def test_multilabel_hamming_loss():
# Dense label indicator matrix format
y1 = np.array([[0, 1, 1], [1, 0, 1]])
y2 = np.array([[0, 0, 1], [1, 0, 1]])
w = np.array([1, 3])
assert_equal(hamming_loss(y1, y2), 1 / 6)
assert_equal(hamming_loss(y1, y1), 0)
assert_equal(hamming_loss(y2, y2), 0)
assert_equal(hamming_loss(y2, 1 - y2), 1)
assert_equal(hamming_loss(y1, 1 - y1), 1)
assert_equal(hamming_loss(y1, np.zeros(y1.shape)), 4 / 6)
assert_equal(hamming_loss(y2, np.zeros(y1.shape)), 0.5)
assert_equal(hamming_loss(y1, y2, sample_weight=w), 1. / 12)
assert_equal(hamming_loss(y1, 1-y2, sample_weight=w), 11. / 12)
assert_equal(hamming_loss(y1, np.zeros_like(y1), sample_weight=w), 2. / 3)
# sp_hamming only works with 1-D arrays
assert_equal(hamming_loss(y1[0], y2[0]), sp_hamming(y1[0], y2[0]))
def hamming_loss(y_true, y_pred, classes=None):
"""Compute the average Hamming loss.
The Hamming loss is the fraction of labels that are incorrectly predicted.
Parameters
----------
y_true : array-like or label indicator matrix
Ground truth (correct) labels.
y_pred : array-like or label indicator matrix
Predicted labels, as returned by a classifier.
classes : array, shape = [n_labels], optional
Integer array of labels.
Returns
-------
loss : float or int,
Return the average Hamming loss between element of ``y_true`` and
``y_pred``.
See Also
--------
accuracy_score, jaccard_similarity_score, zero_one_loss
Notes
-----
In multiclass classification, the Hamming loss correspond to the Hamming
distance between ``y_true`` and ``y_pred`` which is equivalent to the
subset ``zero_one_loss`` function.
In multilabel classification, the Hamming loss is different from the
subset zero-one loss. The zero-one loss considers the entire set of labels
for a given sample incorrect if it does entirely match the true set of
labels. Hamming loss is more forgiving in that it penalizes the individual
labels.
The Hamming loss is upperbounded by the subset zero-one loss. When
normalized over samples, the Hamming loss is always between 0 and 1.
References
----------
.. [1] Grigorios Tsoumakas, Ioannis Katakis. Multi-Label Classification:
An Overview. International Journal of Data Warehousing & Mining,
3(3), 1-13, July-September 2007.
.. [2] `Wikipedia entry on the Hamming distance
<http://en.wikipedia.org/wiki/Hamming_distance>`_
Examples
--------
>>> from sklearn.metrics import hamming_loss
>>> y_pred = [1, 2, 3, 4]
>>> y_true = [2, 2, 3, 4]
>>> hamming_loss(y_true, y_pred)
0.25
In the multilabel case with binary label indicators:
>>> hamming_loss(np.array([[0, 1], [1, 1]]), np.zeros((2, 2)))
0.75
"""
y_type, y_true, y_pred = _check_clf_targets(y_true, y_pred)
if classes is None:
classes = unique_labels(y_true, y_pred)
else:
classes = np.asarray(classes)
if y_type == 'multilabel-indicator':
return np.mean(y_true != y_pred)
elif y_type == 'multilabel-sequences':
loss = np.array([
len(set(pred).symmetric_difference(true))
for pred, true in zip(y_pred, y_true)
])
return np.mean(loss) / np.size(classes)
elif y_type in ["binary", "multiclass"]:
return sp_hamming(y_true, y_pred)
else:
raise ValueError("{0} is not supported".format(y_type))
def hamming_loss(y_true, y_pred, classes=None):
"""Compute the average Hamming loss.
The Hamming loss is the fraction of labels that are incorrectly predicted.
Parameters
----------
y_true : array-like or label indicator matrix
Ground truth (correct) labels.
y_pred : array-like or label indicator matrix
Predicted labels, as returned by a classifier.
classes : array, shape = [n_labels], optional
Integer array of labels.
Returns
-------
loss : float or int,
Return the average Hamming loss between element of ``y_true`` and
``y_pred``.
See Also
--------
accuracy_score, jaccard_similarity_score, zero_one_loss
Notes
-----
In multiclass classification, the Hamming loss correspond to the Hamming
distance between ``y_true`` and ``y_pred`` which is equivalent to the
subset ``zero_one_loss`` function.
In multilabel classification, the Hamming loss is different from the
subset zero-one loss. The zero-one loss considers the entire set of labels
for a given sample incorrect if it does entirely match the true set of
labels. Hamming loss is more forgiving in that it penalizes the individual
labels.
The Hamming loss is upperbounded by the subset zero-one loss. When
normalized over samples, the Hamming loss is always between 0 and 1.
References
----------
.. [1] Grigorios Tsoumakas, Ioannis Katakis. Multi-Label Classification:
An Overview. International Journal of Data Warehousing & Mining,
3(3), 1-13, July-September 2007.
.. [2] `Wikipedia entry on the Hamming distance
<http://en.wikipedia.org/wiki/Hamming_distance>`_
Examples
--------
>>> from sklearn.metrics import hamming_loss
>>> y_pred = [1, 2, 3, 4]
>>> y_true = [2, 2, 3, 4]
>>> hamming_loss(y_true, y_pred)
0.25
In the multilabel case with binary label indicators:
>>> hamming_loss(np.array([[0, 1], [1, 1]]), np.zeros((2, 2)))
0.75
"""
y_type, y_true, y_pred = _check_clf_targets(y_true, y_pred)
if classes is None:
classes = unique_labels(y_true, y_pred)
else:
classes = np.asarray(classes)
if y_type == 'multilabel-indicator':
return np.mean(y_true != y_pred)
elif y_type == 'multilabel-sequences':
loss = np.array([len(set(pred).symmetric_difference(true))
for pred, true in zip(y_pred, y_true)])
return np.mean(loss) / np.size(classes)
elif y_type in ["binary", "multiclass"]:
return sp_hamming(y_true, y_pred)
else:
raise ValueError("{0} is not supported".format(y_type))