Package org.apache.commons.math3.distribution

Class MixtureMultivariateNormalDistribution

java.lang.Object
org.apache.commons.math3.distribution.AbstractMultivariateRealDistribution
org.apache.commons.math3.distribution.MixtureMultivariateRealDistribution<MultivariateNormalDistribution>
org.apache.commons.math3.distribution.MixtureMultivariateNormalDistribution
All Implemented Interfaces:
MultivariateRealDistribution
public class MixtureMultivariateNormalDistribution extends MixtureMultivariateRealDistribution<MultivariateNormalDistribution>
Multivariate normal mixture distribution. This class is mainly syntactic sugar.
Since:
3.2
See Also:

  • Constructor Details

    • MixtureMultivariateNormalDistribution

      public MixtureMultivariateNormalDistribution(double[] weights, double[][] means, double[][][] covariances)
      Creates a multivariate normal mixture distribution.

      Note: this constructor will implicitly create an instance of Well19937c as random generator to be used for sampling only (see MixtureMultivariateRealDistribution.sample() and AbstractMultivariateRealDistribution.sample(int)). In case no sampling is needed for the created distribution, it is advised to pass null as random generator via the appropriate constructors to avoid the additional initialisation overhead.

      Parameters:
      weights - Weights of each component.
      means - Mean vector for each component.
      covariances - Covariance matrix for each component.

    • MixtureMultivariateNormalDistribution

      public MixtureMultivariateNormalDistribution(List<Pair<Double,MultivariateNormalDistribution>> components)
      Creates a mixture model from a list of distributions and their associated weights.

      Note: this constructor will implicitly create an instance of Well19937c as random generator to be used for sampling only (see MixtureMultivariateRealDistribution.sample() and AbstractMultivariateRealDistribution.sample(int)). In case no sampling is needed for the created distribution, it is advised to pass null as random generator via the appropriate constructors to avoid the additional initialisation overhead.

      Parameters:
      components - List of (weight, distribution) pairs from which to sample.

    • MixtureMultivariateNormalDistribution

      public MixtureMultivariateNormalDistribution(RandomGenerator rng, List<Pair<Double,MultivariateNormalDistribution>> components) throws NotPositiveException, DimensionMismatchException
      Creates a mixture model from a list of distributions and their associated weights.
      Parameters:
      rng - Random number generator.
      components - Distributions from which to sample.
      Throws:
      NotPositiveException - if any of the weights is negative.
      DimensionMismatchException - if not all components have the same number of variables.