Package opennlp.tools.namefind

Klasse TokenNameFinderCrossValidator

java.lang.Object

opennlp.tools.namefind.TokenNameFinderCrossValidator

public class TokenNameFinderCrossValidator
extends Object

Cross validator for TokenNameFinder.

Konstruktorübersicht

Konstruktoren

Konstruktor	Beschreibung
TokenNameFinderCrossValidator(String languageCode, String type, TrainingParameters trainParams, byte[] featureGeneratorBytes, Map<String,Object> resources, TokenNameFinderEvaluationMonitor... listeners)	Initializes a TokenNameFinderCrossValidator with the given parameters.
TokenNameFinderCrossValidator(String languageCode, String type, TrainingParameters params, byte[] featureGeneratorBytes, Map<String,Object> resources, SequenceCodec<String> codec, TokenNameFinderEvaluationMonitor... listeners)	Initializes a TokenNameFinderCrossValidator with the given parameters.
TokenNameFinderCrossValidator(String languageCode, String type, TrainingParameters params, TokenNameFinderFactory factory, TokenNameFinderEvaluationMonitor... listeners)	Initializes a TokenNameFinderCrossValidator with the given parameters.

Methodenübersicht

Modifizierer und Typ	Methode	Beschreibung
void	evaluate(ObjectStream<NameSample> samples, int nFolds)	Starts the evaluation.
FMeasure	getFMeasure()

Von Klasse geerbte Methoden java.lang.Object

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

Konstruktordetails

TokenNameFinderCrossValidator

public TokenNameFinderCrossValidator(String languageCode,
 String type,
 TrainingParameters params,
 byte[] featureGeneratorBytes,
 Map<String,Object> resources,
 SequenceCodec<String> codec,
 TokenNameFinderEvaluationMonitor... listeners)

Initializes a TokenNameFinderCrossValidator with the given parameters.

Parameter:

languageCode - The ISO conform language code.

type - null or an override type for all types in the training data.

params - The TrainingParameters for the context of cross validation.

featureGeneratorBytes - The byte[] representing the feature generator descriptor.

resources - Additional resources in a mapping.

codec - The SequenceCodec to use.

listeners - the evaluation listeners.

TokenNameFinderCrossValidator

public TokenNameFinderCrossValidator(String languageCode,
 String type,
 TrainingParameters trainParams,
 byte[] featureGeneratorBytes,
 Map<String,Object> resources,
 TokenNameFinderEvaluationMonitor... listeners)

Initializes a TokenNameFinderCrossValidator with the given parameters.

Parameter:

languageCode - The ISO conform language code.

type - null or an override type for all types in the training data.

featureGeneratorBytes - The byte[] representing the feature generator descriptor.

resources - Additional resources in a mapping.

listeners - the evaluation listeners.

TokenNameFinderCrossValidator

public TokenNameFinderCrossValidator(String languageCode,
 String type,
 TrainingParameters params,
 TokenNameFinderFactory factory,
 TokenNameFinderEvaluationMonitor... listeners)

Initializes a TokenNameFinderCrossValidator with the given parameters.

Parameter:

languageCode - The ISO conform language code.

type - null or an override type for all types in the training data.

params - The TrainingParameters for the context of cross validation.

factory - The TokenNameFinderFactory for creating related objects.

listeners - the evaluation listeners.

Methodendetails

evaluate

public void evaluate(ObjectStream<NameSample> samples,
 int nFolds)
              throws IOException

Starts the evaluation.

Note: The name samples need to be grouped on a document basis.

Parameter:

samples - The ObjectStream of samples to train and test with.

nFolds - Number of folds. It must be greater than zero.

Löst aus:

IOException - Thrown if IO errors occurred.

getFMeasure

public FMeasure getFMeasure()