def sample(self, model, data, nsamples=None, walker_initial_pos=None):
if nsamples is not None:
# deprecated as of 3.3
from holopy.fitting import fit_warning
fit_warning('EmceeStrategy(nsamples=X)',
'passing nsamples to EmceeStrategy.sample')
self.nsamples = nsamples
if walker_initial_pos is not None:
# deprecated as of 3.3
from holopy.fitting import fit_warning
fit_warning('EmceeStrategy(walker_initial_pos=X)',
'passing walker_initial_pos to EmceeStrategy.sample')
self.walker_initial_pos = walker_initial_pos
time_start = time.time()
if self.npixels is not None:
data = make_subset_data(data, pixels=self.npixels, seed=self.seed)
if self.walker_initial_pos is None:
self.walker_initial_pos = model.generate_guess(self.nwalkers,
seed=self.seed)
sampler = sample_emcee(model=model, data=data, nwalkers=self.nwalkers,
walker_initial_pos=self.walker_initial_pos,
nsamples=self.nsamples, parallel=self.parallel,
seed=self.seed)
samples = emcee_samples_DataArray(sampler, model._parameters)
lnprobs = emcee_lnprobs_DataArray(sampler)
d_time = time.time() - time_start
kwargs = {'lnprobs': lnprobs, 'samples': samples}
return SamplingResult(data, model, self, d_time, kwargs)
def from_yaml(cls, loader, node):
node = _purge_ties(node)
fields = loader.construct_mapping(node, deep=True)
try:
parameters = fields['_parameters']
maps = fields['_maps']
except KeyError:
from holopy.fitting import fit_warning
fit_warning('newly saved model', 'the old one')
kwargs = fields
return cls(**kwargs)
else:
dummy_scatterer = fields['scatterer']
scatterer_parameters = read_map(maps['scatterer'], parameters)
scatterer = dummy_scatterer.from_parameters(scatterer_parameters)
kwargs = {'scatterer': scatterer, 'theory': fields['theory']}
kwargs.update(read_map(maps['optics'], parameters))
if 'model' in maps:
kwargs.update(read_map(maps['model'], parameters))
if 'theory' in maps:
kwargs.update(read_map(maps['theory'], parameters))
model = cls(**kwargs)
if model._parameters == parameters:
model._parameter_names = fields['_parameter_names']
else:
msg = ("Detected inconsistencies when reloading Model. "
"It may differ from previously saved object")
warnings.warn(msg, UserWarning)
return model
def _purge_ties(node):
'''
Temporary function to purge ties when reloading Scatterers saved pre-3.4
'''
if isinstance(node, yaml.MappingNode):
value = [(scalar, _purge_ties(mapping))
for scalar, mapping in node.value if scalar.value != 'ties']
if value != node.value:
from holopy.fitting import fit_warning
tie_msg = ('. Ignoring previously defined ties. '
'Use Model.add_tie() to reassign them')
fit_warning('newly saved model', 'the old one' + tie_msg)
node.value = value
elif isinstance(node, yaml.SequenceNode):
node.value = [_purge_ties(val) for val in node.value]
return node
def values(self):
from holopy.fitting import fit_warning
fit_warning('SamplingResult.intervals', 'SamplingResult.values')
return self.intervals
def MAP(self):
from holopy.fitting import fit_warning
fit_warning('SamplingResult.parameters', 'SamplingResult.MAP')
return self._parameters
def output_scatterer(self):
from holopy.fitting import fit_warning
fit_warning('FitResult.scatterer', 'SamplingResult.output_scatterer()')
return self.scatterer
def best_fit(self):
# this method is published in the HoloPy paper
from holopy.fitting import fit_warning
fit_warning('FitResult.hologram', 'SamplingResult.best_fit()')
return self.hologram
def sample(self, data, strategy=None):
from holopy.fitting import fit_warning
from holopy.inference.interface import validate_strategy
fit_warning('holopy.sample()', 'model.sample()')
strategy = validate_strategy(strategy, 'sample')
return strategy.sample(self, data)