Skip to content

feat: DataFrame.join supports Series other #1303

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

Merged
merged 1 commit into from
Jan 21, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion bigframes/dataframe.py
Original file line number Diff line number Diff line change
Expand Up @@ -3039,8 +3039,15 @@ def merge(
return DataFrame(block)

def join(
self, other: DataFrame, *, on: Optional[str] = None, how: str = "left"
self,
other: Union[DataFrame, bigframes.series.Series],
*,
on: Optional[str] = None,
how: str = "left",
) -> DataFrame:
if isinstance(other, bigframes.series.Series):
other = other.to_frame()

left, right = self, other

if not left.columns.intersection(right.columns).empty:
Expand Down
21 changes: 21 additions & 0 deletions tests/system/small/test_dataframe.py
Original file line number Diff line number Diff line change
Expand Up @@ -2554,6 +2554,27 @@ def test_join_param_on(scalars_dfs, how):
assert_pandas_df_equal(bf_result, pd_result, ignore_order=True)


@all_joins
def test_df_join_series(scalars_dfs, how):
bf_df, pd_df = scalars_dfs

bf_df_a = bf_df[["string_col", "int64_col", "rowindex_2"]]
bf_df_a = bf_df_a.assign(rowindex_2=bf_df_a["rowindex_2"] + 2)
bf_series_b = bf_df["float64_col"]

if how == "cross":
with pytest.raises(ValueError):
bf_df_a.join(bf_series_b, on="rowindex_2", how=how)
else:
bf_result = bf_df_a.join(bf_series_b, on="rowindex_2", how=how).to_pandas()

pd_df_a = pd_df[["string_col", "int64_col", "rowindex_2"]]
pd_df_a = pd_df_a.assign(rowindex_2=pd_df_a["rowindex_2"] + 2)
pd_series_b = pd_df["float64_col"]
pd_result = pd_df_a.join(pd_series_b, on="rowindex_2", how=how)
assert_pandas_df_equal(bf_result, pd_result, ignore_order=True)


@pytest.mark.parametrize(
("by", "ascending", "na_position"),
[
Expand Down
2 changes: 1 addition & 1 deletion third_party/bigframes_vendored/pandas/core/frame.py
Original file line number Diff line number Diff line change
Expand Up @@ -4384,7 +4384,7 @@ def join(self, other, *, on: Optional[str] = None, how: str) -> DataFrame:

Args:
other:
DataFrame with an Index similar to the Index of this one.
DataFrame or Series with an Index similar to the Index of this one.
on:
Column in the caller to join on the index in other, otherwise
joins index-on-index. Like an Excel VLOOKUP operation.
Expand Down
Loading