BUG: min/max on empty categorical fails

doc/source/whatsnew/v1.0.0.rst

@@ -667,6 +667,7 @@ Categorical
  same type as if one used the :meth:`.str.` / :meth:`.dt.` on a :class:`Series` of that type. E.g. when accessing :meth:`Series.dt.tz_localize` on a
  :class:`Categorical` with duplicate entries, the accessor was skipping duplicates (:issue:`27952`)
 - Bug in :meth:`DataFrame.replace` and :meth:`Series.replace` that would give incorrect results on categorical data (:issue:`26988`)
+- Bug where calling :meth:`Categorical.min` or :meth:`Categorical.max` on an empty Categorical would raise a numpy exception (:issue:`30227`)
 
 
 Datetimelike

pandas/core/arrays/categorical.py

@@ -39,7 +39,7 @@
 from pandas.core.dtypes.dtypes import CategoricalDtype
 from pandas.core.dtypes.generic import ABCIndexClass, ABCSeries
 from pandas.core.dtypes.inference import is_hashable
-from pandas.core.dtypes.missing import isna, notna
+from pandas.core.dtypes.missing import isna, na_value_for_dtype, notna
 
 from pandas._typing import ArrayLike, Dtype, Ordered
 from pandas.core import ops
@@ -2116,6 +2116,10 @@ def min(self, skipna=True):
 
  Only ordered `Categoricals` have a minimum!
 
+ .. versionchanged:: 1.0.0
+
+ Returns an NA value on empty arrays
+
  Raises
  ------
  TypeError
@@ -2126,6 +2130,10 @@ def min(self, skipna=True):
  min : the minimum of this `Categorical`
  """
  self.check_for_ordered("min")
+
+ if not len(self._codes):
+ return self.dtype.na_value
+
  good = self._codes != -1
  if not good.all():
  if skipna:
@@ -2143,6 +2151,10 @@ def max(self, skipna=True):
 
  Only ordered `Categoricals` have a maximum!
 
+ .. versionchanged:: 1.0.0
+
+ Returns an NA value on empty arrays
+
  Raises
  ------
  TypeError
@@ -2153,6 +2165,10 @@ def max(self, skipna=True):
  max : the maximum of this `Categorical`
  """
  self.check_for_ordered("max")
+
+ if not len(self._codes):
+ return self.dtype.na_value
+
  good = self._codes != -1
  if not good.all():
  if skipna:

pandas/tests/arrays/categorical/test_analytics.py

@@ -5,14 +5,13 @@
 
 from pandas.compat import PYPY
 
-from pandas import Categorical, Index, Series
+from pandas import Categorical, Index, Series, date_range
 from pandas.api.types import is_scalar
 import pandas.util.testing as tm
 
 
 class TestCategoricalAnalytics:
- def test_min_max(self):
-
+ def test_min_max_not_ordered(self):
  # unordered cats have no min/max
  cat = Categorical(["a", "b", "c", "d"], ordered=False)
  msg = "Categorical is not ordered for operation {}"
@@ -21,6 +20,7 @@ def test_min_max(self):
  with pytest.raises(TypeError, match=msg.format("max")):
  cat.max()
 
+ def test_min_max_ordered(self):
  cat = Categorical(["a", "b", "c", "d"], ordered=True)
  _min = cat.min()
  _max = cat.max()
@@ -35,6 +35,24 @@ def test_min_max(self):
  assert _min == "d"
  assert _max == "a"
 
+ @pytest.mark.parametrize(
+ "categories,expected",
+ [
+ (list("ABC"), np.NaN),
+ ([1, 2, 3], np.NaN),
+ (Series(date_range("2020-01-01", periods=3), dtype="category"), np.NaN),
+ ],
+ )
+ def test_min_max_ordered_empty(self, categories, expected):
+ # GH 30227
+ cat = Categorical([], categories=list("ABC"), ordered=True)
+
+ result = cat.min()
+ assert result is expected
+
+ result = cat.max()
+ assert result is expected
+
  @pytest.mark.parametrize("skipna", [True, False])
  def test_min_max_with_nan(self, skipna):
  # GH 25303