pymc.backends.zarr.ZarrChain#

class pymc.backends.zarr.ZarrChain(store, stats_bijection, synchronizer=None, model=None, vars=None, test_point=None, draws_per_chunk=1, fn=None)[source]#

Interface object to interact with a single chain in a ZarrTrace.

Parameters:
storezarr.storage.BaseStore | collections.abc.MutableMapping

The store object where the zarr groups and arrays will be stored and read from. This store must exist before creating a ZarrChain object. ZarrChain are only intended to be used as interfaces to the individual chains of ZarrTrace objects. This means that the ZarrTrace should be the one that creates the store that is then provided to a ZarrChain.

stats_bijectionpymc.step_methods.compound.StatsBijection

An object that maps between a list of step method stats and a dictionary of said stats with the accompanying stepper index.

synchronizerzarr.sync.Synchronizer | None

The synchronizer to use for the underlying zarr arrays.

modelModel

If None, the model is taken from the with context.

varsSequence[TensorVariable] | None

Sampling values will be stored for these variables. If None, model.unobserved_RVs is used.

test_pointdict[str, numpy.ndarray] | None

This is not used and is inherited from the signature of BaseTrace, which uses it to determine the shape and dtype of vars.

draws_per_chunkint

The number of draws that make up a chunk in the variable’s posterior array. The interface only writes the samples to the store once a chunk is completely filled.

Methods

ZarrChain.__init__(store, stats_bijection[, ...])

ZarrChain.buffer(group, var_name, value)

ZarrChain.clear_buffers()

ZarrChain.close()

Close the backend.

ZarrChain.flush()

Write the data stored in the internal buffer to the desired zarr store.

ZarrChain.get_sampler_stats(stat_name[, ...])

Get sampler statistics from the trace.

ZarrChain.get_values(varname[, burn, thin])

Get values from trace.

ZarrChain.link_stepper(step_method)

Provide a reference to the step method used during sampling.

ZarrChain.point(idx)

Return point values at idx for current chain.

ZarrChain.record(draw, stats)

Record the step method's returned draw and stats.

ZarrChain.record_sampling_state([step])

Record the sampling state information to the store's _sampling_state group.

ZarrChain.setup(draws, chain, sampler_vars)

Perform chain-specific setup.

ZarrChain.store_sampling_state(sampling_state)

Attributes

stat_names

chain

Chain number.

varnames

Names of tracked variables.

sampler_vars

Sampler stats for each sampler.