org.ai_heuristic.eval.text

Class Idf

java.lang.Object

org.ai_heuristic.eval.text.BowHeuristic

org.ai_heuristic.eval.text.Idf

Direct Known Subclasses:

CfIdf

public class Idf
extends BowHeuristic

This class calculates the inverse document frequency for a list of terms on bag-of-words. the following rules have been added. If there is only 1 list and therefore a total document count N of 1, the idf is ignored and a value of 1.0 is returned. If the term count t is 0 (it should not be) then it is set to 1. The value used is Math.log(N/t).

Author:

Kieran Greer

Field Summary

Fields inherited from class org.ai_heuristic.eval.text.BowHeuristic

termCount, termList

Constructor Summary

Constructors

Constructor and Description
Idf() Create a new instance of Idf.

Method Summary

Modifier and Type	Method and Description
java.util.HashMap<java.lang.String,java.lang.Float>	calcIDF(java.util.ArrayList<BagOfWords> bowList) Create the inverse term document frequency for the selected documents.

Methods inherited from class org.ai_heuristic.eval.text.BowHeuristic

createBoW, createBoW, getTermCount, sortTermOrder, sortTopTermOrder

Methods inherited from class java.lang.Object

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

Constructor Detail

Idf

public Idf()

Create a new instance of Idf.

Method Detail

calcIDF

public java.util.HashMap<java.lang.String,java.lang.Float> calcIDF(java.util.ArrayList<BagOfWords> bowList)
                                                            throws java.lang.Exception

Create the inverse term document frequency for the selected documents.

Parameters:

bowList - list of bag or words to process.

Returns:

the idf scores for each term.

Throws:

java.lang.Exception - any error.