table of contents
GBRAND(1) | User Commands | GBRAND(1) |
NAME¶
gbrand - Sampling from random distributions
SYNOPSIS¶
gbrand [options] NAME PARAMETERS...
DESCRIPTION¶
Generates a grid of i.i.d. samples from a distribution. The name of the distribution and its parameters are specified on the command line. the column index. Indeces start from 1. If more than one function are provided they are printed one after the other. The type of random number generator and the default seed can be set with the environment variables GSL_RNG_TYPE and GSL_RNG_SEED, respectively, as documented in GSL manual.
OPTIONS¶
- -r
- specify number of rows (default 1)
- -c
- specify number of columns (default 1)
- -R
- set the seed (default 1)
- -v
- verbose mode
- -h
- this help
List of valid distributions (with parameters):¶
- beta
- a,b = shape parameters
- binomial
- p = probability, N = number of trials
- bivariate-gaussian
- sigmax = x std.dev., sigmay = y std.dev., rho = correlation
- cauchy
- a = scale parameter
- chisq
- nu = degrees of freedom
- dir-2d
- none
- dir-3d
- none
- dir-nd
- n1 = number of dimensions of hypersphere
- erlang
- a = scale parameter, b = order
- exponential
- mu = mean value
- exppow
- a = scale parameter, b = power (1=exponential, 2=gaussian)
- aexppow
- m = mode, al = left scale, ar = right scale, bl = left shape, br = right shape
- fdist
- nu1, nu2 = degrees of freedom parameters
- flat
- a = lower limit, b = upper limit
- gamma
- a = order, b = scale
- gaussian-tail
- a = lower limit, sigma = standard deviation
- gaussian
- sigma = standard deviation
- geometric
- p = bernoulli trial probability of success
- gumbel1
- a = order, b = scale parameter
- gumbel2
- a = order, b = scale parameter
- hypergeometric
- n1 = # tagged, n2 = # untagged, t = number of trials
- laplace
- a = scale parameter
- landau
- none
- levy
- c = scale, a = power (1=cauchy, 2=gaussian)
- levy-skew
- c = scale, a = power (1=cauchy, 2=gaussian), b = skew
- logarithmic
- p = probability
- logistic
- a = scale parameter
- lognormal
- zeta = location parameter, sigma = scale parameter
- negative-binomial
- p = probability, a = order
- pareto
- a = power, b = scale parameter
- pascal
- p = probability, n = order (integer)
- poisson
- mu = scale parameter
- rayleigh-tail
- a = lower limit, sigma = scale parameter
- rayleigh
- sigma = scale parameter
- tdist
- nu = degrees of freedom
- ugaussian-tail
- a = lower limit
- ugaussian
- none
- weibull
- a = scale parameter, b = exponent
- pareto3
- a = power, b = exponential parameter, s = scale parameter
EXAMPLES¶
- gbrand -c 2 -r 100 gaussian 2.5
- generate two columns of 100 rows each sampling from a Gaussian distribution with mean 0 and standard deviation 2.5
- gbrand -R 145 -r 1000 exponential 1
- one hundredth exponantial variates with parameters 1, the the seed of the RNG is set to 145
- gbrand -r 10 flat 3 4
- ten realizations of the r.v. uniformly distributed in [3,4]
AUTHOR¶
Written by Giulio Bottazzi
REPORTING BUGS¶
Report bugs to <gbutils@googlegroups.com>
Package home page <http://cafim.sssup.it/~giulio/software/gbutils/index.html>
COPYRIGHT¶
Copyright © 2001-2018 Giulio Bottazzi This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License (version 2) as published by the Free Software Foundation;
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
June 2021 | gbrand 6.2 |