_array_equal(indexer,
                                     np.array([0, 3, 2], dtype=np.int64))
 
+    def test_reindex_empty_index(self):
+        # See GH16770
+        c = CategoricalIndex([])
+        res, indexer = c.reindex(['a', 'b'])
+        tm.assert_index_equal(res, Index(['a', 'b']), exact=True)
+        tm.assert_numpy_array_equal(indexer,
+                                    np.array([-1, -1], dtype=np.int64))
+
     def test_duplicates(self):
 
         idx = CategoricalIndex([0, 0, 0], name='foo')