de.unihalle.informatik.MiToBo.clustering

Class KMeans

java.lang.Object

de.unihalle.informatik.Alida.operator.ALDOperator

de.unihalle.informatik.MiToBo.core.operator.MTBOperator

de.unihalle.informatik.MiToBo.clustering.KMeans

All Implemented Interfaces:

de.unihalle.informatik.Alida.datatypes.ALDConfigurationValidator, de.unihalle.informatik.Alida.operator.events.ALDOperatorExecutionProgressEventListener, EventListener

@ALDAOperator(genericExecutionMode=NONE,
              level=STANDARD)
public class KMeans
extends MTBOperator

Clustering of (feature) vectors with k-means based on Weka library.

Author:

Birgit Moeller, Elisabeth Piltz

Nested Class Summary

Nested classes/interfaces inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

de.unihalle.informatik.Alida.operator.ALDOperator.HidingMode, de.unihalle.informatik.Alida.operator.ALDOperator.HistoryConstructionMode

Field Summary

Fields

Modifier and Type	Field and Description
private MTBTableModel	clusterLabels List of assigned cluster indices, starting with 1.
private int	clusterNum Number of clusters to be used.
private MTBTableModel	data Data to be clustered.
private int[]	excludeList Exclude list with indices of attributes to ignore.

Fields inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

completeDAG, name, operatorExecutionEventlistenerList, portHashAccess, verbose, versionProvider

Constructor Summary

Constructors

Constructor and Description
KMeans() Default constructor.

Method Summary

Modifier and Type	Method and Description
private void	doClustering(weka.core.Instances dataSet) Does the actual clustering.
MTBTableModel	getDataLabels() Get assigned labels.
protected void	operate() This method does the actual work.
private weka.core.Instances	prepareWekaData() Converts the given data set into Weka instances.
void	setClusterNum(int num) Specify number of clusters.
void	setExcludeList(int[] ids) Specify attributes to be excluded.
void	setInputData(MTBTableModel inputData) Specify input data.

Methods inherited from class de.unihalle.informatik.MiToBo.core.operator.MTBOperator

readResolve

Methods inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

addOperatorExecutionProgressEventListener, addParameter, addParameter, addParameterUnconditioned, fieldContained, fireOperatorExecutionProgressEvent, getALDPortHashAccessKey, getConstructionMode, getDocumentation, getHidingMode, getInactiveParameterNames, getInInoutNames, getInInoutNames, getInNames, getInOutNames, getMissingRequiredInputs, getName, getNumParameters, getOutInoutNames, getOutNames, getParameter, getParameterDescriptor, getParameterDescriptorUnconditioned, getParameterNames, getParameterUnconditioned, getSupplementalNames, getVerbose, getVersion, handleOperatorExecutionProgressEvent, hasInOutParameters, hasParameter, isAnnotatedParameter, isConfigured, print, print, print, printInterface, printInterface, readHistory, reinitializeParameterDescriptors, removeOperatorExecutionProgressEventListener, removeParameter, runOp, runOp, runOp, setConstructionMode, setConstructionMode, setConstructionMode, setHidingMode, setName, setParameter, setParameterUnconditioned, setVerbose, toStringVerbose, unconfiguredItems, validate, validateCustom, validateGeneric, writeHistory, writeHistory, writeHistory

Methods inherited from class java.lang.Object

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

Field Detail

data

@Parameter(label="Data set",
           required=true,
           dataIOOrder=0,
           direction=IN,
           mode=STANDARD,
           description="Data set to be clustered.")
private MTBTableModel data

Data to be clustered.

Each line of the table represents one vector, headers encode attributes.

clusterNum

@Parameter(label="Number of clusters",
           required=true,
           dataIOOrder=1,
           direction=IN,
           mode=STANDARD,
           description="Number of clusters.")
private int clusterNum

Number of clusters to be used.

excludeList

@Parameter(label="Exclude list",
           required=true,
           dataIOOrder=2,
           direction=IN,
           mode=ADVANCED,
           description="Indices to exclude.")
private int[] excludeList

Exclude list with indices of attributes to ignore.

Note that the attribute indices start with 1.

clusterLabels

@Parameter(label="Cluster labels",
           dataIOOrder=0,
           direction=OUT,
           description="Labels.")
private transient MTBTableModel clusterLabels

List of assigned cluster indices, starting with 1.

Constructor Detail

KMeans

public KMeans()
       throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Default constructor.

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Method Detail

operate

protected void operate()
                throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException

This method does the actual work.

Specified by:

operate in class de.unihalle.informatik.Alida.operator.ALDOperator

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

prepareWekaData

private weka.core.Instances prepareWekaData()

Converts the given data set into Weka instances.

Returns:

Weka data set.

doClustering

private void doClustering(weka.core.Instances dataSet)
                   throws Exception

Does the actual clustering.

Parameters:

dataSet - Data set to be clustered.

Throws:

Exception

setInputData

public void setInputData(MTBTableModel inputData)

Specify input data.

Parameters:

inputData - Data to be clustered.

setClusterNum

public void setClusterNum(int num)

Specify number of clusters.

Parameters:

num - Number of clusters to be applied.

setExcludeList

public void setExcludeList(int[] ids)

Specify attributes to be excluded.

Parameters:

ids - List of IDs to be ignored.

getDataLabels

public MTBTableModel getDataLabels()

Get assigned labels.

Returns:

Table with cluster labels.