dragon.ir.clustering.featurefilter

Class AbstractFeatureFilter

java.lang.Object

dragon.ir.clustering.featurefilter.AbstractFeatureFilter

All Implemented Interfaces:

FeatureFilter

Direct Known Subclasses:

DocFrequencyFilter, NullFeatureFilter

public abstract class AbstractFeatureFilter
extends Object
implements FeatureFilter

Title:

Description:

Copyright: Copyright (c) 2005

Company: IST, Drexel University

Version:

1.0

Author:

Davis Zhou

Field Summary

Fields

Modifier and Type	Field and Description
protected int[]	featureMap
protected int	selectedFeatureNum

Constructor Summary

Constructors

Constructor and Description
AbstractFeatureFilter()

Method Summary

Modifier and Type	Method and Description
int	getSelectedFeatureNum()
protected abstract int[]	getSelectedFeatures(IndexReader indexReader, IRDoc[] docSet)
void	initialize(IndexReader indexReader, IRDoc[] docSet) This method chooses a subset of features for text clustering
boolean	isSelected(int originalFeatureIndex)
int	map(int originalFeatureIndex) Map the old feature index to the index in the new feature space.
protected void	setSelectedFeatures(int[] selectedFeatures)

Methods inherited from class java.lang.Object

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

Field Detail

featureMap

protected int[] featureMap

selectedFeatureNum

protected int selectedFeatureNum

Constructor Detail

AbstractFeatureFilter

public AbstractFeatureFilter()

Method Detail

getSelectedFeatures

protected abstract int[] getSelectedFeatures(IndexReader indexReader,
                                             IRDoc[] docSet)

initialize

public void initialize(IndexReader indexReader,
                       IRDoc[] docSet)

Description copied from interface: FeatureFilter

This method chooses a subset of features for text clustering

Specified by:

initialize in interface FeatureFilter

Parameters:

indexReader - the index reader for a collection

docSet - the document set for clustering

setSelectedFeatures

protected void setSelectedFeatures(int[] selectedFeatures)

isSelected

public boolean isSelected(int originalFeatureIndex)

Specified by:

isSelected in interface FeatureFilter

Parameters:

originalFeatureIndex - the index of the feature in the old feature space

Returns:

true if the given feature is selected for text clustering

map

public int map(int originalFeatureIndex)

Description copied from interface: FeatureFilter

Map the old feature index to the index in the new feature space.

Specified by:

map in interface FeatureFilter

Parameters:

originalFeatureIndex - the index of the feature before feature selection

Returns:

the index of the feature the new space. If the feature is not selected, it will return -1.

getSelectedFeatureNum

public int getSelectedFeatureNum()

Specified by:

getSelectedFeatureNum in interface FeatureFilter

Returns:

the number of selected features