class RegCluster(BaseEstimator, ClusterMixin, TransformerMixin):
""" Class to perform regular clustering of a given data set
RegCluster can be passed a radius or an approximate number of clusters. If a number of clusters is passed, KCenter
clustering is used to estimate the necessary radius. RegCluster randomly chooses a point and assigns all points
within the radius of this point to the same cluster. Then it proceeds with the nearest point, which is not yet
assigned to a cluster and puts all unassigned points within the radius of this point in the next cluster and so on.
Parameters
----------
radius: float
radius of clusters
n_clusters: int
desired number of clusters
Examples
--------
>>> cluster = RegCluster(radius=5.1)
>>> cluster.fit(data)
Attributes
----------
cluster_centers: list
list with the points, which are the centers of the clusters
centerFrames : list
list of indices of center points in data array
labels_ : list
list with number of cluster of each frame
clusterSize_ : list
list with number of frames in each cluster
"""
def __init__(self, radius=None, n_clusters=None):
if radius is None and n_clusters is None:
raise RuntimeError("radius or n_clusters needs to be set")
self.radius = radius
self.n_clusters = n_clusters
self.labels_ = []
def fit(self, data):
""" performs clustering of data
Parameters
----------
data: np.ndarray
array of data points to cluster
merge: int
minimal number of frames within each cluster. Smaller clusters are merged into next big one
"""
# if n_clusters is given and no r, estimate n_clusters
if self.radius is None:
from htmd.clustering.kcenters import KCenter
estClust = KCenter(n_clusters=self.n_clusters)
estClust.fit(data)
self.radius = estClust.distance.max()
logger.info("Estimated radius = {}".format(self.radius))
from pyemma.coordinates.clustering.regspace import RegularSpaceClustering
self._reg = RegularSpaceClustering(dmin=self.radius)
self.labels_ = self._reg.fit_transform(data).flatten()
@property
def cluster_centers_(self):
return self._reg.clustercenters
@property
def clusterSize(self):
return np.bincount(self.labels_)
class RegCluster(BaseEstimator, ClusterMixin, TransformerMixin):
""" Class to perform regular clustering of a given data set
RegCluster can be passed a radius or an approximate number of clusters. If a number of clusters is passed, KCenter
clustering is used to estimate the necessary radius. RegCluster randomly chooses a point and assigns all points
within the radius of this point to the same cluster. Then it proceeds with the nearest point, which is not yet
assigned to a cluster and puts all unassigned points within the radius of this point in the next cluster and so on.
Parameters
----------
radius: float
radius of clusters
n_clusters: int
desired number of clusters
Examples
--------
>>> cluster = RegCluster(radius=5.1)
>>> cluster.fit(data)
Attributes
----------
cluster_centers: list
list with the points, which are the centers of the clusters
centerFrames : list
list of indices of center points in data array
labels_ : list
list with number of cluster of each frame
clusterSize_ : list
list with number of frames in each cluster
"""
def __init__(self, radius=None, n_clusters=None):
if radius is None and n_clusters is None:
raise RuntimeError("radius or n_clusters needs to be set")
self.radius = radius
self.n_clusters = n_clusters
self.labels_ = []
def fit(self, data):
""" performs clustering of data
Parameters
----------
data: np.ndarray
array of data points to cluster
merge: int
minimal number of frames within each cluster. Smaller clusters are merged into next big one
"""
# if n_clusters is given and no r, estimate n_clusters
if self.radius is None:
from htmd.clustering.kcenters import KCenter
estClust = KCenter(n_clusters=self.n_clusters)
estClust.fit(data)
self.radius = estClust.distance.max()
logger.info("Estimated radius = {}".format(self.radius))
from pyemma.coordinates.clustering.regspace import RegularSpaceClustering
self._reg = RegularSpaceClustering(dmin=self.radius)
self.labels_ = self._reg.fit_transform(data).flatten()
@property
def cluster_centers_(self):
return self._reg.clustercenters
@property
def clusterSize(self):
return np.bincount(self.labels_)
