def return_meshed_point_cloud(self, sourcepoint, points, simplify=0.1):
#from sklearn.cluster import KMeans as kmeans
from sklearn.cluster import MiniBatchKMeans as mbkmeans
from scipy.spatial import Delaunay as delaunay
nclusters = int(len(points) * simplify)
#km = kmeans(n_clusters=nclusters, init='k-means++', n_init=10, max_iter=300, tol=0.0001, precompute_distances='auto', verbose=0, random_state=None, copy_x=True, n_jobs=1, algorithm='auto').fit(points)
km = mbkmeans(n_clusters=nclusters,
init='k-means++',
n_init=10,
max_iter=300,
tol=0.001,
verbose=0,
random_state=None,
init_size=3 * nclusters).fit(points)
self.clusters = km.cluster_centers_
clusters = [list(item) for item in list(km.cluster_centers_)]
if list(sourcepoint) in clusters:
print('sourcepoint already in clusters')
else:
clusters = [list(sourcepoint)] + clusters
print('got ' + str(len(clusters)) + ' clusters')
tri_volume = delaunay(np.array(clusters),
furthest_site=False,
incremental=False,
qhull_options=None)
return (tri_volume.points, tri_volume.simplices)
def kminicluster(data, numclusters, start=None): return mbkmeans(n_clusters=numclusters).fit(*format_data(data,start))
def kminicluster(data, numclusters, start=None):
"""Clusters the data using mini batch kmeans."""
return mbkmeans(n_clusters=numclusters).fit(*format_data(data, start))
def kminicluster(data, numclusters, start=None, init='kmeans++'):
return mbkmeans(n_clusters=numclusters,
init=init).fit(*format_data(data, start))
def kminicluster(data, numclusters, start=None,init='kmeans++'): return mbkmeans(n_clusters=numclusters,init=init).fit(*format_data(data,start))
def kminicluster(data, numclusters, start=None):
"""Clusters the data using mini batch kmeans."""
return mbkmeans(n_clusters=numclusters).fit(*format_data(data,start))