Package adams.gui.tools.wekainvestigator.tab.clustertab.evaluation

Class ClassesToClusters

java.lang.Object

adams.core.logging.LoggingObject

adams.gui.tools.wekainvestigator.evaluation.AbstractEvaluation<ClusterTab,ResultItem>

adams.gui.tools.wekainvestigator.tab.clustertab.evaluation.AbstractClustererEvaluation

adams.gui.tools.wekainvestigator.tab.clustertab.evaluation.ClassesToClusters

All Implemented Interfaces:

GlobalInfoSupporter, LoggingSupporter, SizeOfHandler, StatusMessageHandler, Serializable

public class ClassesToClusters
extends AbstractClustererEvaluation

Tries to map the clusters of the built clusterer to the class labels in the dataset.

Author:

FracPete (fracpete at waikato dot ac dot nz)

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected BaseComboBox<String>	m_ComboBoxClass	the class attribute.
protected BaseComboBox<String>	m_ComboBoxTest	the test set.
protected BaseComboBox<String>	m_ComboBoxTrain	the train set.
protected DefaultComboBoxModel<String>	m_ModelClass	the class attribute model.
protected DefaultComboBoxModel<String>	m_ModelDatasets	the datasets model.
protected ParameterPanel	m_PanelParameters	the panel with the parameters.

Fields inherited from class adams.gui.tools.wekainvestigator.evaluation.AbstractEvaluation

m_Owner, m_PanelOptions

Fields inherited from class adams.core.logging.LoggingObject

m_Logger, m_LoggingIsEnabled, m_LoggingLevel

Constructor Summary

Constructors

Constructor	Description
ClassesToClusters()

Method Summary

Modifier and Type	Method	Description
void	activate(int index)	Activates the specified dataset.
String	canEvaluate(weka.clusterers.Clusterer clusterer)	Tests whether the clusterer can be evaluated.
protected int	classIndex(weka.core.Instances data)	Returns the index of the selected class attribute in the provided dataset.
void	deserialize(Map<String,Object> data, MessageCollection errors)	Restores the objects.
protected void	doEvaluate(weka.clusterers.Clusterer clusterer, ResultItem item)	Evaluates the clusterer and updates the result item.
String	getName()	Returns the name of the evaluation (displayed in combobox).
String	globalInfo()	Returns a string describing the object.
ResultItem	init(weka.clusterers.Clusterer clusterer)	Initializes the result item.
protected void	initGUI()	Initializes the widgets.
protected int	numClasses()	Returns the number of classes in the test set.
protected weka.core.Instances	removeClassAttribute(weka.core.Instances data)	Removes the class attribute from the dataset (if present).
Map<String,Object>	serialize(Set<AbstractInvestigatorTab.SerializationOption> options)	Returns the objects for serialization.
protected String	toMatrixString(int numClusters, int[][] counts, int[] clusterTotals, weka.core.Instances inst)	Returns a "confusion" style matrix of classes to clusters assignments
void	update()	Updates the settings panel.

Methods inherited from class adams.gui.tools.wekainvestigator.tab.clustertab.evaluation.AbstractClustererEvaluation

evaluate, getEvaluations

Methods inherited from class adams.gui.tools.wekainvestigator.evaluation.AbstractEvaluation

addObjectSize, addToHistory, getOwner, getPanel, getProperties, getTestingUpdateInterval, initialize, isValidDataIndex, listOrArray, setOwner, showStatus, toString

Methods inherited from class adams.core.logging.LoggingObject

configureLogger, getLogger, getLoggingLevel, initializeLogging, isLoggingEnabled, sizeOf

Methods inherited from class java.lang.Object

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

Field Detail

m_PanelParameters

protected ParameterPanel m_PanelParameters

the panel with the parameters.

m_ComboBoxTrain

protected BaseComboBox<String> m_ComboBoxTrain

the train set.

m_ComboBoxTest

protected BaseComboBox<String> m_ComboBoxTest

the test set.

m_ModelDatasets

protected DefaultComboBoxModel<String> m_ModelDatasets

the datasets model.

m_ComboBoxClass

protected BaseComboBox<String> m_ComboBoxClass

the class attribute.

m_ModelClass

protected DefaultComboBoxModel<String> m_ModelClass

the class attribute model.

Constructor Detail

ClassesToClusters

public ClassesToClusters()

Method Detail

globalInfo

public String globalInfo()

Returns a string describing the object.

Returns:

a description suitable for displaying in the gui

initGUI

protected void initGUI()

Initializes the widgets.

Overrides:

initGUI in class AbstractEvaluation<ClusterTab,ResultItem>

getName

public String getName()

Returns the name of the evaluation (displayed in combobox).

Specified by:

getName in class AbstractEvaluation<ClusterTab,ResultItem>

Returns:

the name

canEvaluate

public String canEvaluate(weka.clusterers.Clusterer clusterer)

Tests whether the clusterer can be evaluated.

Specified by:

canEvaluate in class AbstractClustererEvaluation

Parameters:

clusterer - the current clusterer

Returns:

null if successful, otherwise error message

init

public ResultItem init(weka.clusterers.Clusterer clusterer)
                throws Exception

Initializes the result item.

Specified by:

init in class AbstractClustererEvaluation

Parameters:

clusterer - the current clusterer

Returns:

the initialized history item

Throws:

Exception - if initialization fails

numClasses

protected int numClasses()

Returns the number of classes in the test set.

Returns:

the number of classes, -1 in case of error

classIndex

protected int classIndex(weka.core.Instances data)

Returns the index of the selected class attribute in the provided dataset.

Parameters:

data - the dataset to get the class index for

Returns:

the class index, -1 if failed to locate attribute

removeClassAttribute

protected weka.core.Instances removeClassAttribute(weka.core.Instances data)

Removes the class attribute from the dataset (if present).

Parameters:

data - the dataset to process

Returns:

the clean dataset

toMatrixString

protected String toMatrixString(int numClusters,
                                int[][] counts,
                                int[] clusterTotals,
                                weka.core.Instances inst)
                         throws Exception

Returns a "confusion" style matrix of classes to clusters assignments

Parameters:

counts - the counts of classes for each cluster

clusterTotals - total number of examples in each cluster

inst - the training instances (with class)

Returns:

the "confusion" style matrix as string

Throws:

Exception - if matrix can't be generated

doEvaluate

protected void doEvaluate(weka.clusterers.Clusterer clusterer,
                          ResultItem item)
                   throws Exception

Evaluates the clusterer and updates the result item.

Specified by:

doEvaluate in class AbstractClustererEvaluation

Parameters:

clusterer - the current clusterer

item - the item to update

Throws:

Exception - if evaluation fails

update

public void update()

Updates the settings panel.

Specified by:

update in class AbstractEvaluation<ClusterTab,ResultItem>

activate

public void activate(int index)

Activates the specified dataset.

Specified by:

activate in class AbstractEvaluation<ClusterTab,ResultItem>

Parameters:

index - the index of the dataset

serialize

public Map<String,Object> serialize(Set<AbstractInvestigatorTab.SerializationOption> options)

Returns the objects for serialization.

Overrides:

serialize in class AbstractEvaluation<ClusterTab,ResultItem>

Parameters:

options - what to serialize

Returns:

the mapping of the objects to serialize

deserialize

public void deserialize(Map<String,Object> data,
                        MessageCollection errors)

Restores the objects.

Overrides:

deserialize in class AbstractEvaluation<ClusterTab,ResultItem>

Parameters:

data - the data to restore

errors - for storing errors