def perform_clustering(seed, m_data, labels, n_clusters):
# Singleview kmeans clustering
# Cluster each view separately
s_kmeans = KMeans(n_clusters=n_clusters, random_state=seed, n_init=100)
s_clusters_v1 = s_kmeans.fit_predict(m_data[0])
s_clusters_v2 = s_kmeans.fit_predict(m_data[1])
# Concatenate the multiple views into a single view
s_data = np.hstack(m_data)
s_clusters = s_kmeans.fit_predict(s_data)
# Compute nmi between true class labels and singleview cluster labels
s_nmi_v1 = nmi_score(labels, s_clusters_v1)
s_nmi_v2 = nmi_score(labels, s_clusters_v2)
s_nmi = nmi_score(labels, s_clusters)
print('Singleview View 1 NMI Score: {0:.3f}\n'.format(s_nmi_v1))
print('Singleview View 2 NMI Score: {0:.3f}\n'.format(s_nmi_v2))
print('Singleview Concatenated NMI Score: {0:.3f}\n'.format(s_nmi))
# Multiview kmeans clustering
# Use the MultiviewKMeans instance to cluster the data
m_kmeans = MultiviewKMeans(n_clusters=n_clusters,
n_init=100,
random_state=seed)
m_clusters = m_kmeans.fit_predict(m_data)
# Compute nmi between true class labels and multiview cluster labels
m_nmi = nmi_score(labels, m_clusters)
print('Multiview NMI Score: {0:.3f}\n'.format(m_nmi))
return m_clusters
def test_fit_predict_n_jobs_all(data_random):
n_clusters = data_random['n_clusters']
kmeans = MultiviewKMeans(n_clusters=n_clusters, n_jobs=-1)
cluster_pred = kmeans.fit_predict(data_random['test_data'])
assert (data_random['n_test'] == cluster_pred.shape[0])
for cl in cluster_pred:
assert (cl >= 0 and cl < data_random['n_clusters'])
def test_fit_predict_n_clusters():
n_clusters = 3
v1_data = np.array([[0, 0], [1, 0], [0, 1]])
v2_data = np.array([[0, 0], [1, 0], [0, 1]])
data = [v1_data, v2_data]
kmeans = MultiviewKMeans(n_clusters=n_clusters)
cluster_pred = kmeans.fit_predict(data)
cluster_pred = list(set(cluster_pred))
assert (len(cluster_pred) == n_clusters)
def test_fit_predict_init_random(data_random):
n_clusters = data_random['n_clusters']
init = 'random'
kmeans = MultiviewKMeans(n_clusters=n_clusters, init='random')
cluster_pred = kmeans.fit_predict(data_random['test_data'])
assert (data_random['n_test'] == cluster_pred.shape[0])
for cl in cluster_pred:
assert (cl >= 0 and cl < data_random['n_clusters'])
def test_fit_predict_max_iter(data_random):
n_clusters = data_random['n_clusters']
max_iter = 5
kmeans = MultiviewKMeans(n_clusters=n_clusters, max_iter=max_iter)
cluster_pred = kmeans.fit_predict(data_random['test_data'])
assert (data_random['n_test'] == cluster_pred.shape[0])
for cl in cluster_pred:
assert (cl >= 0 and cl < data_random['n_clusters'])
def test_fit_predict_patience(data_random):
n_clusters = data_random['n_clusters']
patience = 10
kmeans = MultiviewKMeans(n_clusters=n_clusters, patience=patience)
cluster_pred = kmeans.fit_predict(data_random['test_data'])
assert (data_random['n_test'] == cluster_pred.shape[0])
for cl in cluster_pred:
assert (cl >= 0 and cl < data_random['n_clusters'])
def test_fit_predict_init_predefined():
n_clusters = 2
v1_centroid = np.array([[0, 0], [1, 1]])
v2_centroid = np.array([[0, 0], [1, 1]])
centroids = [v1_centroid, v2_centroid]
v1_data = np.array([[0, 0], [0.3, 0.2], [0.5, 0.5], [0.7, 0.7], [1, 1]])
v2_data = np.array([[0, 0], [0.2, 0.4], [0.5, 0.5], [0.4, 0.7], [1, 1]])
data = [v1_data, v2_data]
kmeans = MultiviewKMeans(n_clusters=n_clusters, init=centroids)
cluster_pred = kmeans.fit_predict(data)
s_data = np.hstack(Xs)
s_clusters = s_kmeans.fit_predict(s_data)
# Compute nmi between true class labels and singleview cluster labels
s_nmi_v1 = nmi_score(labels, s_clusters_v1)
s_nmi_v2 = nmi_score(labels, s_clusters_v2)
s_nmi = nmi_score(labels, s_clusters)
print('Singleview View 1 NMI Score: {0:.3f}\n'.format(s_nmi_v1))
print('Singleview View 2 NMI Score: {0:.3f}\n'.format(s_nmi_v2))
print('Singleview Concatenated NMI Score: {0:.3f}\n'.format(s_nmi))
# Multiview kmeans clustering
# Use the MultiviewKMeans instance to cluster the data
m_kmeans = MultiviewKMeans(n_clusters=n_class, random_state=RANDOM_SEED)
m_clusters = m_kmeans.fit_predict(Xs)
# Compute nmi between true class labels and multiview cluster labels
m_nmi = nmi_score(labels, m_clusters)
print('Multiview NMI Score: {0:.3f}\n'.format(m_nmi))
###############################################################################
# Comparing predicted cluster labels vs the truth
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# We will display the clustering results of the Multiview kmeans clustering
# algorithm below, along with the true class labels.
# Running TSNE to display clustering results via low dimensional embedding
tsne = TSNE()
new_data_1 = tsne.fit_transform(Xs[0])