BUG: add_categories losing dtype information (#48847)

phofl · web-flow · commit c7623b37d073 · 2022-09-29T13:48:23.000-07:00
diff --git a/doc/source/whatsnew/v1.6.0.rst b/doc/source/whatsnew/v1.6.0.rst
@@ -160,7 +160,7 @@ Bug fixes
 
 Categorical
 ^^^^^^^^^^^
--
+- Bug in :meth:`Categorical.set_categories` losing dtype information (:issue:`48812`)
 -
 
 Datetimelike
diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
@@ -56,7 +56,10 @@
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import validate_bool_kwarg
 
-from pandas.core.dtypes.cast import coerce_indexer_dtype
+from pandas.core.dtypes.cast import (
+    coerce_indexer_dtype,
+    find_common_type,
+)
 from pandas.core.dtypes.common import (
     ensure_int64,
     ensure_platform_int,
@@ -1292,7 +1295,19 @@ def add_categories(
             raise ValueError(
                 f"new categories must not include old categories: {already_included}"
             )
-        new_categories = list(self.dtype.categories) + list(new_categories)
+
+        if hasattr(new_categories, "dtype"):
+            from pandas import Series
+
+            dtype = find_common_type(
+                [self.dtype.categories.dtype, new_categories.dtype]
+            )
+            new_categories = Series(
+                list(self.dtype.categories) + list(new_categories), dtype=dtype
+            )
+        else:
+            new_categories = list(self.dtype.categories) + list(new_categories)
+
         new_dtype = CategoricalDtype(new_categories, self.ordered)
 
         cat = self if inplace else self.copy()
diff --git a/pandas/tests/arrays/categorical/test_api.py b/pandas/tests/arrays/categorical/test_api.py
@@ -11,6 +11,7 @@
     DataFrame,
     Index,
     Series,
+    StringDtype,
 )
 import pandas._testing as tm
 from pandas.core.arrays.categorical import recode_for_categories
@@ -237,6 +238,25 @@ def test_add_categories_existing_raises(self):
         with pytest.raises(ValueError, match=msg):
             cat.add_categories(["d"])
 
+    def test_add_categories_losing_dtype_information(self):
+        # GH#48812
+        cat = Categorical(Series([1, 2], dtype="Int64"))
+        ser = Series([4], dtype="Int64")
+        result = cat.add_categories(ser)
+        expected = Categorical(
+            Series([1, 2], dtype="Int64"), categories=Series([1, 2, 4], dtype="Int64")
+        )
+        tm.assert_categorical_equal(result, expected)
+
+        cat = Categorical(Series(["a", "b", "a"], dtype=StringDtype()))
+        ser = Series(["d"], dtype=StringDtype())
+        result = cat.add_categories(ser)
+        expected = Categorical(
+            Series(["a", "b", "a"], dtype=StringDtype()),
+            categories=Series(["a", "b", "d"], dtype=StringDtype()),
+        )
+        tm.assert_categorical_equal(result, expected)
+
     def test_set_categories(self):
         cat = Categorical(["a", "b", "c", "a"], ordered=True)
         exp_categories = Index(["c", "b", "a"])

Original file line number	Diff line number	Diff line change
`@@ -160,7 +160,7 @@ Bug fixes`
`160`	`160`
`161`	`161`	`Categorical`
`162`	`162`	`^^^^^^^^^^^`
`163`		`--`
	`163`	+- Bug in :meth:`Categorical.set_categories` losing dtype information (:issue:`48812`)
`164`	`164`	`-`
`165`	`165`
`166`	`166`	`Datetimelike`