Thanks to visit codestin.com
Credit goes to github.com

Skip to content

feat: support pd.cut() for array-like type #2064

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 1 commit into from
Sep 10, 2025
Merged

feat: support pd.cut() for array-like type #2064

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
8 changes: 6 additions & 2 deletions bigframes/core/reshape/tile.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@
import bigframes_vendored.pandas.core.reshape.tile as vendored_pandas_tile
import pandas as pd

import bigframes
import bigframes.constants
import bigframes.core.expression as ex
import bigframes.core.ordering as order
Expand All @@ -32,7 +33,7 @@


def cut(
x: bigframes.series.Series,
x,
Copy link
Contributor

Choose a reason for hiding this comment

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

Do we want to drop the type hints? Though pandas doesn't have for this parameter, giving hints helps users to know what to pass in.

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 point. I'm keeping x untyped to remain consistent with Series.__init__(), which also doesn't have type hints.

bins: typing.Union[
int,
pd.IntervalIndex,
Expand Down Expand Up @@ -60,9 +61,12 @@ def cut(
f"but found {type(list(labels)[0])}. {constants.FEEDBACK_LINK}"
)

if x.size == 0:
if len(x) == 0:
raise ValueError("Cannot cut empty array.")

if not isinstance(x, bigframes.series.Series):
x = bigframes.series.Series(x)

if isinstance(bins, int):
if bins <= 0:
raise ValueError("`bins` should be a positive integer.")
Expand Down
12 changes: 12 additions & 0 deletions tests/system/small/test_pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -520,6 +520,18 @@ def _convert_pandas_category(pd_s: pd.Series):
)


def test_cut_for_array():
"""Avoid regressions for internal issue 329866195"""
sc = [30, 80, 40, 90, 60, 45, 95, 75, 55, 100, 65, 85]
x = [20, 40, 60, 80, 100]

pd_result: pd.Series = pd.Series(pd.cut(sc, x))
bf_result = bpd.cut(sc, x)

pd_result = _convert_pandas_category(pd_result)
pd.testing.assert_series_equal(bf_result.to_pandas(), pd_result)


@pytest.mark.parametrize(
("right", "labels"),
[
Expand Down
3 changes: 3 additions & 0 deletions tests/unit/test_pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,7 @@ def test_method_matches_session(method_name: str):
)
def test_cut_raises_with_invalid_labels(bins: int, labels, error_message: str):
mock_series = mock.create_autospec(bigframes.pandas.Series, instance=True)
mock_series.__len__.return_value = 5
with pytest.raises(ValueError, match=error_message):
bigframes.pandas.cut(mock_series, bins, labels=labels)

Expand Down Expand Up @@ -160,6 +161,8 @@ def test_cut_raises_with_unsupported_labels():
)
def test_cut_raises_with_invalid_bins(bins: int, error_message: str):
mock_series = mock.create_autospec(bigframes.pandas.Series, instance=True)
mock_series.__len__.return_value = 5

with pytest.raises(ValueError, match=error_message):
bigframes.pandas.cut(mock_series, bins, labels=False)

Expand Down
6 changes: 3 additions & 3 deletions third_party/bigframes_vendored/pandas/core/reshape/tile.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,11 @@

import pandas as pd

from bigframes import constants, series
from bigframes import constants


def cut(
x: series.Series,
x,
bins: typing.Union[
int,
pd.IntervalIndex,
Expand Down Expand Up @@ -113,7 +113,7 @@ def cut(
dtype: struct<left_inclusive: int64, right_exclusive: int64>[pyarrow]

Args:
x (bigframes.pandas.Series):
x (array-like):
The input Series to be binned. Must be 1-dimensional.
bins (int, pd.IntervalIndex, Iterable):
The criteria to bin by.
Expand Down