weka.clusterers

Class FarthestFirst

java.lang.Object

weka.clusterers.AbstractClusterer

weka.clusterers.RandomizableClusterer

weka.clusterers.FarthestFirst

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Clusterer, CapabilitiesHandler, CapabilitiesIgnorer, CommandlineRunnable, OptionHandler, Randomizable, RevisionHandler, TechnicalInformationHandler

public class FarthestFirst
extends RandomizableClusterer
implements TechnicalInformationHandler

Cluster data using the FarthestFirst algorithm.

For more information see:

Hochbaum, Shmoys (1985). A best possible heuristic for the k-center problem. Mathematics of Operations Research. 10(2):180-184.

Sanjoy Dasgupta: Performance Guarantees for Hierarchical Clustering. In: 15th Annual Conference on Computational Learning Theory, 351-363, 2002.

Notes:
- works as a fast simple approximate clusterer
- modelled after SimpleKMeans, might be a useful initializer for it

BibTeX:

 @article{Hochbaum1985,
    author = {Hochbaum and Shmoys},
    journal = {Mathematics of Operations Research},
    number = {2},
    pages = {180-184},
    title = {A best possible heuristic for the k-center problem},
    volume = {10},
    year = {1985}
 }
 
 @inproceedings{Dasgupta2002,
    author = {Sanjoy Dasgupta},
    booktitle = {15th Annual Conference on Computational Learning Theory},
    pages = {351-363},
    publisher = {Springer},
    title = {Performance Guarantees for Hierarchical Clustering},
    year = {2002}
 }
 

Valid options are:

 -N <num>
  number of clusters. (default = 2).

 -S <num>
  Random number seed.
  (default 1)

See Also:

RandomizableClusterer, Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected Instances	m_ClusterCentroids holds the cluster centroids
protected Instances	m_instances training instances, not necessary to keep, could be replaced by m_ClusterCentroids where needed for header info
protected int	m_NumClusters number of clusters to generate
protected ReplaceMissingValues	m_ReplaceMissingFilter replace missing values in training instances

Fields inherited from class weka.clusterers.RandomizableClusterer

m_Seed, m_SeedDefault

Fields inherited from class weka.clusterers.AbstractClusterer

m_Debug, m_DoNotCheckCapabilities

Constructor Summary

Constructors

Constructor and Description
FarthestFirst()

Method Summary

Modifier and Type	Method and Description
void	buildClusterer(Instances data) Generates a clusterer.
int	clusterInstance(Instance instance) Classifies a given instance.
protected int	clusterProcessedInstance(Instance instance) clusters an instance that has been through the filters
protected double	difference(int index, double val1, double val2) Computes the difference between two given attribute values.
protected double	distance(Instance first, Instance second) Calculates the distance between two instances
protected int	farthestAway(double[] minDistance, boolean[] selected)
Capabilities	getCapabilities() Returns default capabilities of the clusterer.
Instances	getClusterCentroids() Get the centroids found by FarthestFirst
int	getNumClusters() gets the number of clusters to generate
java.lang.String[]	getOptions() Gets the current settings of FarthestFirst
java.lang.String	getRevision() Returns the revision string.
TechnicalInformation	getTechnicalInformation() Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.
java.lang.String	globalInfo() Returns a string describing this clusterer
protected void	initMinMax(Instances data)
java.util.Enumeration<Option>	listOptions() Returns an enumeration describing the available options.
static void	main(java.lang.String[] argv) Main method for testing this class.
protected double	norm(double x, int i) Normalizes a given value of a numeric attribute.
int	numberOfClusters() Returns the number of clusters.
java.lang.String	numClustersTipText() Returns the tip text for this property
void	setNumClusters(int n) set the number of clusters to generate
void	setOptions(java.lang.String[] options) Parses a given list of options.
java.lang.String	toString() return a string describing this clusterer
protected void	updateMinDistance(double[] minDistance, boolean[] selected, Instances data, Instance center)

Methods inherited from class weka.clusterers.RandomizableClusterer

getSeed, seedTipText, setSeed

Methods inherited from class weka.clusterers.AbstractClusterer

debugTipText, distributionForInstance, doNotCheckCapabilitiesTipText, forName, getDebug, getDoNotCheckCapabilities, makeCopies, makeCopy, postExecution, preExecution, run, runClusterer, setDebug, setDoNotCheckCapabilities

Methods inherited from class java.lang.Object

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

Field Detail

m_instances

protected Instances m_instances

training instances, not necessary to keep, could be replaced by m_ClusterCentroids where needed for header info

m_ReplaceMissingFilter

protected ReplaceMissingValues m_ReplaceMissingFilter

replace missing values in training instances

m_NumClusters

protected int m_NumClusters

number of clusters to generate

m_ClusterCentroids

protected Instances m_ClusterCentroids

holds the cluster centroids

Constructor Detail

FarthestFirst

public FarthestFirst()

Method Detail

globalInfo

public java.lang.String globalInfo()

Returns a string describing this clusterer

Returns:

a description of the evaluator suitable for displaying in the explorer/experimenter gui

getTechnicalInformation

public TechnicalInformation getTechnicalInformation()

Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.

Specified by:

getTechnicalInformation in interface TechnicalInformationHandler

Returns:

the technical information about this class

getCapabilities

public Capabilities getCapabilities()

Returns default capabilities of the clusterer.

Specified by:

getCapabilities in interface Clusterer

Specified by:

getCapabilities in interface CapabilitiesHandler

Overrides:

getCapabilities in class AbstractClusterer

Returns:

the capabilities of this clusterer

See Also:

Capabilities

buildClusterer

public void buildClusterer(Instances data)
                    throws java.lang.Exception

Generates a clusterer. Has to initialize all fields of the clusterer that are not being set via options.

Specified by:

buildClusterer in interface Clusterer

Specified by:

buildClusterer in class AbstractClusterer

Parameters:

data - set of instances serving as training data

Throws:

java.lang.Exception - if the clusterer has not been generated successfully

updateMinDistance

protected void updateMinDistance(double[] minDistance,
                                 boolean[] selected,
                                 Instances data,
                                 Instance center)

farthestAway

protected int farthestAway(double[] minDistance,
                           boolean[] selected)

initMinMax

protected void initMinMax(Instances data)

clusterProcessedInstance

protected int clusterProcessedInstance(Instance instance)

clusters an instance that has been through the filters

Parameters:

instance - the instance to assign a cluster to

Returns:

a cluster number

clusterInstance

public int clusterInstance(Instance instance)
                    throws java.lang.Exception

Classifies a given instance.

Specified by:

clusterInstance in interface Clusterer

Overrides:

clusterInstance in class AbstractClusterer

Parameters:

instance - the instance to be assigned to a cluster

Returns:

the number of the assigned cluster as an integer if the class is enumerated, otherwise the predicted value

Throws:

java.lang.Exception - if instance could not be classified successfully

distance

protected double distance(Instance first,
                          Instance second)

Calculates the distance between two instances

Parameters:

first - the first instance

second - the second instance

Returns:

the distance between the two given instances, between 0 and 1

difference

protected double difference(int index,
                            double val1,
                            double val2)

Computes the difference between two given attribute values.

norm

protected double norm(double x,
                      int i)

Normalizes a given value of a numeric attribute.

Parameters:

x - the value to be normalized

i - the attribute's index

Returns:

the normalized value

numberOfClusters

public int numberOfClusters()
                     throws java.lang.Exception

Returns the number of clusters.

Specified by:

numberOfClusters in interface Clusterer

Specified by:

numberOfClusters in class AbstractClusterer

Returns:

the number of clusters generated for a training dataset.

Throws:

java.lang.Exception - if number of clusters could not be returned successfully

getClusterCentroids

public Instances getClusterCentroids()

Get the centroids found by FarthestFirst

Returns:

the centroids found by FarthestFirst

listOptions

public java.util.Enumeration<Option> listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface OptionHandler

Overrides:

listOptions in class RandomizableClusterer

Returns:

an enumeration of all the available options.

numClustersTipText

public java.lang.String numClustersTipText()

Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

setNumClusters

public void setNumClusters(int n)
                    throws java.lang.Exception

set the number of clusters to generate

Parameters:

n - the number of clusters to generate

Throws:

java.lang.Exception - if number of clusters is negative

getNumClusters

public int getNumClusters()

gets the number of clusters to generate

Returns:

the number of clusters to generate

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a given list of options.

Valid options are:

 -N <num>
  number of clusters. (default = 2).

 -S <num>
  Random number seed.
  (default 1)

Specified by:

setOptions in interface OptionHandler

Overrides:

setOptions in class RandomizableClusterer

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported

getOptions

public java.lang.String[] getOptions()

Gets the current settings of FarthestFirst

Specified by:

getOptions in interface OptionHandler

Overrides:

getOptions in class RandomizableClusterer

Returns:

an array of strings suitable for passing to setOptions()

toString

public java.lang.String toString()

return a string describing this clusterer

Overrides:

toString in class java.lang.Object

Returns:

a description of the clusterer as a string

getRevision

public java.lang.String getRevision()

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Overrides:

getRevision in class AbstractClusterer

Returns:

the revision

main

public static void main(java.lang.String[] argv)

Main method for testing this class.

Parameters:

argv - should contain the following arguments:

-t training file [-N number of clusters]