10000 [MRG+1] LabelBinarizer single label case now works for sparse and dense case by devashishd12 · Pull Request #6221 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

[MRG+1] LabelBinarizer single label case now works for sparse and dense case #6221

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
Mar 21, 2016
Merged

[MRG+1] LabelBinarizer single label case now works for sparse and dense case #6221

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
11 changes: 7 additions & 4 deletions sklearn/preprocessing/label.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -472,10 +472,13 @@ def label_binarize(y, classes, neg_label=0, pos_label=1, sparse_output=False):
classes = np.asarray(classes)

if y_type == "binary":
if len(classes) == 1:
Y = np.zeros((len(y), 1), dtype=np.int)
Y += neg_label
return Y
if n_classes == 1:
if sparse_output:
return sp.csr_matrix((n_samples, 1), dtype=int)
else:
Y = np.zeros((len(y), 1), dtype=np.int)
Y += neg_label
return Y
elif len(classes) >= 3:
y_type = "multiclass"

Expand Down
14 changes: 12 additions & 2 deletions sklearn/preprocessing/tests/test_label.py
View file
Open in desktop
437C
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@

from sklearn.utils.testing import assert_array_equal
from sklearn.utils.testing import assert_equal
from sklearn.utils.testing import assert_true
from sklearn.utils.testing import assert_raises
from sklearn.utils.testing import assert_raise_message
from sklearn.utils.testing import ignore_warnings
Expand All @@ -35,16 +36,25 @@ def toarray(a):


def test_label_binarizer():
lb = LabelBinarizer()

# one-class case defaults to negative label
# For dense case:
inp = ["pos", "pos", "pos", "pos"]
lb = LabelBinarizer(sparse_output=False)
expected = np.array([[0, 0, 0, 0]]).T
got = lb.fit_transform(inp)
assert_array_equal(lb.classes_, ["pos"])
assert_array_equal(expected, got)
assert_array_equal(lb.inverse_transform(got), inp)

# For sparse case:
lb = LabelBinarizer(sparse_output=True)
got = lb.fit_transform(inp)
assert_true(issparse(got))
assert_array_equal(lb.classes_, ["pos"])
assert_array_equal(expected, got.toarray())
assert_array_equal(lb.inverse_transform(got.toarray()), inp)

lb = LabelBinarizer(sparse_output=False)
# two-class case
inp = ["neg", "pos", "pos", "neg"]
expected = np.array([[0, 1, 1, 0]]).T
Expand Down
0