ivory.ffg.stats

Class GlobalStats

java.lang.Object

ivory.ffg.stats.GlobalStats

public class GlobalStats
extends Object

Global statistics used in computing features (e.g., idf and cf)

Author:

Nima Asadi

Constructor Summary

Constructors

Constructor and Description
GlobalStats(HMapIF idf, HMapIF cf, int documentCount, long collectionLength, float avgDocumentLength, float defaultDf, float defaultCf) Creates an instance of this class with the provided information

Method Summary

Methods

Modifier and Type	Method and Description
float	getAvgDocumentLength()
float	getCf(int term)
HMapIF	getCfs()
long	getCollectionLength()
float	getDefaultCf()
float	getDefaultDf()
float	getDefaultIdf()
int	getDocumentCount()
float	getIdf(int term)
HMapIF	getIdfs()

Methods inherited from class java.lang.Object

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

Constructor Detail

GlobalStats

public GlobalStats(HMapIF idf,
           HMapIF cf,
           int documentCount,
           long collectionLength,
           float avgDocumentLength,
           float defaultDf,
           float defaultCf)

Creates an instance of this class with the provided information

Parameters:

idf - Map of term ids to IDF values

cf - Map of term ids to Collection Frequency (CF) values

documentCount - Number of documents in the collection

collectionLength - Length of the collection (i.e., number of terms)

avgDocumentLength - Average length of documents (i.e., average number of term per document

defaultDf - Default value for document frequency (used for phrase queries)

defaultCf - Default value for collection frequency (used for phrase queries)

Method Detail

getAvgDocumentLength

public float getAvgDocumentLength()

Returns:

Average document length in the collection

getCf

public float getCf(int term)

Parameters:

term - Term id

Returns:

cf value of a term

getCfs

public HMapIF getCfs()

Returns:

collection frequencies

getCollectionLength

public long getCollectionLength()

Returns:

Length of the collection (i.e., number of terms)

getDefaultCf

public float getDefaultCf()

Returns:

Default collection frequency

getDefaultDf

public float getDefaultDf()

Returns:

Default document frequency

getDefaultIdf

public float getDefaultIdf()

Returns:

Default inverse-document frequency

getDocumentCount

public int getDocumentCount()

Returns:

Total number of documents in the collection

getIdf

public float getIdf(int term)

Parameters:

term - Term id

Returns:

idf value of a term

getIdfs

public HMapIF getIdfs()

Returns:

idf values