de.jungblut.online.bayes

Class NaiveBayesLearner

java.lang.Object

de.jungblut.online.ml.AbstractOnlineLearner<BayesianProbabilityModel>

de.jungblut.online.bayes.NaiveBayesLearner

All Implemented Interfaces:

OnlineLearner<BayesianProbabilityModel>

public class NaiveBayesLearner
extends AbstractOnlineLearner<BayesianProbabilityModel>

Multinomial naive bayes learner. This class now contains a sparse internal representations of the "feature given class" probabilities. Thus it can be scaled to very large text corpora and large numbers of classes easily. The internal accesses are thread-safe, so a parallel stream can be used.

Author:

thomas.jungblut

Field Summary

Fields inherited from class de.jungblut.online.ml.AbstractOnlineLearner

featureDimension, numOutcomeClasses, outcomeDimension, streamSupplier

Constructor Summary

Constructors

Constructor and Description
NaiveBayesLearner() Default constructor to construct this classifier.
NaiveBayesLearner(boolean verbose) Pass true if this classifier should output some progress information to the logger.

Method Summary

Modifier and Type	Method and Description
BayesianProbabilityModel	train(java.util.function.Supplier<java.util.stream.Stream<de.jungblut.online.ml.FeatureOutcomePair>> streamSupplier) Trains a new model using the supplied streams.

Methods inherited from class de.jungblut.online.ml.AbstractOnlineLearner

init, peekDimensions, setVerbose, verbose

Methods inherited from class java.lang.Object

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

Constructor Detail

NaiveBayesLearner

public NaiveBayesLearner()

Default constructor to construct this classifier.

NaiveBayesLearner

public NaiveBayesLearner(boolean verbose)

Pass true if this classifier should output some progress information to the logger.

Method Detail

train

public BayesianProbabilityModel train(java.util.function.Supplier<java.util.stream.Stream<de.jungblut.online.ml.FeatureOutcomePair>> streamSupplier)

Description copied from interface: OnlineLearner

Trains a new model using the supplied streams. In case an algorithm needs multiple iterations, it simply gets a new one from the supplier.

Parameters:

streamSupplier - the supplier that creates a new stream that can be consumed.

Returns:

the trained model.