Skip to content

CoW: Optimize Series.reset_index to make lazy copy #52040

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.

Sign up for GitHub

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

Merged
merged 3 commits into from
Mar 17, 2023
Merged

CoW: Optimize Series.reset_index to make lazy copy #52040

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e091543
CoW: Optimize Series.reset_index to make lazy copy
phofl Mar 16, 2023
60b131f
Update
phofl Mar 16, 2023
b71f453
Update
phofl Mar 16, 2023
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
4 changes: 4 additions & 0 deletions pandas/core/series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1550,6 +1550,10 @@ def reset_index(

if inplace:
self.index = new_index
elif using_copy_on_write():
new_ser = self.copy(deep=False)
new_ser.index = new_index
return new_ser.__finalize__(self, method="reset_index")
else:
return self._constructor(
self._values.copy(), index=new_index, copy=False
Expand Down
15 changes: 15 additions & 0 deletions pandas/tests/copy_view/test_methods.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,6 +233,21 @@ def test_reset_index(using_copy_on_write):
tm.assert_frame_equal(df, df_orig)


@pytest.mark.parametrize("index", [pd.RangeIndex(0, 2), Index([1, 2])])
def test_reset_index_series_drop(using_copy_on_write, index):
ser = Series([1, 2], index=index)
ser_orig = ser.copy()
ser2 = ser.reset_index(drop=True)
if using_copy_on_write:
assert np.shares_memory(get_array(ser), get_array(ser2))
assert not ser._mgr._has_no_reference(0)
else:
assert not np.shares_memory(get_array(ser), get_array(ser2))

ser2.iloc[0] = 100
tm.assert_series_equal(ser, ser_orig)


def test_rename_columns(using_copy_on_write):
# Case: renaming columns returns a new dataframe
# + afterwards modifying the result
Expand Down