emcee.sampler module

The base sampler class implementing various helpful functions.

class emcee.sampler.Sampler(dim, lnprobfn, args=[])

Bases: object

An abstract sampler object that implements various helper functions

Parameters:

• dim – The number of dimensions in the parameter space.

• lnpostfn – A function that takes a vector in the parameter space as input and returns the natural logarithm of the posterior probability for that position.

• args – (optional) A list of extra arguments for lnpostfn. lnpostfn will be called with the sequence lnpostfn(p, *args).

property acceptance_fraction

The fraction of proposed steps that were accepted.

property acor

The autocorrelation time of each parameter in the chain (length: dim) as estimated by the acor module.

property chain

A pointer to the Markov chain.

clear_chain()

An alias for reset() kept for backwards compatibility.

property flatchain

Alias of chain provided for compatibility.

get_lnprob(p)

Return the log-probability at the given position.

property lnprobability

A list of the log-probability values associated with each step in the chain.

property random_state

The state of the internal random number generator. In practice, it’s the result of calling get_state() on a numpy.random.mtrand.RandomState object. You can try to set this property but be warned that if you do this and it fails, it will do so silently.

reset()

Clear chain, lnprobability and the bookkeeping parameters.

run_mcmc(pos0, N, rstate0=None, lnprob0=None, **kwargs)

Iterate sample() for N iterations and return the result.

Parameters:

• p0 – The initial position vector.

• N – The number of steps to run.

• lnprob0 – (optional) The log posterior probability at position p0. If lnprob is not provided, the initial value is calculated.

• rstate0 – (optional) The state of the random number generator. See the random_state() property for details.

• kwargs – (optional) Other parameters that are directly passed to sample().

sample(*args, **kwargs)