org.knowceans.corpus
Class DisjointDocTerms

java.lang.Object
  org.knowceans.corpus.DisjointDocTerms

public class DisjointDocTerms
extends java.lang.Object

DisjointDocTerms partitions the a given document-term matrix into P mutually exclusive document subsets and term subsets. Based on these, index sets can be retrieved into the original corpus for paralle access to mutually exclusive documents and terms.

Author:

gregor

Constructor Summary

DisjointDocTerms(int[][] w, int V)

Method Summary

int[][]	getDisjointDocuments(int P) get the set of disjoint m for each threadd.
int[][]	getDisjointTerms(int P) get the set of disjoint terms
int[][][]	getDisjointTokens(int P) get the set of disjoint words for a corpus
static void	main(java.lang.String[] args)

Methods inherited from class java.lang.Object

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

Constructor Detail

DisjointDocTerms

public DisjointDocTerms(int[][] w,
                        int V)

Method Detail

main

public static void main(java.lang.String[] args)

getDisjointDocuments

public int[][] getDisjointDocuments(int P)

get the set of disjoint m for each threadd.

Parameters:

P -

Returns:

m = int[p][i]

getDisjointTerms

public int[][] getDisjointTerms(int P)

get the set of disjoint terms

Parameters:

P -

Returns:

int[q][i] -> t

getDisjointTokens

public int[][][] getDisjointTokens(int P)

get the set of disjoint words for a corpus

Parameters:

w - int[m][n] -> t

Returns:

int[q][m][i] -> n