org.apache.spark.mllib.clustering

Class GaussianMixtureModel

java.lang.Object

org.apache.spark.mllib.clustering.GaussianMixtureModel

All Implemented Interfaces:

java.io.Serializable, Saveable

public class GaussianMixtureModel
extends java.lang.Object
implements scala.Serializable, Saveable

Multivariate Gaussian Mixture Model (GMM) consisting of k Gaussians, where points are drawn from each Gaussian i=1..k with probability w(i); mu(i) and sigma(i) are the respective mean and covariance for each Gaussian distribution i=1..k.

param: weights Weights for each Gaussian distribution in the mixture, where weights(i) is the weight for Gaussian i, and weights.sum == 1 param: gaussians Array of MultivariateGaussian where gaussians(i) represents the Multivariate Gaussian (Normal) Distribution for Gaussian i

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
GaussianMixtureModel(double[] weights, MultivariateGaussian[] gaussians)

Method Summary

Methods

Modifier and Type	Method and Description
protected java.lang.String	formatVersion() Current version of model save/load format.
MultivariateGaussian[]	gaussians()
int	k() Number of gaussians in mixture
static GaussianMixtureModel	load(SparkContext sc, java.lang.String path)
JavaRDD<java.lang.Integer>	predict(JavaRDD<Vector> points) Java-friendly version of predict()
RDD<java.lang.Object>	predict(RDD<Vector> points) Maps given points to their cluster indices.
int	predict(Vector point) Maps given point to its cluster index.
RDD<double[]>	predictSoft(RDD<Vector> points) Given the input vectors, return the membership value of each vector to all mixture components.
double[]	predictSoft(Vector point) Given the input vector, return the membership values to all mixture components.
void	save(SparkContext sc, java.lang.String path) Save this model to the given path.
double[]	weights()

Methods inherited from class java.lang.Object

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

Constructor Detail

GaussianMixtureModel

public GaussianMixtureModel(double[] weights,
                    MultivariateGaussian[] gaussians)

Method Detail

load

public static GaussianMixtureModel load(SparkContext sc,
                        java.lang.String path)

weights

public double[] weights()

gaussians

public MultivariateGaussian[] gaussians()

formatVersion

protected java.lang.String formatVersion()

Description copied from interface: Saveable

Current version of model save/load format.

Specified by:

formatVersion in interface Saveable

save

public void save(SparkContext sc,
        java.lang.String path)

Description copied from interface: Saveable

Save this model to the given path.

This saves: - human-readable (JSON) model metadata to path/metadata/ - Parquet formatted data to path/data/

The model may be loaded using Loader.load.

Specified by:

save in interface Saveable

Parameters:

sc - Spark context used to save model data.

path - Path specifying the directory in which to save this model. If the directory already exists, this method throws an exception.

k

public int k()

Number of gaussians in mixture

Returns:

(undocumented)

predict

public RDD<java.lang.Object> predict(RDD<Vector> points)

Maps given points to their cluster indices.

Parameters:

points - (undocumented)

Returns:

(undocumented)

predict

public int predict(Vector point)

Maps given point to its cluster index.

Parameters:

point - (undocumented)

Returns:

(undocumented)

predict

public JavaRDD<java.lang.Integer> predict(JavaRDD<Vector> points)

Java-friendly version of predict()

Parameters:

points - (undocumented)

Returns:

(undocumented)

predictSoft

public RDD<double[]> predictSoft(RDD<Vector> points)

Given the input vectors, return the membership value of each vector to all mixture components.

Parameters:

points - (undocumented)

Returns:

(undocumented)

predictSoft

public double[] predictSoft(Vector point)

Given the input vector, return the membership values to all mixture components.

Parameters:

point - (undocumented)

Returns:

(undocumented)