jsat.distributions.multivariate

Interface MultivariateDistribution

All Superinterfaces:

java.lang.Cloneable, java.io.Serializable

All Known Implementing Classes:

Dirichlet, EMGaussianMixture, MetricKDE, MultivariateDistributionSkeleton, MultivariateKDE, NormalM, NormalMR, ProductKDE, SymmetricDirichlet

public interface MultivariateDistribution
extends java.lang.Cloneable, java.io.Serializable

This interface represents the contract that any continuous multivariate distribution must implement

Method Summary

Modifier and Type	Method and Description
MultivariateDistribution	clone()
default double	logPdf(double... x) Computes the log of the probability density function.
double	logPdf(Vec x) Computes the log of the probability density function.
default double	pdf(double... x) Returns the probability of a given vector from this distribution.
default double	pdf(Vec x) Returns the probability of a given vector from this distribution.
java.util.List<Vec>	sample(int count, java.util.Random rand) Performs sampling on the current distribution.
default boolean	setUsingData(DataSet dataSet) Sets the parameters of the distribution to attempt to fit the given list of data points.
default boolean	setUsingData(DataSet dataSet, boolean parallel) Sets the parameters of the distribution to attempt to fit the given list of data points.
default <V extends Vec> boolean	setUsingData(java.util.List<V> dataSet) Sets the parameters of the distribution to attempt to fit the given list of vectors.
<V extends Vec> boolean	setUsingData(java.util.List<V> dataSet, boolean parallel) Sets the parameters of the distribution to attempt to fit the given list of vectors.
default boolean	setUsingDataList(java.util.List<DataPoint> dataPoints) Sets the parameters of the distribution to attempt to fit the given list of data points.

Method Detail

logPdf

default double logPdf(double... x)

Computes the log of the probability density function. If the probability of the input is zero, the log of zero would be Double.NEGATIVE_INFINITY. Instead, -Double.MAX_VALUE is returned.

Parameters:

x - the array for the vector the get the log probability of

Returns:

the log of the probability.

Throws:

java.lang.ArithmeticException - if the vector is not the correct length, or the distribution has not yet been set

logPdf

double logPdf(Vec x)

Computes the log of the probability density function. If the probability of the input is zero, the log of zero would be Double.NEGATIVE_INFINITY. Instead, -Double.MAX_VALUE is returned.

Parameters:

x - the vector the get the log probability of

Returns:

the log of the probability.

Throws:

java.lang.ArithmeticException - if the vector is not the correct length, or the distribution has not yet been set

pdf

default double pdf(double... x)

Returns the probability of a given vector from this distribution. By definition, the probability will always be in the range [0, 1].

Parameters:

x - the array of the vector the get the log probability of

Returns:

the probability

Throws:

java.lang.ArithmeticException - if the vector is not the correct length, or the distribution has not yet been set

pdf

default double pdf(Vec x)

Returns the probability of a given vector from this distribution. By definition, the probability will always be in the range [0, 1].

Parameters:

x - the vector the get the log probability of

Returns:

the probability

Throws:

java.lang.ArithmeticException - if the vector is not the correct length, or the distribution has not yet been set

setUsingData

default <V extends Vec> boolean setUsingData(java.util.List<V> dataSet)

Sets the parameters of the distribution to attempt to fit the given list of vectors. All vectors are assumed to have the same weight.

Type Parameters:

V - the vector type

Parameters:

dataSet - the list of data points

Returns:

true if the distribution was fit to the data, or false if the distribution could not be fit to the data set.

setUsingData

<V extends Vec> boolean setUsingData(java.util.List<V> dataSet,
                                     boolean parallel)

Sets the parameters of the distribution to attempt to fit the given list of vectors. All vectors are assumed to have the same weight.

Type Parameters:

V - the vector type

Parameters:

dataSet - the list of data points

parallel - true if the training should be done using multiple-cores, false for single threaded.

Returns:

true if the distribution was fit to the data, or false if the distribution could not be fit to the data set.

setUsingDataList

default boolean setUsingDataList(java.util.List<DataPoint> dataPoints)

Sets the parameters of the distribution to attempt to fit the given list of data points. The weights of the data points will be used.

Parameters:

dataPoints - the list of data points to use

Returns:

true if the distribution was fit to the data, or false if the distribution could not be fit to the data set.

setUsingData

default boolean setUsingData(DataSet dataSet)

Sets the parameters of the distribution to attempt to fit the given list of data points. The weights of the data points will be used.

Parameters:

dataSet - the data set to use

Returns:

true if the distribution was fit to the data, or false if the distribution could not be fit to the data set.

setUsingData

default boolean setUsingData(DataSet dataSet,
                             boolean parallel)

Sets the parameters of the distribution to attempt to fit the given list of data points. The weights of the data points will be used.

Parameters:

dataSet - the data set to use

parallel - the source of threads for computation

Returns:

true if the distribution was fit to the data, or false if the distribution could not be fit to the data set.

clone

MultivariateDistribution clone()

sample

java.util.List<Vec> sample(int count,
                           java.util.Random rand)

Performs sampling on the current distribution.

Parameters:

count - the number of iid samples to draw

rand - the source of randomness

Returns:

a list of sample vectors from this distribution