class arviz.SamplingWrapper(model, idata_orig=None, log_lik_fun=None, is_ufunc=True, posterior_vars=None, sample_kwargs=None, idata_kwargs=None, log_lik_kwargs=None, apply_ufunc_kwargs=None)[source]

Class wrapping sampling routines for its usage via ArviZ.

Using a common class, all inference backends can be supported in ArviZ. Hence, statistical functions requiring refitting like Leave Future Out or Simulation Based Calibration can be performed from ArviZ.

For usage examples see user guide pages on Sampling wrappers.See other SamplingWrapper classes at wrappers api section.


The model object used for sampling.

idata_origInferenceData, optional

Original InferenceData object.

log_lik_funcallable, optional

For simple cases where the pointwise log likelihood is a Python function, this function will be used to calculate the log likelihood. Otherwise, point_log_likelihood method must be implemented. It’s callback must be log_lik_fun(*args, **log_lik_kwargs) and will be called using wrap_xarray_ufunc() or xarray.apply_ufunc() depending on the value of is_ufunc.

For more details on args or log_lik_kwargs see the notes and parameters posterior_vars and log_lik_kwargs.

is_ufuncbool, default True

If True, call log_lik_fun using xarray.apply_ufunc() otherwise use wrap_xarray_ufunc().

posterior_varslist of str, optional

List of variable names to unpack as args for log_lik_fun. Each string in the list will be used to retrieve a DataArray from the Dataset in the posterior group and passed to log_lik_fun.

sample_kwargsdict, optional

Sampling kwargs are stored as class attributes for their usage in the sample method.

idata_kwargsdict, optional

kwargs are stored as class attributes to be used in the get_inference_data method.

log_lik_kwargsdict, optional

Keyword arguments passed to log_lik_fun.

apply_ufunc_kwargsdict, optional

Passed to xarray.apply_ufunc() or wrap_xarray_ufunc().


Sampling wrappers are an experimental feature in a very early stage. Please use them with caution.


Example of log_like_fun usage.


SamplingWrapper.__init__(model[, ...])


Check that all methods listed are implemented.


Convert the fitted_model to an InferenceData object.


Get the log likelilhood samples \(\log p_{post(-i)}(y_i)\).


Sample self.model on the modified_observed_data subset.


Select a subset of the observations in idata_orig.