def majority_vote_classifier(classifiers, same_feature_space=True):
assert len(classifiers) % 2 != 0
if same_feature_space:
classifier = lambda x: mode([c(x) for c in classifiers])[0][0]
else:
classifier = lambda x: mode([classifiers[i](x[i]) \
for i in xrange(len(classifiers))])[0][0]
return classifier
def majority_vote_classifier(classifiers, same_feature_space=True):
assert len(classifiers) % 2 != 0
if same_feature_space:
classifier = lambda x: mode([c(x) for c in classifiers])[0][0]
else:
classifier = lambda x: mode([classifiers[i](x[i]) \
for i in xrange(len(classifiers))])[0][0]
return classifier
def classifier(x):
x = np.asarray(x).ravel()
assert len(x) == d, "Incorrect dimensionality. The input data must " "be %d-dimensional." % d
dists = cdist([x], data, metric=dist_metric, **dist_kwargs).squeeze()
sorted_dists_idx = dists.argsort()[0:k]
weights = 1 / (dists[sorted_dists_idx] ** 2) if weighted else None
return mode(labels[sorted_dists_idx], weights)[0][0]
def classifier(x):
x = np.asarray(x).ravel()
assert len(x) == d, "Incorrect dimensionality. The input data must " \
"be %d-dimensional." % d
dists = cdist([x], data, metric=dist_metric, **dist_kwargs).squeeze()
sorted_dists_idx = dists.argsort()[0:k]
weights = 1 / (dists[sorted_dists_idx]**2) if weighted else None
return mode(labels[sorted_dists_idx], weights)[0][0]