Package com.amazon.randomcutforest.testutils

Class NormalMixtureTestData

java.lang.Object

com.amazon.randomcutforest.testutils.NormalMixtureTestData

public class NormalMixtureTestData
extends Object

This class samples point from a mixture of 2 multi-variate normal distribution with covariance matrices of the form sigma * I. One of the normal distributions is considered the base distribution, the second is considered the anomaly distribution, and there are random transitions between the two.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	NormalMixtureTestData.NormalDistribution

Constructor Summary

Constructors

Constructor	Description
NormalMixtureTestData()
NormalMixtureTestData(double baseMu, double anomalyMu)
NormalMixtureTestData(double baseMu, double baseSigma, double anomalyMu, double anomalySigma, double transitionToAnomalyProbability, double transitionToBaseProbability)

Method Summary

Modifier and Type	Method	Description
double[][]	generateTestData(int numberOfRows, int numberOfColumns)
double[][]	generateTestData(int numberOfRows, int numberOfColumns, int seed)
MultiDimDataWithKey	generateTestDataWithKey(int numberOfRows, int numberOfColumns, int seed)

Methods inherited from class java.lang.Object

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

Constructor Details

NormalMixtureTestData

public NormalMixtureTestData(double baseMu,
 double baseSigma,
 double anomalyMu,
 double anomalySigma,
 double transitionToAnomalyProbability,
 double transitionToBaseProbability)

NormalMixtureTestData

public NormalMixtureTestData()

NormalMixtureTestData

public NormalMixtureTestData(double baseMu,
 double anomalyMu)

Method Details

generateTestData

public double[][] generateTestData(int numberOfRows,
 int numberOfColumns)

generateTestData

public double[][] generateTestData(int numberOfRows,
 int numberOfColumns,
 int seed)

generateTestDataWithKey

public MultiDimDataWithKey generateTestDataWithKey(int numberOfRows,
 int numberOfColumns,
 int seed)