edu.udo.cs.wvtool.generic.vectorcreation
Class TFIDF

java.lang.Object
  edu.udo.cs.wvtool.generic.vectorcreation.TFIDF

All Implemented Interfaces:

WVTVectorCreator

public class TFIDF
extends java.lang.Object
implements WVTVectorCreator

This class represents a mechanism to create TFIDF word vectors. The resulting vectors are normalized.

Version:

$Id: TFIDF.java,v 1.2 2006/06/06 11:45:23 mjwurst Exp $

Author:

Michael Wurst

Constructor Summary

TFIDF()

Method Summary

WVTWordVector

createVector(int[] frequencies, int numTermOccurences, WVTWordList wordList, WVTDocumentInfo d) Create a word vector from term frequencies and a word list.

Methods inherited from class java.lang.Object

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

Constructor Detail

TFIDF

public TFIDF()

Method Detail

createVector

public WVTWordVector createVector(int[] frequencies,
                                  int numTermOccurences,
                                  WVTWordList wordList,
                                  WVTDocumentInfo d)

Description copied from interface: WVTVectorCreator

Create a word vector from term frequencies and a word list.

Specified by:

createVector in interface WVTVectorCreator

Parameters:

frequencies - an array containing the frequencies, by which individual terms occur in the document

wordList - a pointer to a WVTWordList

d - the WVTDocumentInfo value, describing the document being processed

Returns:

a WVTWordVector value

See Also:

WVTVectorCreator.createVector(int[], int, edu.udo.cs.wvtool.wordlist.WVTWordList, edu.udo.cs.wvtool.main.WVTDocumentInfo)