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

fix: make explode respect the index labels #1064

Merged
merged 1 commit into from
Oct 8, 2024
Merged

fix: make explode respect the index labels #1064

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
2 changes: 1 addition & 1 deletion bigframes/core/blocks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1390,7 +1390,7 @@ def explode(
expr,
column_labels=self.column_labels,
index_columns=self.index_columns,
index_labels=self.column_labels.names,
index_labels=self._index_labels,
)

def _standard_stats(self, column_id) -> typing.Sequence[agg_ops.UnaryAggregateOp]:
Expand Down
20 changes: 19 additions & 1 deletion tests/system/small/test_multiindex.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1178,7 +1178,7 @@ def test_column_multi_index_dot_not_supported():
bf1 @ bf2


def test_explode_w_multi_index():
def test_explode_w_column_multi_index():
data = [[[1, 1], np.nan, [3, 3]], [[2], [5], []]]
multi_level_columns = pandas.MultiIndex.from_arrays(
[["col0", "col0", "col1"], ["col00", "col01", "col11"]]
Expand All @@ -1197,6 +1197,24 @@ def test_explode_w_multi_index():
)


def test_explode_w_multi_index():
data = [[[1, 1], np.nan, [3, 3]], [[2], [5], []]]
columns = ["col00", "col01", "col11"]
multi_index = pandas.MultiIndex.from_frame(
pandas.DataFrame({"idx0": [5, 1], "idx1": ["z", "x"]})
)

df = bpd.DataFrame(data, index=multi_index, columns=columns)
pd_df = df.to_pandas()

pandas.testing.assert_frame_equal(
df.explode("col00").to_pandas(),
pd_df.explode("col00"),
check_dtype=False,
check_index_type=False,
)


def test_column_multi_index_w_na_stack(scalars_df_index, scalars_pandas_df_index):
columns = ["int64_too", "int64_col", "rowindex_2"]
level1 = pandas.Index(["b", "c", "d"])
Expand Down
22 changes: 22 additions & 0 deletions tests/system/small/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3852,6 +3852,28 @@ def test_series_explode(data):
pytest.param([5, 1, 3, 2], False, id="ignore_unordered_index"),
pytest.param(["z", "x", "a", "b"], True, id="str_index"),
pytest.param(["z", "x", "a", "b"], False, id="ignore_str_index"),
pytest.param(
pd.Index(["z", "x", "a", "b"], name="idx"), True, id="str_named_index"
),
pytest.param(
pd.Index(["z", "x", "a", "b"], name="idx"),
False,
id="ignore_str_named_index",
),
pytest.param(
pd.MultiIndex.from_frame(
pd.DataFrame({"idx0": [5, 1, 3, 2], "idx1": ["z", "x", "a", "b"]})
),
True,
id="multi_index",
),
pytest.param(
pd.MultiIndex.from_frame(
pd.DataFrame({"idx0": [5, 1, 3, 2], "idx1": ["z", "x", "a", "b"]})
),
False,
id="ignore_multi_index",
),
],
)
def test_series_explode_w_index(index, ignore_index):
Expand Down