Java Doc for IBk.java in » Science » weka » weka » classifiers » lazy » Java Source Code / Java DocumentationJava Source Code and Java Documentation

Java Source Code / Java Documentation

1.	6.0 JDK Core
2.	6.0 JDK Modules
3.	6.0 JDK Modules com.sun
4.	6.0 JDK Modules com.sun.java
5.	6.0 JDK Modules sun
6.	6.0 JDK Platform
7.	Ajax
8.	Apache Harmony Java SE
9.	Aspect oriented
10.	Authentication Authorization
11.	Blogger System
12.	Build
13.	Byte Code
14.	Cache
15.	Chart
16.	Chat
17.	Code Analyzer
18.	Collaboration
19.	Content Management System
20.	Database Client
21.	Database DBMS
22.	Database JDBC Connection Pool
23.	Database ORM
24.	Development
25.	EJB Server geronimo
26.	EJB Server GlassFish
27.	EJB Server JBoss 4.2.1
28.	EJB Server resin 3.1.5
29.	ERP CRM Financial
30.	ESB
31.	Forum
32.	GIS
33.	Graphic Library
34.	Groupware
35.	HTML Parser
36.	IDE
37.	IDE Eclipse
38.	IDE Netbeans
39.	Installer
40.	Internationalization Localization
41.	Inversion of Control
42.	Issue Tracking
43.	J2EE
44.	JBoss
45.	JMS
46.	JMX
47.	Library
48.	Mail Clients
49.	Net
50.	Parser
51.	PDF
52.	Portal
53.	Profiler
54.	Project Management
55.	Report
56.	RSS RDF
57.	Rule Engine
58.	Science
59.	Scripting
60.	Search Engine
61.	Security
62.	Sevlet Container
63.	Source Control
64.	Swing Library
65.	Template Engine
66.	Test Coverage
67.	Testing
68.	UML
69.	Web Crawler
70.	Web Framework
71.	Web Mail
72.	Web Server
73.	Web Services
74.	Web Services apache cxf 2.0.1
75.	Web Services AXIS2
76.	Wiki Engine
77.	Workflow Engines
78.	XML
79.	XML UI

Java

Java Tutorial

Illustrator Tutorials

GIMP Tutorials

C# / C Sharp

C# / CSharp Tutorial

C# / CSharp Open Source

SQL Server / T-SQL Tutorial

Oracle PL / SQL

Oracle PL/SQL Tutorial

Flash / Flex / ActionScript

VBA / Excel / Access / Word

XML

XML Tutorial

Microsoft Office PowerPoint 2007 Tutorial

Microsoft Office Excel 2007 Tutorial

Microsoft Office Word 2007 Tutorial

Java Source Code / Java Documentation » Science » weka » weka.classifiers.lazy

Source Cross Reference

Class Diagram

Java Document (Java Doc)

java.lang .Object

weka.classifiers .Classifier

weka.classifiers.lazy .IBk

IBk

public class IBk extends Classifier implements OptionHandler,UpdateableClassifier,WeightedInstancesHandler,TechnicalInformationHandler,AdditionalMeasureProducer(Code)

K-nearest neighbours classifier. Can select appropriate value of K based on cross-validation. Can also do distance weighting.

For more information, see

D. Aha, D. Kibler (1991). Instance-based learning algorithms. Machine Learning. 6:37-66.

BibTeX:

 @article{Aha1991,
 author = {D. Aha and D. Kibler},
 journal = {Machine Learning},
 pages = {37-66},
 title = {Instance-based learning algorithms},
 volume = {6},
 year = {1991}
 }

Valid options are:

 -I
 Weight neighbours by the inverse of their distance
 (use when k > 1)

 -F
 Weight neighbours by 1 - their distance
 (use when k > 1)

 -K <number of neighbors>
 Number of nearest neighbours (k) used in classification.
 (Default = 1)

 -E
 Minimise mean squared error rather than mean absolute
 error when using -X option with numeric prediction.

 -W <window size>
 Maximum number of training instances maintained.
 Training instances are dropped FIFO. (Default = no window)

 -X
 Select the number of nearest neighbours between 1
 and the k value specified using hold-one-out evaluation
 on the training data (use when k > 1)

 -A
 The nearest neighbour search algorithm to use (default: weka.core.neighboursearch.LinearNNSearch).

author:
   Stuart Inglis (singlis@cs.waikato.ac.nz)
author:
   Len Trigg (trigg@cs.waikato.ac.nz)
author:
   Eibe Frank (eibe@cs.waikato.ac.nz)
version:
   $Revision: 1.40 $

Field Summary
final public static Tag[]	TAGS_WEIGHTING possible instance weighting methods.
final public static int	WEIGHT_INVERSE weight by 1/distance.
final public static int	WEIGHT_NONE no weighting.
final public static int	WEIGHT_SIMILARITY weight by 1-distance.
protected int	m_ClassType The class attribute type.
protected boolean	m_CrossValidate Whether to select k by cross validation.
protected int	m_DistanceWeighting Whether the neighbours should be distance-weighted.
protected boolean	m_MeanSquared Whether to minimise mean squared error rather than mean absolute error when cross-validating on numeric prediction tasks.
protected NearestNeighbourSearch	m_NNSearch for nearest-neighbor search.
protected double	m_NumAttributesUsed The number of attributes the contribute to a prediction.
protected int	m_NumClasses The number of class values (or 1 if predicting numeric).
protected Instances	m_Train The training instances used for classification.
protected int	m_WindowSize The maximum number of training instances allowed.
protected int	m_kNN The number of neighbours to use for classification (currently).
protected int	m_kNNUpper The value of kNN provided by the user.
protected boolean	m_kNNValid Whether the value of k selected by cross validation has been invalidated by a change in the training instances.
final static long	serialVersionUID for serialization.

Constructor Summary
public	IBk(int k) IBk classifier.
public	IBk() IB1 classifer.

Method Summary
public String	KNNTipText() Returns the tip text for this property.
public void	buildClassifier(Instances instances) Generates the classifier.
protected void	crossValidate() Select the best value for k by hold-one-out cross-validation. If the class attribute is nominal, classification error is minimised.
public String	crossValidateTipText() Returns the tip text for this property.
public String	distanceWeightingTipText() Returns the tip text for this property.
public double[]	distributionForInstance(Instance instance) Calculates the class membership probabilities for the given test instance.
public Enumeration	enumerateMeasures() Returns an enumeration of the additional measure names produced by the neighbour search algorithm.
public Capabilities	getCapabilities() Returns default capabilities of the classifier.
public boolean	getCrossValidate() Gets whether hold-one-out cross-validation will be used to select the best k value.
public SelectedTag	getDistanceWeighting() Gets the distance weighting method used.
public int	getKNN() Gets the number of neighbours the learner will use.
public boolean	getMeanSquared() Gets whether the mean squared error is used rather than mean absolute error when doing cross-validation.
public double	getMeasure(String additionalMeasureName) Returns the value of the named measure from the neighbour search algorithm.
public NearestNeighbourSearch	getNearestNeighbourSearchAlgorithm() Returns the current nearestNeighbourSearch algorithm in use.
public int	getNumTraining() Get the number of training instances the classifier is currently using.
public String[]	getOptions() Gets the current settings of IBk.
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.
public int	getWindowSize() Gets the maximum number of instances allowed in the training pool.
public String	globalInfo() Returns a string describing classifier.
protected void	init() Initialise scheme variables.
public Enumeration	listOptions() Returns an enumeration describing the available options.
public static void	main(String[] argv) Main method for testing this class.
protected double[]	makeDistribution(Instances neighbours, double[] distances) Turn the list of nearest neighbors into a probability distribution.
public String	meanSquaredTipText() Returns the tip text for this property.
public String	nearestNeighbourSearchAlgorithmTipText() Returns the tip text for this property.
public Instances	pruneToK(Instances neighbours, double[] distances, int k) Prunes the list to contain the k nearest neighbors.
public void	setCrossValidate(boolean newCrossValidate) Sets whether hold-one-out cross-validation will be used to select the best k value.
public void	setDistanceWeighting(SelectedTag newMethod) Sets the distance weighting method used.
public void	setKNN(int k) Set the number of neighbours the learner is to use.
public void	setMeanSquared(boolean newMeanSquared) Sets whether the mean squared error is used rather than mean absolute error when doing cross-validation.
public void	setNearestNeighbourSearchAlgorithm(NearestNeighbourSearch nearestNeighbourSearchAlgorithm) Sets the nearestNeighbourSearch algorithm to be used for finding nearest neighbour(s).
public void	setOptions(String[] options) Parses a given list of options.
public void	setWindowSize(int newWindowSize) Sets the maximum number of instances allowed in the training pool.
public String	toString() Returns a description of this classifier.
public void	updateClassifier(Instance instance) Adds the supplied instance to the training set.
public String	windowSizeTipText() Returns the tip text for this property.

Field Detail

TAGS_WEIGHTING
final public static Tag[] TAGS_WEIGHTING(Code)
	possible instance weighting methods.

WEIGHT_INVERSE
final public static int WEIGHT_INVERSE(Code)
	weight by 1/distance.

WEIGHT_NONE
final public static int WEIGHT_NONE(Code)
	no weighting.

WEIGHT_SIMILARITY
final public static int WEIGHT_SIMILARITY(Code)
	weight by 1-distance.

m_ClassType
protected int m_ClassType(Code)
	The class attribute type.

m_CrossValidate
protected boolean m_CrossValidate(Code)
	Whether to select k by cross validation.

m_DistanceWeighting
protected int m_DistanceWeighting(Code)
	Whether the neighbours should be distance-weighted.

m_MeanSquared
protected boolean m_MeanSquared(Code)
	Whether to minimise mean squared error rather than mean absolute error when cross-validating on numeric prediction tasks.

m_NNSearch
protected NearestNeighbourSearch m_NNSearch(Code)
	for nearest-neighbor search.

m_NumAttributesUsed
protected double m_NumAttributesUsed(Code)
	The number of attributes the contribute to a prediction.

m_NumClasses
protected int m_NumClasses(Code)
	The number of class values (or 1 if predicting numeric).

m_Train
protected Instances m_Train(Code)
	The training instances used for classification.

m_WindowSize
protected int m_WindowSize(Code)
	The maximum number of training instances allowed. When this limit is reached, old training instances are removed, so the training data is "windowed". Set to 0 for unlimited numbers of instances.

m_kNN
protected int m_kNN(Code)
	The number of neighbours to use for classification (currently).

m_kNNUpper
protected int m_kNNUpper(Code)
	The value of kNN provided by the user. This may differ from m_kNN if cross-validation is being used.

m_kNNValid
protected boolean m_kNNValid(Code)
	Whether the value of k selected by cross validation has been invalidated by a change in the training instances.

serialVersionUID
final static long serialVersionUID(Code)
	for serialization.

Constructor Detail

IBk
public IBk(int k)(Code)
	IBk classifier. Simple instance-based learner that uses the class of the nearest k training instances for the class of the test instances. Parameters: k - the number of nearest neighbors to use for prediction

IBk
public IBk()(Code)
	IB1 classifer. Instance-based learner. Predicts the class of the single nearest training instance for each test instance.

Method Detail

KNNTipText
public String KNNTipText()(Code)
	Returns the tip text for this property. tip text for this property suitable fordisplaying in the explorer/experimenter gui

buildClassifier
public void buildClassifier(Instances instances) throws Exception(Code)
	Generates the classifier. Parameters: instances - set of instances serving as training data throws: Exception - if the classifier has not been generated successfully

crossValidate
protected void crossValidate()(Code)
	Select the best value for k by hold-one-out cross-validation. If the class attribute is nominal, classification error is minimised. If the class attribute is numeric, mean absolute error is minimised

crossValidateTipText
public String crossValidateTipText()(Code)
	Returns the tip text for this property. tip text for this property suitable fordisplaying in the explorer/experimenter gui

distanceWeightingTipText
public String distanceWeightingTipText()(Code)
	Returns the tip text for this property. tip text for this property suitable fordisplaying in the explorer/experimenter gui

distributionForInstance
public double[] distributionForInstance(Instance instance) throws Exception(Code)
	Calculates the class membership probabilities for the given test instance. Parameters: instance - the instance to be classified predicted class probability distribution throws: Exception - if an error occurred during the prediction

enumerateMeasures
public Enumeration enumerateMeasures()(Code)
	Returns an enumeration of the additional measure names produced by the neighbour search algorithm. an enumeration of the measure names

getCapabilities
public Capabilities getCapabilities()(Code)
	Returns default capabilities of the classifier. the capabilities of this classifier

getCrossValidate
public boolean getCrossValidate()(Code)
	Gets whether hold-one-out cross-validation will be used to select the best k value. true if cross-validation will be used.

getDistanceWeighting
public SelectedTag getDistanceWeighting()(Code)
	Gets the distance weighting method used. Will be one of WEIGHT_NONE, WEIGHT_INVERSE, or WEIGHT_SIMILARITY the distance weighting method used.

getKNN
public int getKNN()(Code)
	Gets the number of neighbours the learner will use. the number of neighbours.

getMeanSquared
public boolean getMeanSquared()(Code)
	Gets whether the mean squared error is used rather than mean absolute error when doing cross-validation. true if so.

getMeasure
public double getMeasure(String additionalMeasureName)(Code)
	Returns the value of the named measure from the neighbour search algorithm. Parameters: additionalMeasureName - the name of the measure to query for its value the value of the named measure throws: IllegalArgumentException - if the named measure is not supported

getNearestNeighbourSearchAlgorithm
public NearestNeighbourSearch getNearestNeighbourSearchAlgorithm()(Code)
	Returns the current nearestNeighbourSearch algorithm in use. the NearestNeighbourSearch algorithm currently in use.

getNumTraining
public int getNumTraining()(Code)
	Get the number of training instances the classifier is currently using. the number of training instances the classifier is currently using

getOptions
public String[] getOptions()(Code)
	Gets the current settings of IBk. an array of strings suitable for passing to setOptions()

getTechnicalInformation
public TechnicalInformation getTechnicalInformation()(Code)
	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. the technical information about this class

getWindowSize
public int getWindowSize()(Code)
	Gets the maximum number of instances allowed in the training pool. The addition of new instances above this value will result in old instances being removed. A value of 0 signifies no limit to the number of training instances. Value of WindowSize.

globalInfo
public String globalInfo()(Code)
	Returns a string describing classifier. a description suitable fordisplaying in the explorer/experimenter gui

init
protected void init()(Code)
	Initialise scheme variables.

listOptions
public Enumeration listOptions()(Code)
	Returns an enumeration describing the available options. an enumeration of all the available options.

main
public static void main(String[] argv)(Code)
	Main method for testing this class. Parameters: argv - should contain command line options (see setOptions)

makeDistribution
protected double[] makeDistribution(Instances neighbours, double[] distances) throws Exception(Code)
	Turn the list of nearest neighbors into a probability distribution. Parameters: neighbours - the list of nearest neighboring instances Parameters: distances - the distances of the neighbors the probability distribution throws: Exception - if computation goes wrong or has no class attribute

meanSquaredTipText
public String meanSquaredTipText()(Code)
	Returns the tip text for this property. tip text for this property suitable fordisplaying in the explorer/experimenter gui

nearestNeighbourSearchAlgorithmTipText
public String nearestNeighbourSearchAlgorithmTipText()(Code)
	Returns the tip text for this property. tip text for this property suitable fordisplaying in the explorer/experimenter gui

pruneToK
public Instances pruneToK(Instances neighbours, double[] distances, int k)(Code)
	Prunes the list to contain the k nearest neighbors. If there are multiple neighbors at the k'th distance, all will be kept. Parameters: neighbours - the neighbour instances. Parameters: distances - the distances of the neighbours from target instance. Parameters: k - the number of neighbors to keep. the pruned neighbours.

setCrossValidate
public void setCrossValidate(boolean newCrossValidate)(Code)
	Sets whether hold-one-out cross-validation will be used to select the best k value. Parameters: newCrossValidate - true if cross-validation should be used.

setDistanceWeighting
public void setDistanceWeighting(SelectedTag newMethod)(Code)
	Sets the distance weighting method used. Values other than WEIGHT_NONE, WEIGHT_INVERSE, or WEIGHT_SIMILARITY will be ignored. Parameters: newMethod - the distance weighting method to use

setKNN
public void setKNN(int k)(Code)
	Set the number of neighbours the learner is to use. Parameters: k - the number of neighbours.

setMeanSquared
public void setMeanSquared(boolean newMeanSquared)(Code)
	Sets whether the mean squared error is used rather than mean absolute error when doing cross-validation. Parameters: newMeanSquared - true if so.

setNearestNeighbourSearchAlgorithm
public void setNearestNeighbourSearchAlgorithm(NearestNeighbourSearch nearestNeighbourSearchAlgorithm)(Code)
	Sets the nearestNeighbourSearch algorithm to be used for finding nearest neighbour(s). Parameters: nearestNeighbourSearchAlgorithm - - The NearestNeighbourSearch class.

setOptions

public void setOptions(String[] options) throws Exception(Code)

Parses a given list of options.

Valid options are:

 -I
 Weight neighbours by the inverse of their distance
 (use when k > 1)

 -F
 Weight neighbours by 1 - their distance
 (use when k > 1)

 -K <number of neighbors>
 Number of nearest neighbours (k) used in classification.
 (Default = 1)

 -E
 Minimise mean squared error rather than mean absolute
 error when using -X option with numeric prediction.

 -W <window size>
 Maximum number of training instances maintained.
 Training instances are dropped FIFO. (Default = no window)

 -X
 Select the number of nearest neighbours between 1
 and the k value specified using hold-one-out evaluation
 on the training data (use when k > 1)

 -A
 The nearest neighbour search algorithm to use (default: weka.core.neighboursearch.LinearNNSearch).

Parameters:
options - the list of options as an array of strings
throws:
Exception - if an option is not supported

setWindowSize
public void setWindowSize(int newWindowSize)(Code)
	Sets the maximum number of instances allowed in the training pool. The addition of new instances above this value will result in old instances being removed. A value of 0 signifies no limit to the number of training instances. Parameters: newWindowSize - Value to assign to WindowSize.

toString
public String toString()(Code)
	Returns a description of this classifier. a description of this classifier as a string.

updateClassifier
public void updateClassifier(Instance instance) throws Exception(Code)
	Adds the supplied instance to the training set. Parameters: instance - the instance to add throws: Exception - if instance could not be incorporatedsuccessfully

windowSizeTipText
public String windowSizeTipText()(Code)
	Returns the tip text for this property. tip text for this property suitable fordisplaying in the explorer/experimenter gui

Fields inherited from weka.classifiers.Classifier

protected boolean m_Debug(Code)(Java Doc)

Methods inherited from weka.classifiers.Classifier

abstract public void buildClassifier(Instances data) throws Exception(Code)(Java Doc)
public double classifyInstance(Instance instance) throws Exception(Code)(Java Doc)
public String debugTipText()(Code)(Java Doc)
public double[] distributionForInstance(Instance instance) throws Exception(Code)(Java Doc)
public static Classifier forName(String classifierName, String[] options) throws Exception(Code)(Java Doc)
public Capabilities getCapabilities()(Code)(Java Doc)
public boolean getDebug()(Code)(Java Doc)
public String[] getOptions()(Code)(Java Doc)
public Enumeration listOptions()(Code)(Java Doc)
public static Classifier[] makeCopies(Classifier model, int num) throws Exception(Code)(Java Doc)
public static Classifier makeCopy(Classifier model) throws Exception(Code)(Java Doc)
protected static void runClassifier(Classifier classifier, String[] options)(Code)(Java Doc)
public void setDebug(boolean debug)(Code)(Java Doc)
public void setOptions(String[] options) throws Exception(Code)(Java Doc)

Methods inherited from java.lang.Object

native protected Object clone() throws CloneNotSupportedException(Code)(Java Doc)
public boolean equals(Object obj)(Code)(Java Doc)
protected void finalize() throws Throwable(Code)(Java Doc)
final native public Class getClass()(Code)(Java Doc)
native public int hashCode()(Code)(Java Doc)
final native public void notify()(Code)(Java Doc)
final native public void notifyAll()(Code)(Java Doc)
public String toString()(Code)(Java Doc)
final native public void wait(long timeout) throws InterruptedException(Code)(Java Doc)
final public void wait(long timeout, int nanos) throws InterruptedException(Code)(Java Doc)
final public void wait() throws InterruptedException(Code)(Java Doc)

www.java2java.com | Contact Us

All other trademarks are property of their respective owners.