Package org.apache.spark.ml.stat.distribution

Class MultivariateGaussian

Object

org.apache.spark.ml.stat.distribution.MultivariateGaussian

All Implemented Interfaces:

Serializable

public class MultivariateGaussian
extends Object
implements Serializable

This class provides basic functionality for a Multivariate Gaussian (Normal) Distribution. In the event that the covariance matrix is singular, the density will be computed in a reduced dimensional subspace under which the distribution is supported. (see here)

param: mean The mean vector of the distribution param: cov The covariance matrix of the distribution

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
MultivariateGaussian(Vector mean, Matrix cov)

Method Summary

Modifier and Type	Method	Description
Matrix	cov()
double	logpdf(Vector x)	Returns the log-density of this multivariate Gaussian at given point, x
Vector	mean()
double	pdf(Vector x)	Returns density of this multivariate Gaussian at given point, x

Methods inherited from class java.lang.Object

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

Constructor Details

MultivariateGaussian

public MultivariateGaussian(Vector mean,
 Matrix cov)

Method Details

cov

public Matrix cov()

logpdf

public double logpdf(Vector x)

Returns the log-density of this multivariate Gaussian at given point, x

Parameters:

x - (undocumented)

Returns:

(undocumented)

mean

public Vector mean()

pdf

public double pdf(Vector x)

Returns density of this multivariate Gaussian at given point, x

Parameters:

x - (undocumented)

Returns:

(undocumented)