Modifier and Type	Class and Description
private static class	MultivariateNormalMixtureExpectationMaximization.DataRow Class used for sorting user-supplied data.

Modifier and Type	Field and Description
private final double[][]	data The data to fit.
private static final int	DEFAULT_MAX_ITERATIONS Default maximum number of iterations allowed per fitting process.
private static final double	DEFAULT_THRESHOLD Default convergence threshold for fitting.
private MixtureMultivariateNormalDistribution	fittedModel The model fit against the data.
private double	logLikelihood The log likelihood of the data given the fitted model.

Access	Constructor and Description
public	MultivariateNormalMixtureExpectationMaximization(double[][] Data to use in fitting procedure data) Creates an object to fit a multivariate normal mixture model to data.

Modifier and Type	Method and Description
public static MixtureMultivariateNormalDistribution	Returns: Multivariate normal mixture model estimated from the data estimate(final double[][] Data to estimate distribution data, final int Number of components for estimated mixture numComponents) Helper method to create a multivariate normal mixture model which can be used to initialize `fit(MixtureMultivariateNormalDistribution)`.
public void	fit(final MixtureMultivariateNormalDistribution Model containing initial values of weights and multivariate normals initialMixture, final int Maximum iterations allowed for fit maxIterations, final double Convergence threshold computed as difference in logLikelihoods between successive iterations threshold) Fit a mixture model to the data supplied to the constructor.
public void	fit(MixtureMultivariateNormalDistribution Model containing initial values of weights and multivariate normals initialMixture) Fit a mixture model to the data supplied to the constructor.
public MixtureMultivariateNormalDistribution	Returns: fitted model or `null` if no fit has been performed yet. getFittedModel() Gets the fitted model.
public double	Returns: Log likelihood of data or zero of no data has been fit getLogLikelihood() Gets the log likelihood of the data under the fitted model.

data	back to summary
private final double[][] data The data to fit.

DEFAULT_MAX_ITERATIONS	back to summary
private static final int DEFAULT_MAX_ITERATIONS Default maximum number of iterations allowed per fitting process.

DEFAULT_THRESHOLD	back to summary
private static final double DEFAULT_THRESHOLD Default convergence threshold for fitting.

fittedModel	back to summary
private MixtureMultivariateNormalDistribution fittedModel The model fit against the data.

logLikelihood	back to summary
private double logLikelihood The log likelihood of the data given the fitted model.

MultivariateNormalMixtureExpectationMaximization	back to summary
public MultivariateNormalMixtureExpectationMaximization(double[][] data) throws NotStrictlyPositiveException, DimensionMismatchException, NumberIsTooSmallException Creates an object to fit a multivariate normal mixture model to data. Parameters data:double[][] Data to use in fitting procedure Exceptions NotStrictlyPositiveException: if data has no rows DimensionMismatchException: if rows of data have different numbers of columns NumberIsTooSmallException: if the number of columns in the data is less than 2

Method Detail

estimate back to summary

estimate	back to summary
public static MixtureMultivariateNormalDistribution estimate(final double[][] data, final int numComponents) throws NotStrictlyPositiveException, DimensionMismatchException Helper method to create a multivariate normal mixture model which can be used to initialize `fit(MixtureMultivariateNormalDistribution)`. This method uses the data supplied to the constructor to try to determine a good mixture model at which to start the fit, but it is not guaranteed to supply a model which will find the optimal solution or even converge. Parameters data:double[][] Data to estimate distribution numComponents:int Number of components for estimated mixture Returns:MixtureMultivariateNormalDistribution Multivariate normal mixture model estimated from the data Exceptions NotStrictlyPositiveException: if data has less than 2 rows DimensionMismatchException: if rows of data have different numbers of columns NumberIsTooLargeException: if `numComponents` is greater than the number of data rows. NumberIsTooSmallException: if `numComponents < 2`.

public static MixtureMultivariateNormalDistribution estimate(final double[][] data, final int numComponents) throws NotStrictlyPositiveException, DimensionMismatchException

Helper method to create a multivariate normal mixture model which can be used to initialize fit(MixtureMultivariateNormalDistribution). This method uses the data supplied to the constructor to try to determine a good mixture model at which to start the fit, but it is not guaranteed to supply a model which will find the optimal solution or even converge.

Parameters

data:double[][]: Data to estimate distribution
numComponents:int: Number of components for estimated mixture

Returns:MixtureMultivariateNormalDistribution

Multivariate normal mixture model estimated from the data

Exceptions

NotStrictlyPositiveException:: if data has less than 2 rows
DimensionMismatchException:: if rows of data have different numbers of columns
NumberIsTooLargeException:: if numComponents is greater than the number of data rows.
NumberIsTooSmallException:: if numComponents < 2.

fit	back to summary
public void fit(final MixtureMultivariateNormalDistribution initialMixture, final int maxIterations, final double threshold) throws SingularMatrixException, NotStrictlyPositiveException, DimensionMismatchException Fit a mixture model to the data supplied to the constructor. The quality of the fit depends on the concavity of the data provided to the constructor and the initial mixture provided to this function. If the data has many local optima, multiple runs of the fitting function with different initial mixtures may be required to find the optimal solution. If a SingularMatrixException is encountered, it is possible that another initialization would work. Parameters initialMixture:MixtureMultivariateNormalDistribution Model containing initial values of weights and multivariate normals maxIterations:int Maximum iterations allowed for fit threshold:double Convergence threshold computed as difference in logLikelihoods between successive iterations Exceptions SingularMatrixException: if any component's covariance matrix is singular during fitting NotStrictlyPositiveException: if numComponents is less than one or threshold is less than Double.MIN_VALUE DimensionMismatchException: if initialMixture mean vector and data number of columns are not equal

fit

back to summary

public void fit(final MixtureMultivariateNormalDistribution initialMixture, final int maxIterations, final double threshold) throws SingularMatrixException, NotStrictlyPositiveException, DimensionMismatchException

Fit a mixture model to the data supplied to the constructor. The quality of the fit depends on the concavity of the data provided to the constructor and the initial mixture provided to this function. If the data has many local optima, multiple runs of the fitting function with different initial mixtures may be required to find the optimal solution. If a SingularMatrixException is encountered, it is possible that another initialization would work.

Parameters

initialMixture:MixtureMultivariateNormalDistribution: Model containing initial values of weights and multivariate normals
maxIterations:int: Maximum iterations allowed for fit
threshold:double: Convergence threshold computed as difference in logLikelihoods between successive iterations

Exceptions

SingularMatrixException:: if any component's covariance matrix is singular during fitting
NotStrictlyPositiveException:: if numComponents is less than one or threshold is less than Double.MIN_VALUE
DimensionMismatchException:: if initialMixture mean vector and data number of columns are not equal

fit	back to summary
public void fit(MixtureMultivariateNormalDistribution initialMixture) throws SingularMatrixException, NotStrictlyPositiveException Fit a mixture model to the data supplied to the constructor. The quality of the fit depends on the concavity of the data provided to the constructor and the initial mixture provided to this function. If the data has many local optima, multiple runs of the fitting function with different initial mixtures may be required to find the optimal solution. If a SingularMatrixException is encountered, it is possible that another initialization would work. Parameters initialMixture:MixtureMultivariateNormalDistribution Model containing initial values of weights and multivariate normals Exceptions SingularMatrixException: if any component's covariance matrix is singular during fitting NotStrictlyPositiveException: if numComponents is less than one or threshold is less than Double.MIN_VALUE

fit

back to summary

public void fit(MixtureMultivariateNormalDistribution initialMixture) throws SingularMatrixException, NotStrictlyPositiveException

Parameters

initialMixture:MixtureMultivariateNormalDistribution: Model containing initial values of weights and multivariate normals

Exceptions

SingularMatrixException:: if any component's covariance matrix is singular during fitting
NotStrictlyPositiveException:: if numComponents is less than one or threshold is less than Double.MIN_VALUE

getFittedModel back to summary

getFittedModel	back to summary
public MixtureMultivariateNormalDistribution getFittedModel() Gets the fitted model. Returns:MixtureMultivariateNormalDistribution fitted model or `null` if no fit has been performed yet.

public MixtureMultivariateNormalDistribution getFittedModel()

Gets the fitted model.

Returns:MixtureMultivariateNormalDistribution: fitted model or null if no fit has been performed yet.

getLogLikelihood	back to summary
public double getLogLikelihood() Gets the log likelihood of the data under the fitted model. Returns:double Log likelihood of data or zero of no data has been fit

getLogLikelihood

back to summary

public double getLogLikelihood()

Gets the log likelihood of the data under the fitted model.

Returns:double: Log likelihood of data or zero of no data has been fit

org.apache.commons.math3.distribution.fitting back to summary

private Class MultivariateNormalMixtureExpectationMaximization.DataRow

Class Inheritance

extends Object
implements Comparable<MultivariateNormalMixtureExpectationMaximization.DataRow>

java.lang.Object
org.apache.commons.math3.distribution.fitting.MultivariateNormalMixtureExpectationMaximization.DataRow

All Implemented Interfaces

java.lang.Comparable

Class used for sorting user-supplied data.

Field Summary

Modifier and Type	Field and Description
private Double	mean Mean of the data row.
private final double[]	row One data row.

Constructor Summary

Access	Constructor and Description
pack-priv	DataRow(final double[] Data to use for the row data) Create a data row.

Method Summary

Modifier and Type	Method and Description
public int	Returns: int for sorting compareTo(final MultivariateNormalMixtureExpectationMaximization.DataRow The other row other) Implements java.lang.Comparable.compareTo. Compare two data rows.
public boolean	equals(Object the reference object with which to compare. other) Overrides java.lang.Object.equals. Indicates whether some other object is "equal to" this one.
public double[]	Returns: data row array getRow() Get a data row.
public int	hashCode() Overrides java.lang.Object.hashCode. Returns a hash code value for this object.

Inherited from java.lang.Object:: clone finalize getClass notify notifyAll toString wait wait wait

Field Detail

mean	back to summary
private Double mean Mean of the data row.

row	back to summary
private final double[] row One data row.

Constructor Detail

DataRow	back to summary
pack-priv DataRow(final double[] data) Create a data row. Parameters data:double[] Data to use for the row

DataRow

back to summary

pack-priv DataRow(final double[] data)

Create a data row.

Parameters

data:double[]: Data to use for the row

Method Detail

compareTo	back to summary
public int compareTo(final MultivariateNormalMixtureExpectationMaximization.DataRow other) Implements java.lang.Comparable.compareTo. Compare two data rows. Parameters other:MultivariateNormalMixtureExpectationMaximization.DataRow The other row Returns:int int for sorting

compareTo

back to summary

public int compareTo(final MultivariateNormalMixtureExpectationMaximization.DataRow other)

Implements java.lang.Comparable.compareTo.

Compare two data rows.

Parameters

other:MultivariateNormalMixtureExpectationMaximization.DataRow: The other row

Returns:int

int for sorting

equals back to summary

equals	back to summary
public boolean equals(Object other) Overrides java.lang.Object.equals. Doc from java.lang.Object.equals. Indicates whether some other object is "equal to" this one. The `equals` method implements an equivalence relation on non-null object references: It is reflexive: for any non-null reference value `x`, `x.equals(x)` should return `true`. It is symmetric: for any non-null reference values `x` and `y`, `x.equals(y)` should return `true` if and only if `y.equals(x)` returns `true`. It is transitive: for any non-null reference values `x`, `y`, and `z`, if `x.equals(y)` returns `true` and `y.equals(z)` returns `true`, then `x.equals(z)` should return `true`. It is consistent: for any non-null reference values `x` and `y`, multiple invocations of `x.equals(y)` consistently return `true` or consistently return `false`, provided no information used in `equals` comparisons on the objects is modified. For any non-null reference value `x`, `x.equals(null)` should return `false`. An equivalence relation partitions the elements it operates on into equivalence classes; all the members of an equivalence class are equal to each other. Members of an equivalence class are substitutable for each other, at least for some purposes. Parameters other:Object the reference object with which to compare. Returns:boolean `true` if this object is the same as the obj argument; `false` otherwise. Annotations @Override

public boolean equals(Object other)

Overrides java.lang.Object.equals.

Doc from java.lang.Object.equals.

Indicates whether some other object is "equal to" this one.

The equals method implements an equivalence relation on non-null object references:

It is reflexive: for any non-null reference value x, x.equals(x) should return true.
It is symmetric: for any non-null reference values x and y, x.equals(y) should return true if and only if y.equals(x) returns true.
It is transitive: for any non-null reference values x, y, and z, if x.equals(y) returns true and y.equals(z) returns true, then x.equals(z) should return true.
It is consistent: for any non-null reference values x and y, multiple invocations of x.equals(y) consistently return true or consistently return false, provided no information used in equals comparisons on the objects is modified.
For any non-null reference value x, x.equals(null) should return false.

An equivalence relation partitions the elements it operates on into equivalence classes; all the members of an equivalence class are equal to each other. Members of an equivalence class are substitutable for each other, at least for some purposes.

Parameters

other:Object: the reference object with which to compare.

Returns:boolean

true if this object is the same as the obj argument; false otherwise.

Annotations

@Override

getRow	back to summary
public double[] getRow() Get a data row. Returns:double[] data row array

getRow

back to summary

public double[] getRow()

Get a data row.

Returns:double[]: data row array

hashCode back to summary

hashCode	back to summary
public int hashCode() Overrides java.lang.Object.hashCode. Doc from java.lang.Object.hashCode. Returns a hash code value for this object. This method is supported for the benefit of hash tables such as those provided by `java.util.HashMap`. The general contract of `hashCode` is: Whenever it is invoked on the same object more than once during an execution of a Java application, the `hashCode` method must consistently return the same integer, provided no information used in `equals` comparisons on the object is modified. This integer need not remain consistent from one execution of an application to another execution of the same application. If two objects are equal according to the `equals` method, then calling the `hashCode` method on each of the two objects must produce the same integer result. It is not required that if two objects are unequal according to the `equals` method, then calling the `hashCode` method on each of the two objects must produce distinct integer results. However, the programmer should be aware that producing distinct integer results for unequal objects may improve the performance of hash tables. Returns:int a hash code value for this object Annotations @Override

public int hashCode()

Overrides java.lang.Object.hashCode.

Doc from java.lang.Object.hashCode.

Returns a hash code value for this object. This method is supported for the benefit of hash tables such as those provided by java.util.HashMap.

The general contract of hashCode is:

Whenever it is invoked on the same object more than once during an execution of a Java application, the hashCode method must consistently return the same integer, provided no information used in equals comparisons on the object is modified. This integer need not remain consistent from one execution of an application to another execution of the same application.
If two objects are equal according to the equals method, then calling the hashCode method on each of the two objects must produce the same integer result.
It is not required that if two objects are unequal according to the equals method, then calling the hashCode method on each of the two objects must produce distinct integer results. However, the programmer should be aware that producing distinct integer results for unequal objects may improve the performance of hash tables.

Returns:int

a hash code value for this object

Annotations

@Override

public Class MultivariateNormalMixtureExpectationMaximization

Nested and Inner Type Summary

Field Summary

Constructor Summary

Method Summary

Field Detail

Constructor Detail

Method Detail

private Class MultivariateNormalMixtureExpectationMaximization.DataRow

Field Summary

Constructor Summary

Method Summary

Field Detail

Constructor Detail

Method Detail