edu.uci.ics.jung.algorithms.importance
Class HITSWithPriors

java.lang.Object
  edu.uci.ics.jung.algorithms.IterativeProcess
      edu.uci.ics.jung.algorithms.importance.AbstractRanker
          edu.uci.ics.jung.algorithms.importance.RelativeAuthorityRanker
              edu.uci.ics.jung.algorithms.importance.HITSWithPriors

public class HITSWithPriors

extends RelativeAuthorityRanker

Algorithm that extends the HITS algorithm by incorporating root nodes (priors). Whereas in HITS the importance of a node is implicitly computed relative to all nodes in the graph, now importance is computed relative to the specified root nodes.

A simple example of usage is:

 HITSWithPriors ranker = new HITSWithPriors(someGraph,0.3,rootSet);
 ranker.evaluate();
 ranker.printRankings();
 

Running time: O(|V|*I) where |V| is the number of vertices and I is the number of iterations until convergence

Author:

Scott White

See Also:

"Algorithms for Estimating Relative Importance in Graphs by Scott White and Padhraic Smyth, 2003"

Field Summary

Fields inherited from class edu.uci.ics.jung.algorithms.importance.RelativeAuthorityRanker

PRIOR_KEY

Fields inherited from class edu.uci.ics.jung.algorithms.importance.AbstractRanker

DEFAULT_EDGE_WEIGHT_KEY

Constructor Summary

HITSWithPriors(Graph graph, boolean useAuthorityForRanking, double bias, java.util.Set priors, java.lang.String edgeWeightKey)
More specialized constructor where the type of importance can be specified.

HITSWithPriors(Graph graph, double bias, java.util.Set priors)
Constructs an instance of the ranker where the type of importance that is associated with the rank score is the node's importance as an authority.

Method Summary

double	getRankScore(UserDataContainer v) Given a node, returns the corresponding rank score.
java.lang.String	getRankScoreKey() the user datum key used to store the rank scores
void	setUseAuthorityForRanking(boolean useAuthorityForRanking) If evaluate() has not already been called, the user can override the type of importance.

Methods inherited from class edu.uci.ics.jung.algorithms.importance.RelativeAuthorityRanker

setPriorRankScore

Methods inherited from class edu.uci.ics.jung.algorithms.importance.AbstractRanker

getEdgeWeightKeyName, getRankings, getRankScores, isRankingNodes, printRankings, setNormalizeRankings, setRemoveRankScoresOnFinalize, setUserDefinedEdgeWeightKey

Methods inherited from class edu.uci.ics.jung.algorithms.IterativeProcess

evaluate, getDesiredPrecision, getIterations, getMaximumIterations, getPrecision, hasConverged, relativePrecision, setDesiredPrecision, setMaximumIterations

Methods inherited from class java.lang.Object

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

Constructor Detail

HITSWithPriors

public HITSWithPriors(Graph graph,
                      double bias,
                      java.util.Set priors)

Constructs an instance of the ranker where the type of importance that is associated with the rank score is the node's importance as an authority.

Parameters:

graph - the graph whose nodes are to be ranked

bias - the weight that should be placed on the root nodes (between 0 and 1)

priors - the set of root nodes

HITSWithPriors

public HITSWithPriors(Graph graph,
                      boolean useAuthorityForRanking,
                      double bias,
                      java.util.Set priors,
                      java.lang.String edgeWeightKey)

More specialized constructor where the type of importance can be specified.

Parameters:

graph - the graph whose nodes are to be ranked

useAuthorityForRanking -

bias - the weight that should be placed on the root nodes (between 0 and 1)

priors - the set of root nodes

Method Detail

getRankScoreKey

public java.lang.String getRankScoreKey()

the user datum key used to store the rank scores

Specified by:

getRankScoreKey in class AbstractRanker

Returns:

the key

getRankScore

public double getRankScore(UserDataContainer v)

Given a node, returns the corresponding rank score. This implementation of getRankScore assumes the decoration representing the rank score is of type MutableDouble.

Overrides:

getRankScore in class AbstractRanker

Returns:

the rank score for this node

setUseAuthorityForRanking

public void setUseAuthorityForRanking(boolean useAuthorityForRanking)

If evaluate() has not already been called, the user can override the type of importance. (hub or authority) that should be associated with the rank score.

Parameters:

useAuthorityForRanking - if true, authority is used; if false, hub is used