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

Jump to bottom

(fix): raise error on non-integer floating types in iterables #1746

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

(fix): raise error on non-integer floating types in iterables #1746

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dd853e7
(fix): raise error on non-integer floating types
ilan-gold Nov 8, 2024
98f7bea
(chore): release note
ilan-gold Nov 8, 2024
150d8aa
(fix): test for float32 and float64
ilan-gold Nov 11, 2024
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
1 change: 1 addition & 0 deletions docs/release-notes/1746.bugfix.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Error out on floating point indices that are not actually integers {user}`ilan-gold`
6 changes: 6 additions & 0 deletions src/anndata/_core/index.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,12 @@ def name_idx(i):
indexer = np.array(indexer)
if len(indexer) == 0:
indexer = indexer.astype(int)
if isinstance(indexer, np.ndarray) and np.issubdtype(
indexer.dtype, np.floating
):
indexer_int = indexer.astype(int)
if np.all((indexer - indexer_int) != 0):
raise IndexError(f"Indexer {indexer!r} has floating point values.")
if issubclass(indexer.dtype.type, np.integer | np.floating):
return indexer # Might not work for range indexes
elif issubclass(indexer.dtype.type, np.bool_):
Expand Down
16 changes: 16 additions & 0 deletions tests/test_views.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -814,6 +814,22 @@ def test_index_3d_errors(index: tuple[int | EllipsisType, ...], expected_error:
gen_adata((10, 10))[index]


@pytest.mark.parametrize(
"index",
[
pytest.param(sparse.csr_matrix(np.random.random((1, 10))), id="sparse"),
pytest.param([1.2, 3.4], id="list"),
*(
pytest.param(np.array([1.2, 2.3], dtype=dtype), id=f"ndarray-{dtype}")
for dtype in [np.float32, np.float64]
),
],
)
def test_index_float_sequence_raises_error(index):
with pytest.raises(IndexError, match=r"has floating point values"):
gen_adata((10, 10))[index]
Comment on lines +817 to +830
Copy link
Member

Choose a reason for hiding this comment

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

Suggested change
@pytest.mark.parametrize(
"index",
[
pytest.param(sparse.csr_matrix(np.random.random((1, 10))), id="sparse"),
pytest.param([1.2, 3.4], id="list"),
*(
pytest.param(np.array([1.2, 2.3], dtype=dtype), id=f"ndarray-{dtype}")
for dtype in [np.float32, np.float64]
),
],
)
def test_index_float_sequence_raises_error(index):
with pytest.raises(IndexError, match=r"has floating point values"):
gen_adata((10, 10))[index]
@pytest.mark.parametrize(
"index",
[
pytest.param(sparse.csr_matrix(np.random.random((1, 10))), id="sparse"),
pytest.param([1.2, 3.4], id="list"),
pytest.param(np.array([1.2, 2.3], dtype=dtype), id=f"ndarray-{dtype}")
],
)
@pytest.mark.parametrize("dtype", [np.float32, np.float64])
def test_index_float_sequence_raises_error(index, dtype):
index = index.astype(dtype)
with pytest.raises(IndexError, match=r"has floating point values"):
gen_adata((10, 10))[index]

Copy link
Contributor Author

@ilan-gold ilan-gold Nov 11, 2024 •
edited
Loading

Choose a reason for hiding this comment

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

@flying-sheep is the goal here to ensure dtype is checked on sparse matrices as well? I think it's enough to check the numpy arrays. Also we can't astype a list. Also dtype is not accessible outside of its parametrization/the test.



# @pytest.mark.parametrize("dim", ["obs", "var"])
# @pytest.mark.parametrize(
# ("idx", "pat"),
Expand Down