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 loc-getitem ordering when index contains duplicate labels #13659

Merged
merged 5 commits into from
Jul 12, 2023
+21 −3
Merged

Fix loc-getitem ordering when index contains duplicate labels #13659

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
65bf861
Fix loc-getitem ordering when index contains duplicate labels
wence- Jul 4, 2023
f260c03
Handle case that column names are not strings
wence- Jul 12, 2023
02a573b
Update python/cudf/cudf/core/dataframe.py
galipremsagar Jul 12, 2023
d0cfb11
Merge branch 'branch-23.08' into wence/fix/issue-13658
galipremsagar Jul 12, 2023
e9c735e
Update dataframe.py
galipremsagar Jul 12, 2023
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
6 changes: 4 additions & 2 deletions python/cudf/cudf/core/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -291,12 +291,14 @@ def _getitem_tuple_arg(self, arg):
{tmp_col_name: column.arange(len(tmp_arg[0]))},
index=as_index(tmp_arg[0]),
)
cantor_name = "_" + "_".join(columns_df._data.names)
wence- marked this conversation as resolved.
Show resolved Hide resolved
columns_df[cantor_name] = column.arange(len(columns_df))
df = other_df.join(columns_df, how="inner")
# as join is not assigning any names to index,
# update it over here
df.index.name = columns_df.index.name
df = df.sort_values(tmp_col_name)
df.drop(columns=[tmp_col_name], inplace=True)
df = df.sort_values(by=[tmp_col_name, cantor_name])
df.drop(columns=[tmp_col_name, cantor_name], inplace=True)
# There were no indices found
if len(df) == 0:
raise KeyError(arg)
Expand Down
2 changes: 1 addition & 1 deletion python/cudf/cudf/core/indexed_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,7 @@ def _indices_from_labels(obj, labels):
rhs = cudf.DataFrame(
{"_": cudf.core.column.arange(len(obj))}, index=obj.index
)
return lhs.join(rhs).sort_values("__")["_"]
return lhs.join(rhs).sort_values(by=["__", "_"])["_"]


def _get_label_range_or_mask(index, start, stop, step):
Expand Down
14 changes: 14 additions & 0 deletions python/cudf/cudf/tests/test_indexing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1996,6 +1996,20 @@ def test_loc_missing_label_keyerror_issue_13379(index):
cdf.loc[[0, 5]]


@pytest.mark.parametrize("series", [True, False], ids=["Series", "DataFrame"])
def test_loc_repeated_label_ordering_issue_13658(series):
# https://github.com/rapidsai/cudf/issues/13658
values = range(2048)
index = [1 for _ in values]
if series:
frame = cudf.Series(values, index=index)
else:
frame = cudf.DataFrame({"a": values}, index=index)
expect = frame.to_pandas().loc[[1]]
actual = frame.loc[[1]]
assert_eq(actual, expect)


class TestLocIndexWithOrder:
# https://github.com/rapidsai/cudf/issues/12833
@pytest.fixture(params=["increasing", "decreasing", "neither"])
Expand Down