uk.ac.shef.dcs.oak.jate.core.algorithm
Class TermExFeatureWrapper

java.lang.Object
  extended by uk.ac.shef.dcs.oak.jate.core.algorithm.AbstractFeatureWrapper
      extended by uk.ac.shef.dcs.oak.jate.core.algorithm.TermExFeatureWrapper

public class TermExFeatureWrapper
extends AbstractFeatureWrapper

TermExFeatureWrapper wraps an instance of FeatureDocumentTermFrequency, which tells a candidate term's distribution over a corpus, each document in the corpus, and existence in documents; another instance of FeatureCorpusTermFrequency which tells individual words' distributions over corpus; and an instance of FeatureRefCorpusTermFrequency, which tells individual words' distributions in a reference corpus.


Constructor Summary
TermExFeatureWrapper(FeatureDocumentTermFrequency termfreq, FeatureCorpusTermFrequency wordfreq, FeatureRefCorpusTermFrequency ref)
          Default constructor
 
Method Summary
 double getNormFreqInDoc(java.lang.String t, int d)
           
 double getRefWordFreqNorm(java.lang.String word)
           
 int getSumTermFreqInDocs(java.lang.String term)
           
 int[] getTermAppear(java.lang.String t)
           
 int getTermFreq(java.lang.String term)
           
 int getTermFreqInDoc(java.lang.String term, int d)
           
 java.util.Set<java.lang.String> getTerms()
           
 int getTotalCorpusTermFreq()
           
 int getWordFreq(java.lang.String word)
           
 
Methods inherited from class uk.ac.shef.dcs.oak.jate.core.algorithm.AbstractFeatureWrapper
toString
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Constructor Detail

TermExFeatureWrapper

public TermExFeatureWrapper(FeatureDocumentTermFrequency termfreq,
                            FeatureCorpusTermFrequency wordfreq,
                            FeatureRefCorpusTermFrequency ref)
Default constructor

Parameters:
termfreq -
wordfreq -
ref -
Method Detail

getTotalCorpusTermFreq

public int getTotalCorpusTermFreq()
Returns:
total number of occurrences of terms in the corpus

getTermFreq

public int getTermFreq(java.lang.String term)
Parameters:
term -
Returns:
the number of occurrences of a candidate term in the corpus

getTermFreqInDoc

public int getTermFreqInDoc(java.lang.String term,
                            int d)
Parameters:
term -
d -
Returns:
the term's frequency in document with id=d

getTermAppear

public int[] getTermAppear(java.lang.String t)
Parameters:
t -
Returns:
the ids of documents in which term t is found

getSumTermFreqInDocs

public int getSumTermFreqInDocs(java.lang.String term)
Parameters:
term -
Returns:
total number of occurrences of a term in the documents in which it is found

getNormFreqInDoc

public double getNormFreqInDoc(java.lang.String t,
                               int d)
Parameters:
t -
d -
Returns:
normalised term frequency in a document with id=d. It is equal to freq of term t in d divided by total term frequency in d.

getWordFreq

public int getWordFreq(java.lang.String word)
Parameters:
word -
Returns:
the number of occurrences of a word in the corpus

getRefWordFreqNorm

public double getRefWordFreqNorm(java.lang.String word)
Parameters:
word -
Returns:
the normalised frequency of a word in the reference corpus. It is equal to freq of word w divided by total frequencies

getTerms

public java.util.Set<java.lang.String> getTerms()
Specified by:
getTerms in class AbstractFeatureWrapper
Returns:
set of candidate term strings