Add allow_sets-kwarg to is_list_like

doc/source/whatsnew/v0.24.0.txt

@@ -198,6 +198,8 @@ Other Enhancements
 - :meth:`round`, :meth:`ceil`, and meth:`floor` for :class:`DatetimeIndex` and :class:`Timestamp` now support an ``ambiguous`` argument for handling datetimes that are rounded to ambiguous times (:issue:`18946`)
 - :class:`Resampler` now is iterable like :class:`GroupBy` (:issue:`15314`).
 - :meth:`Series.resample` and :meth:`DataFrame.resample` have gained the :meth:`Resampler.quantile` (:issue:`15023`).
+- :meth:`pandas.core.dtypes.is_list_like` has gained a keyword ``allow_sets`` which is ``True`` by default; if ``False``,
+ all instances of ``set`` will not be considered "list-like" anymore (:issue:`23061`)
 - :meth:`Index.to_frame` now supports overriding column name(s) (:issue:`22580`).
 - New attribute :attr:`__git_version__` will return git commit sha of current build (:issue:`21295`).
 - Compatibility with Matplotlib 3.0 (:issue:`22790`).

pandas/compat/__init__.py

@@ -141,6 +141,7 @@ def lfilter(*args, **kwargs):
  Mapping = collections.abc.Mapping
  Sequence = collections.abc.Sequence
  Sized = collections.abc.Sized
+ Set = collections.abc.Set
 
 else:
  # Python 2
@@ -201,6 +202,7 @@ def get_range_parameters(data):
  Mapping = collections.Mapping
  Sequence = collections.Sequence
  Sized = collections.Sized
+ Set = collections.Set
 
 if PY2:
  def iteritems(obj, **kw):

pandas/core/dtypes/common.py

@@ -16,10 +16,10 @@
  ABCSparseArray, ABCSparseSeries, ABCCategoricalIndex, ABCIndexClass,
  ABCDateOffset)
 from pandas.core.dtypes.inference import ( # noqa:F401
- is_bool, is_integer, is_hashable, is_iterator, is_float,
- is_dict_like, is_scalar, is_string_like, is_list_like, is_number,
- is_file_like, is_re, is_re_compilable, is_sequence, is_nested_list_like,
- is_named_tuple, is_array_like, is_decimal, is_complex, is_interval)
+ is_bool, is_integer, is_float, is_number, is_decimal, is_complex,
+ is_re, is_re_compilable, is_dict_like, is_string_like, is_file_like,
+ is_list_like, is_nested_list_like, is_sequence, is_named_tuple,
+ is_hashable, is_iterator, is_array_like, is_scalar, is_interval)
 
 _POSSIBLY_CAST_DTYPES = {np.dtype(t).name
  for t in ['O', 'int8', 'uint8', 'int16', 'uint16',

pandas/core/dtypes/inference.py

@@ -5,7 +5,7 @@
 from numbers import Number
 from pandas import compat
 from pandas.compat import (PY2, string_types, text_type,
- string_and_binary_types, re_type)
+ string_and_binary_types, re_type, Set)
 from pandas._libs import lib
 
 is_bool = lib.is_bool
@@ -247,7 +247,7 @@ def is_re_compilable(obj):
  return True
 
 
-def is_list_like(obj):
+def is_list_like(obj, allow_sets=True):
  """
  Check if the object is list-like.
 
@@ -259,6 +259,10 @@ def is_list_like(obj):
  Parameters
  ----------
  obj : The object to check.
+ allow_sets : boolean, default True
+ If this parameter is False, sets will not be considered list-like
+
+ .. versionadded:: 0.24.0
 
  Returns
  -------
@@ -283,11 +287,15 @@ def is_list_like(obj):
  False
  """
 
- return (isinstance(obj, compat.Iterable) and
+ return (isinstance(obj, compat.Iterable)
  # we do not count strings/unicode/bytes as list-like
- not isinstance(obj, string_and_binary_types) and
+ and not isinstance(obj, string_and_binary_types)
+
  # exclude zero-dimensional numpy arrays, effectively scalars
- not (isinstance(obj, np.ndarray) and obj.ndim == 0))
+ and not (isinstance(obj, np.ndarray) and obj.ndim == 0)
+
+ # exclude sets if allow_sets is False
+ and not (allow_sets is False and isinstance(obj, Set)))
 
 
 def is_array_like(obj):

pandas/tests/dtypes/test_inference.py

@@ -64,20 +64,30 @@ def __getitem__(self):
 
 
 @pytest.mark.parametrize(
- "ll",
- [
- [], [1], (1, ), (1, 2), {'a': 1},
- {1, 'a'}, Series([1]),
- Series([]), Series(['a']).str,
- np.array([2])])
-def test_is_list_like_passes(ll):
- assert inference.is_list_like(ll)
+ "obj, expected",
+ list(zip([
+ [], [1], tuple(), (1, ), (1, 2), {'a': 1}, {1, 'a'}, np.array([2]),
+ Series([1]), Series([]), Series(['a']).str, Index([]), Index([1]),
+ DataFrame(), DataFrame([[1]]), iter([1, 2]), (x for x in [1, 2]),
+ np.ndarray((2,) * 2), np.ndarray((2,) * 3), np.ndarray((2,) * 4)
+ ], [True] * 30))
+ + list(zip([1, '2', object(), str, np.array(2)], [False] * 10)))
+def test_is_list_like(obj, expected):
+ assert inference.is_list_like(obj) == expected
 
 
 @pytest.mark.parametrize(
- "ll", [1, '2', object(), str, np.array(2)])
-def test_is_list_like_fails(ll):
- assert not inference.is_list_like(ll)
+ "obj, expected",
+ list(zip([
+ [], [1], tuple(), (1, ), (1, 2), {'a': 1}, np.array([2]),
+ Series([1]), Series([]), Series(['a']).str, Index([]), Index([1]),
+ DataFrame(), DataFrame([[1]]), iter([1, 2]), (x for x in [1, 2]),
+ np.ndarray((2,) * 2), np.ndarray((2,) * 3), np.ndarray((2,) * 4)
+ ], [True] * 30))
+ + list(zip([1, '2', object(), str, np.array(2),
+ {1, 'a'}, frozenset({1, 'a'})], [False] * 10)))
+def test_is_list_like_disallow_sets(obj, expected):
+ assert inference.is_list_like(obj, allow_sets=False) == expected
 
 
 def test_is_array_like():