Skip to content

fix: support converting empty time Series to pyarrow Array #11

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 5 commits into from
Sep 29, 2021
Merged

fix: support converting empty time Series to pyarrow Array #11

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
e793ec6
fix: support converting empty `time` Series to pyarrow Array
tswast Sep 27, 2021
e08f7fc
use object dtype for time numpy array
tswast Sep 27, 2021
281afb9
backport to_numpy
tswast Sep 28, 2021
1613bb6
Merge remote-tracking branch 'upstream/main' into issue10-arrow-coverage
tswast Sep 28, 2021
63b946c
remove redundant test
tswast Sep 28, 2021
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
3 changes: 2 additions & 1 deletion db_dtypes/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,7 +125,8 @@ def to_numpy(self, dtype="object"):

def __arrow_array__(self, type=None):
return pyarrow.array(
self.to_numpy(), type=type if type is not None else pyarrow.time64("ns"),
self.to_numpy(dtype="object"),
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

This might have performance implications, but it does seem to prevent the cast to float64 for empty arrays. Also, the dtype seems to be object whenever there are any values in the array, anyway.

Copy link

Choose a reason for hiding this comment

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

I approached this by adding the missing to_numpy() for pandas <1, that just uses astype('object')

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Sweet. That seems to have done the trick. I copied the implementation from your PR https://github.com/googleapis/python-db-dtypes-pandas/pull/9/files#diff-1956943f14005805ef968dfc37c26fe3eee995786f62a1c66dee5a29d9b1a251R111

type=type if type is not None else pyarrow.time64("ns"),
)


Expand Down
163 changes: 163 additions & 0 deletions tests/unit/test_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,163 @@
# Copyright 2021 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import datetime as dt

import pandas
import pyarrow
import pytest

# To register the types.
import db_dtypes # noqa


@pytest.mark.parametrize(
("series", "expected"),
(
(pandas.Series([], dtype="date"), pyarrow.array([], type=pyarrow.date32())),
(
pandas.Series([None, None, None], dtype="date"),
pyarrow.array([None, None, None], type=pyarrow.date32()),
),
(
pandas.Series(
[dt.date(2021, 9, 27), None, dt.date(2011, 9, 27)], dtype="date"
),
pyarrow.array(
[dt.date(2021, 9, 27), None, dt.date(2011, 9, 27)],
type=pyarrow.date32(),
),
),
(
pandas.Series(
[dt.date(1677, 9, 22), dt.date(1970, 1, 1), dt.date(2262, 4, 11)],
dtype="date",
),
pyarrow.array(
[dt.date(1677, 9, 22), dt.date(1970, 1, 1), dt.date(2262, 4, 11)],
type=pyarrow.date32(),
),
),
(pandas.Series([], dtype="time"), pyarrow.array([], type=pyarrow.time64("ns"))),
(
pandas.Series([None, None, None], dtype="time"),
pyarrow.array([None, None, None], type=pyarrow.time64("ns")),
),
(
pandas.Series(
[dt.time(0, 0, 0, 0), None, dt.time(23, 59, 59, 999_999)], dtype="time"
),
pyarrow.array(
[dt.time(0, 0, 0, 0), None, dt.time(23, 59, 59, 999_999)],
type=pyarrow.time64("ns"),
),
),
(
pandas.Series(
[
dt.time(0, 0, 0, 0),
dt.time(12, 30, 15, 125_000),
dt.time(23, 59, 59, 999_999),
],
dtype="time",
),
pyarrow.array(
[
dt.time(0, 0, 0, 0),
dt.time(12, 30, 15, 125_000),
dt.time(23, 59, 59, 999_999),
],
type=pyarrow.time64("ns"),
),
),
),
)
def test_to_arrow(series, expected):
array = pyarrow.array(series)
assert array.equals(expected)


@pytest.mark.parametrize(
("series", "expected"),
(
(pandas.Series([], dtype="date"), pyarrow.array([], type=pyarrow.date64())),
(
pandas.Series([None, None, None], dtype="date"),
pyarrow.array([None, None, None], type=pyarrow.date64()),
),
(
pandas.Series(
[dt.date(2021, 9, 27), None, dt.date(2011, 9, 27)], dtype="date"
),
pyarrow.array(
[dt.date(2021, 9, 27), None, dt.date(2011, 9, 27)],
type=pyarrow.date64(),
),
),
(
pandas.Series(
[dt.date(1677, 9, 22), dt.date(1970, 1, 1), dt.date(2262, 4, 11)],
dtype="date",
),
pyarrow.array(
[dt.date(1677, 9, 22), dt.date(1970, 1, 1), dt.date(2262, 4, 11)],
type=pyarrow.date64(),
),
),
(pandas.Series([], dtype="time"), pyarrow.array([], type=pyarrow.time32("ms"))),
(
pandas.Series([None, None, None], dtype="time"),
pyarrow.array([None, None, None], type=pyarrow.time32("ms")),
),
(
pandas.Series(
[dt.time(0, 0, 0, 0), None, dt.time(23, 59, 59, 999_000)], dtype="time"
),
pyarrow.array(
[dt.time(0, 0, 0, 0), None, dt.time(23, 59, 59, 999_000)],
type=pyarrow.time32("ms"),
),
),
(
pandas.Series(
[dt.time(0, 0, 0, 0), None, dt.time(23, 59, 59, 999_999)], dtype="time"
),
pyarrow.array(
[dt.time(0, 0, 0, 0), None, dt.time(23, 59, 59, 999_999)],
type=pyarrow.time64("us"),
),
),
(
pandas.Series(
[
dt.time(0, 0, 0, 0),
dt.time(12, 30, 15, 125_000),
dt.time(23, 59, 59, 999_999),
],
dtype="time",
),
pyarrow.array(
[
dt.time(0, 0, 0, 0),
dt.time(12, 30, 15, 125_000),
dt.time(23, 59, 59, 999_999),
],
type=pyarrow.time64("us"),
),
),
),
)
def test_to_arrow_w_arrow_type(series, expected):
array = pyarrow.array(series, type=expected.type)
assert array.equals(expected)
Comment on lines +1 to +163
Copy link

Choose a reason for hiding this comment

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

Your tests are nicer than mine. :)

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Thanks! They did catch a bug with empty arrays, so I'm glad I wrote them

11 changes: 0 additions & 11 deletions tests/unit/test_dtypes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,6 @@
import datetime

import packaging.version
import pyarrow.lib
import pytest

pd = pytest.importorskip("pandas")
Expand Down Expand Up @@ -670,13 +669,3 @@ def test_bad_time_parsing(value, error):
def test_bad_date_parsing(value, error):
with pytest.raises(ValueError, match=error):
_cls("date")([value])


@for_date_and_time
def test_date___arrow__array__(dtype):
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Removed because it's redundant with the new test_arrow.py tests.

a = _make_one(dtype)
ar = a.__arrow_array__()
assert isinstance(
ar, pyarrow.Date32Array if dtype == "date" else pyarrow.Time64Array,
)
assert [v.as_py() for v in ar] == list(a)