BUG/API: Categorical constructor scalar categories (#16340)

* BUG: Categorical constructor scalar categories Categorical constructor no longer accepts scalars for categories. Closes #16022

Author: TomAugspurger

doc/source/whatsnew/v0.21.0.txt

@@ -37,6 +37,8 @@ Backwards incompatible API changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 - Support has been dropped for Python 3.4 (:issue:`15251`)
+- The Categorical constructor no longer accepts a scalar for the ``categories`` keyword. (:issue:`16022`)
+
 
 .. _whatsnew_0210.api:
 
@@ -110,6 +112,9 @@ Numeric
 ^^^^^^^
 
 
+Categorical
+^^^^^^^^^^^
+
 
 Other
 ^^^^^

pandas/core/categorical.py

@@ -533,6 +533,9 @@ def _validate_categories(cls, categories, fastpath=False):
  if not isinstance(categories, ABCIndexClass):
  dtype = None
  if not hasattr(categories, "dtype"):
+ if not is_list_like(categories):
+ raise TypeError("`categories` must be list-like. "
+ "Got {} instead".format(repr(categories)))
  categories = _convert_to_list_like(categories)
  # On categories with NaNs, int values would be converted to
  # float. Use "object" dtype to prevent this.

pandas/tests/test_categorical.py

@@ -256,12 +256,6 @@ def f():
  assert len(cat.codes) == 1
  assert cat.codes[0] == 0
 
- cat = pd.Categorical([1], categories=1)
- assert len(cat.categories) == 1
- assert cat.categories[0] == 1
- assert len(cat.codes) == 1
- assert cat.codes[0] == 0
-
  # Catch old style constructor useage: two arrays, codes + categories
  # We can only catch two cases:
  # - when the first is an integer dtype and the second is not
@@ -285,6 +279,11 @@ def f():
  c = Categorical(np.array([], dtype='int64'), # noqa
  categories=[3, 2, 1], ordered=True)
 
+ def test_constructor_not_sequence(self):
+ # https://github.com/pandas-dev/pandas/issues/16022
+ with pytest.raises(TypeError):
+ Categorical(['a', 'b'], categories='a')
+
  def test_constructor_with_null(self):
 
  # Cannot have NaN in categories