Skip to content

support tuple in startswith/endswith for arrow strings #56580

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 6 commits into from
Dec 21, 2023
Merged

support tuple in startswith/endswith for arrow strings #56580

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
3629f97
support tuple in startswith/endswith for arrow strings
Dec 20, 2023
9100d45
gh
Dec 20, 2023
618387f
improve test
Dec 20, 2023
756b4e2
improve tests
Dec 20, 2023
4cfb730
Update pandas/core/arrays/arrow/array.py
rohanjain101 Dec 21, 2023
6f1d269
Update pandas/core/arrays/arrow/array.py
rohanjain101 Dec 21, 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
1 change: 1 addition & 0 deletions doc/source/whatsnew/v2.2.0.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -601,6 +601,7 @@ Strings
- Bug in :meth:`Series.__mul__` for :class:`ArrowDtype` with ``pyarrow.string`` dtype and ``string[pyarrow]`` for the pyarrow backend (:issue:`51970`)
- Bug in :meth:`Series.str.find` when ``start < 0`` for :class:`ArrowDtype` with ``pyarrow.string`` (:issue:`56411`)
- Bug in :meth:`Series.str.replace` when ``n < 0`` for :class:`ArrowDtype` with ``pyarrow.string`` (:issue:`56404`)
- Bug in :meth:`Series.str.startswith` and :meth:`Series.str.endswith` with arguments of type ``tuple[str, ...]`` for :class:`ArrowDtype` with ``pyarrow.string`` dtype (:issue:`56579`)
- Bug in :meth:`Series.str.startswith` and :meth:`Series.str.endswith` with arguments of type ``tuple[str, ...]`` for ``string[pyarrow]`` (:issue:`54942`)

Interval
Expand Down
30 changes: 26 additions & 4 deletions pandas/core/arrays/arrow/array.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2174,14 +2174,36 @@ def _str_contains(
result = result.fill_null(na)
return type(self)(result)

def _str_startswith(self, pat: str, na=None):
result = pc.starts_with(self._pa_array, pattern=pat)
def _str_startswith(self, pat: str | tuple[str, ...], na=None):
if isinstance(pat, str):
result = pc.starts_with(self._pa_array, pattern=pat)
else:
if len(pat) == 0:
# For empty tuple, pd.StringDtype() returns null for missing values
# and false for valid values.
result = pc.if_else(pc.is_null(self._pa_array), None, False)
else:
result = pc.starts_with(self._pa_array, pattern=pat[0])

for p in pat[1:]:
result = pc.or_(result, pc.starts_with(self._pa_array, pattern=p))
if not isna(na):
result = result.fill_null(na)
return type(self)(result)

def _str_endswith(self, pat: str, na=None):
result = pc.ends_with(self._pa_array, pattern=pat)
def _str_endswith(self, pat: str | tuple[str, ...], na=None):
if isinstance(pat, str):
result = pc.ends_with(self._pa_array, pattern=pat)
else:
if len(pat) == 0:
# For empty tuple, pd.StringDtype() returns null for missing values
# and false for valid values.
result = pc.if_else(pc.is_null(self._pa_array), None, False)
else:
result = pc.ends_with(self._pa_array, pattern=pat[0])

for p in pat[1:]:
result = pc.or_(result, pc.ends_with(self._pa_array, pattern=p))
if not isna(na):
result = result.fill_null(na)
return type(self)(result)
Expand Down
24 changes: 19 additions & 5 deletions pandas/tests/extension/test_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1801,19 +1801,33 @@ def test_str_contains_flags_unsupported():
@pytest.mark.parametrize(
"side, pat, na, exp",
[
["startswith", "ab", None, [True, None]],
["startswith", "b", False, [False, False]],
["endswith", "b", True, [False, True]],
["endswith", "bc", None, [True, None]],
["startswith", "ab", None, [True, None, False]],
["startswith", "b", False, [False, False, False]],
["endswith", "b", True, [False, True, False]],
["endswith", "bc", None, [True, None, False]],
["startswith", ("a", "e", "g"), None, [True, None, True]],
["endswith", ("a", "c", "g"), None, [True, None, True]],
["startswith", (), None, [False, None, False]],
["endswith", (), None, [False, None, False]],
],
)
def test_str_start_ends_with(side, pat, na, exp):
ser = pd.Series(["abc", None], dtype=ArrowDtype(pa.string()))
ser = pd.Series(["abc", None, "efg"], dtype=ArrowDtype(pa.string()))
result = getattr(ser.str, side)(pat, na=na)
expected = pd.Series(exp, dtype=ArrowDtype(pa.bool_()))
tm.assert_series_equal(result, expected)


@pytest.mark.parametrize("side", ("startswith", "endswith"))
def test_str_starts_ends_with_all_nulls_empty_tuple(side):
Copy link
Contributor Author

Choose a reason for hiding this comment

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

I added this test because in case of empty tuple, code to create series is:

result = pc.if_else(pc.is_null(self._pa_array), None, False)

I thought that if self._pa_array was all nulls, that resulting datatype may be null[pyarrow] (when we want bool[pyarrow]), I added this test to validate that bool is preserved, even in all nulls case.

ser = pd.Series([None, None], dtype=ArrowDtype(pa.string()))
result = getattr(ser.str, side)(())

# bool datatype preserved for all nulls.
expected = pd.Series([None, None], dtype=ArrowDtype(pa.bool_()))
tm.assert_series_equal(result, expected)


@pytest.mark.parametrize(
"arg_name, arg",
[["pat", re.compile("b")], ["repl", str], ["case", False], ["flags", 1]],
Expand Down