Package org.carrot2.text.preprocessing

Class PreprocessingContext.AllLabels

java.lang.Object

org.carrot2.text.preprocessing.PreprocessingContext.AllLabels

Enclosing class:

PreprocessingContext

public class PreprocessingContext.AllLabels
extends Object

Information about words and phrases that might be good cluster label candidates. Each entry in each array corresponds to one label candidate.

All arrays in this class have the same length and values across different arrays correspond to each other for the same index.

Field Summary

Fields

Modifier and Type	Field	Description
com.carrotsearch.hppc.BitSet[]	documentIndices	Indices of documents assigned to the label candidate.
int[]	featureIndex	Feature index of the label candidate.
int	firstPhraseIndex	The first index in featureIndex which points to PreprocessingContext.AllPhrases, or -1 if there are no phrases in featureIndex.

Constructor Summary

Constructors

Constructor	Description
AllLabels()

Method Summary

Modifier and Type	Method	Description
CharSequence	getLabel(int index)
int	size()
String	toString()	For debugging purposes.

Methods inherited from class java.lang.Object

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

Field Details

featureIndex

public int[] featureIndex

Feature index of the label candidate. Features whose values are less than the size of PreprocessingContext.AllWords arrays are single word features and point to entries in PreprocessingContext.AllWords. Features whose values are larger or equal to the size of PreprocessingContext.AllWords, after subtracting the size of PreprocessingContext.AllWords, point to PreprocessingContext.AllPhrases.

This array is produced by LabelFilterProcessor.

documentIndices

public com.carrotsearch.hppc.BitSet[] documentIndices

Indices of documents assigned to the label candidate.

This array is produced by DocumentAssigner.

firstPhraseIndex

public int firstPhraseIndex

The first index in featureIndex which points to PreprocessingContext.AllPhrases, or -1 if there are no phrases in featureIndex.

This value is set by LabelFilterProcessor.

See Also:

featureIndex

Constructor Details

AllLabels

public AllLabels()

Method Details

toString

public String toString()

For debugging purposes.

Overrides:

toString in class Object

getLabel

public CharSequence getLabel(int index)

size

public int size()