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.

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

fix: fix read_gbq_function issue in dataframe apply method #1174

Merged
merged 22 commits into from
Jan 18, 2025
Merged
Show file tree
Hide file tree
Changes from 9 commits
Commits
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
11 changes: 10 additions & 1 deletion bigframes/dataframe.py
Original file line number Diff line number Diff line change
Expand Up @@ -3959,7 +3959,16 @@ def apply(self, func, *, axis=0, args: typing.Tuple = (), **kwargs):
return result_series

# Per-column apply
results = {name: func(col, *args, **kwargs) for name, col in self.items()}
if hasattr(func, "bigframes_remote_function"):
jialuoo marked this conversation as resolved.
Show resolved Hide resolved
jialuoo marked this conversation as resolved.
Show resolved Hide resolved
if args or kwargs:
warnings.warn(
"The args and kwargs are not supported in the remote function.",
category=bigframes.exceptions.ArgsAndKwargsNotSupportedWarning,
)
results = {name: col.apply(func) for name, col in self.items()}
jialuoo marked this conversation as resolved.
Show resolved Hide resolved
else:
results = {name: func(col, *args, **kwargs) for name, col in self.items()}
jialuoo marked this conversation as resolved.
Show resolved Hide resolved

if all(
[
isinstance(val, bigframes.series.Series) or utils.is_list_like(val)
Expand Down
4 changes: 4 additions & 0 deletions bigframes/exceptions.py
Original file line number Diff line number Diff line change
Expand Up @@ -77,3 +77,7 @@ class ApiDeprecationWarning(FutureWarning):

class BadIndexerKeyWarning(Warning):
"""The indexer key is not used correctly."""


class ArgsAndKwargsNotSupportedWarning(Warning):
jialuoo marked this conversation as resolved.
Show resolved Hide resolved
"""The args and kwargs are not supported."""
24 changes: 24 additions & 0 deletions tests/system/small/test_remote_function.py
Original file line number Diff line number Diff line change
Expand Up @@ -839,6 +839,30 @@ def test_read_gbq_function_enforces_explicit_types(
)


@pytest.mark.flaky(retries=2, delay=120)
def test_df_apply(session, scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bdf = bigframes.pandas.DataFrame(
{
"Column1": scalars_df["string_col"],
"Column2": scalars_df["string_col"],
}
)

func_ref = session.read_gbq_function("bqutil.fn.cw_lower_case_ascii_only")
bf_result = bdf.apply(func_ref).to_pandas()
# The str.lower() method has the same functionality as func_ref.
jialuoo marked this conversation as resolved.
Show resolved Hide resolved
pd_result = pd.DataFrame(
{
"Column1": scalars_pandas_df["string_col"].str.lower(),
"Column2": scalars_pandas_df["string_col"].str.lower(),
}
)

pd.testing.assert_series_equal(pd_result["Column1"], bf_result["Column1"])
pd.testing.assert_series_equal(pd_result["Column2"], bf_result["Column2"])


@pytest.mark.flaky(retries=2, delay=120)
def test_read_gbq_function_multiple_inputs_not_a_row_processor(session):
with pytest.raises(ValueError) as context:
Expand Down
Loading