basic
– Lowlevel random numbers¶
The aesara.tensor.random
module provides randomnumber drawing functionality
that closely resembles the numpy.random
module.
Reference¶

class
aesara.tensor.random.
RandomStream
[source]¶ A helper class that tracks changes in a shared
numpy.random.RandomState
and behaves likenumpy.random.RandomState
by managing access toRandomVariable
s. For example:from aesara.tensor.random.utils import RandomStream rng = RandomStream() sample = rng.normal(0, 1, size=(2, 2))

class
aesara.tensor.random.
RandomStateType
(Type)[source]¶ A
Type
for variables that will takenumpy.random.RandomState
values.

aesara.tensor.random.
random_state_type
(name=None)[source]¶ Return a new
Variable
whoseVariable.type
is an instance ofRandomStateType
.
Distributions¶
Aesara can produce RandomVariable
s that draw samples from many different statistical distributions, using the following Op
s. The RandomVariable
s behave similarly to NumPy’s Generalized Universal Functions (or gunfunc
): it supports “core” random variable Op
s that map distinctly shaped inputs to potentially nonscalar outputs. We document this behavior in the following with gufunc
like signatures.

class
aesara.tensor.random.basic.
UniformRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A uniform continuous random variable.
The probability density function for
uniform
within the interval is:
__call__
(low=0.0, high=1.0, size=None, **kwargs)[source]¶ Draw samples from a uniform distribution.
The results are undefined when
high < low
.Signature¶
(), () > ()
param low: Lower boundary of the output interval; all values generated will be greater than or equal to low
.param high: Upper boundary of the output interval; all values generated will be less than or equal to high
.param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
RandIntRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A discrete uniform random variable.
Only available for
RandomStateType
. Useintegers
withRandomGeneratorType
s.
__call__
(low, high=None, size=None, **kwargs)[source]¶ Draw samples from a discrete uniform distribution.
Signature¶
() > ()
param low: Lower boundary of the output interval. All values generated will be greater than or equal to low
, unlesshigh=None
, in which case all values generated are greater than or equal to0
and smaller thanlow
(exclusive).param high: Upper boundary of the output interval. All values generated will be smaller than high
(exclusive).param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
, in which case a single sample is returned.


class
aesara.tensor.random.basic.
IntegersRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A discrete uniform random variable.
Only available for
RandomGeneratorType
. Userandint
withRandomStateType
s.
__call__
(low, high=None, size=None, **kwargs)[source]¶ Draw samples from a discrete uniform distribution.
Signature¶
() > ()
param low: Lower boundary of the output interval. All values generated will be greater than or equal to low
(inclusive).param high: Upper boundary of the output interval. All values generated will be smaller than high
(exclusive).param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
, in which case a single sample is returned.


class
aesara.tensor.random.basic.
ChoiceRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ Randomly choose an element in a sequence.

__call__
(a, size=None, replace=True, p=None, **kwargs)[source]¶ Generate a random sample from an array.
Signature¶
(x) > ()
param a: The array from which to randomly sample an element. If an int, a sample is generated from aesara.tensor.arange(a)
.param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent samples are returned. Default isNone
, in which case a single sample is returned.param replace: When True
, sampling is performed with replacement.param p: The probabilities associated with each entry in a
. If not given, all elements have equal probability.


class
aesara.tensor.random.basic.
PermutationRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ Randomly shuffle a sequence.

class
aesara.tensor.random.basic.
BernoulliRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A Bernoulli discrete random variable.
The probability mass function for
bernoulli
in terms of the probability of success of a single trial is:where .

__call__
(p, size=None, **kwargs)[source]¶ Draw samples from a Bernoulli distribution.
Signature¶
() > ()
param p: Probability of success of a single trial. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
BetaRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A beta continuous random variable.
The probability density function for
beta
in terms of its parameters and is:for . is the beta function defined as:

__call__
(alpha, beta, size=None, **kwargs)[source]¶ Draw samples from a beta distribution.
Signature¶
(), () > ()
param alpha: Alpha parameter of the distribution. Must be positive. param beta: Beta parameter of the distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
BetaBinomialRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A betabinomial discrete random variable.
The probability mass function for
betabinom
in terms of its shape parameters , , and the probability is:where is the beta function:

__call__
(n, a, b, size=None, **kwargs)[source]¶ Draw samples from a betabinomial distribution.
Signature¶
(), (), () > ()
param n: Shape parameter . Must be a positive integer. param a: Shape parameter . Must be positive. param b: Shape parameter . Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
BinomialRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A binomial discrete random variable.
The probability mass function for
binomial
for the number of successes in terms of the probability of success of a single trial and the number of trials is:
__call__
(n, p, size=None, **kwargs)[source]¶ Draw samples from a binomial distribution.
Signature¶
(), () > ()
param n: Number of trials . Must be a positive integer. param p: Probability of success of a single trial. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
CauchyRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A Cauchy continuous random variable.
The probability density function for
cauchy
in terms of its location parameter and scale parameter is:where .

__call__
(loc=0.0, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a Cauchy distribution.
Signature¶
(), () > ()
param loc: Location parameter of the distribution. param scale: Scale parameter of the distribution. Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
CategoricalRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A categorical discrete random variable.
The probability mass function of
categorical
in terms of its event probabilities is:where .

__call__
(p, size=None, **kwargs)[source]¶ Draw samples from a discrete categorical distribution.
Signature¶
(j) > ()
param p: An array that contains the event probabilities. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed random samples are returned. Default isNone
, in which case a single sample is returned.


class
aesara.tensor.random.basic.
ChiSquareRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A chi square continuous random variable.
The probability density function for
chisquare
in terms of the number of degrees of freedom is:for . is the gamma function:
This variable is obtained by summing the squares independent, standard normally distributed random variables.

__call__
(df, size=None, **kwargs)[source]¶ Draw samples from a chisquare distribution.
Signature¶
() > ()
param df: The number of degrees of freedom. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
DirichletRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A Dirichlet continuous random variable.
The probability density function for
dirichlet
in terms of the vector of concentration parameters is:where is a vector, such that and .

__call__
(alphas, size=None, **kwargs)[source]¶ Draw samples from a dirichlet distribution.
Signature¶
(k) > (k)
param alphas: A sequence of concentration parameters of the distribution. A sequence of length k
will produce samples of lengthk
.param size: Given a size of, for example, (r, s, t)
,r * s * t
independent, identically distributed samples are generated. Because each sample isk
dimensional, the output shape is(r, s, t, k)
. If no shape is specified, a singlek
dimensional sample is returned.


class
aesara.tensor.random.basic.
ExponentialRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ An exponential continuous random variable.
The probability density function for
exponential
in terms of its scale parameter is:for and .

__call__
(scale=1.0, size=None, **kwargs)[source]¶ Draw samples from an exponential distribution.
Signature¶
() > ()
param scale: The scale of the distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
GammaRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A gamma continuous random variable.
The probability density function for
gamma
in terms of the shape parameter and rate parameter is:for , and . is the gamma function:

__call__
(shape, rate, size=None, **kwargs)[source]¶ Draw samples from a gamma distribution.
Signature¶
(), () > ()
param shape: The shape of the gamma distribution. Must be positive. param rate: The rate of the gamma distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
GenGammaRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A generalized gamma continuous random variable.
The probability density function of
gengamma
in terms of its scale parameter and other parameters and is:for , where .

__call__
(alpha=1.0, p=1.0, lambd=1.0, size=None, **kwargs)[source]¶ Draw samples from a generalized gamma distribution.
Signature¶
(), (), () > ()
param alpha: Parameter . Must be positive. param p: Parameter . Must be positive. param lambd: Scale parameter . Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
GeometricRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A geometric discrete random variable.
The probability mass function for
geometric
for the number of successes before the first failure in terms of the probability of success of a single trial is:for .

__call__
(p, size=None, **kwargs)[source]¶ Draw samples from a geometric distribution.
Signature¶
() > ()
param p: Probability of success of an individual trial. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
GumbelRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A gumbel continuous random variable.
The probability density function for
gumbel
in terms of its location parameter and scale parameter is:for .

__call__
(loc: Union[ndarray, float], scale: Union[ndarray, float] = 1.0, size: Optional[Union[List[int], int]] = None, **kwargs) RandomVariable [source]¶ Draw samples from a gumbel distribution.
Signature¶
(), () > ()
param loc: The location parameter of the distribution. param scale: The scale of the distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
HalfCauchyRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A halfCauchy continuous random variable.
The probability density function for
halfcauchy
in terms of its location parameter and scale parameter is:for where .

__call__
(loc=0.0, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a halfCauchy distribution.
Signature¶
(), () > ()
param loc: Location parameter of the distribution. param scale: Scale parameter of the distribution. Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
, in which case a single sample is returned.


class
aesara.tensor.random.basic.
HalfNormalRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A halfnormal continuous random variable.
The probability density function for
halfnormal
in terms of its location parameter and scale parameter is:for and .

__call__
(loc=0.0, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a halfnormal distribution.
Signature¶
(), () > ()
param loc: Location parameter of the distribution. param scale: Scale parameter of the distribution. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
HyperGeometricRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A hypergeometric discrete random variable.
The probability mass function for
hypergeometric
for the number of successes in draws without replacement, from a finite population of size with desired items is:
__call__
(ngood, nbad, nsample, size=None, **kwargs)[source]¶ Draw samples from a geometric distribution.
Signature¶
(), (), () > ()
param ngood: Number of desirable items in the population. Positive integer. param nbad: Number of undesirable items in the population. Positive integer. param nsample: Number of items sampled. Must be less than , i.e. ngood + nbad
.` Positive integer.param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
InvGammaRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ An inversegamma continuous random variable.
The probability density function for
invgamma
in terms of its shape parameter and scale parameter is:for , where and . is the gamma function :

__call__
(shape, scale, size=None, **kwargs)[source]¶ Draw samples from an inversegamma distribution.
Signature¶
(), () > ()
param shape: Shape parameter of the distribution. Must be positive. param scale: Scale parameter of the distribution. Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed sample are returned. Default isNone
, in which case a single sample is returned.


class
aesara.tensor.random.basic.
LaplaceRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A Laplace continuous random variable.
The probability density function for
laplace
in terms of its location parameter and scale parameter is:with .

__call__
(loc=0.0, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a Laplace distribution.
Signature¶
(), () > ()
param loc: Location parameter of the distribution. param scale: Scale parameter of the distribution. Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
LogisticRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A logistic continuous random variable.
The probability density function for
logistic
in terms of its location parameter and scale parameter is :for .

__call__
(loc=0, scale=1, size=None, **kwargs)[source]¶ Draw samples from a logistic distribution.
Signature¶
(), () > ()
param loc: The location parameter of the distribution. param scale: The scale of the distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
LogNormalRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A lognormal continuous random variable.
The probability density function for
lognormal
in terms of the mean parameter and sigma parameter is:for and .

__call__
(mean=0.0, sigma=1.0, size=None, **kwargs)[source]¶ Draw sample from a lognormal distribution.
Signature¶
(), () > ()
param mean: Mean of the random variable’s natural logarithm. param sigma: Standard deviation of the random variable’s natural logarithm. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
MultinomialRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A multinomial discrete random variable.
The probability mass function of
multinomial
in terms of the number of experiments and the probabilities of the different possible outcomes is:where and .
Notes
The length of the support dimension is determined by the last dimension in the second parameter (i.e. the probabilities vector).

__call__
(n, p, size=None, **kwargs)[source]¶ Draw samples from a discrete multinomial distribution.
Signature¶
(), (n) > (n)
param n: Number of experiments . Must be a positive integer. param p: Probabilities of each of the different outcomes. param size: Given a size of, for example, (r, s, t)
,r * s * t
independent, identically distributed samples are generated. Because each sample isk
dimensional, the output shape is(r, s, t, k)
. If no shape is specified, a singlek
dimensional sample is returned.


class
aesara.tensor.random.basic.
MvNormalRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A multivariate normal random variable.
The probability density function for
multivariate_normal
in term of its location parameter and covariance matrix iswhere is a positive semidefinite matrix.

__call__
(mean=None, cov=None, size=None, **kwargs)[source]¶ “Draw samples from a multivariate normal distribution.
Signature¶
(n), (n,n) > (n)
param mean: Location parameter (mean) of the distribution. Vector of length N
.param cov: Covariance matrix of the distribution. Must be a symmetric and positivesemidefinite NxN
matrix.param size: Given a size of, for example, (m, n, k)
,m * n * k
independent, identically distributed samples are generated. Because each sample isN
dimensional, the output shape is(m, n, k, N)
. If no shape is specified, a singleN
dimensional sample is returned.


class
aesara.tensor.random.basic.
NegBinomialRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A negative binomial discrete random variable.
The probability mass function for
nbinom
for the number of draws before observing the th success in terms of the probability of success of a single trial is:
__call__
(n, p, size=None, **kwargs)[source]¶ Draw samples from a negative binomial distribution.
Signature¶
(), () > ()
param n: Number of successes . Must be a positive integer. param p: Probability of success of a single trial. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
NormalRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A normal continuous random variable.
The probability density function for
normal
in terms of its location parameter (mean) and scale parameter (standard deviation) is:for .

__call__
(loc=0.0, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a normal distribution.
Signature¶
(), () > ()
param loc: Mean of the normal distribution. param scale: Standard deviation of the normal distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
ParetoRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A pareto continuous random variable.
The probability density function for
pareto
in terms of its shape parameter and scale parameter is:and is defined for .

__call__
(b, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a pareto distribution.
Signature¶
(), () > ()
param b: The shape (or exponent) of the pareto distribution. Must be positive. param scale: The scale of the pareto distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
PoissonRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A poisson discrete random variable.
The probability mass function for
poisson
in terms of the expected number of events is:for .

__call__
(lam=1.0, size=None, **kwargs)[source]¶ Draw samples from a poisson distribution.
Signature¶
() > ()
param lam: Expected number of events . Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
StandardNormalRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A standard normal continuous random variable.
The probability density function for
standard_normal
is:
__call__
(size=None, **kwargs)[source]¶ Draw samples from a standard normal distribution.
Signature¶
nil > ()
param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
StudentTRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A Student’s t continuous random variable.
The probability density function for
t
in terms of its degrees of freedom parameter , location parameter and scale parameter is:for , .

__call__
(df, loc=0.0, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a Student’s t distribution.
Signature¶
(), (), () > ()
param df: Degrees of freedom parameter of the distribution. Must be positive. param loc: Location parameter of the distribution. param scale: Scale parameter of the distribution. Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
TriangularRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A triangular continuous random variable.
The probability density function for
triangular
within the interval and mode (where the peak of the distribution occurs) is:
__call__
(left, mode, right, size=None, **kwargs)[source]¶ Draw samples from a triangular distribution.
Signature¶
(), (), () > ()
param left: Lower boundary of the output interval; all values generated will be greater than or equal to left
.param mode: Mode of the distribution, where the peak occurs. Must be such that left <= mode <= right
.param right: Upper boundary of the output interval; all values generated will be less than or equal to right
. Must be larger thanleft
.param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
TruncExponentialRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A truncated exponential continuous random variable.
The probability density function for
truncexp
in terms of its shape parameter , location parameter and scale parameter is:for and .

__call__
(b, loc=0.0, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a truncated exponential distribution.
Signature¶
(), (), () > ()
param b: Shape parameter of the distribution. Must be positive. param loc: Location parameter of the distribution. param scale: Scale parameter of the distribution. Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
in which case a single sample is returned.


class
aesara.tensor.random.basic.
VonMisesRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A von Misses continuous random variable.
The probability density function for
vonmisses
in terms of its mode and dispersion parameter is :for and . is the modified Bessel function of order 0.

__call__
(mu, kappa, size=None, **kwargs)[source]¶ Draw samples from a von Mises distribution.
Signature¶
(), () > ()
param mu: The mode of the distribution. param kappa: The dispersion parameter of the distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.


class
aesara.tensor.random.basic.
WaldRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A Wald (or inverse Gaussian) continuous random variable.
The probability density function for
wald
in terms of its mean parameter and shape parameter is:for , where and .

__call__
(mean=1.0, scale=1.0, size=None, **kwargs)[source]¶ Draw samples from a Wald distribution.
Signature¶
(), () > ()
param mean: Mean parameter of the distribution. Must be positive. param shape: Shape parameter of the distribution. Must be positive. param size: Sample shape. If the given size is (m, n, k)
, thenm * n * k
independent, identically distributed samples are returned. Default isNone
, in which case a single sample is returned.


class
aesara.tensor.random.basic.
WeibullRV
(name=None, ndim_supp=None, ndims_params=None, dtype=None, inplace=None)[source]¶ A weibull continuous random variable.
The probability density function for
weibull
in terms of its shape parameter is :for and .

__call__
(shape, size=None, **kwargs)[source]¶ Draw samples from a weibull distribution.
Signature¶
() > ()
param shape: The shape of the distribution. Must be positive. param size: Sample shape. If the given size is, e.g. (m, n, k)
thenm * n * k
independent, identically distributed random variables are returned. Default isNone
in which case a single random variable is returned.
