Skip to content

API/TST: expand tests for string any/all reduction + fix pyarrow-based implementation #59414

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 2 commits into from
Aug 6, 2024
Merged

API/TST: expand tests for string any/all reduction + fix pyarrow-based implementation #59414

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
83a8059
API/TST: expand tests for string any/all reduction + fix pyarrow-base…
jorisvandenbossche Aug 5, 2024
868ba40
Merge remote-tracking branch 'upstream/main' into string-dtype-reduct…
jorisvandenbossche Aug 6, 2024
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
6 changes: 3 additions & 3 deletions pandas/core/arrays/string_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -697,9 +697,9 @@ def _reduce(
self, name: str, *, skipna: bool = True, keepdims: bool = False, **kwargs
):
if name in ["any", "all"]:
if not skipna and name == "all":
nas = pc.invert(pc.is_null(self._pa_array))
arr = pc.and_kleene(nas, pc.not_equal(self._pa_array, ""))
if not skipna:
nas = pc.is_null(self._pa_array)
arr = pc.or_kleene(nas, pc.not_equal(self._pa_array, ""))
Comment on lines -701 to +702
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Before, for converting the string array to a boolean array, True values were considered as "not "", and not null", and this diff changed that to "not "", or null"

else:
arr = pc.not_equal(self._pa_array, "")
return ArrowExtensionArray(arr)._reduce(
Expand Down
51 changes: 44 additions & 7 deletions pandas/tests/reductions/test_reductions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1062,25 +1062,62 @@ def test_any_all_datetimelike(self):
assert df.any().all()
assert not df.all().any()

def test_any_all_pyarrow_string(self):
def test_any_all_string_dtype(self, any_string_dtype):
# GH#54591
pytest.importorskip("pyarrow")
ser = Series(["", "a"], dtype="string[pyarrow_numpy]")
if (
isinstance(any_string_dtype, pd.StringDtype)
and any_string_dtype.na_value is pd.NA
):
# the nullable string dtype currently still raise an error
# https://github.com/pandas-dev/pandas/issues/51939
ser = Series(["a", "b"], dtype=any_string_dtype)
with pytest.raises(TypeError):
ser.any()
with pytest.raises(TypeError):
ser.all()
return

ser = Series(["", "a"], dtype=any_string_dtype)
assert ser.any()
assert not ser.all()
assert ser.any(skipna=False)
assert not ser.all(skipna=False)

ser = Series([None, "a"], dtype="string[pyarrow_numpy]")
ser = Series([np.nan, "a"], dtype=any_string_dtype)
assert ser.any()
assert ser.all()
assert not ser.all(skipna=False)
assert ser.any(skipna=False)
assert ser.all(skipna=False) # NaN is considered truthy
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The places where I currently commented this # NaN is considered truthy are the test cases where the result would change from True to False if NaN would be considered as falsey instead.


ser = Series([None, ""], dtype="string[pyarrow_numpy]")
ser = Series([np.nan, ""], dtype=any_string_dtype)
assert not ser.any()
assert not ser.all()
assert ser.any(skipna=False) # NaN is considered truthy
assert not ser.all(skipna=False)

ser = Series(["a", "b"], dtype="string[pyarrow_numpy]")
ser = Series(["a", "b"], dtype=any_string_dtype)
assert ser.any()
assert ser.all()
assert ser.any(skipna=False)
assert ser.all(skipna=False)

ser = Series([], dtype=any_string_dtype)
assert not ser.any()
assert ser.all()
assert not ser.any(skipna=False)
assert ser.all(skipna=False)

ser = Series([""], dtype=any_string_dtype)
assert not ser.any()
assert not ser.all()
assert not ser.any(skipna=False)
assert not ser.all(skipna=False)

ser = Series([np.nan], dtype=any_string_dtype)
assert not ser.any()
assert ser.all()
assert ser.any(skipna=False) # NaN is considered truthy
assert ser.all(skipna=False) # NaN is considered truthy

def test_timedelta64_analytics(self):
# index min/max
Expand Down