Skip to content

TST: Multiindex slicing with NaNs, unexpected results for #25154 #39356

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

Merged
merged 7 commits into from
Feb 5, 2021
Merged

TST: Multiindex slicing with NaNs, unexpected results for #25154 #39356

Changes from 5 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a9a4ff4
TST: Added test case for Multiindex slicing with NaNs issue #25154
theodorju Jan 21, 2021
c0cb975
Merge remote-tracking branch 'upstream/master' into pandas-25154
theodorju Jan 21, 2021
da9a5f0
Removed unecessary definitions.
theodorju Jan 23, 2021
df14980
Addition of test cases.
theodorju Feb 4, 2021
071256c
Modifications in test_frame_getitem_nan_cols_multiindex to use tm.ass…
theodorju Feb 4, 2021
548ca8a
Reverting changes in test_series_getitem_indexing_errors
theodorju Feb 4, 2021
ada8989
Added new line in test_series_getitem_multiindex
theodorju Feb 5, 2021
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
83 changes: 81 additions & 2 deletions pandas/tests/indexing/multiindex/test_getitem.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@
[(0, Series([1], index=[0])), (1, Series([2, 3], index=[1, 2]))],
)
def test_series_getitem_multiindex(access_method, level1_value, expected):

# GH 6018
# series regression getitem with a multi-index

Expand Down Expand Up @@ -87,7 +86,8 @@ def test_series_getitem_returns_scalar(
(lambda s: s[(2000, 3, 4)], KeyError, r"^\(2000, 3, 4\)$"),
(lambda s: s.loc[(2000, 3, 4)], KeyError, r"^\(2000, 3, 4\)$"),
(lambda s: s.loc[(2000, 3, 4, 5)], IndexingError, "Too many indexers"),
(lambda s: s.__getitem__(len(s)), KeyError, ""), # match should include len(s)
(lambda s: s.__getitem__(len(s)), KeyError, ""),
# match should include len(s)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is there a reason you are doing this and removed the line above?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This was changed by accident. Sorry for missing it.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should I revert those changes in this PR?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes please

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for pointing this out. Requested changes were implemented.

(lambda s: s[len(s)], KeyError, ""), # match should include len(s)
(
lambda s: s.iloc[len(s)],
Expand Down Expand Up @@ -229,6 +229,85 @@ def test_frame_getitem_nan_multiindex(nulls_fixture):
tm.assert_frame_equal(result, expected)


@pytest.mark.parametrize(
"indexer,expected",
[
(
(["b"], ["bar", np.nan]),
(
DataFrame(
[[2, 3], [5, 6]],
columns=MultiIndex.from_tuples([("b", "bar"), ("b", np.nan)]),
dtype="int64",
)
),
),
(
(["a", "b"]),
(
DataFrame(
[[1, 2, 3], [4, 5, 6]],
columns=MultiIndex.from_tuples(
[("a", "foo"), ("b", "bar"), ("b", np.nan)]
),
dtype="int64",
)
),
),
(
(["b"]),
(
DataFrame(
[[2, 3], [5, 6]],
columns=MultiIndex.from_tuples([("b", "bar"), ("b", np.nan)]),
dtype="int64",
)
),
),
(
(["b"], ["bar"]),
(
DataFrame(
[[2], [5]],
columns=MultiIndex.from_tuples([("b", "bar")]),
dtype="int64",
)
),
),
(
(["b"], [np.nan]),
(
DataFrame(
[[3], [6]],
columns=MultiIndex(
codes=[[1], [-1]], levels=[["a", "b"], ["bar", "foo"]]
),
dtype="int64",
)
),
),
(("b", np.nan), Series([3, 6], dtype="int64", name=("b", np.nan))),
],
)
def test_frame_getitem_nan_cols_multiindex(
indexer,
expected,
nulls_fixture,
):
# Slicing MultiIndex including levels with nan values, for more information
# see GH#25154
df = DataFrame(
[[1, 2, 3], [4, 5, 6]],
columns=MultiIndex.from_tuples(
[("a", "foo"), ("b", "bar"), ("b", nulls_fixture)]
),
dtype="int64",
)

result = df.loc[:, indexer]
tm.assert_equal(result, expected)


# ----------------------------------------------------------------------------
# test indexing of DataFrame with multi-level Index with duplicates
# ----------------------------------------------------------------------------
Expand Down