test9.cpp File Reference

---

Detailed Description

Test of DensityTreePdf.

This test:

• creates a random multivariate Gaussian mixture,
• samples from this mixture and constructs a density tree,
• compares the mean and covariance of the density tree with that of the original mixture.
• directly samples from the density tree and compares the mean and covariance of this sample set with that of the original mixture.
• importance samples from the density tree using a single Gaussian fit to the original mixture and compares the mean and covariance of this sample set with that of the original mixture.

Results are as follows:

Mixture mean
[2](0.295305,0.261496)
Mixture covariance
[2,2]((0.728494,-0.0597473),(-0.0597473,0.938613))
Sample mean
[2](0.294434,0.261816)
Sample covariance
[2,2]((0.728574,-0.0593636),(-0.0593636,0.938486))
Density tree mean
[2](0.298064,0.274742)
Density tree covariance
[2,2]((0.888996,-0.0492226),(-0.0492226,1.12449))
Density tree sample mean
[2](0.299049,0.274198)
Density tree sample covariance
[2,2]((0.890722,-0.0633334),(-0.0633334,1.1234))
Density tree importance sample mean
[2](0.385459,0.213461)
Density tree importance sample covariance
[2,2]((1.63716,-0.159855),(-0.159855,2.25733))

Original Gaussian mixture

Density tree approximation

Definition in file test9.cpp.

Go to the source code of this file.

Functions
aux::GaussianPdf	createRandomGaussian (const unsigned int M, const double minMean=-1.0, const double maxMean=1.0, const double minCov=-1.0, const double maxCov=1.0)
	Create random Gaussian distribution.
int	main (int argc, const char *argv[])
	Run tests.
Variables
unsigned int	M = 2
	Dimensionality of the distribution.
unsigned int	COMPONENTS = 4
	Number of components in the Gaussian mixture.
unsigned int	P = 1000000
	Number of samples to take.
unsigned int	RES = 200
	Resolution of plots.

---

Function Documentation

aux::GaussianPdf createRandomGaussian	(	const unsigned int	M,
		const double	minMean = -1.0,
		const double	maxMean = 1.0,
		const double	minCov = -1.0,
		const double	maxCov = 1.0
	)

Create random Gaussian distribution.

Parameters:

	M	Dimensionality of the Gaussian.
	minMean	Minimum value of any component of the mean.
	maxMean	Maximum value of any component of the mean.
	minCov	Minimum value of any component of the covariance.
	maxCov	Maximum value of any component of the covariance.

Returns:

Gaussian with given dimensionality, with mean and covariance randomly generated uniformly from within the given bounds.

Definition at line 78 of file test9.cpp.

int main	(	int	argc,
		const char *	argv[]
	)

Run tests.

Definition at line 106 of file test9.cpp.

---

Variable Documentation

unsigned int COMPONENTS = 4

Number of components in the Gaussian mixture.

Definition at line 53 of file test9.cpp.

unsigned int M = 2

Dimensionality of the distribution.

Definition at line 48 of file test9.cpp.

unsigned int P = 1000000

Number of samples to take.

Definition at line 58 of file test9.cpp.

unsigned int RES = 200

Resolution of plots.

Definition at line 63 of file test9.cpp.

---