edu.ucla.sspace.clustering

Class OnlineKMeans<T extends DoubleVector>

java.lang.Object

edu.ucla.sspace.clustering.OnlineKMeans<T>

All Implemented Interfaces:

Generator<OnlineClustering<T>>

public class OnlineKMeans<T extends DoubleVector>
extends Object
implements Generator<OnlineClustering<T>>

A Generator class for generating a new OnlineKMeansClustering instance. This class supports the following properties:

Property:
Default:

This variable sets the weight given to the mean vector in a rolling average of vectors.

Property:
Default: 0.35

This variable sets the threshold for merging two clusters.

Property:
Default: 15

This variable sets the maximum number of clusters used.

Author:

Keith Stevens

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
class	OnlineKMeans.OnlineKMeansClustering<T extends DoubleVector> A simple online implementation of K-Means clustering for Vectors, with the option to perform agglomerative clustering once all elements have been clustered.

Field Summary

Fields

Modifier and Type	Field and Description
static int	DEFAULT_MAX_CLUSTERS The default number of clusters.
static double	DEFAULT_MERGE_THRESHOLD The default merge threshold.
static String	MERGE_THRESHOLD_PROPERTY The property for setting the threshold for merging two clusters.

Constructor Summary

Constructors

Constructor and Description
OnlineKMeans() Creates a new generator using the system properties.
OnlineKMeans(Properties props) Creates a new generator using the given properties.

Method Summary

Methods

Modifier and Type	Method and Description
OnlineClustering<T>	generate() Generates a new instance of a OnlineClustering based on the values used to construct this generator.
String	toString()

Methods inherited from class java.lang.Object

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

Field Detail

MERGE_THRESHOLD_PROPERTY

public static final String MERGE_THRESHOLD_PROPERTY

The property for setting the threshold for merging two clusters.

See Also:

Constant Field Values

DEFAULT_MERGE_THRESHOLD

public static final double DEFAULT_MERGE_THRESHOLD

The default merge threshold.

See Also:

Constant Field Values

DEFAULT_MAX_CLUSTERS

public static final int DEFAULT_MAX_CLUSTERS

The default number of clusters.

See Also:

Constant Field Values

Constructor Detail

OnlineKMeans

public OnlineKMeans()

Creates a new generator using the system properties.

OnlineKMeans

public OnlineKMeans(Properties props)

Creates a new generator using the given properties.

Method Detail

generate

public OnlineClustering<T> generate()

Generates a new instance of a OnlineClustering based on the values used to construct this generator.

Specified by:

generate in interface Generator<OnlineClustering<T extends DoubleVector>>

toString

public String toString()

Overrides:

toString in class Object