BoundedGaussianPrior

class dysmalpy.parameters.BoundedGaussianPrior(center=0, stddev=1.0)

Bases: Prior

Object for Gaussian priors that only extend to a minimum and maximum value

Parameters:

• center (float) – Mean of the Gaussian prior

• stddev (float) – Standard deviation of the Gaussian prior

Methods Summary

log_prior(param, **kwargs)	Returns the log value of the prior given the parameter value
prior_unit_transform(param, u, **kwargs)	Transforms a uniform random variable Uniform[0.,1.] to the prior distribution
sample_prior(param[, N])	Returns a random sample of parameter values distributed according to the prior

Methods Documentation

log_prior(param, **kwargs)

Returns the log value of the prior given the parameter value

The parameter value is first checked to see if its within param.bounds. If so then the standard Gaussian distribution is used to calculate the prior.

Parameters:

param (DysmalParameter) – DysmalParameter object with which the prior is associated

Returns:

lprior – Log prior value calculated using pdf if param.value is within param.bounds

Return type:

float

prior_unit_transform(param, u, **kwargs)

Transforms a uniform random variable Uniform[0.,1.] to the prior distribution

Parameters:

• param (DysmalParameter) – DysmalParameter object with which the prior is associated

• u (float or list-like) – Random uniform variable(s) drawn from Uniform[0.,1.]

Returns:

v – Transformation of the random uniform variable u to random value(s) drawn from the prior distribution.

Return type:

float or list-like

sample_prior(param, N=1, **kwargs)

Returns a random sample of parameter values distributed according to the prior

Parameters:

• param (DysmalParameter) – DysmalParameter object with which the prior is associated

• N (int, optional) – Size of random sample. Default is 1.

Returns:

rsamp – Random sample of parameter values

Return type:

float or array