BUG: Categorical setitem, comparison with tuple category (#36623)

Author: jbrockmendel

doc/source/whatsnew/v1.2.0.rst

@@ -293,7 +293,7 @@ Bug fixes
 Categorical
 ^^^^^^^^^^^
 - :meth:`Categorical.fillna` will always return a copy, will validate a passed fill value regardless of whether there are any NAs to fill, and will disallow a ``NaT`` as a fill value for numeric categories (:issue:`36530`)
--
+- Bug in :meth:`Categorical.__setitem__` that incorrectly raised when trying to set a tuple value (:issue:`20439`)
 -
 
 Datetimelike

pandas/core/arrays/categorical.py

@@ -28,6 +28,7 @@
  is_dict_like,
  is_dtype_equal,
  is_extension_array_dtype,
+ is_hashable,
  is_integer_dtype,
  is_list_like,
  is_object_dtype,
@@ -62,8 +63,9 @@ def _cat_compare_op(op):
 
  @unpack_zerodim_and_defer(opname)
  def func(self, other):
- if is_list_like(other) and len(other) != len(self):
- # TODO: Could this fail if the categories are listlike objects?
+ hashable = is_hashable(other)
+ if is_list_like(other) and len(other) != len(self) and not hashable:
+ # in hashable case we may have a tuple that is itself a category
  raise ValueError("Lengths must match.")
 
  if not self.ordered:
@@ -91,7 +93,7 @@ def func(self, other):
  ret[mask] = fill_value
  return ret
 
- if is_scalar(other):
+ if hashable:
  if other in self.categories:
  i = self._unbox_scalar(other)
  ret = op(self._codes, i)
@@ -1885,7 +1887,8 @@ def _validate_setitem_value(self, value):
  new_codes = self._validate_listlike(value)
  value = Categorical.from_codes(new_codes, dtype=self.dtype)
 
- rvalue = value if is_list_like(value) else [value]
+ # wrap scalars and hashable-listlikes in list
+ rvalue = value if not is_hashable(value) else [value]
 
  from pandas import Index
 

pandas/tests/arrays/categorical/test_indexing.py

@@ -75,14 +75,22 @@ def test_setitem_different_unordered_raises(self, other):
  pd.Categorical(["b", "a"], categories=["a", "b", "c"], ordered=True),
  ],
  )
- def test_setitem_same_ordered_rasies(self, other):
+ def test_setitem_same_ordered_raises(self, other):
  # Gh-24142
  target = pd.Categorical(["a", "b"], categories=["a", "b"], ordered=True)
  mask = np.array([True, False])
  msg = "Cannot set a Categorical with another, without identical categories"
  with pytest.raises(ValueError, match=msg):
  target[mask] = other[mask]
 
+ def test_setitem_tuple(self):
+ # GH#20439
+ cat = pd.Categorical([(0, 1), (0, 2), (0, 1)])
+
+ # This should not raise
+ cat[1] = cat[0]
+ assert cat[1] == (0, 1)
+
 
 class TestCategoricalIndexing:
  def test_getitem_slice(self):

pandas/tests/arrays/categorical/test_operators.py

@@ -179,6 +179,20 @@ def test_comparison_with_unknown_scalars(self):
  tm.assert_numpy_array_equal(cat == 4, np.array([False, False, False]))
  tm.assert_numpy_array_equal(cat != 4, np.array([True, True, True]))
 
+ def test_comparison_with_tuple(self):
+ cat = pd.Categorical(np.array(["foo", (0, 1), 3, (0, 1)], dtype=object))
+
+ result = cat == "foo"
+ expected = np.array([True, False, False, False], dtype=bool)
+ tm.assert_numpy_array_equal(result, expected)
+
+ result = cat == (0, 1)
+ expected = np.array([False, True, False, True], dtype=bool)
+ tm.assert_numpy_array_equal(result, expected)
+
+ result = cat != (0, 1)
+ tm.assert_numpy_array_equal(result, ~expected)
+
  def test_comparison_of_ordered_categorical_with_nan_to_scalar(
  self, compare_operators_no_eq_ne
  ):