gov.sandia.cognition.learning.algorithm.clustering.cluster

Class NormalizedCentroidClusterCreator

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.learning.algorithm.clustering.cluster.NormalizedCentroidClusterCreator

All Implemented Interfaces:

ClusterCreator<NormalizedCentroidCluster<Vectorizable>,Vectorizable>, IncrementalClusterCreator<NormalizedCentroidCluster<Vectorizable>,Vectorizable>, CloneableSerializable, java.io.Serializable, java.lang.Cloneable

public class NormalizedCentroidClusterCreator
extends AbstractCloneableSerializable
implements IncrementalClusterCreator<NormalizedCentroidCluster<Vectorizable>,Vectorizable>

A cluster creator for NormalizedCentroidClusters which are clusters that have a normalized centroid in addition to the usual centroid. The normalized centroid is the centroid formed from normalizing each member of the cluster to have unit length.

Author:

nsingh

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
NormalizedCentroidClusterCreator() Creates a new instance of VectorizableCentroidClusterCreator()

Method Summary

Modifier and Type	Method and Description
void	addClusterMember(NormalizedCentroidCluster<Vectorizable> cluster, Vectorizable member) Adds a member to the given cluster.
NormalizedCentroidCluster<Vectorizable>	createCluster() Creates a new, empty cluster.
NormalizedCentroidCluster<Vectorizable>	createCluster(java.util.Collection<? extends Vectorizable> members) Create a new cluster from the given members of that cluster.
boolean	removeClusterMember(NormalizedCentroidCluster<Vectorizable> cluster, Vectorizable member) Removes a member from the given cluster.

Methods inherited from class gov.sandia.cognition.util.AbstractCloneableSerializable

clone

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable

clone

Constructor Detail

NormalizedCentroidClusterCreator

public NormalizedCentroidClusterCreator()

Creates a new instance of VectorizableCentroidClusterCreator()

Method Detail

createCluster

public NormalizedCentroidCluster<Vectorizable> createCluster()

Description copied from interface: IncrementalClusterCreator

Creates a new, empty cluster.

Specified by:

createCluster in interface IncrementalClusterCreator<NormalizedCentroidCluster<Vectorizable>,Vectorizable>

Returns:

A new, empty cluster.

createCluster

public NormalizedCentroidCluster<Vectorizable> createCluster(java.util.Collection<? extends Vectorizable> members)

Description copied from interface: ClusterCreator

Create a new cluster from the given members of that cluster.

Specified by:

createCluster in interface ClusterCreator<NormalizedCentroidCluster<Vectorizable>,Vectorizable>

Parameters:

members - The members of the cluster.

Returns:

A new cluster created from the given members.

addClusterMember

public void addClusterMember(NormalizedCentroidCluster<Vectorizable> cluster,
                             Vectorizable member)

Description copied from interface: IncrementalClusterCreator

Adds a member to the given cluster.

Specified by:

addClusterMember in interface IncrementalClusterCreator<NormalizedCentroidCluster<Vectorizable>,Vectorizable>

Parameters:

cluster - The cluster to add a member to.

member - The member to add to the cluster.

removeClusterMember

public boolean removeClusterMember(NormalizedCentroidCluster<Vectorizable> cluster,
                                   Vectorizable member)

Description copied from interface: IncrementalClusterCreator

Removes a member from the given cluster.

Specified by:

removeClusterMember in interface IncrementalClusterCreator<NormalizedCentroidCluster<Vectorizable>,Vectorizable>

Parameters:

cluster - The cluster to remove the member from.

member - The member to remove.

Returns:

True if the member was successfully removed. False if there was an error, such as the member not actually being in the cluster to start with.