jsat.classifiers.bayesian

Class MultinomialNaiveBayes

java.lang.Object

jsat.classifiers.BaseUpdateableClassifier

jsat.classifiers.bayesian.MultinomialNaiveBayes

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Classifier, UpdateableClassifier, Parameterized

public class MultinomialNaiveBayes
extends BaseUpdateableClassifier
implements Parameterized

An implementation of the Multinomial Naive Bayes model (MNB). In this model, vectors are implicitly assumed to be sparse and that zero values can be skipped. This model requires that all numeric features be non negative, any negative value will be treated as a zero.

Note: the is no reason to ever use more than one epoch for MNB

MNB requires taking the log probabilities to perform predictions, which created a trade off. Updating the classifier requires the non log form, but updates require the log form, making classification take considerably longer to take the logs of the probabilities. This can be reduced by finalizing the model. This prevents the model from being updated further, but reduces classification time. By default, this will be done after a call to train(jsat.classifiers.ClassificationDataSet) but not after update(jsat.classifiers.DataPoint, int)

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
MultinomialNaiveBayes() Creates a new Multinomial model with laplace smoothing
MultinomialNaiveBayes(double smoothing) Creates a new Multinomial model with the given amount of smoothing

Method Summary

Modifier and Type	Method and Description
CategoricalResults	classify(DataPoint data) Performs classification on the given data point.
MultinomialNaiveBayes	clone()
void	finalizeModel() Finalizes the current model.
double	getSmoothing()
boolean	isFinalizeAfterTraining() Returns true if the model will be finalized after batch training.
void	setFinalizeAfterTraining(boolean finalizeAfterTraining) If set true, the model will be finalized after a call to train(jsat.classifiers.ClassificationDataSet).
void	setSmoothing(double smoothing) Sets the amount of smoothing applied to the model.
void	setUp(CategoricalData[] categoricalAttributes, int numericAttributes, CategoricalData predicting) Prepares the classifier to begin learning from its UpdateableClassifier.update(jsat.classifiers.DataPoint, int) method.
boolean	supportsWeightedData() Indicates whether the model knows how to train using weighted data points.
void	train(ClassificationDataSet dataSet) Trains the classifier and constructs a model for classification using the given data set.
void	train(ClassificationDataSet dataSet, boolean parallel) Trains the classifier and constructs a model for classification using the given data set.
void	update(DataPoint dataPoint, int targetClass) Updates the classifier by giving it a new data point to learn from.

Methods inherited from class jsat.classifiers.BaseUpdateableClassifier

getEpochs, setEpochs, trainEpochs

Methods inherited from class java.lang.Object

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

Methods inherited from interface jsat.parameters.Parameterized

getParameter, getParameters

Constructor Detail

MultinomialNaiveBayes

public MultinomialNaiveBayes()

Creates a new Multinomial model with laplace smoothing

MultinomialNaiveBayes

public MultinomialNaiveBayes(double smoothing)

Creates a new Multinomial model with the given amount of smoothing

Parameters:

smoothing - the amount of smoothing to apply

Method Detail

setSmoothing

public void setSmoothing(double smoothing)

Sets the amount of smoothing applied to the model.
Using a value of 1.0 is equivalent to laplace smoothing

The smoothing can be changed after the model has already been trained without needed to re-train the model for the change to take effect.

Parameters:

smoothing - the positive smoothing constant

getSmoothing

public double getSmoothing()

Returns:

the smoothing applied to categorical counts

setFinalizeAfterTraining

public void setFinalizeAfterTraining(boolean finalizeAfterTraining)

If set true, the model will be finalized after a call to train(jsat.classifiers.ClassificationDataSet). This prevents the model from being updated in an online fashion for an reduction in classification time.

Parameters:

finalizeAfterTraining - true to finalize after a call to train, false to keep the model updatable.

isFinalizeAfterTraining

public boolean isFinalizeAfterTraining()

Returns true if the model will be finalized after batch training. false if it will be left in an updatable state.

Returns:

true if the model will be finalized after batch training.

clone

public MultinomialNaiveBayes clone()

Specified by:

clone in interface Classifier

Specified by:

clone in interface UpdateableClassifier

Specified by:

clone in class BaseUpdateableClassifier

train

public void train(ClassificationDataSet dataSet,
                  boolean parallel)

Description copied from interface: Classifier

Trains the classifier and constructs a model for classification using the given data set. If the training method knows how, it will used the threadPool to conduct training in parallel. This method will block until the training has completed.

Specified by:

train in interface Classifier

Overrides:

train in class BaseUpdateableClassifier

Parameters:

dataSet - the data set to train on

parallel - true if multiple threads should be used to train the model. false if it should be done in a single threaded manner.

train

public void train(ClassificationDataSet dataSet)

Description copied from interface: Classifier

Trains the classifier and constructs a model for classification using the given data set.

Specified by:

train in interface Classifier

Overrides:

train in class BaseUpdateableClassifier

Parameters:

dataSet - the data set to train on

finalizeModel

public void finalizeModel()

Finalizes the current model. This prevents the model from being updated further, causing update(jsat.classifiers.DataPoint, int) to throw an exception. This finalization reduces the cost of calling classify(jsat.classifiers.DataPoint)

setUp

public void setUp(CategoricalData[] categoricalAttributes,
                  int numericAttributes,
                  CategoricalData predicting)

Description copied from interface: UpdateableClassifier

Prepares the classifier to begin learning from its UpdateableClassifier.update(jsat.classifiers.DataPoint, int) method.

Specified by:

setUp in interface UpdateableClassifier

Parameters:

categoricalAttributes - an array containing the categorical attributes that will be in each data point

numericAttributes - the number of numeric attributes that will be in each data point

predicting - the information for the target class that will be predicted

update

public void update(DataPoint dataPoint,
                   int targetClass)

Description copied from interface: UpdateableClassifier

Updates the classifier by giving it a new data point to learn from.

Specified by:

update in interface UpdateableClassifier

Parameters:

dataPoint - the data point to learn

targetClass - the target class of the data point

classify

public CategoricalResults classify(DataPoint data)

Description copied from interface: Classifier

Performs classification on the given data point.

Specified by:

classify in interface Classifier

Parameters:

data - the data point to classify

Returns:

the results of the classification.

supportsWeightedData

public boolean supportsWeightedData()

Description copied from interface: Classifier

Indicates whether the model knows how to train using weighted data points. If it does, the model will train assuming the weights. The values returned by this method may change depending on the parameters set for the model.

Specified by:

supportsWeightedData in interface Classifier

Returns:

true if the model supports weighted data, false otherwise