edu.stanford.nlp.classify
Class AbstractLinearClassifierFactory<L,F>

java.lang.Object
  edu.stanford.nlp.classify.AbstractLinearClassifierFactory<L,F>

Type Parameters:

L - The type of the labels in the Dataset and Datum

F - The type of the features in the Dataset and Datum

All Implemented Interfaces:

ClassifierFactory<L,F,Classifier<L,F>>, java.io.Serializable

Direct Known Subclasses:

LinearClassifierFactory

public abstract class AbstractLinearClassifierFactory<L,F>
extends java.lang.Object
implements ClassifierFactory<L,F,Classifier<L,F>>

Shared methods for training a LinearClassifier. Inheriting classes need to implement the trainWeights method.

Author:

Dan Klein, Sarah Spikes (sdspikes@cs.stanford.edu) (Templatization)

See Also:

Serialized Form

Constructor Summary

AbstractLinearClassifierFactory()

Method Summary

LinearClassifier<L,F>	trainClassifier(java.util.Collection<Datum<L,F>> examples) Takes a Collection of Datum objects and gives you back a Classifier trained on it.
LinearClassifier<L,F>	trainClassifier(GeneralDataset<L,F> data) Trains a Classifier on a Dataset.
Classifier<L,F>	trainClassifier(java.util.List<RVFDatum<L,F>> examples)
LinearClassifier<L,F>	trainClassifier(java.lang.ref.Reference<java.util.Collection<Datum<L,F>>> ref) Takes a Reference to a Collection of Datum objects and gives you back a Classifier trained on them
protected abstract double[][]	trainWeights(GeneralDataset<L,F> dataset)

Methods inherited from class java.lang.Object

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

Constructor Detail

AbstractLinearClassifierFactory

public AbstractLinearClassifierFactory()

Method Detail

trainClassifier

public Classifier<L,F> trainClassifier(java.util.List<RVFDatum<L,F>> examples)

Specified by:

trainClassifier in interface ClassifierFactory<L,F,Classifier<L,F>>

trainWeights

protected abstract double[][] trainWeights(GeneralDataset<L,F> dataset)

trainClassifier

public LinearClassifier<L,F> trainClassifier(java.util.Collection<Datum<L,F>> examples)

Takes a Collection of Datum objects and gives you back a Classifier trained on it.

Parameters:

examples - Collection of Datum objects to train the classifier on

Returns:

A Classifier trained on it.

trainClassifier

public LinearClassifier<L,F> trainClassifier(java.lang.ref.Reference<java.util.Collection<Datum<L,F>>> ref)

Takes a Reference to a Collection of Datum objects and gives you back a Classifier trained on them

Parameters:

ref - Reference to a Collection of Datum objects to train the classifier on

Returns:

A Classifier trained on a collection of Datum

trainClassifier

public LinearClassifier<L,F> trainClassifier(GeneralDataset<L,F> data)

Trains a Classifier on a Dataset.

Specified by:

trainClassifier in interface ClassifierFactory<L,F,Classifier<L,F>>

Returns:

A Classifier trained on the data.