def test_label_binarizer_errors():
# Check that invalid arguments yield ValueError
one_class = np.array([0, 0, 0, 0])
lb = LabelBinarizer().fit(one_class)
multi_label = [(2, 3), (0, ), (0, 2)]
with pytest.raises(ValueError):
lb.transform(multi_label)
lb = LabelBinarizer()
with pytest.raises(ValueError):
lb.transform([])
with pytest.raises(ValueError):
lb.inverse_transform([])
with pytest.raises(ValueError):
LabelBinarizer(neg_label=2, pos_label=1)
with pytest.raises(ValueError):
LabelBinarizer(neg_label=2, pos_label=2)
with pytest.raises(ValueError):
LabelBinarizer(neg_label=1, pos_label=2, sparse_output=True)
# Fail on y_type
with pytest.raises(ValueError):
_inverse_binarize_thresholding(y=csr_matrix([[1, 2], [2, 1]]),
output_type="foo",
classes=[1, 2],
threshold=0)
# Sequence of seq type should raise ValueError
y_seq_of_seqs = [[], [1, 2], [3], [0, 1, 3], [2]]
with pytest.raises(ValueError):
LabelBinarizer().fit_transform(y_seq_of_seqs)
# Fail on the number of classes
with pytest.raises(ValueError):
_inverse_binarize_thresholding(y=csr_matrix([[1, 2], [2, 1]]),
output_type="foo",
classes=[1, 2, 3],
threshold=0)
# Fail on the dimension of 'binary'
with pytest.raises(ValueError):
_inverse_binarize_thresholding(y=np.array([[1, 2, 3], [2, 1, 3]]),
output_type="binary",
classes=[1, 2, 3],
threshold=0)
# Fail on multioutput data
with pytest.raises(ValueError):
LabelBinarizer().fit(np.array([[1, 3], [2, 1]]))
with pytest.raises(ValueError):
label_binarize(np.array([[1, 3], [2, 1]]), [1, 2, 3])
def test_label_binarize_with_class_order():
out = label_binarize([1, 6], classes=[1, 2, 4, 6])
expected = np.array([[1, 0, 0, 0], [0, 0, 0, 1]])
assert_array_equal(out, expected)
# Modified class order
out = label_binarize([1, 6], classes=[1, 6, 4, 2])
expected = np.array([[1, 0, 0, 0], [0, 1, 0, 0]])
assert_array_equal(out, expected)
out = label_binarize([0, 1, 2, 3], classes=[3, 2, 0, 1])
expected = np.array([[0, 0, 1, 0], [0, 0, 0, 1], [0, 1, 0, 0],
[1, 0, 0, 0]])
assert_array_equal(out, expected)
def test_label_binarize_multiclass():
y = [0, 1, 2]
classes = [0, 1, 2]
pos_label = 2
neg_label = 0
expected = 2 * np.eye(3)
check_binarized_results(y, classes, pos_label, neg_label, expected)
with pytest.raises(ValueError):
label_binarize(y,
classes,
neg_label=-1,
pos_label=pos_label,
sparse_output=True)
def check_binarized_results(y, classes, pos_label, neg_label, expected):
for sparse_output in [True, False]:
if ((pos_label == 0 or neg_label != 0) and sparse_output):
with pytest.raises(ValueError):
label_binarize(y,
classes,
neg_label=neg_label,
pos_label=pos_label,
sparse_output=sparse_output)
continue
# check label_binarize
binarized = label_binarize(y,
classes,
neg_label=neg_label,
pos_label=pos_label,
sparse_output=sparse_output)
assert_array_equal(toarray(binarized), expected)
assert issparse(binarized) == sparse_output
# check inverse
y_type = type_of_target(y)
if y_type == "multiclass":
inversed = _inverse_binarize_multiclass(binarized, classes=classes)
else:
inversed = _inverse_binarize_thresholding(
binarized,
output_type=y_type,
classes=classes,
threshold=((neg_label + pos_label) / 2.))
assert_array_equal(toarray(inversed), toarray(y))
# Check label binarizer
lb = LabelBinarizer(neg_label=neg_label,
pos_label=pos_label,
sparse_output=sparse_output)
binarized = lb.fit_transform(y)
assert_array_equal(toarray(binarized), expected)
assert issparse(binarized) == sparse_output
inverse_output = lb.inverse_transform(binarized)
assert_array_equal(toarray(inverse_output), toarray(y))
assert issparse(inverse_output) == issparse(y)
def test_label_binarize_multilabel():
y_ind = np.array([[0, 1, 0], [1, 1, 1], [0, 0, 0]])
classes = [0, 1, 2]
pos_label = 2
neg_label = 0
expected = pos_label * y_ind
y_sparse = [
sparse_matrix(y_ind) for sparse_matrix in
[coo_matrix, csc_matrix, csr_matrix, dok_matrix, lil_matrix]
]
for y in [y_ind] + y_sparse:
check_binarized_results(y, classes, pos_label, neg_label, expected)
with pytest.raises(ValueError):
label_binarize(y,
classes,
neg_label=-1,
pos_label=pos_label,
sparse_output=True)
def test_invalid_input_label_binarize():
with pytest.raises(ValueError):
label_binarize([0, 2], classes=[0, 2], pos_label=0, neg_label=1)