Skip to content

ENH: pyarrow temporal dtypes support quantile in some cases #50868

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 1 commit into from
Jan 20, 2023
Merged

ENH: pyarrow temporal dtypes support quantile in some cases #50868

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
18 changes: 17 additions & 1 deletion pandas/core/arrays/arrow/array.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1204,7 +1204,23 @@ def _quantile(
-------
same type as self
"""
result = pc.quantile(self._data, q=qs, interpolation=interpolation)
pa_dtype = self._data.type

data = self._data
if pa.types.is_temporal(pa_dtype) and interpolation in ["lower", "higher"]:
# https://github.com/apache/arrow/issues/33769 in these cases
# we can cast to ints and back
nbits = pa_dtype.bit_width
if nbits == 32:
data = data.cast(pa.int32())
else:
data = data.cast(pa.int64())

result = pc.quantile(data, q=qs, interpolation=interpolation)

if pa.types.is_temporal(pa_dtype) and interpolation in ["lower", "higher"]:
result = result.cast(pa_dtype)

return type(self)(result)

def _mode(self: ArrowExtensionArrayT, dropna: bool = True) -> ArrowExtensionArrayT:
Expand Down
14 changes: 9 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 @@ -1294,7 +1294,11 @@ def test_quantile(data, interpolation, quantile, request):
ser.quantile(q=quantile, interpolation=interpolation)
return

if not (pa.types.is_integer(pa_dtype) or pa.types.is_floating(pa_dtype)):
if pa.types.is_integer(pa_dtype) or pa.types.is_floating(pa_dtype):
pass
elif pa.types.is_temporal(data._data.type) and interpolation in ["lower", "higher"]:
pass
else:
request.node.add_marker(
pytest.mark.xfail(
raises=pa.ArrowNotImplementedError,
Expand All @@ -1308,10 +1312,10 @@ def test_quantile(data, interpolation, quantile, request):
assert result == data[0]
else:
# Just check the values
result = result.astype("float64[pyarrow]")
expected = pd.Series(
data.take([0, 0]).astype("float64[pyarrow]"), index=[0.5, 0.5]
)
expected = pd.Series(data.take([0, 0]), index=[0.5, 0.5])
if pa.types.is_integer(pa_dtype) or pa.types.is_floating(pa_dtype):
expected = expected.astype("float64[pyarrow]")
result = result.astype("float64[pyarrow]")
tm.assert_series_equal(result, expected)


Expand Down