Skip to content
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

BUG: ArrowExtensionArray.to_numpy from timestamp to int #56567

Merged
merged 5 commits into from
Dec 21, 2023
Merged

BUG: ArrowExtensionArray.to_numpy from timestamp to int #56567

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b09aa83
BUG: ArrowExtensionArray.to_numpy from timestamp to int
mroeschke Dec 19, 2023
7669844
Include check for object
mroeschke Dec 19, 2023
2f4fa97
Merge remote-tracking branch 'upstream/main' into bug/arrow/to_numpy_dt
mroeschke Dec 19, 2023
f8d9454
Adjust test
mroeschke Dec 19, 2023
ed99237
Merge remote-tracking branch 'upstream/main' into bug/arrow/to_numpy_dt
mroeschke Dec 19, 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
16 changes: 6 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 @@ -1313,16 +1313,12 @@ def to_numpy(
copy = False

if pa.types.is_timestamp(pa_type) or pa.types.is_duration(pa_type):
result = data._maybe_convert_datelike_array()
if (pa.types.is_timestamp(pa_type) and pa_type.tz is not None) or (
dtype is not None and dtype.kind == "O"
):
dtype = object
else:
# GH 55997
dtype = None
na_value = pa_type.to_pandas_dtype().type("nat", pa_type.unit)
result = result.to_numpy(dtype=dtype, na_value=na_value)
# GH 55997
if dtype != object and na_value is self.dtype.na_value:
na_value = lib.no_default
result = data._maybe_convert_datelike_array().to_numpy(
dtype=dtype, na_value=na_value
)
elif pa.types.is_time(pa_type) or pa.types.is_date(pa_type):
# convert to list of python datetime.time objects before
# wrapping in ndarray
Expand Down
13 changes: 12 additions & 1 deletion pandas/tests/extension/test_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2996,7 +2996,10 @@ def test_to_numpy_temporal(pa_type, dtype):
value = pd.Timestamp(1, unit=pa_type.unit, tz=pa_type.tz).as_unit(pa_type.unit)

if dtype == object or (pa.types.is_timestamp(pa_type) and pa_type.tz is not None):
na = pd.NA
if dtype == object:
na = pd.NA
else:
na = pd.NaT
expected = np.array([value, na], dtype=object)
assert result[0].unit == value.unit
else:
Expand Down Expand Up @@ -3108,3 +3111,11 @@ def test_string_to_time_parsing_cast():
ArrowExtensionArray(pa.array([time(11, 41, 43, 76160)], from_pandas=True))
)
tm.assert_series_equal(result, expected)


def test_to_numpy_timestamp_to_int():
# GH 55997
ser = pd.Series(["2020-01-01 04:30:00"], dtype="timestamp[ns][pyarrow]")
result = ser.to_numpy(dtype=np.int64)
expected = np.array([1577853000000000000])
tm.assert_numpy_array_equal(result, expected)