jsat.classifiers.bayesian

Class ODE

java.lang.Object

jsat.classifiers.BaseUpdateableClassifier

jsat.classifiers.bayesian.ODE

All Implemented Interfaces:

Serializable, Cloneable, Classifier, UpdateableClassifier

public class ODE
extends BaseUpdateableClassifier

One-Dependence Estimators (ODE) is an extension of Naive Bayes that, instead of assuming all features are independent, assumes all features are dependent on one other feature besides the target class. Because of this extra dependence requirement, the implementation only allows for categorical features.
This class is primarily for use by AODE

See: Webb, G., & Boughton, J. (2005). Not so naive bayes: Aggregating one-dependence estimators. Machine Learning, 1–24. Retrieved from here

Author:

Edward Raff

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected double[][][][]	counts First index is the number of target values 2nd index is the number of values for the dependent variable 3rd is the number of categorical variables, including the dependent one 4th is the count for the variable value
protected int	dependent The attribute we will be dependent on
protected int	depTargets The number of possible values for the dependent variable
protected int	predTargets The number of possible values in the target class
protected double[][]	priors The prior probability of each combination of target and dependent variable
protected double	priorSum

Constructor Summary

Constructors

Modifier	Constructor and Description
	ODE(int dependent) Creates a new ODE classifier
protected	ODE(ODE toClone) Copy constructor

Method Summary

Modifier and Type	Method and Description
CategoricalResults	classify(DataPoint data) Performs classification on the given data point.
ODE	clone()
protected double	getLogPrb(int[] catVals, int c)
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	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, trainC, trainC, trainEpochs

Methods inherited from class java.lang.Object

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

Field Detail

dependent

protected int dependent

The attribute we will be dependent on

predTargets

protected int predTargets

The number of possible values in the target class

depTargets

protected int depTargets

The number of possible values for the dependent variable

counts

protected double[][][][] counts

First index is the number of target values
2nd index is the number of values for the dependent variable
3rd is the number of categorical variables, including the dependent one
4th is the count for the variable value

priors

protected double[][] priors

The prior probability of each combination of target and dependent variable

priorSum

protected double priorSum

Constructor Detail

ODE

public ODE(int dependent)

Creates a new ODE classifier

Parameters:

dependent - the categorical feature to be dependent of

ODE

protected ODE(ODE toClone)

Copy constructor

Parameters:

toClone - the ODE to copy

Method Detail

classify

public CategoricalResults classify(DataPoint data)

Description copied from interface: Classifier

Performs classification on the given data point.

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.

Returns:

true if the model supports weighted data, false otherwise

clone

public ODE clone()

Specified by:

clone in interface Classifier

Specified by:

clone in interface UpdateableClassifier

Specified by:

clone in class BaseUpdateableClassifier

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.

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.

Parameters:

dataPoint - the data point to learn

targetClass - the target class of the data point

getLogPrb

protected double getLogPrb(int[] catVals,
                           int c)

Parameters:

catVals - the catigorical values for a data point

c - the target value to get the probability of

Returns:

the non normalized log probability of the data point belonging to the target class c