gov.sandia.cognition.graph.community

Class Permanence<NodeNameType>

java.lang.Object

gov.sandia.cognition.graph.community.Permanence<NodeNameType>

@PublicationReference(author="Tanmoy Chakraborty, Sriram Srinivasan, Niloy Ganguly, Animesh Mukherjee, and Sanjukta Bhowmick",
                      title="On the permanence of vertices in network communities",
                      year=2014,
                      type=Conference)
public class Permanence<NodeNameType>
extends java.lang.Object

Constructor Summary

Constructors

Constructor and Description
Permanence(DirectedNodeEdgeGraph<NodeNameType> graph, int maxNumPasses, double minPermanenceGain) Initialize the class with the input graph and parameters

Method Summary

Modifier and Type	Method and Description
double	permanence() Returns the permanence discovered by running solveCommunities.
NodePartitioning<NodeNameType>	solveCommunities() Performs the actual permanence-maximization computation and returns the resulting partitioning.

Methods inherited from class java.lang.Object

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

Constructor Detail

Permanence

public Permanence(DirectedNodeEdgeGraph<NodeNameType> graph,
                  int maxNumPasses,
                  double minPermanenceGain)

Initialize the class with the input graph and parameters

Parameters:

graph - The graph to be partitioned

maxNumPasses - The maximum number of passes to perform

minPermanenceGain - The minimum permanence gain to be considered for each iteration

Method Detail

solveCommunities

public NodePartitioning<NodeNameType> solveCommunities()

Performs the actual permanence-maximization computation and returns the resulting partitioning.

Returns:

The resulting partitioning

permanence

public double permanence()

Returns the permanence discovered by running solveCommunities. If called before solveCommunities, this throws an exception.

Returns:

the permanence discovered by running solveCommunities