autofit.LogGaussianPrior#

class LogGaussianPrior[source]#

Bases: Prior

A prior for a variable whose logarithm is gaussian distributed. Work in natural log.

The conversion of an input unit value, u, to a physical value, p, via the prior is as follows:

\[p = \mu + (\sigma * sqrt(2) * erfcinv(2.0 * (1.0 - u))\]

For example for prior = LogGaussianPrior(mean=1.0, sigma=2.0), an input prior.value_for(unit=0.5) is equal to 1.0.

[Rich describe how this is done via message]

Parameters:

mean (float) – The natural log of the distribution’s mean.
sigma (float) – The spread of this distribution in natural log space, e.g. sigma=1.0 means P(ln x) has a standard deviation of 1.
lower_limit (float) – A lower limit in real space (not log); physical values below this are rejected.
upper_limit (float) – A upper limit in real space (not log); physical values above this are rejected.

Examples

prior = af.LogGaussianPrior(mean=1.0, sigma=2.0, lower_limit=0.0, upper_limit=2.0)

physical_value = prior.value_for(unit=0.5)

Methods

`assert_within_limits`
`dict`	A dictionary representation of this prior
`for_class_and_attribute_name`
`from_dict`	Returns a prior from a JSON representation.
`gaussian_prior_model_for_arguments`
`has`	Does this instance have an attribute which is of type cls?
`instance_for_arguments`
`log_prior_from_value`
`make_indexes`
`name_of_class`	A string name for the class, with the prior suffix removed.
`new`	Returns a copy of this prior with a new id assigned making it distinct
`next_id`
`project`
`random`	A random value sampled from this prior
`replacing_for_path`	Create a new model replacing the value for a given path with a new value
`tree_flatten`
`tree_unflatten`	Create a prior from a flattened PyTree
`unit_value_for`	Compute the unit value between 0 and 1 for the physical value.
`value_for`	Return a physical value for a value between 0 and 1 with the transformation described by this prior.
`with_limits`	Create a new gaussian prior centred between two limits with sigma distance between this limits.
`with_message`

Attributes

`component_number`
`factor`	A callable PDF used as a factor in factor graphs
`identifier`
`label`
`limits`
`lower_unit_limit`	The lower limit for this prior in unit vector space
`name`
`ndim`	How many dimensions does this variable have?
`parameter_string`
`upper_unit_limit`	The upper limit for this prior in unit vector space
`width`

classmethod with_limits(lower_limit, upper_limit)[source]#

Create a new gaussian prior centred between two limits with sigma distance between this limits.

Note that these limits are not strict so exceptions will not be raised for values outside of the limits.

This function is typically used in prior passing, where the result of a model-fit are used to create new Gaussian priors centred on the previously estimated median PDF model.

Parameters:

lower_limit (float) – The lower limit of the new Gaussian prior.
upper_limit (float) – The upper limit of the new Gaussian Prior.

Return type:

A new GaussianPrior

value_for(unit, ignore_prior_limits=False)[source]#

Return a physical value for a value between 0 and 1 with the transformation described by this prior.

Parameters:: unit (float) – A unit value between 0 and 1.
Return type:: A physical value, mapped from the unit value accoridng to the prior.