edu.iastate.jtm.util
Class VocabularyCounter

java.lang.Object
  edu.iastate.jtm.util.VocabularyCounter

public abstract class VocabularyCounter
extends java.lang.Object

Author:

Jing Ding edu.iastate.jtm.util jtm

Nested Class Summary

static class

VocabularyCounter.TfDf

Field Summary

protected static int	DF
protected int	grandDocumentCount
protected int	grandTermCount
protected static int	TDF
protected static int	TF
protected java.util.Map	vocabulary

Constructor Summary

VocabularyCounter()

Method Summary

abstract void	count(java.io.File input) Count word frequency in input.
int	getDocumentCount(java.lang.Object term)
double	getDocumentFrequency(java.lang.Object term)
int	getGrandDocumentCount()
int	getGrandTermCount()
double	getIdf(java.lang.Object term)
VocabularyCounter.TfDf[]	getSortedFrequency()
java.lang.Object[]	getSortedVocabulary()
int	getTermCount(java.lang.Object term)
double	getTermFrequency(java.lang.Object term)
VocabularyCounter.TfDf	getTfDf(java.lang.Object term)
java.util.Set	getVocabulary()
int	getVocabularySize()
void	register(java.lang.Object term, int which) Add a new word to the vocabulary, or update count of a registered word.
void	remove(java.lang.Object term)
void	save(java.io.File output) Save word count to output.

Methods inherited from class java.lang.Object

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

Field Detail

vocabulary

protected java.util.Map vocabulary

grandTermCount

protected int grandTermCount

grandDocumentCount

protected int grandDocumentCount

TF

protected static final int TF

See Also:

Constant Field Values

DF

protected static final int DF

See Also:

Constant Field Values

TDF

protected static final int TDF

See Also:

Constant Field Values

Constructor Detail

VocabularyCounter

public VocabularyCounter()

Method Detail

register

public void register(java.lang.Object term,
                     int which)

Add a new word to the vocabulary, or update count of a registered word.

Parameters:

term -

save

public void save(java.io.File output)
          throws java.io.IOException

Save word count to output.

Parameters:

output -

Throws:

java.io.IOException

getGrandTermCount

public int getGrandTermCount()

getGrandDocumentCount

public int getGrandDocumentCount()

getTermCount

public int getTermCount(java.lang.Object term)

getDocumentCount

public int getDocumentCount(java.lang.Object term)

getTermFrequency

public double getTermFrequency(java.lang.Object term)

getDocumentFrequency

public double getDocumentFrequency(java.lang.Object term)

getIdf

public double getIdf(java.lang.Object term)

getTfDf

public VocabularyCounter.TfDf getTfDf(java.lang.Object term)

remove

public void remove(java.lang.Object term)

getVocabulary

public java.util.Set getVocabulary()

getVocabularySize

public int getVocabularySize()

getSortedVocabulary

public java.lang.Object[] getSortedVocabulary()

getSortedFrequency

public VocabularyCounter.TfDf[] getSortedFrequency()

count

public abstract void count(java.io.File input)
                    throws java.io.IOException

Count word frequency in input.

Parameters:

input -

Throws:

java.io.FileNotFoundException

java.io.IOException