Skip to content

MNT Clean-up deprecations for 1.7: byte labels #31236

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 1 commit into from
Apr 24, 2025
Merged

MNT Clean-up deprecations for 1.7: byte labels #31236

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
9 changes: 2 additions & 7 deletions sklearn/metrics/tests/test_ranking.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -873,20 +873,15 @@ def test_binary_clf_curve_implicit_pos_label(curve_func):
np.testing.assert_allclose(int_curve_part, float_curve_part)


# TODO(1.7): Update test to check for error when bytes support is removed.
@pytest.mark.filterwarnings("ignore:Support for labels represented as bytes")
@pytest.mark.parametrize("curve_func", [precision_recall_curve, roc_curve])
@pytest.mark.parametrize("labels_type", ["list", "array"])
def test_binary_clf_curve_implicit_bytes_pos_label(curve_func, labels_type):
# Check that using bytes class labels raises an informative
# error for any supported string dtype:
labels = _convert_container([b"a", b"b"], labels_type)
msg = (
"y_true takes value in {b'a', b'b'} and pos_label is not "
"specified: either make y_true take value in {0, 1} or "
"{-1, 1} or pass pos_label explicitly."
)
with pytest.raises(ValueError, match=msg):
msg = "Support for labels represented as bytes is not supported"
with pytest.raises(TypeError, match=msg):
curve_func(labels, [0.0, 1.0])


Expand Down
13 changes: 4 additions & 9 deletions sklearn/utils/multiclass.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -358,17 +358,12 @@ def _raise_or_return():
y = check_array(y, dtype=object, **check_y_kwargs)

try:
# TODO(1.7): Change to ValueError when byte labels is deprecated.
# labels in bytes format
first_row_or_val = y[[0], :] if issparse(y) else y[0]
# labels in bytes format
if isinstance(first_row_or_val, bytes):
warnings.warn(
(
"Support for labels represented as bytes is deprecated in v1.5 and"
" will error in v1.7. Convert the labels to a string or integer"
" format."
),
FutureWarning,
raise TypeError(
"Support for labels represented as bytes is not supported. Convert "
"the labels to a string or integer format."
)
# The old sequence of sequences format
if (
Expand Down
10 changes: 3 additions & 7 deletions sklearn/utils/tests/test_multiclass.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -602,16 +602,12 @@ def test_ovr_decision_function():
assert_allclose(dec_values, dec_values_one, atol=1e-6)


# TODO(1.7): Change to ValueError when byte labels is deprecated.
@pytest.mark.parametrize("input_type", ["list", "array"])
def test_labels_in_bytes_format(input_type):
def test_labels_in_bytes_format_error(input_type):
# check that we raise an error with bytes encoded labels
# non-regression test for:
# https://github.com/scikit-learn/scikit-learn/issues/16980
target = _convert_container([b"a", b"b"], input_type)
err_msg = (
"Support for labels represented as bytes is deprecated in v1.5 and will"
" error in v1.7. Convert the labels to a string or integer format."
)
with pytest.warns(FutureWarning, match=err_msg):
err_msg = "Support for labels represented as bytes is not supported"
with pytest.raises(TypeError, match=err_msg):
type_of_target(target)