Var.new_obs()

Contents

Var.new_obs()#

classmethod Var.new_obs(value, dist=None, name='', distribution=None, convert='default')[source]#

Initializes a strong variable that holds observed data.

An observed variables is a strong variable that can have a distribution. If it does have a distribution, its log_prob is counted in a model’s log likelihood, i.e. log_lik.

Parameters:

  • value (Any) – The value of the variable.

  • dist (Dist | None, default: None) – The probability distribution of the variable.

  • name (str, default: '') – The name of the variable. If you do not specify a name, a unique name will be automatically generated upon initialization of a Model.

  • convert (Callable[[Any], Any] | Literal['default'], default: 'default') – A function used to process the value of this variable. The default uses the function stored in convert_value, which is jax.numpy.asarray.

  • distribution (Dist | None, default: None) – Deprecated argument name for the probability distribution of the variable, kept for backwards-compatibility. Please use the new name dist.

See also

Var.new_param

Initializes a strong variable that acts as a model parameter.

Var.new_calc

Initializes a weak variable that is a function of other variables.

Var.new_value

Initializes a strong variable without a distribution.

Return type:

Var

Examples

A simple observed variable without a distribution and without a name:

>>> x = lsl.Var.new_obs(1.0)
>>> x
Var(name="")

A simple observed variable with a normal distribution:

>>> prior = lsl.Dist(tfd.Normal, loc=0.0, scale=1.0)
>>> x = lsl.Var.new_param(1.0, dist=prior)
>>> x
Var(name="")
Contents