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

Jump to bottom

Deprecate groupby fillna #15000

Merged
merged 1 commit into from
Feb 8, 2024
Merged

Deprecate groupby fillna #15000

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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
17 changes: 6 additions & 11 deletions python/cudf/cudf/core/groupby/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2227,6 +2227,12 @@ def fillna(
-------
DataFrame or Series
"""
warnings.warn(
"groupby fillna is deprecated and "
"will be removed in a future version. Use groupby ffill or groupby bfill "
"for forward or backward filling instead.",
FutureWarning,
)
if inplace:
raise NotImplementedError("Does not support inplace yet.")
if limit is not None:
Expand All @@ -2244,17 +2250,6 @@ def fillna(
if method is not None:
if method not in {"ffill", "bfill"}:
raise ValueError("Method can only be of 'ffill', 'bfill'.")
# Do not remove until pandas 3.0 support is added.
assert (
PANDAS_LT_300
), "Need to drop after pandas-3.0 support is added."
warnings.warn(
f"{type(self).__name__}.fillna with 'method' is "
"deprecated and will raise in a future version. "
"Use obj.ffill() or obj.bfill() instead.",
FutureWarning,
)

return getattr(self, method, limit)()

values = self.obj.__class__._from_data(
Expand Down
23 changes: 13 additions & 10 deletions python/cudf/cudf/tests/test_groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
import cudf
from cudf import DataFrame, Series
from cudf.api.extensions import no_default
from cudf.core._compat import PANDAS_GE_200, PANDAS_GE_210
from cudf.core._compat import PANDAS_GE_200, PANDAS_GE_210, PANDAS_GE_220
from cudf.core.udf._ops import arith_ops, comparison_ops, unary_ops
from cudf.core.udf.groupby_typing import SUPPORTED_GROUPBY_NUMPY_TYPES
from cudf.core.udf.utils import UDFError, precompiled
Expand Down Expand Up @@ -2745,10 +2745,10 @@ def test_groupby_fillna_multi_value(nelem):
}
# cudf can't fillna with a pandas.Timedelta type
fill_values["4"] = fill_values["4"].to_numpy()

expect = pdf.groupby(key_col).fillna(value=fill_values)

got = gdf.groupby(key_col).fillna(value=fill_values)
with expect_warning_if(PANDAS_GE_220):
expect = pdf.groupby(key_col).fillna(value=fill_values)
with pytest.warns(FutureWarning):
got = gdf.groupby(key_col).fillna(value=fill_values)

assert_groupby_results_equal(expect[value_cols], got[value_cols])

Expand Down Expand Up @@ -2791,11 +2791,12 @@ def test_groupby_fillna_multi_value_df(nelem):
# cudf can't fillna with a pandas.Timedelta type
fill_values["4"] = fill_values["4"].to_numpy()
fill_values = pd.DataFrame(fill_values, index=pdf.index)

expect = pdf.groupby(key_col).fillna(value=fill_values)
with expect_warning_if(PANDAS_GE_220):
expect = pdf.groupby(key_col).fillna(value=fill_values)

fill_values = cudf.from_pandas(fill_values)
got = gdf.groupby(key_col).fillna(value=fill_values)
with pytest.warns(FutureWarning):
got = gdf.groupby(key_col).fillna(value=fill_values)

assert_groupby_results_equal(expect[value_cols], got[value_cols])

Expand All @@ -2812,11 +2813,13 @@ def test_groupby_various_by_fillna(by, data, args):
ps = pd.Series(data)
gs = cudf.from_pandas(ps)

with expect_warning_if(PANDAS_GE_210 and "method" in args):
with expect_warning_if(
(PANDAS_GE_210 and "method" in args) or PANDAS_GE_220
):
expect = ps.groupby(by).fillna(**args)
if isinstance(by, pd.Grouper):
by = cudf.Grouper(level=by.level)
with expect_warning_if("method" in args):
with pytest.warns(FutureWarning):
got = gs.groupby(by).fillna(**args)

assert_groupby_results_equal(expect, got, check_dtype=False)
Expand Down