Skip to content

ENH: ArrowExtensionArray(duration) workarounds for pyarrow versions >= 11.0 #54515

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 4 commits into from
Aug 13, 2023
Merged

ENH: ArrowExtensionArray(duration) workarounds for pyarrow versions >= 11.0 #54515

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a78836b
use version flag
lukemanley Aug 12, 2023
2216a1f
more cases
lukemanley Aug 12, 2023
3b644d0
updates
lukemanley Aug 12, 2023
93304e2
fix
lukemanley Aug 12, 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
19 changes: 9 additions & 10 deletions pandas/core/arrays/arrow/array.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1011,12 +1011,11 @@ def factorize(
) -> tuple[np.ndarray, ExtensionArray]:
null_encoding = "mask" if use_na_sentinel else "encode"

pa_type = self._pa_array.type
if pa.types.is_duration(pa_type):
data = self._pa_array
pa_type = data.type
if pa_version_under11p0 and pa.types.is_duration(pa_type):
# https://github.com/apache/arrow/issues/15226#issuecomment-1376578323
data = self._pa_array.cast(pa.int64())
else:
data = self._pa_array
data = data.cast(pa.int64())

if pa.types.is_dictionary(data.type):
encoded = data
Expand All @@ -1034,7 +1033,7 @@ def factorize(
)
uniques = type(self)(encoded.chunk(0).dictionary)

if pa.types.is_duration(pa_type):
if pa_version_under11p0 and pa.types.is_duration(pa_type):
uniques = cast(ArrowExtensionArray, uniques.astype(self.dtype))
return indices, uniques

Expand Down Expand Up @@ -1273,15 +1272,15 @@ def unique(self) -> Self:
"""
pa_type = self._pa_array.type

if pa.types.is_duration(pa_type):
if pa_version_under11p0 and pa.types.is_duration(pa_type):
# https://github.com/apache/arrow/issues/15226#issuecomment-1376578323
data = self._pa_array.cast(pa.int64())
else:
data = self._pa_array

pa_result = pc.unique(data)

if pa.types.is_duration(pa_type):
if pa_version_under11p0 and pa.types.is_duration(pa_type):
pa_result = pa_result.cast(pa_type)

return type(self)(pa_result)
Expand All @@ -1304,7 +1303,7 @@ def value_counts(self, dropna: bool = True) -> Series:
Series.value_counts
"""
pa_type = self._pa_array.type
if pa.types.is_duration(pa_type):
if pa_version_under11p0 and pa.types.is_duration(pa_type):
# https://github.com/apache/arrow/issues/15226#issuecomment-1376578323
data = self._pa_array.cast(pa.int64())
else:
Expand All @@ -1324,7 +1323,7 @@ def value_counts(self, dropna: bool = True) -> Series:
values = values.filter(mask)
counts = counts.filter(mask)

if pa.types.is_duration(pa_type):
if pa_version_under11p0 and pa.types.is_duration(pa_type):
values = values.cast(pa_type)

counts = ArrowExtensionArray(counts)
Expand Down