Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Backport PR #24967 on branch 0.24.x (REGR: Preserve order by default in Index.difference) #25013

Merged
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions doc/source/whatsnew/v0.24.1.rst
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@ Fixed Regressions

- Bug in :meth:`DataFrame.itertuples` with ``records`` orient raising an ``AttributeError`` when the ``DataFrame`` contained more than 255 columns (:issue:`24939`)
- Bug in :meth:`DataFrame.itertuples` orient converting integer column names to strings prepended with an underscore (:issue:`24940`)
- Fixed regression in :class:`Index.intersection` incorrectly sorting the values by default (:issue:`24959`).

.. _whatsnew_0241.enhancements:

Expand Down
8 changes: 6 additions & 2 deletions pandas/core/indexes/base.py
Original file line number Diff line number Diff line change
Expand Up @@ -2333,7 +2333,7 @@ def union(self, other, sort=True):
def _wrap_setop_result(self, other, result):
return self._constructor(result, name=get_op_result_name(self, other))

def intersection(self, other, sort=True):
def intersection(self, other, sort=False):
"""
Form the intersection of two Index objects.

Expand All @@ -2342,11 +2342,15 @@ def intersection(self, other, sort=True):
Parameters
----------
other : Index or array-like
sort : bool, default True
sort : bool, default False
Sort the resulting index if possible

.. versionadded:: 0.24.0

.. versionchanged:: 0.24.1

Changed the default from ``True`` to ``False``.

Returns
-------
intersection : Index
Expand Down
10 changes: 9 additions & 1 deletion pandas/core/indexes/datetimes.py
Original file line number Diff line number Diff line change
Expand Up @@ -594,14 +594,22 @@ def _wrap_setop_result(self, other, result):
name = get_op_result_name(self, other)
return self._shallow_copy(result, name=name, freq=None, tz=self.tz)

def intersection(self, other, sort=True):
def intersection(self, other, sort=False):
"""
Specialized intersection for DatetimeIndex objects. May be much faster
than Index.intersection

Parameters
----------
other : DatetimeIndex or array-like
sort : bool, default True
Sort the resulting index if possible.

.. versionadded:: 0.24.0

.. versionchanged:: 0.24.1

Changed the default from ``True`` to ``False``.

Returns
-------
Expand Down
6 changes: 3 additions & 3 deletions pandas/core/indexes/interval.py
Original file line number Diff line number Diff line change
Expand Up @@ -1093,8 +1093,8 @@ def equals(self, other):
def overlaps(self, other):
return self._data.overlaps(other)

def _setop(op_name):
def func(self, other, sort=True):
def _setop(op_name, sort=True):
def func(self, other, sort=sort):
other = self._as_like_interval_index(other)

# GH 19016: ensure set op will not return a prohibited dtype
Expand Down Expand Up @@ -1128,7 +1128,7 @@ def is_all_dates(self):
return False

union = _setop('union')
intersection = _setop('intersection')
intersection = _setop('intersection', sort=False)
difference = _setop('difference')
symmetric_difference = _setop('symmetric_difference')

Expand Down
6 changes: 5 additions & 1 deletion pandas/core/indexes/multi.py
Original file line number Diff line number Diff line change
Expand Up @@ -2910,7 +2910,7 @@ def union(self, other, sort=True):
return MultiIndex.from_arrays(lzip(*uniq_tuples), sortorder=0,
names=result_names)

def intersection(self, other, sort=True):
def intersection(self, other, sort=False):
"""
Form the intersection of two MultiIndex objects.

Expand All @@ -2922,6 +2922,10 @@ def intersection(self, other, sort=True):

.. versionadded:: 0.24.0

.. versionchanged:: 0.24.1

Changed the default from ``True`` to ``False``.

Returns
-------
Index
Expand Down
6 changes: 5 additions & 1 deletion pandas/core/indexes/range.py
Original file line number Diff line number Diff line change
Expand Up @@ -343,7 +343,7 @@ def equals(self, other):

return super(RangeIndex, self).equals(other)

def intersection(self, other, sort=True):
def intersection(self, other, sort=False):
"""
Form the intersection of two Index objects.

Expand All @@ -355,6 +355,10 @@ def intersection(self, other, sort=True):

.. versionadded:: 0.24.0

.. versionchanged:: 0.24.1

Changed the default from ``True`` to ``False``.

Returns
-------
intersection : Index
Expand Down
22 changes: 17 additions & 5 deletions pandas/tests/indexes/test_base.py
Original file line number Diff line number Diff line change
Expand Up @@ -765,6 +765,11 @@ def test_intersect_str_dates(self, sort):

assert len(result) == 0

def test_intersect_nosort(self):
result = pd.Index(['c', 'b', 'a']).intersection(['b', 'a'])
expected = pd.Index(['b', 'a'])
tm.assert_index_equal(result, expected)

@pytest.mark.parametrize("sort", [True, False])
def test_chained_union(self, sort):
# Chained unions handles names correctly
Expand Down Expand Up @@ -1595,20 +1600,27 @@ def test_drop_tuple(self, values, to_drop):
for drop_me in to_drop[1], [to_drop[1]]:
pytest.raises(KeyError, removed.drop, drop_me)

@pytest.mark.parametrize("method,expected", [
@pytest.mark.parametrize("method,expected,sort", [
('intersection', np.array([(1, 'A'), (2, 'A'), (1, 'B'), (2, 'B')],
dtype=[('num', int), ('let', 'a1')]),
False),

('intersection', np.array([(1, 'A'), (1, 'B'), (2, 'A'), (2, 'B')],
dtype=[('num', int), ('let', 'a1')])),
dtype=[('num', int), ('let', 'a1')]),
True),

('union', np.array([(1, 'A'), (1, 'B'), (1, 'C'), (2, 'A'), (2, 'B'),
(2, 'C')], dtype=[('num', int), ('let', 'a1')]))
(2, 'C')], dtype=[('num', int), ('let', 'a1')]),
True)
])
def test_tuple_union_bug(self, method, expected):
def test_tuple_union_bug(self, method, expected, sort):
index1 = Index(np.array([(1, 'A'), (2, 'A'), (1, 'B'), (2, 'B')],
dtype=[('num', int), ('let', 'a1')]))
index2 = Index(np.array([(1, 'A'), (2, 'A'), (1, 'B'),
(2, 'B'), (1, 'C'), (2, 'C')],
dtype=[('num', int), ('let', 'a1')]))

result = getattr(index1, method)(index2)
result = getattr(index1, method)(index2, sort=sort)
assert result.ndim == 1

expected = Index(expected)
Expand Down