Skip to content

feat: support date data type for to_datetime() #1902

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 11 commits into from
Jul 11, 2025
+42 −8
Merged

feat: support date data type for to_datetime() #1902

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
e15ee50
feat: support date data type for to_datetime()
sycai Jul 11, 2025
dc9ebda
Merge branch 'main' into sycai_to_dt
sycai Jul 11, 2025
a99dacb
add test preconditions
sycai Jul 11, 2025
5ab4741
Merge branch 'main' into sycai_to_dt
sycai Jul 11, 2025
f0eecff
fix test
sycai Jul 11, 2025
c80bb2c
fix lint
sycai Jul 11, 2025
e9194d3
fix tests
sycai Jul 11, 2025
b85b09b
fix lint
sycai Jul 11, 2025
9189762
fix test
sycai Jul 11, 2025
371e315
update docstring
sycai Jul 11, 2025
7839f64
update docstring
sycai Jul 11, 2025
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
12 changes: 8 additions & 4 deletions bigframes/core/tools/datetimes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
# limitations under the License.

from collections.abc import Mapping
from datetime import datetime
from datetime import date, datetime
from typing import Optional, Union

import bigframes_vendored.constants as constants
Expand All @@ -28,7 +28,7 @@

def to_datetime(
arg: Union[
Union[int, float, str, datetime],
Union[int, float, str, datetime, date],
Copy link
Contributor

Choose a reason for hiding this comment

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

The docstring located at third_party/bigframes_vendored/pandas/core/tools/datetimes.py should be updated too.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Good call. Done.

vendored_pandas_datetimes.local_iterables,
bigframes.series.Series,
bigframes.dataframe.DataFrame,
Expand All @@ -38,7 +38,7 @@ def to_datetime(
format: Optional[str] = None,
unit: Optional[str] = None,
) -> Union[pd.Timestamp, datetime, bigframes.series.Series]:
if isinstance(arg, (int, float, str, datetime)):
if isinstance(arg, (int, float, str, datetime, date)):
return pd.to_datetime(
arg,
utc=utc,
Expand All @@ -62,7 +62,11 @@ def to_datetime(
f"Unit parameter is not supported for non-numerical input types. {constants.FEEDBACK_LINK}"
)

if arg.dtype in (bigframes.dtypes.TIMESTAMP_DTYPE, bigframes.dtypes.DATETIME_DTYPE):
if arg.dtype in (
bigframes.dtypes.TIMESTAMP_DTYPE,
bigframes.dtypes.DATETIME_DTYPE,
bigframes.dtypes.DATE_DTYPE,
):
to_type = (
bigframes.dtypes.TIMESTAMP_DTYPE if utc else bigframes.dtypes.DATETIME_DTYPE
)
Expand Down
2 changes: 2 additions & 0 deletions bigframes/operations/datetime_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,7 @@ def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionT
dtypes.FLOAT_DTYPE,
dtypes.INT_DTYPE,
dtypes.STRING_DTYPE,
dtypes.DATE_DTYPE,
):
raise TypeError("expected string or numeric input")
return pd.ArrowDtype(pa.timestamp("us", tz=None))
Expand All @@ -67,6 +68,7 @@ def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionT
dtypes.FLOAT_DTYPE,
dtypes.INT_DTYPE,
dtypes.STRING_DTYPE,
dtypes.DATE_DTYPE,
):
raise TypeError("expected string or numeric input")
return pd.ArrowDtype(pa.timestamp("us", tz="UTC"))
Expand Down
23 changes: 23 additions & 0 deletions tests/system/small/operations/test_datetimes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,12 +13,15 @@
# limitations under the License.

import datetime
import typing

import numpy
from packaging import version
from pandas import testing
import pandas as pd
import pytest

import bigframes.pandas as bpd
import bigframes.series
from bigframes.testing.utils import assert_series_equal

Expand Down Expand Up @@ -548,3 +551,23 @@ def test_timedelta_dt_accessors_on_wrong_type_raise_exception(scalars_dfs, acces

with pytest.raises(TypeError):
access(bf_df["timestamp_col"])


@pytest.mark.parametrize(
"col",
# TODO(b/431276706) test timestamp_col too.
["date_col", "datetime_col"],
)
def test_to_datetime(scalars_dfs, col):
if version.Version(pd.__version__) <= version.Version("2.1.0"):
pytest.skip("timezone conversion bug")
bf_df, pd_df = scalars_dfs

actual_result = typing.cast(
bigframes.series.Series, bpd.to_datetime(bf_df[col])
).to_pandas()

expected_result = pd.Series(pd.to_datetime(pd_df[col]))
testing.assert_series_equal(
actual_result, expected_result, check_dtype=False, check_index_type=False
)
13 changes: 9 additions & 4 deletions third_party/bigframes_vendored/pandas/core/tools/datetimes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,22 @@
# Contains code from https://github.com/pandas-dev/pandas/blob/main/pandas/core/tools/datetimes.py

from datetime import datetime
from datetime import date, datetime
from typing import List, Mapping, Tuple, Union

import pandas as pd

from bigframes import constants, series
from bigframes import constants, dataframe, series

local_iterables = Union[List, Tuple, pd.Series, pd.DataFrame, Mapping]


def to_datetime(
arg,
arg: Union[
Union[int, float, str, datetime, date],
local_iterables,
series.Series,
dataframe.DataFrame,
],
*,
utc=False,
format=None,
Expand Down Expand Up @@ -58,7 +63,7 @@ def to_datetime(
dtype: timestamp[us, tz=UTC][pyarrow]

Args:
arg (int, float, str, datetime, list, tuple, 1-d array, Series):
arg (int, float, str, datetime, date, list, tuple, 1-d array, Series):
The object to convert to a datetime.
utc (bool, default False):
Control timezone-related parsing, localization and conversion. If True, the
Expand Down