org.datamanager.clustering.matrix
Class DocumentTermMatrixImpl

java.lang.Object
  |
  +--org.datamanager.clustering.matrix.DocumentTermMatrixImpl

All Implemented Interfaces:

DocumentTermMatrix

public class DocumentTermMatrixImpl

extends Object

implements DocumentTermMatrix

A basic DocumentTermMatrix implementation.

Field Summary

static int	COLUMN_GROWTH_MULTIPLIER How fast we grow columns when the matrix fills up.
static int	MAXIMUM_TERMS_INDEXED Maximum number of terms we will index.
static int	MINIMUM_WORD_LENGTH How long a word must be to be added to the matrix.
static int	ROW_GROWTH_MULTIPLIER How fast we grow rows when the matrix fills up.

Method Summary

void	addWords(Entity entity, WordFrequencyMapEntityValue newWords) Adds words from the provided WordFrequencyMapEntityValue to the document term matrix.
static DocumentTermMatrixImpl	getDocumentTermMatrix() Gets the singleton instance of this DocumentTermMatrix.
protected static DoubleMatrix2D	getMatrix() Gets the document x term matrix.
double	getSimilarityBetween(Entity entityOne, Entity entityTwo) Gets the similarity between two entities by doing a LSA look up for documents documents clustering matrix.
void	makeDocumentByDocumentMatrix() Creates a docment by document matrix representing similarity distances by creating the Singular Value Decomposition of the document by term matrix.
ClusterableMatrix	toClusterableMatrix() Returns a ClusterableMatrix of the documents in this matrix.

Methods inherited from class java.lang.Object

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

Field Detail

MINIMUM_WORD_LENGTH

public static final int MINIMUM_WORD_LENGTH

How long a word must be to be added to the matrix.

See Also:

Constant Field Values

ROW_GROWTH_MULTIPLIER

public static final int ROW_GROWTH_MULTIPLIER

How fast we grow rows when the matrix fills up.

See Also:

Constant Field Values

COLUMN_GROWTH_MULTIPLIER

public static final int COLUMN_GROWTH_MULTIPLIER

How fast we grow columns when the matrix fills up.

See Also:

Constant Field Values

MAXIMUM_TERMS_INDEXED

public static final int MAXIMUM_TERMS_INDEXED

Maximum number of terms we will index.

See Also:

Constant Field Values

Method Detail

toClusterableMatrix

public ClusterableMatrix toClusterableMatrix()

Description copied from interface: DocumentTermMatrix

Returns a ClusterableMatrix of the documents in this matrix.

Specified by:

toClusterableMatrix in interface DocumentTermMatrix

addWords

public void addWords(Entity entity,
                     WordFrequencyMapEntityValue newWords)

Adds words from the provided WordFrequencyMapEntityValue to the document term matrix.

Specified by:

addWords in interface DocumentTermMatrix

makeDocumentByDocumentMatrix

public void makeDocumentByDocumentMatrix()

Creates a docment by document matrix representing similarity distances by creating the Singular Value Decomposition of the document by term matrix. FIXME: this is incomplete. See http://ella.slis.indiana.edu/~katy/L697/code/lsa.html

getDocumentTermMatrix

public static DocumentTermMatrixImpl getDocumentTermMatrix()

Gets the singleton instance of this DocumentTermMatrix.

getMatrix

protected static DoubleMatrix2D getMatrix()

Gets the document x term matrix.

getSimilarityBetween

public double getSimilarityBetween(Entity entityOne,
                                   Entity entityTwo)

Gets the similarity between two entities by doing a LSA look up for documents documents clustering matrix.

Specified by:

getSimilarityBetween in interface DocumentTermMatrix