# estimate bandwidth for mean shift
bandwidth = cluster.estimate_bandwidth(X, quantile=0.3)
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(X, n_neighbors=10)
# make connectivity symmetric
connectivity = 0.5 * (connectivity + connectivity.T)
# Compute distances
# distances = np.exp(-euclidean_distances(X))
distances = euclidean_distances(X)
# create clustering estimators
ms = cluster.MeanShift(bandwidth=bandwidth, bin_seeding=True)
two_means = cluster.MiniBatchKMeans(n_clusters=25)
ward = cluster.Ward(n_clusters=25)
# ward = cluster.AgglomerativeClustering(n_clusters=2,linkage='ward', connectivity=connectivity)
spectral = cluster.SpectralClustering(n_clusters=25,
eigen_solver='arpack',
affinity="nearest_neighbors")
dbscan = cluster.DBSCAN(eps=.2)
affinity_propagation = cluster.AffinityPropagation(damping=.9,
preference=-200)
# average_linkage = cluster.AgglomerativeClustering(linkage="average", affinity="cityblock", n_clusters=2, connectivity=connectivity)
for name, algorithm in [
('MiniBatchKMeans', two_means),
('AffinityPropagation', affinity_propagation),
('MeanShift', ms),
('SpectralClustering', spectral),
# estimate bandwidth for mean shift
bandwidth = cluster.estimate_bandwidth(X, quantile=0.3)
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(X, n_neighbors=10)
# make connectivity symmetric
connectivity = 0.5 * (connectivity + connectivity.T)
# Compute distances
#distances = np.exp(-euclidean_distances(X))
distances = euclidean_distances(X)
# create clustering estimators
ms = cluster.MeanShift(bandwidth=bandwidth, bin_seeding=True)
two_means = cluster.MiniBatchKMeans(n_clusters=2)
ward_five = cluster.Ward(n_clusters=2, connectivity=connectivity)
spectral = cluster.SpectralClustering(n_clusters=2,
eigen_solver='arpack',
affinity="nearest_neighbors")
dbscan = cluster.DBSCAN(eps=.2)
affinity_propagation = cluster.AffinityPropagation(damping=.9,
preference=-200)
for algorithm in [
two_means, affinity_propagation, ms, spectral, ward_five, dbscan
]:
# predict cluster memberships
t0 = time.time()
algorithm.fit(X)
t1 = time.time()
if hasattr(algorithm, 'labels_'):
def ward(matrix):
ward = skcluster.Ward(n_clusters=50, compute_full_tree=False)
ward.fit(matrix)
return ward.labels_