def predict(self, x):
"""
applying multiple estimators for prediction
Args:
x (numpy.ndarray): NxD array
Returns:
numpy.ndarray: predicted labels, Nx1 array
"""
predictions = []
confidences = []
for i in self.estimators:
estimators_from_i = self.estimators[i]
for j in estimators_from_i:
estimator = estimators_from_i[j]
confidence = np.ravel(estimator.decision_function(x))
indices = (confidence > 0).astype(np.int)
prediction = self.classes_[indices]
predictions.append(prediction.reshape(-1, 1))
confidences.append(confidence.reshape(-1, 1))
predictions = np.hstack(predictions)
confidences = np.hstack(confidences)
y = _ovr_decision_function(predictions,
confidences, len(self.classes_))
return self.classes_[y.argmax(axis=1)]
def test_ovr_decision_function():
# test properties for ovr decision function
predictions = np.array([[0, 1, 1],
[0, 1, 0],
[0, 1, 1],
[0, 1, 1]])
confidences = np.array([[-1e16, 0, -1e16],
[1., 2., -3.],
[-5., 2., 5.],
[-0.5, 0.2, 0.5]])
n_classes = 3
dec_values = _ovr_decision_function(predictions, confidences, n_classes)
# check that the decision values are within 0.5 range of the votes
votes = np.array([[1, 0, 2],
[1, 1, 1],
[1, 0, 2],
[1, 0, 2]])
assert_allclose(votes, dec_values, atol=0.5)
# check that the prediction are what we expect
# highest vote or highest confidence if there is a tie.
# for the second sample we have a tie (should be won by 1)
expected_prediction = np.array([2, 1, 2, 2])
assert_array_equal(np.argmax(dec_values, axis=1), expected_prediction)
# third and fourth sample have the same vote but third sample
# has higher confidence, this should reflect on the decision values
assert (dec_values[2, 2] > dec_values[3, 2])
# assert subset invariance.
dec_values_one = [_ovr_decision_function(np.array([predictions[i]]),
np.array([confidences[i]]),
n_classes)[0] for i in range(4)]
assert_allclose(dec_values, dec_values_one, atol=1e-6)
def test_ovr_decision_function():
# test properties for ovr decision function
predictions = np.array([[0, 1, 1],
[0, 1, 0],
[0, 1, 1],
[0, 1, 1]])
confidences = np.array([[-1e16, 0, -1e16],
[1., 2., -3.],
[-5., 2., 5.],
[-0.5, 0.2, 0.5]])
n_classes = 3
dec_values = _ovr_decision_function(predictions, confidences, n_classes)
# check that the decision values are within 0.5 range of the votes
votes = np.array([[1, 0, 2],
[1, 1, 1],
[1, 0, 2],
[1, 0, 2]])
assert_allclose(votes, dec_values, atol=0.5)
# check that the prediction are what we expect
# highest vote or highest confidence if there is a tie.
# for the second sample we have a tie (should be won by 1)
expected_prediction = np.array([2, 1, 2, 2])
assert_array_equal(np.argmax(dec_values, axis=1), expected_prediction)
# third and fourth sample have the same vote but third sample
# has higher confidence, this should reflect on the decision values
assert (dec_values[2, 2] > dec_values[3, 2])
# assert subset invariance.
dec_values_one = [_ovr_decision_function(np.array([predictions[i]]),
np.array([confidences[i]]),
n_classes)[0] for i in range(4)]
assert_allclose(dec_values, dec_values_one, atol=1e-6)