#include "gstlearn_export.hpp"
#include "Matrix/MatrixSquareSymmetric.hpp"
#include "Basic/VectorNumT.hpp"

Functions
GSTLEARN_EXPORT void	law_set_old_style (bool style)

GSTLEARN_EXPORT int	law_get_random_seed (void)

GSTLEARN_EXPORT void	law_set_random_seed (int seed)

GSTLEARN_EXPORT double	law_uniform (double mini=0., double maxi=1.)

GSTLEARN_EXPORT int	law_int_uniform (int mini, int maxi)

GSTLEARN_EXPORT double	law_gaussian (double mean=0., double sigma=1.)

GSTLEARN_EXPORT double	law_exponential (double lambda=1.)

GSTLEARN_EXPORT double	law_gamma (double alpha, double beta=1.)

GSTLEARN_EXPORT double	law_df_poisson (int i, double parameter)

GSTLEARN_EXPORT VectorDouble	law_df_poisson_vec (VectorInt is, double parameter)

GSTLEARN_EXPORT int	law_poisson (double parameter)

GSTLEARN_EXPORT double	law_stable_standard_agd (double alpha, double beta)

GSTLEARN_EXPORT double	law_stable_standard_a1gd (double beta)

GSTLEARN_EXPORT double	law_stable_standard_abgd (double alpha)

GSTLEARN_EXPORT double	law_stable_a (double alpha, double beta, double gamma, double delta)

GSTLEARN_EXPORT double	law_stable_a1 (double beta, double gamma, double delta)

GSTLEARN_EXPORT double	law_stable (double alpha, double beta, double gamma, double delta)

GSTLEARN_EXPORT int	law_binomial (int n, double p)

GSTLEARN_EXPORT double	law_beta1 (double parameter1, double parameter2)

GSTLEARN_EXPORT double	law_beta2 (double parameter1, double parameter2)

GSTLEARN_EXPORT double	law_df_gaussian (double value)

GSTLEARN_EXPORT double	law_dnorm (double value, double mean, double std)

GSTLEARN_EXPORT double	law_cdf_gaussian (double value)

GSTLEARN_EXPORT double	law_invcdf_gaussian (double value)

GSTLEARN_EXPORT double	law_gaussian_between_bounds (double binf, double bsup)

GSTLEARN_EXPORT double	law_df_bigaussian (VectorDouble &vect, VectorDouble &mean, MatrixSquareSymmetric &correl)

GSTLEARN_EXPORT double	law_df_quadgaussian (VectorDouble &vect, MatrixSquareSymmetric &correl)

GSTLEARN_EXPORT double	law_df_multigaussian (VectorDouble &vect, MatrixSquareSymmetric &correl)

GSTLEARN_EXPORT VectorInt	law_random_path (int nech)

GSTLEARN_EXPORT VectorDouble	law_exp_sample (const double tabin, int mode, int nvar, int nechin, int nechout, int niter, int nconst, double consts, int seed, double percent)

GSTLEARN_EXPORT int	sampleInteger (int minit, int maxi)

Function Documentation

◆ law_beta1()

GSTLEARN_EXPORT double law_beta1	(	double	parameter1,
		double	parameter2
	)

Generate random numbers according to a beta distribution (first kind)

Returns: Beta random value (first kind)

Parameters

[in]	parameter1	first parameter of the beta distribution
[in]	parameter2	first parameter of the beta distribution

◆ law_beta2()

GSTLEARN_EXPORT double law_beta2	(	double	parameter1,
		double	parameter2
	)

Generate random numbers according to a beta distribution (second kind)

Returns: Beta random value (second kind)

Parameters

[in]	parameter1	first parameter of the beta distribution
[in]	parameter2	first parameter of the beta distribution

◆ law_binomial()

GSTLEARN_EXPORT int law_binomial	(	int	n,
		double	p
	)

Generates a binomial value

Returns: The binomial value

Parameters

[in]	n	Number of trials
[in]	p	Event probability

◆ law_cdf_gaussian()

GSTLEARN_EXPORT double law_cdf_gaussian ( double value )

Cumulated density function of a gaussian distribution

Returns: Gaussian cumulated density function

Parameters

[in] value raw value

Remarks: Handbook P932 (26.2.17) precision <7.5 E-08

◆ law_df_bigaussian()

GSTLEARN_EXPORT double law_df_bigaussian	(	VectorDouble &	vect,
		VectorDouble &	mean,
		MatrixSquareSymmetric &	correl
	)

Density function of a bigaussian distribution

Returns: Gaussian density function

Parameters

[in]	vect	Array of values (Dimension = 2)
[in]	mean	Array of means (Dimension = 2)
[in]	correl	Correlation matrix (Dimension: 2*2)

◆ law_df_gaussian()

GSTLEARN_EXPORT double law_df_gaussian ( double value )

Density function of a gaussian distribution

Returns: Gaussian density function

Parameters

[in] value raw value

◆ law_df_multigaussian()

GSTLEARN_EXPORT double law_df_multigaussian	(	VectorDouble &	vect,
		MatrixSquareSymmetric &	correl
	)

Density function of a multigaussian distribution

Returns: Gaussian density function

Parameters

[in]	vect	Array of values (Dimension = nvar)
[in]	correl	Correlation matrix (Dimension: nvar*nvar)

◆ law_df_poisson()

GSTLEARN_EXPORT double law_df_poisson	(	int	i,
		double	parameter
	)

◆ law_df_poisson_vec()

GSTLEARN_EXPORT VectorDouble law_df_poisson_vec	(	VectorInt	is,
		double	parameter
	)

◆ law_df_quadgaussian()

GSTLEARN_EXPORT double law_df_quadgaussian	(	VectorDouble &	vect,
		MatrixSquareSymmetric &	correl
	)

Density function of a quadrigaussian distribution

Returns: Gaussian density function

Parameters

[in]	vect	Array of values (Dimension = nvar)
[in]	correl	Correlation matrix (Dimension: nvar*nvar)

◆ law_dnorm()

GSTLEARN_EXPORT double law_dnorm	(	double	value,
		double	mean,
		double	std
	)

Density function of a (non-normalized) gaussian distribution

Returns: Gaussian density function

Parameters

[in]	value	Raw value
[in]	mean	Mean value
[in]	std	Standard deviation

◆ law_exp_sample()

GSTLEARN_EXPORT VectorDouble law_exp_sample	(	const double *	tabin,
		int	mode,
		int	nvar,
		int	nechin,
		int	nechout,
		int	niter,
		int	nconst,
		double *	consts,
		int	seed,
		double	percent
	)

Sample a multivariate empirical distribution

Returns: Address to the newly created array

Parameters

[in]	tabin	Input array
[in]	mode	Describes the way 'tabin' and 'tabout' are filled 1: by column; 2: by row
[in]	nvar	Number of variables (input and output)
[in]	nechin	Number of samples in the input array
[in]	nechout	Number of created samples
[in]	niter	Maximum number of iterations
[in]	nconst	Number of constraints
[in]	consts	Array of constraints (optional) (Dimension: nconst * (nvar+1)) This array is entered by line
[in]	seed	Value for the seed generator
[in]	percent	Dimension of the convolution kernel expressed as a percentage of the dispersion st. dev. Should be between 0 and 100

Remarks: The input array must be isotopic (otherwise, an error is issued); The resulting VectorDouble if dimensionned to nvar * nechout; Consider nvar1 = nvar + 1; Sample temp[1:nvar1] is authorized for Constraint 'iconst' if:; Sum_ivar1^{1:nvar1) consts[iconst,ivar1) * temp[ivar1] > 0

◆ law_exponential()

GSTLEARN_EXPORT double law_exponential ( double lambda )

Generate random numbers according to exponential distribution

Returns: Exponential random value

Parameters

[in] lambda Parameter of exponential distribution

◆ law_gamma()

GSTLEARN_EXPORT double law_gamma	(	double	alpha,
		double	beta
	)

Generate random numbers according to a gamma distribution

Returns: Gamma random value

Parameters

[in]	alpha	parameter of the gamma distribution
[in]	beta	Second parameter of the Gamma distribution

◆ law_gaussian()

GSTLEARN_EXPORT double law_gaussian	(	double	mean,
		double	sigma
	)

Generate random numbers according to a gaussian distribution

Returns: Gaussian random value

Parameters

[in]	mean	Mean of the Normal Distribution
[in]	sigma	Standard deviation of the Normal Distribution

◆ law_gaussian_between_bounds()

GSTLEARN_EXPORT double law_gaussian_between_bounds	(	double	binf,
		double	bsup
	)

Generates a gaussian value which lies in an interval

Returns: The gaussian value

Parameters

[in]	binf	lower bound of the interval
[in]	bsup	upper bound of the interval

◆ law_get_random_seed()

GSTLEARN_EXPORT int law_get_random_seed ( void )

read the seed for the random number generator

Returns: The current value of the seed (integer)

◆ law_int_uniform()

GSTLEARN_EXPORT int law_int_uniform	(	int	mini,
		int	maxi
	)

Draw an integer random number according to a uniform distribution

Returns: Integer Uniform random value within an interval

Parameters

[in]	mini	minimum value
[in]	maxi	maximum value

◆ law_invcdf_gaussian()

GSTLEARN_EXPORT double law_invcdf_gaussian ( double value )

Inverse cumulated density function of a gaussian distribution

Returns: Inverse of gaussian cumulated density function

Parameters

[in] value cumulative density

◆ law_poisson()

GSTLEARN_EXPORT int law_poisson ( double parameter )

Generate random number according to a poisson distribution

Returns: Poisson random value

Parameters

[in] parameter parameter of the Poisson distribution

Remarks: Method Ahrens-Dieter (1973)

◆ law_random_path()

GSTLEARN_EXPORT VectorInt law_random_path ( int nech )

Define a random path

Parameters

[in] nech : Number of samples

◆ law_set_old_style()

GSTLEARN_EXPORT void law_set_old_style ( bool style )

Set the type of Usage for Random Number Generation

Parameters

style true for using Old Style; false for using New Style

◆ law_set_random_seed()

GSTLEARN_EXPORT void law_set_random_seed ( int seed )

Sets the seed for the random number generator

Parameters

[in] seed the new value given to the seed

◆ law_stable()

GSTLEARN_EXPORT double law_stable	(	double	alpha,
		double	beta,
		double	gamma,
		double	delta
	)

Generate random numbers according to a stable distribution

Returns: Stable value with unit parameters

Parameters

[in]	alpha	value of the alpha parameter
[in]	beta	value of the beta parameter
[in]	gamma	value of the gamma parameter
[in]	delta	value of the delta parameter

◆ law_stable_a()

GSTLEARN_EXPORT double law_stable_a	(	double	alpha,
		double	beta,
		double	gamma,
		double	delta
	)

Generate random numbers according to a stable distribution (alpha != 1)

Returns: Stable value with unit parameters

Parameters

[in]	alpha	value of the alpha parameter
[in]	beta	value of the beta parameter
[in]	gamma	value of the gamma parameter
[in]	delta	value of the delta parameter

◆ law_stable_a1()

GSTLEARN_EXPORT double law_stable_a1	(	double	beta,
		double	gamma,
		double	delta
	)

Generate random numbers according to a stable distribution (alpha=1)

Returns: Stable value with unit parameters

Parameters

[in]	beta	value of the beta parameter
[in]	gamma	value of the gamma parameter
[in]	delta	value of the delta parameter

◆ law_stable_standard_a1gd()

GSTLEARN_EXPORT double law_stable_standard_a1gd ( double beta )

Generate random numbers according to a standard stable distribution (alpha=1)

Returns: Stable value with standard parameters (alpha=gamma=1,delta=0)

Parameters

[in] beta value of the beta parameter

◆ law_stable_standard_abgd()

GSTLEARN_EXPORT double law_stable_standard_abgd ( double alpha )

Generate random numbers according to a standard stable distribution

Returns: Stable value with std. parameters (beta=gamma=1,delta=0,alpha!=1)

Parameters

[in] alpha value of the alpha parameter

◆ law_stable_standard_agd()

GSTLEARN_EXPORT double law_stable_standard_agd	(	double	alpha,
		double	beta
	)

Generate random numbers according to a standard stable distribution

Returns: Stable value with standard parameters (gamma=1,delta=0,alpha!=1)

Parameters

[in]	alpha	value of the alpha parameter
[in]	beta	value of the beta parameter

◆ law_uniform()

GSTLEARN_EXPORT double law_uniform	(	double	mini,
		double	maxi
	)

Draw a random number according to a uniform distribution

Returns: Uniform random value within an interval

Parameters

[in]	mini	minimum value
[in]	maxi	maximum value

◆ sampleInteger()

GSTLEARN_EXPORT int sampleInteger	(	int	mini,
		int	maxi
	)

Returns an integer sampled uniformly wihtin the interval [mini, maxi]

Parameters

mini	Lower bound (included)
maxi	Upper bound (included)

Functions

Function Documentation

◆ law_beta1()

◆ law_beta2()

◆ law_binomial()

◆ law_cdf_gaussian()

◆ law_df_bigaussian()

◆ law_df_gaussian()

◆ law_df_multigaussian()

◆ law_df_poisson()

◆ law_df_poisson_vec()

◆ law_df_quadgaussian()

◆ law_dnorm()

◆ law_exp_sample()

◆ law_exponential()

◆ law_gamma()

◆ law_gaussian()

◆ law_gaussian_between_bounds()

◆ law_get_random_seed()

◆ law_int_uniform()

◆ law_invcdf_gaussian()

◆ law_poisson()

◆ law_random_path()

◆ law_set_old_style()

◆ law_set_random_seed()

◆ law_stable()

◆ law_stable_a()

◆ law_stable_a1()

◆ law_stable_standard_a1gd()

◆ law_stable_standard_abgd()

◆ law_stable_standard_agd()

◆ law_uniform()

◆ sampleInteger()