def fitfunc(self, fitfunc):
self._fitfunc = fitfunc
self._fitfunc_has_xerr = False
if 'x_err' in getargspec(fitfunc).args:
self._fitfunc_has_xerr = True
def sample(self, steps, nthin=1, random_state=None, f=None, callback=None,
verbose=True, pool=0):
"""
Performs sampling from the objective.
Parameters
----------
steps : int
Collect `steps` samples into the chain. The sampler will run a
total of `steps * nthin` moves.
nthin : int, optional
Each chain sample is separated by `nthin` iterations.
random_state : int or `np.random.RandomState`, optional
If `random_state` is an int, a new `np.random.RandomState` instance
is used, seeded with `random_state`.
If `random_state` is already a `np.random.RandomState` instance,
then that `np.random.RandomState` instance is used. Specify
`random_state` for repeatable sampling
f : file-like or str
File to incrementally save chain progress to. Each row in the file
is a flattened array of size `(nwalkers, ndim)` or
`(ntemps, nwalkers, ndim)`. There are `steps` rows in the
file.
callback : callable
callback function to be called at each iteration step
verbose : bool, optional
Gives updates on the sampling progress
pool : int or map-like object, optional
If `pool` is an `int` then it specifies the number of threads to
use for parallelization. If `pool == 0`, then all CPU's are used.
If pool is an object with a map method that follows the same
calling sequence as the built-in map function, then this pool is
used for parallelisation.
Notes
-----
Please see :class:`emcee.EnsembleSampler` for its detailed behaviour.
>>> # we'll burn the first 500 steps
>>> fitter.sample(500)
>>> # after you've run those, then discard them by resetting the
>>> # sampler.
>>> fitter.sampler.reset()
>>> # Now collect 40 steps, each step separated by 50 sampler
>>> # generations.
>>> fitter.sample(40, nthin=50)
One can also burn and thin in `Curvefitter.process_chain`.
"""
self._check_vars_unchanged()
if self._state is None:
self.initialise()
self.__pt_iterations = 0
if isinstance(self.sampler, PTSampler):
steps *= nthin
# for saving progress to file
def _callback_wrapper(state, h=None):
if callback is not None:
callback(state.coords, state.log_prob)
if h is not None:
# if you're parallel tempering, then you only
# want to save every nthin
if isinstance(self.sampler, PTSampler):
self.__pt_iterations += 1
if self.__pt_iterations % nthin:
return None
h.write(' '.join(map(str, state.coords.ravel())))
h.write('\n')
# set the random state of the sampler
# normally one could give this as an argument to the sample method
# but PTSampler didn't historically accept that...
if random_state is not None:
rstate0 = check_random_state(random_state).get_state()
self._state.random_state = rstate0
if isinstance(self.sampler, PTSampler):
self.sampler._random = rstate0
# remove chains from each of the parameters because they slow down
# pickling but only if they are parameter objects.
flat_params = f_unique(flatten(self.objective.parameters))
flat_params = [param for param in flat_params if is_parameter(param)]
# zero out all the old parameter stderrs
for param in flat_params:
param.stderr = None
param.chain = None
# make sure the checkpoint file exists
if f is not None:
with possibly_open_file(f, 'w') as h:
# write the shape of each step of the chain
h.write('# ')
shape = self._state.coords.shape
h.write(', '.join(map(str, shape)))
h.write('\n')
# using context manager means we kill off zombie pool objects
# but does mean that the pool has to be specified each time.
with possibly_create_pool(pool) as g, possibly_open_file(f, 'a') as h:
# if you're not creating more than 1 thread, then don't bother with
# a pool.
if pool == 1:
self.sampler.pool = None
else:
self.sampler.pool = g
# these kwargs are provided to the sampler.sample method
kwargs = {'iterations': steps,
'thin': nthin}
# new emcee arguments
sampler_args = getargspec(self.sampler.sample).args
if 'progress' in sampler_args and verbose:
kwargs['progress'] = True
verbose = False
if 'thin_by' in sampler_args:
kwargs['thin_by'] = nthin
kwargs.pop('thin', 0)
# ptemcee returns coords, lnprob
# emcee returns a State object
if isinstance(self.sampler, PTSampler):
for result in self.sampler.sample(self._state.coords,
**kwargs):
self._state = State(result[0],
log_prob=result[1] + result[2],
random_state=self.sampler._random)
_callback_wrapper(self._state, h=h)
else:
for state in self.sampler.sample(self._state,
**kwargs):
self._state = state
_callback_wrapper(state, h=h)
self.sampler.pool = None
# finish off the progress bar
if verbose:
sys.stdout.write("\n")
# sets parameter value and stderr
return process_chain(self.objective, self.chain)
def sample(
self,
steps,
nthin=1,
random_state=None,
f=None,
callback=None,
verbose=True,
pool=-1,
):
"""
Performs sampling from the objective.
Parameters
----------
steps : int
Collect `steps` samples into the chain. The sampler will run a
total of `steps * nthin` moves.
nthin : int, optional
Each chain sample is separated by `nthin` iterations.
random_state : {int, `np.random.RandomState`, `np.random.Generator`}
If `random_state` is not specified the `~np.random.RandomState`
singleton is used.
If `random_state` is an int, a new ``RandomState`` instance is
used, seeded with random_state.
If `random_state` is already a ``RandomState`` or a ``Generator``
instance, then that object is used.
Specify `random_state` for repeatable minimizations.
f : file-like or str
File to incrementally save chain progress to. Each row in the file
is a flattened array of size `(nwalkers, ndim)` or
`(ntemps, nwalkers, ndim)`. There are `steps` rows in the
file.
callback : callable
callback function to be called at each iteration step. Has the
signature `callback(coords, logprob)`.
verbose : bool, optional
Gives updates on the sampling progress
pool : int or map-like object, optional
If `pool` is an `int` then it specifies the number of threads to
use for parallelization. If `pool == -1`, then all CPU's are used.
If pool is a map-like callable that follows the same calling
sequence as the built-in map function, then this pool is used for
parallelisation.
Notes
-----
Please see :class:`emcee.EnsembleSampler` for its detailed behaviour.
>>> # we'll burn the first 500 steps
>>> fitter.sample(500)
>>> # after you've run those, then discard them by resetting the
>>> # sampler.
>>> fitter.sampler.reset()
>>> # Now collect 40 steps, each step separated by 50 sampler
>>> # generations.
>>> fitter.sample(40, nthin=50)
One can also burn and thin in `Curvefitter.process_chain`.
"""
self._check_vars_unchanged()
# setup a random number generator
rng = check_random_state(random_state)
if self._state is None:
self.initialise(random_state=rng)
# for saving progress to file
def _callback_wrapper(state, h=None):
if callback is not None:
callback(state.coords, state.log_prob)
if h is not None:
h.write(" ".join(map(str, state.coords.ravel())))
h.write("\n")
# remove chains from each of the parameters because they slow down
# pickling but only if they are parameter objects.
flat_params = f_unique(flatten(self.objective.parameters))
flat_params = [param for param in flat_params if is_parameter(param)]
# zero out all the old parameter stderrs
for param in flat_params:
param.stderr = None
param.chain = None
# make sure the checkpoint file exists
if f is not None:
with possibly_open_file(f, "w") as h:
# write the shape of each step of the chain
h.write("# ")
shape = self._state.coords.shape
h.write(", ".join(map(str, shape)))
h.write("\n")
# set the random state of the sampler
# normally one could give this as an argument to the sample method
# but PTSampler didn't historically accept that...
if isinstance(rng, np.random.RandomState):
rstate0 = rng.get_state()
self._state.random_state = rstate0
self.sampler.random_state = rstate0
# using context manager means we kill off zombie pool objects
# but does mean that the pool has to be specified each time.
with MapWrapper(pool) as g, possibly_open_file(f, "a") as h:
# these kwargs are provided to the sampler.sample method
kwargs = {"iterations": steps, "thin": nthin}
# if you're not creating more than 1 thread, then don't bother with
# a pool.
if isinstance(self.sampler, emcee.EnsembleSampler):
if pool == 1:
self.sampler.pool = None
else:
self.sampler.pool = g
else:
kwargs["mapper"] = g
# new emcee arguments
sampler_args = getargspec(self.sampler.sample).args
if "progress" in sampler_args and verbose:
kwargs["progress"] = True
verbose = False
if "thin_by" in sampler_args:
kwargs["thin_by"] = nthin
kwargs.pop("thin", 0)
# perform the sampling
for state in self.sampler.sample(self._state, **kwargs):
self._state = state
_callback_wrapper(state, h=h)
if isinstance(self.sampler, emcee.EnsembleSampler):
self.sampler.pool = None
# sets parameter value and stderr
return process_chain(self.objective, self.chain)
def fitfunc(self, fitfunc):
self._fitfunc = fitfunc
self._fitfunc_has_xerr = False
if fitfunc is not None and "x_err" in getargspec(fitfunc).args:
self._fitfunc_has_xerr = True
