Skip to content

GH-48314: [Python] Compat with pandas 3.0 changed default datetime unit #48319

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

Open
jorisvandenbossche wants to merge 1 commit into
base: main
Choose a base branch
from
Open

GH-48314: [Python] Compat with pandas 3.0 changed default datetime unit #48319

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
4 changes: 2 additions & 2 deletions python/pyarrow/pandas_compat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,7 +140,7 @@ def get_extension_dtype_info(column):
physical_dtype = str(cats.codes.dtype)
elif hasattr(dtype, 'tz'):
metadata = {'timezone': pa.lib.tzinfo_to_string(dtype.tz)}
physical_dtype = 'datetime64[ns]'
physical_dtype = f'datetime64[{dtype.unit}]'
else:
metadata = None
physical_dtype = str(dtype)
Expand Down Expand Up @@ -1188,7 +1188,7 @@ def _reconstruct_columns_from_metadata(columns, column_indexes):
if _pandas_api.is_ge_v3():
# with pandas 3+, to_datetime returns a unit depending on the string
# data, so we restore it to the original unit from the metadata
level = level.as_unit(np.datetime_data(dtype)[0])
level = level.as_unit(np.datetime_data(numpy_dtype)[0])
# GH-41503: if the column index was decimal, restore to decimal
elif pandas_dtype == "decimal":
level = _pandas_api.pd.Index([decimal.Decimal(i) for i in level])
Expand Down
12 changes: 7 additions & 5 deletions python/pyarrow/tests/test_pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,13 +212,14 @@ def test_column_index_names_are_preserved(self):
df.columns.names = ['a']
_check_pandas_roundtrip(df, preserve_index=True)

def test_column_index_names_with_tz(self):
@pytest.mark.parametrize("tz", [None, "Europe/Brussels"])
def test_column_index_names_datetime(self, tz):
# ARROW-13756
# Bug if index is timezone aware DataTimeIndex

df = pd.DataFrame(
np.random.randn(5, 3),
columns=pd.date_range("2021-01-01", periods=3, freq="50D", tz="CET")
columns=pd.date_range("2021-01-01", periods=3, freq="50D", tz=tz)
)
_check_pandas_roundtrip(df, preserve_index=True)

Expand Down Expand Up @@ -451,7 +452,7 @@ def test_datetimetz_column_index(self):
df = pd.DataFrame(
[(1, 'a', 2.0), (2, 'b', 3.0), (3, 'c', 4.0)],
columns=pd.date_range(
start='2017-01-01', periods=3, tz='America/New_York'
start='2017-01-01', periods=3, tz='America/New_York', unit='us'
Copy link
Member

@pitrou pitrou Dec 3, 2025

Choose a reason for hiding this comment

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

Do we want to parametrize this test on datetime unit or is it superfluous?

)
)
t = pa.Table.from_pandas(df, preserve_index=True)
Expand All @@ -460,7 +461,7 @@ def test_datetimetz_column_index(self):
column_indexes, = js['column_indexes']
assert column_indexes['name'] is None
assert column_indexes['pandas_type'] == 'datetimetz'
assert column_indexes['numpy_type'] == 'datetime64[ns]'
assert column_indexes['numpy_type'] == 'datetime64[us]'

md = column_indexes['metadata']
assert md['timezone'] == 'America/New_York'
Expand Down Expand Up @@ -709,7 +710,8 @@ def test_mismatch_metadata_schema(self):
# It is possible that the metadata and actual schema is not fully
# matching (eg no timezone information for tz-aware column)
# -> to_pandas() conversion should not fail on that
df = pd.DataFrame({"datetime": pd.date_range("2020-01-01", periods=3)})
df = pd.DataFrame({"datetime": pd.date_range(
"2020-01-01", periods=3, unit='ns')})

# OPTION 1: casting after conversion
table = pa.Table.from_pandas(df)
Expand Down
Loading