def sample_model(model,
input_data,
output_folder,
nmr_samples=None,
burnin=None,
thinning=None,
method=None,
recalculate=False,
cl_device_ind=None,
double_precision=False,
store_samples=True,
sample_items_to_save=None,
tmp_results_dir=True,
initialization_data=None,
post_processing=None,
post_sampling_cb=None,
sampler_options=None):
"""Sample a composite model using Markov Chain Monte Carlo sampling.
Args:
model (:class:`~mdt.models.composite.DMRICompositeModel` or str): the model to sample
input_data (:class:`~mdt.utils.MRIInputData`): the input data object containing all
the info needed for the model fitting.
output_folder (string): The path to the folder where to place the output, we will make a subdir with the
model name in it (for the optimization results) and then a subdir with the samples output.
nmr_samples (int): the number of samples we would like to return.
burnin (int): the number of samples to burn-in, that is, to discard before returning the desired
number of samples
thinning (int): how many sample we wait before storing a new one. This will draw extra samples such that
the total number of samples generated is ``nmr_samples * (thinning)`` and the number of samples stored
is ``nmr_samples``. If set to one or lower we store every sample after the burn in.
method (str): The sampling method to use, one of:
- 'AMWG', for the Adaptive Metropolis-Within-Gibbs
- 'SCAM', for the Single Component Adaptive Metropolis
- 'FSL', for the sampling method used in the FSL toolbox
- 'MWG', for the Metropolis-Within-Gibbs (simple random walk metropolis without updates)
If not given, defaults to 'AMWG'.
recalculate (boolean): If we want to recalculate the results if they are already present.
cl_device_ind (int): the index of the CL device to use. The index is from the list from the function
utils.get_cl_devices().
double_precision (boolean): if we would like to do the calculations in double precision
store_samples (boolean): determines if we store any of the samples. If set to False we will store none
of the samples.
sample_items_to_save (list): list of output names we want to store the samples of. If given, we only
store the items specified in this list. Valid items are the free parameter names of the model and the
items 'LogLikelihood' and 'LogPrior'.
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
initialization_data (:class:`~mdt.utils.InitializationData` or dict): provides (extra) initialization data to
use during model fitting. If we are optimizing a cascade model this data only applies to the last model
in the cascade. If a dictionary is given we will load the elements as arguments to the
:class:`mdt.utils.SimpleInitializationData` class. For example::
initialization_data = {'fixes': {...}, 'inits': {...}}
is transformed into::
initialization_data = SimpleInitializationData(fixes={...}, inits={...})
post_processing (dict): a dictionary with flags for post-processing options to enable or disable.
For valid elements, please see the configuration file settings for ``sample`` under ``post_processing``.
Valid input for this parameter is for example: {'sample_statistics': True} to enable automatic calculation
of the sample statistics.
post_sampling_cb (Callable[
[mot.sample.base.SamplingOutput, mdt.models.composite.DMRICompositeModel], Optional[Dict]]):
additional post-processing called after sampling. This function can optionally return a (nested)
dictionary with as keys dir-/file-names and as values maps to be stored in the results directory.
sampler_options (dict): specific options for the MCMC routine. These will be provided to the sampling routine
as additional keyword arguments to the constructor.
Returns:
dict: if store_samples is True then we return the samples per parameter as a numpy memmap. If store_samples
is False we return None
"""
import mdt.utils
from mdt.lib.model_sampling import sample_composite_model
from mdt.models.cascade import DMRICascadeModelInterface
import mot.configuration
settings = mdt.configuration.get_general_sampling_settings()
if nmr_samples is None:
nmr_samples = settings['nmr_samples']
if burnin is None:
burnin = settings['burnin']
if thinning is None:
thinning = settings['thinning']
if not isinstance(initialization_data,
InitializationData) and initialization_data is not None:
initialization_data = SimpleInitializationData(**initialization_data)
if not mdt.utils.check_user_components():
init_user_settings(pass_if_exists=True)
if isinstance(model, str):
model = get_model(model)()
if post_processing:
model.update_active_post_processing('sampling', post_processing)
if isinstance(model, DMRICascadeModelInterface):
raise ValueError(
'The function \'sample_model()\' does not accept cascade models.')
if cl_device_ind is None:
cl_context_action = mot.configuration.VoidConfigurationAction()
else:
cl_context_action = mot.configuration.RuntimeConfigurationAction(
cl_environments=get_cl_devices(cl_device_ind),
double_precision=double_precision)
with mot.configuration.config_context(cl_context_action):
base_dir = os.path.join(output_folder, model.name, 'samples')
if not os.path.isdir(base_dir):
os.makedirs(base_dir)
if recalculate:
shutil.rmtree(base_dir)
logger = logging.getLogger(__name__)
logger.info('Using MDT version {}'.format(__version__))
logger.info('Preparing for model {0}'.format(model.name))
logger.info('The {0} parameters we will sample are: {1}'.format(
len(model.get_free_param_names()), model.get_free_param_names()))
return sample_composite_model(
model,
input_data,
base_dir,
nmr_samples,
thinning,
burnin,
get_temporary_results_dir(tmp_results_dir),
method=method,
recalculate=recalculate,
store_samples=store_samples,
sample_items_to_save=sample_items_to_save,
initialization_data=initialization_data,
post_sampling_cb=post_sampling_cb,
sampler_options=sampler_options)
def sample_model(model,
input_data,
output_folder,
nmr_samples=None,
burnin=None,
thinning=None,
recalculate=False,
cl_device_ind=None,
double_precision=False,
store_samples=True,
sample_items_to_save=None,
tmp_results_dir=True,
save_user_script_info=True,
initialization_data=None,
post_processing=None):
"""Sample a composite model using the Adaptive Metropolis-Within-Gibbs (AMWG) MCMC algorithm [1].
Args:
model (:class:`~mdt.models.composite.DMRICompositeModel` or str): the model to sample
input_data (:class:`~mdt.utils.MRIInputData`): the input data object containing all
the info needed for the model fitting.
output_folder (string): The path to the folder where to place the output, we will make a subdir with the
model name in it (for the optimization results) and then a subdir with the samples output.
nmr_samples (int): the number of samples we would like to return.
burnin (int): the number of samples to burn-in, that is, to discard before returning the desired
number of samples
thinning (int): how many sample we wait before storing a new one. This will draw extra samples such that
the total number of samples generated is ``nmr_samples * (thinning)`` and the number of samples stored
is ``nmr_samples``. If set to one or lower we store every sample after the burn in.
recalculate (boolean): If we want to recalculate the results if they are already present.
cl_device_ind (int): the index of the CL device to use. The index is from the list from the function
utils.get_cl_devices().
double_precision (boolean): if we would like to do the calculations in double precision
store_samples (boolean): determines if we store any of the samples. If set to False we will store none
of the samples.
sample_items_to_save (list): list of output names we want to store the samples of. If given, we only
store the items specified in this list. Valid items are the free parameter names of the model and the
items 'LogLikelihood' and 'LogPrior'.
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
save_user_script_info (boolean, str or SaveUserScriptInfo): The info we need to save about the script the
user is currently executing. If True (default) we use the stack to lookup the script the user is executing
and save that using a SaveFromScript saver. If a string is given we use that filename again for the
SaveFromScript saver. If False or None, we do not write any information. If a SaveUserScriptInfo is
given we use that directly.
initialization_data (:class:`~mdt.utils.InitializationData` or dict): provides (extra) initialization data to
use during model fitting. If we are optimizing a cascade model this data only applies to the last model
in the cascade. If a dictionary is given we will load the elements as arguments to the
:class:`mdt.utils.SimpleInitializationData` class. For example::
initialization_data = {'fixes': {...}, 'inits': {...}}
is transformed into::
initialization_data = SimpleInitializationData(fixes={...}, inits={...})
post_processing (dict): a dictionary with flags for post-processing options to enable or disable.
For valid elements, please see the configuration file settings for ``sampling`` under ``post_processing``.
Valid input for this parameter is for example: {'sample_statistics': True} to enable automatic calculation
of the sampling statistics.
Returns:
dict: if store_samples is True then we return the samples per parameter as a numpy memmap. If store_samples
is False we return None
References:
1. Roberts GO, Rosenthal JS. Examples of adaptive MCMC. J Comput Graph Stat. 2009;18(2):349-367.
doi:10.1198/jcgs.2009.06134.
"""
import mdt.utils
from mot.load_balance_strategies import EvenDistribution
from mdt.model_sampling import sample_composite_model
from mdt.models.cascade import DMRICascadeModelInterface
import mot.configuration
settings = mdt.configuration.get_general_sampling_settings()
if nmr_samples is None:
nmr_samples = settings['nmr_samples']
if burnin is None:
burnin = settings['burnin']
if thinning is None:
thinning = settings['thinning']
if not isinstance(initialization_data,
InitializationData) and initialization_data is not None:
initialization_data = SimpleInitializationData(**initialization_data)
if not mdt.utils.check_user_components():
init_user_settings(pass_if_exists=True)
if isinstance(model, string_types):
model = get_model(model)()
if post_processing:
model.update_active_post_processing('sampling', post_processing)
if isinstance(model, DMRICascadeModelInterface):
raise ValueError(
'The function \'sample_model()\' does not accept cascade models.')
if cl_device_ind is not None and not isinstance(cl_device_ind,
collections.Iterable):
cl_device_ind = [cl_device_ind]
if cl_device_ind is None:
cl_context_action = mot.configuration.VoidConfigurationAction()
else:
cl_envs = [get_cl_devices()[ind] for ind in cl_device_ind]
cl_context_action = mot.configuration.RuntimeConfigurationAction(
cl_environments=cl_envs,
load_balancer=EvenDistribution(),
double_precision=double_precision)
with mot.configuration.config_context(cl_context_action):
base_dir = os.path.join(output_folder, model.name, 'samples')
if not os.path.isdir(base_dir):
os.makedirs(base_dir)
if recalculate:
shutil.rmtree(base_dir)
logger = logging.getLogger(__name__)
logger.info('Using MDT version {}'.format(__version__))
logger.info('Preparing for model {0}'.format(model.name))
logger.info('The parameters we will sample are: {0}'.format(
model.get_free_param_names()))
results = sample_composite_model(
model,
input_data,
base_dir,
nmr_samples,
thinning,
burnin,
get_temporary_results_dir(tmp_results_dir),
recalculate=recalculate,
store_samples=store_samples,
sample_items_to_save=sample_items_to_save,
initialization_data=initialization_data)
easy_save_user_script_info(save_user_script_info,
os.path.join(base_dir, 'used_scripts.py'),
stack()[1][0].f_globals.get('__file__'))
return results
def __init__(self,
model,
input_data,
output_folder,
method=None,
optimizer_options=None,
recalculate=False,
only_recalculate_last=False,
cl_device_ind=None,
double_precision=False,
tmp_results_dir=True,
initialization_data=None,
post_processing=None):
"""Setup model fitting for the given input model and data.
To actually fit the model call run().
Args:
model (str or :class:`~mdt.models.composite.DMRICompositeModel` or :class:`~mdt.models.cascade.DMRICascadeModelInterface`):
the model we want to optimize.
input_data (:class:`~mdt.utils.MRIInputData`): the input data object containing
all the info needed for the model fitting.
output_folder (string): The full path to the folder where to place the output
method (str): The optimization method to use, one of:
- 'Levenberg-Marquardt'
- 'Nelder-Mead'
- 'Powell'
- 'Subplex'
If not given, defaults to 'Powell'.
optimizer_options (dict): extra options passed to the optimization routines.
recalculate (boolean): If we want to recalculate the results if they are already present.
only_recalculate_last (boolean): If we want to recalculate all the models.
This is only of importance when dealing with CascadeModels. If set to true we only recalculate
the last element in the chain (if recalculate is set to True, that is). If set to false,
we recalculate everything. This only holds for the first level of the cascade.
cl_device_ind (int or list): the index of the CL device to use. The index is from the list from the function
get_cl_devices(). This can also be a list of device indices.
double_precision (boolean): if we would like to do the calculations in double precision
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
initialization_data (dict or :class:`~mdt.utils.InitializationData`): extra initialization data to use
during model fitting. If we are optimizing a cascade model this data only applies to the last model in
the cascade.
post_processing (dict): a dictionary with flags for post-processing options to enable or disable.
For valid elements, please see the configuration file settings for ``optimization``
under ``post_processing``. Valid input for this parameter is for example: {'covariance': False}
to disable automatic calculation of the covariance from the Hessian.
"""
if isinstance(model, str):
model = get_model(model)()
if post_processing:
model.update_active_post_processing('optimization',
post_processing)
self._model = model
self._input_data = input_data
self._output_folder = output_folder
self._method = method
self._optimizer_options = optimizer_options
self._recalculate = recalculate
self._only_recalculate_last = only_recalculate_last
self._logger = logging.getLogger(__name__)
self._model_names_list = []
self._tmp_results_dir = get_temporary_results_dir(tmp_results_dir)
if initialization_data is not None and not isinstance(
initialization_data, InitializationData):
self._initialization_data = SimpleInitializationData(
**initialization_data)
else:
self._initialization_data = initialization_data
if cl_device_ind is not None:
self._cl_runtime_info = CLRuntimeInfo(
cl_environments=get_cl_devices(cl_device_ind),
double_precision=double_precision)
else:
self._cl_runtime_info = CLRuntimeInfo(
double_precision=double_precision)
if not model.is_input_data_sufficient(self._input_data):
raise InsufficientProtocolError(
'The provided protocol is insufficient for this model. '
'The reported errors where: {}'.format(
self._model.get_input_data_problems(self._input_data)))
def __init__(self,
model,
problem_data,
output_folder,
optimizer=None,
recalculate=False,
only_recalculate_last=False,
cascade_subdir=False,
cl_device_ind=None,
double_precision=False,
tmp_results_dir=True):
"""Setup model fitting for the given input model and data.
To actually fit the model call run().
Args:
model
(:class:`~mdt.models.composite.DMRICompositeModel` or :class:`~mdt.models.cascade.DMRICascadeModelInterface`):
the model we want to optimize.
problem_data (:class:`~mdt.utils.DMRIProblemData`): the problem data object which contains the dwi image,
the dwi header, the brain_mask and the protocol to use.
output_folder (string): The full path to the folder where to place the output
optimizer (:class:`mot.cl_routines.optimizing.base.AbstractOptimizer`): The optimization routine to use.
If None, we create one using the configuration files.
recalculate (boolean): If we want to recalculate the results if they are already present.
only_recalculate_last (boolean): If we want to recalculate all the models.
This is only of importance when dealing with CascadeModels. If set to true we only recalculate
the last element in the chain (if recalculate is set to True, that is). If set to false,
we recalculate everything. This only holds for the first level of the cascade.
cascade_subdir (boolean): if we want to create a subdirectory for the given model if it is a cascade model.
Per default we output the maps of cascaded results in the same directory, this allows reusing cascaded
results for other cascades (for example, if you cascade BallStick -> Noddi you can use the BallStick
results also for BallStick -> Charmed). This flag disables that behaviour and instead outputs the
results of a cascade model to a subdirectory for that cascade. This does not apply recursive.
cl_device_ind (int): the index of the CL device to use. The index is from the list from the function
get_cl_devices(). This can also be a list of device indices.
double_precision (boolean): if we would like to do the calculations in double precision
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
"""
if isinstance(model, string_types):
model = get_model(model)
model.double_precision = double_precision
self._model = model
self._problem_data = problem_data
self._output_folder = output_folder
if cascade_subdir and isinstance(self._model,
DMRICascadeModelInterface):
self._output_folder += '/{}'.format(self._model.name)
self._optimizer = optimizer
self._recalculate = recalculate
self._only_recalculate_last = only_recalculate_last
self._logger = logging.getLogger(__name__)
self._cl_device_indices = cl_device_ind
self._model_names_list = []
self._tmp_results_dir = get_temporary_results_dir(tmp_results_dir)
if self._cl_device_indices is not None and not isinstance(
self._cl_device_indices, collections.Iterable):
self._cl_device_indices = [self._cl_device_indices]
self._cl_envs = None
self._load_balancer = None
if self._cl_device_indices is not None:
all_devices = get_cl_devices()
self._cl_envs = [
all_devices[ind] for ind in self._cl_device_indices
]
self._load_balancer = EvenDistribution()
if not model.is_protocol_sufficient(self._problem_data.protocol):
raise InsufficientProtocolError(
'The provided protocol is insufficient for this model. '
'The reported errors where: {}'.format(
self._model.get_protocol_problems(
self._problem_data.protocol)))
def fit_model(model,
input_data,
output_folder,
method=None,
recalculate=False,
cl_device_ind=None,
double_precision=False,
tmp_results_dir=True,
initialization_data=None,
use_cascaded_inits=True,
post_processing=None,
optimizer_options=None):
"""Run the optimizer on the given model.
Args:
model (str or :class:`~mdt.models.base.EstimableModel`):
The name of a composite model or an implementation of a composite model.
input_data (:class:`~mdt.utils.MRIInputData`): the input data object containing all
the info needed for the model fitting.
output_folder (string): The path to the folder where to place the output, we will make a subdir with the
model name in it.
method (str): The optimization method to use, one of:
- 'Levenberg-Marquardt'
- 'Nelder-Mead'
- 'Powell'
- 'Subplex'
If not given, defaults to 'Powell'.
recalculate (boolean): If we want to recalculate the results if they are already present.
cl_device_ind (int or list): the index of the CL device to use. The index is from the list from the function
utils.get_cl_devices(). This can also be a list of device indices.
double_precision (boolean): if we would like to do the calculations in double precision
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
initialization_data (dict): provides (extra) initialization data to
use during model fitting. This dictionary can contain the following elements:
* ``inits``: dictionary with per parameter an initialization point
* ``fixes``: dictionary with per parameter a fixed point, this will remove that parameter from the fitting
* ``lower_bounds``: dictionary with per parameter a lower bound
* ``upper_bounds``: dictionary with per parameter a upper bound
* ``unfix``: a list of parameters to unfix
For example::
initialization_data = {
'fixes': {'Stick0.theta: np.array(...), ...},
'inits': {...}
}
use_cascaded_inits (boolean): if set, we initialize the model parameters using :func:`get_optimization_inits`.
You can also overrule the default initializations using the ``initialization_data`` attribute.
post_processing (dict): a dictionary with flags for post-processing options to enable or disable.
For valid elements, please see the configuration file settings for ``optimization``
under ``post_processing``. Valid input for this parameter is for example: {'covariance': False}
to disable automatic calculation of the covariance from the Hessian.
optimizer_options (dict): extra options passed to the optimization routines.
Returns:
dict: The result maps for the given composite model or the last model in the cascade.
This returns the results as 3d/4d volumes for every output map.
"""
logger = logging.getLogger(__name__)
if not check_user_components():
init_user_settings(pass_if_exists=True)
if cl_device_ind is not None:
if not isinstance(cl_device_ind, collections.Iterable):
cl_device_ind = [cl_device_ind]
cl_runtime_info = CLRuntimeInfo(
cl_environments=get_cl_devices(cl_device_ind),
double_precision=double_precision)
else:
cl_runtime_info = CLRuntimeInfo(double_precision=double_precision)
if isinstance(model, str):
model_name = model
model_instance = get_model(model)()
else:
model_name = model.name
model_instance = model
if not model_instance.is_input_data_sufficient(input_data):
raise InsufficientProtocolError(
'The provided protocol is insufficient for this model. '
'The reported errors where: {}'.format(
model_instance.get_input_data_problems(input_data)))
if post_processing:
model_instance.update_active_post_processing('optimization',
post_processing)
if use_cascaded_inits:
if initialization_data is None:
initialization_data = {}
initialization_data['inits'] = initialization_data.get('inits', {})
inits = get_optimization_inits(model_name,
input_data,
output_folder,
cl_device_ind=cl_device_ind)
inits.update(initialization_data['inits'])
initialization_data['inits'] = inits
initialization_data = SimpleInitializationData(**initialization_data)
initialization_data.apply_to_model(model_instance, input_data)
logger.info('Preparing {0} with the cascaded initializations.'.format(
model_name))
if method is None:
method, optimizer_options = get_optimizer_for_model(model_name)
with mot.configuration.config_context(CLRuntimeAction(cl_runtime_info)):
fit_composite_model(model_instance,
input_data,
output_folder,
method,
get_temporary_results_dir(tmp_results_dir),
recalculate=recalculate,
optimizer_options=optimizer_options)
return get_all_nifti_data(os.path.join(output_folder, model_name))
def sample_model(model,
problem_data,
output_folder,
sampler=None,
recalculate=False,
cl_device_ind=None,
double_precision=False,
store_samples=True,
tmp_results_dir=True,
save_user_script_info=True,
initialization_maps=None):
"""Sample a composite model using the given cascading strategy.
Args:
model (:class:`~mdt.models.composite.DMRICompositeModel` or str): the model to sample
problem_data (:class:`~mdt.utils.DMRIProblemData`): the problem data object
output_folder (string): The path to the folder where to place the output, we will make a subdir with the
model name in it (for the optimization results) and then a subdir with the samples output.
sampler (:class:`mot.cl_routines.sampling.base.AbstractSampler`): the sampler to use
recalculate (boolean): If we want to recalculate the results if they are already present.
cl_device_ind (int): the index of the CL device to use. The index is from the list from the function
utils.get_cl_devices().
double_precision (boolean): if we would like to do the calculations in double precision
store_samples (boolean): if set to False we will store none of the samples. Use this
if you are only interested in the volume maps and not in the entire sample chain.
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
save_user_script_info (boolean, str or SaveUserScriptInfo): The info we need to save about the script the
user is currently executing. If True (default) we use the stack to lookup the script the user is executing
and save that using a SaveFromScript saver. If a string is given we use that filename again for the
SaveFromScript saver. If False or None, we do not write any information. If a SaveUserScriptInfo is
given we use that directly.
initialization_maps (dict): 4d maps to initialize the sampling with. Per default this is None,
common practice is to use the maps from an optimization as starting point
Returns:
dict: the samples per parameter as a numpy memmap if store_samples is True
"""
import mdt.utils
from mot.load_balance_strategies import EvenDistribution
from mdt.model_sampling import sample_composite_model
from mdt.models.cascade import DMRICascadeModelInterface
import mot.configuration
if not mdt.utils.check_user_components():
init_user_settings(pass_if_exists=True)
if isinstance(model, string_types):
model = get_model(model)
if isinstance(model, DMRICascadeModelInterface):
raise ValueError(
'The function \'sample_model()\' does not accept cascade models.')
if not model.is_protocol_sufficient(problem_data.protocol):
raise InsufficientProtocolError(
'The given protocol is insufficient for this model. '
'The reported errors where: {}'.format(
model.get_protocol_problems(problem_data.protocol)))
if cl_device_ind is not None and not isinstance(cl_device_ind,
collections.Iterable):
cl_device_ind = [cl_device_ind]
if cl_device_ind is None:
cl_context_action = mot.configuration.VoidConfigurationAction()
else:
cl_context_action = mot.configuration.RuntimeConfigurationAction(
cl_environments=[get_cl_devices()[ind] for ind in cl_device_ind],
load_balancer=EvenDistribution())
with mot.configuration.config_context(cl_context_action):
if sampler is None:
sampler = configuration.get_sampler()
processing_strategy = get_processing_strategy('sampling',
model_names=model.name)
processing_strategy.set_tmp_dir(
get_temporary_results_dir(tmp_results_dir))
output_folder = os.path.join(output_folder, model.name, 'samples')
if not os.path.isdir(output_folder):
os.makedirs(output_folder)
with per_model_logging_context(output_folder, overwrite=recalculate):
logger = logging.getLogger(__name__)
logger.info('Using MDT version {}'.format(__version__))
logger.info('Preparing for model {0}'.format(model.name))
if initialization_maps:
model.set_initial_parameters(
create_roi(initialization_maps, problem_data.mask))
model.double_precision = double_precision
results = sample_composite_model(model,
problem_data,
output_folder,
sampler,
processing_strategy,
recalculate=recalculate,
store_samples=store_samples)
easy_save_user_script_info(save_user_script_info,
output_folder + '/used_scripts.py',
stack()[1][0].f_globals.get('__file__'))
return results
def bootstrap_model(model, input_data, optimization_results, output_folder, bootstrap_method=None,
bootstrap_options=None, nmr_samples=None, optimization_method=None, optimizer_options=None,
recalculate=False, cl_device_ind=None, double_precision=False, keep_samples=True,
tmp_results_dir=True, initialization_data=None):
"""Resample the model using residual bootstrapping.
This is typically used to construct confidence intervals on the optimized parameters.
Args:
model (str or :class:`~mdt.models.base.EstimableModel`): the model to sample
input_data (:class:`~mdt.lib.input_data.MRIInputData`): the input data object containing all
the info needed for the model fitting.
optimization_results (dict or str): the optimization results, either a dictionary with results or the
path to a folder.
output_folder (string): The path to the folder where to place the output, we will make a subdir with the
model name in it (for the optimization results) and then a subdir with the samples output.
bootstrap_method (str): the bootstrap method we want to use, 'residual', or 'wild'. Defaults to 'wild'.
bootstrap_options (dict): bootstrapping options specific for the bootstrap method in use
nmr_samples (int): the number of samples we would like to compute. Defaults to 1000.
optimization_method (str): The optimization method to use, one of:
- 'Levenberg-Marquardt'
- 'Nelder-Mead'
- 'Powell'
- 'Subplex'
If not given, defaults to 'Powell'.
optimizer_options (dict): extra options passed to the optimization routines.
recalculate (boolean): If we want to recalculate the results if they are already present.
cl_device_ind (int): the index of the CL device to use. The index is from the list from the function
utils.get_cl_devices().
double_precision (boolean): if we would like to do the calculations in double precision
keep_samples (boolean): determines if we keep any of the chains. If set to False, the chains will
be discarded after generating the mean and standard deviations.
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
initialization_data (dict): provides (extra) initialization data to
use during model fitting. This dictionary can contain the following elements:
* ``inits``: dictionary with per parameter an initialization point
* ``fixes``: dictionary with per parameter a fixed point, this will remove that parameter from the fitting
* ``lower_bounds``: dictionary with per parameter a lower bound
* ``upper_bounds``: dictionary with per parameter a upper bound
* ``unfix``: a list of parameters to unfix
For example::
initialization_data = {
'fixes': {'Stick0.theta: np.array(...), ...},
'inits': {...}
}
Returns:
dict: if keep_samples is True we return the samples per parameter as a numpy memmap.
If store_samples is False we return None
"""
initialization_data = initialization_data or {}
nmr_samples = nmr_samples or 1000
bootstrap_method = bootstrap_method or 'wild'
if not check_user_components():
init_user_settings(pass_if_exists=True)
if cl_device_ind is None:
cl_context_action = mot.configuration.VoidConfigurationAction()
else:
cl_context_action = mot.configuration.RuntimeConfigurationAction(
cl_environments=get_cl_devices(cl_device_ind),
double_precision=double_precision)
if isinstance(model, str):
model_name = model
model_instance = get_model(model)()
else:
model_name = model.name
model_instance = model
model_instance.update_active_post_processing('optimization', {'uncertainties': False, 'll_and_ic': False})
initialization_data = SimpleInitializationData(**initialization_data)
initialization_data.apply_to_model(model_instance, input_data)
if optimization_method is None:
optimization_method, optimizer_options = get_optimizer_for_model(model_name)
with mot.configuration.config_context(cl_context_action):
from mdt.lib.processing.model_bootstrapping import compute_bootstrap
return compute_bootstrap(model_instance, input_data, optimization_results,
output_folder, bootstrap_method, optimization_method, nmr_samples,
get_temporary_results_dir(tmp_results_dir),
recalculate=recalculate,
keep_samples=keep_samples,
optimizer_options=optimizer_options,
bootstrap_options=bootstrap_options)
def sample_model(model, input_data, output_folder, nmr_samples=None, burnin=None, thinning=None,
method=None, recalculate=False, cl_device_ind=None, cl_load_balancer=None, double_precision=False,
store_samples=True, sample_items_to_save=None, tmp_results_dir=True,
initialization_data=None, post_processing=None, post_sampling_cb=None,
sampler_options=None):
"""Sample a composite model using Markov Chain Monte Carlo sampling.
Args:
model (str or :class:`~mdt.models.base.EstimableModel`): the model to sample
input_data (:class:`~mdt.lib.input_data.MRIInputData`): the input data object containing all
the info needed for the model fitting.
output_folder (string): The path to the folder where to place the output, we will make a subdir with the
model name in it (for the optimization results) and then a subdir with the samples output.
nmr_samples (int): the number of samples we would like to return.
burnin (int): the number of samples to burn-in, that is, to discard before returning the desired
number of samples
thinning (int): how many sample we wait before storing a new one. This will draw extra samples such that
the total number of samples generated is ``nmr_samples * (thinning)`` and the number of samples stored
is ``nmr_samples``. If set to one or lower we store every sample after the burn in.
method (str): The sampling method to use, one of:
- 'AMWG', for the Adaptive Metropolis-Within-Gibbs
- 'SCAM', for the Single Component Adaptive Metropolis
- 'FSL', for the sampling method used in the FSL toolbox
- 'MWG', for the Metropolis-Within-Gibbs (simple random walk metropolis without updates)
If not given, defaults to 'AMWG'.
recalculate (boolean): If we want to recalculate the results if they are already present.
cl_device_ind (List[Union[mot.lib.cl_environments.CLEnvironment, int]]
or mot.lib.cl_environments.CLEnvironment or int): the CL devices to use.
Either provide MOT CLEnvironment's or indices from into the list from the function mdt.get_cl_devices().
cl_load_balancer (mot.lib.load_balancers.LoadBalancer or Tuple[float]): the load balancer to use. Can also
be an array of fractions (summing to 1) with one fraction per device. For example, for two devices one
can specify ``cl_load_balancer = [0.3, 0.7]`` to let one device to more work than another.
double_precision (boolean): if we would like to do the calculations in double precision
store_samples (boolean): determines if we store any of the samples. If set to False we will store none
of the samples.
sample_items_to_save (list): list of output names we want to store the samples of. If given, we only
store the items specified in this list. Valid items are the free parameter names of the model and the
items 'LogLikelihood' and 'LogPrior'.
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
initialization_data (dict): provides (extra) initialization data to
use during model fitting. This dictionary can contain the following elements:
* ``inits``: dictionary with per parameter an initialization point
* ``fixes``: dictionary with per parameter a fixed point, this will remove that parameter from the fitting
* ``lower_bounds``: dictionary with per parameter a lower bound
* ``upper_bounds``: dictionary with per parameter a upper bound
* ``unfix``: a list of parameters to unfix
For example::
initialization_data = {
'fixes': {'Stick0.theta: np.array(...), ...},
'inits': {...}
}
post_processing (dict): a dictionary with flags for post-processing options to enable or disable.
For valid elements, please see the configuration file settings for ``sample`` under ``post_processing``.
Valid input for this parameter is for example: {'univariate_normal': True} to enable automatic calculation
of the univariate normal distribution for the model parameters.
post_sampling_cb (Callable[
[mot.sample.base.SamplingOutput, mdt.models.composite.DMRICompositeModel], Optional[Dict]]):
additional post-processing called after sampling. This function can optionally return a (nested)
dictionary with as keys dir-/file-names and as values maps to be stored in the results directory.
sampler_options (dict): specific options for the MCMC routine. These will be provided to the sampling routine
as additional keyword arguments to the constructor.
Returns:
dict: if store_samples is True then we return the samples per parameter as a numpy memmap. If store_samples
is False we return None
"""
initialization_data = initialization_data or {}
if not check_user_components():
init_user_settings(pass_if_exists=True)
cl_runtime_info = CLRuntimeInfo(cl_environments=cl_device_ind,
double_precision=double_precision,
load_balancer=cl_load_balancer)
settings = get_general_sampling_settings()
if nmr_samples is None:
nmr_samples = settings['nmr_samples']
if burnin is None:
burnin = settings['burnin']
if thinning is None:
thinning = settings['thinning']
if isinstance(model, str):
model_instance = get_model(model)()
else:
model_instance = model
initialization_data = SimpleInitializationData(**initialization_data)
initialization_data.apply_to_model(model_instance, input_data)
if post_processing:
model_instance.update_active_post_processing('sampling', post_processing)
with mot.configuration.config_context(CLRuntimeAction(cl_runtime_info)):
from mdt.lib.processing.model_sampling import sample_composite_model
return sample_composite_model(model_instance, input_data, output_folder, nmr_samples, thinning, burnin,
get_temporary_results_dir(tmp_results_dir),
method=method, recalculate=recalculate,
store_samples=store_samples,
sample_items_to_save=sample_items_to_save,
post_sampling_cb=post_sampling_cb,
sampler_options=sampler_options)
def __init__(self,
model,
input_data,
output_folder,
optimizer=None,
recalculate=False,
only_recalculate_last=False,
cascade_subdir=False,
cl_device_ind=None,
double_precision=False,
tmp_results_dir=True,
initialization_data=None,
post_processing=None):
"""Setup model fitting for the given input model and data.
To actually fit the model call run().
Args:
model (str or :class:`~mdt.models.composite.DMRICompositeModel` or :class:`~mdt.models.cascade.DMRICascadeModelInterface`):
the model we want to optimize.
input_data (:class:`~mdt.utils.MRIInputData`): the input data object containing
all the info needed for the model fitting.
output_folder (string): The full path to the folder where to place the output
optimizer (:class:`mot.cl_routines.optimizing.base.AbstractOptimizer`): The optimization routine to use.
If None, we create one using the configuration files.
recalculate (boolean): If we want to recalculate the results if they are already present.
only_recalculate_last (boolean): If we want to recalculate all the models.
This is only of importance when dealing with CascadeModels. If set to true we only recalculate
the last element in the chain (if recalculate is set to True, that is). If set to false,
we recalculate everything. This only holds for the first level of the cascade.
cascade_subdir (boolean): if we want to create a subdirectory for the given model if it is a cascade model.
Per default we output the maps of cascaded results in the same directory, this allows reusing cascaded
results for other cascades (for example, if you cascade BallStick -> Noddi you can use the BallStick
results also for BallStick -> Charmed). This flag disables that behaviour and instead outputs the
results of a cascade model to a subdirectory for that cascade. This does not apply recursive.
cl_device_ind (int): the index of the CL device to use. The index is from the list from the function
get_cl_devices(). This can also be a list of device indices.
double_precision (boolean): if we would like to do the calculations in double precision
tmp_results_dir (str, True or None): The temporary dir for the calculations. Set to a string to use
that path directly, set to True to use the config value, set to None to disable.
initialization_data (:class:`~mdt.utils.InitializationData`): extra initialization data to use
during model fitting. If we are optimizing a cascade model this data only applies to the last model in the
cascade.
post_processing (dict): a dictionary with flags for post-processing options to enable or disable.
For valid elements, please see the configuration file settings for ``optimization``
under ``post_processing``. Valid input for this parameter is for example: {'covariance': False}
to disable automatic calculation of the covariance from the Hessian.
"""
if isinstance(model, string_types):
model = get_model(model)()
if post_processing:
model.update_active_post_processing('optimization',
post_processing)
self._model = model
self._input_data = input_data
self._output_folder = output_folder
if cascade_subdir and isinstance(self._model,
DMRICascadeModelInterface):
self._output_folder += '/{}'.format(self._model.name)
self._optimizer = optimizer
self._recalculate = recalculate
self._only_recalculate_last = only_recalculate_last
self._logger = logging.getLogger(__name__)
self._model_names_list = []
self._tmp_results_dir = get_temporary_results_dir(tmp_results_dir)
self._initialization_data = initialization_data or SimpleInitializationData(
)
if cl_device_ind is not None and not isinstance(
cl_device_ind, collections.Iterable):
cl_device_ind = [cl_device_ind]
cl_environments = None
if cl_device_ind is not None:
cl_environments = [get_cl_devices()[ind] for ind in cl_device_ind]
self._cl_runtime_info = CLRuntimeInfo(
cl_environments=cl_environments,
load_balancer=EvenDistribution(),
double_precision=double_precision)
if not model.is_input_data_sufficient(self._input_data):
raise InsufficientProtocolError(
'The provided protocol is insufficient for this model. '
'The reported errors where: {}'.format(
self._model.get_input_data_problems(self._input_data)))