opennlp.maxent
Class OnePassRealValueDataIndexer

java.lang.Object
  opennlp.maxent.AbstractDataIndexer
      opennlp.maxent.OnePassDataIndexer
          opennlp.maxent.OnePassRealValueDataIndexer

All Implemented Interfaces:

DataIndexer

public class OnePassRealValueDataIndexer
extends OnePassDataIndexer

An indexer for maxent model data which handles cutoffs for uncommon contextual predicates and provides a unique integer index for each of the predicates and maintains event values.

Author:

Tom Morton

Field Summary

Fields inherited from class opennlp.maxent.AbstractDataIndexer

contexts, numTimesEventsSeen, outcomeLabels, outcomeList, predCounts, predLabels

Constructor Summary

OnePassRealValueDataIndexer(EventStream eventStream, int cutoff)
Two argument constructor for DataIndexer.

Method Summary

float[][]	getValues() Returns the values associated with each event context or null if integer values are to be used.
protected java.util.List	index(gnu.trove.TLinkedList events, gnu.trove.TObjectIntHashMap predicateIndex)
protected int	sortAndMerge(java.util.List eventsToCompare) Sorts and uniques the array of comparable events and return the number of unique events.

Methods inherited from class opennlp.maxent.AbstractDataIndexer

getContexts, getNumTimesEventsSeen, getOutcomeLabels, getOutcomeList, getPredCounts, getPredLabels, toIndexedStringArray, update

Methods inherited from class java.lang.Object

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

Constructor Detail

OnePassRealValueDataIndexer

public OnePassRealValueDataIndexer(EventStream eventStream,
                                   int cutoff)

Two argument constructor for DataIndexer.

Parameters:

eventStream - An Event[] which contains the a list of all the Events seen in the training data.

cutoff - The minimum number of times a predicate must have been observed in order to be included in the model.

Method Detail

getValues

public float[][] getValues()

Description copied from interface: DataIndexer

Returns the values associated with each event context or null if integer values are to be used.

Specified by:

getValues in interface DataIndexer

Overrides:

getValues in class AbstractDataIndexer

Returns:

the values associated with each event context.

sortAndMerge

protected int sortAndMerge(java.util.List eventsToCompare)

Description copied from class: AbstractDataIndexer

Sorts and uniques the array of comparable events and return the number of unique events. This method will alter the eventsToCompare array -- it does an in place sort, followed by an in place edit to remove duplicates.

Overrides:

sortAndMerge in class AbstractDataIndexer

Parameters:

eventsToCompare - a ComparableEvent[] value

Returns:

The number of unique events in the specified list.

index

protected java.util.List index(gnu.trove.TLinkedList events,
                               gnu.trove.TObjectIntHashMap predicateIndex)

Overrides:

index in class OnePassDataIndexer