def dicom_values(self, tags):
"""
Returns a dictionary with the DICOM header fields corresponding
to the given tag names
Parameters
----------
tags : List[Tuple[str, str]]
List of DICOM tag values as 2-tuple of strings, e.g.
[('0080', '0020')]
repository_login : <repository-login-object>
A login object for the repository to avoid having to relogin
for every dicom_header call.
Returns
-------
dct : Dict[Tuple[str, str], str|int|float]
"""
try:
if (self._path is None and self._repository is not None and
hasattr(self.repository, 'dicom_header')):
hdr = self.repository.dicom_header(self)
dct = {t: hdr[t] for t in tags}
else:
# Get the DICOM object for the first file in the fileset
dcm = self.dicom(0)
dct = {t: dcm[t].value for t in tags}
except KeyError as e:
raise ArcanaNameError(
e.args[0], "{} does not have dicom tag {}".format(
self, e.args[0]))
return dct
def session(self, subject_id):
try:
return self._sessions[subject_id]
except KeyError:
raise ArcanaNameError(
subject_id, ("{} doesn't have a session named '{}'".format(
self, subject_id)))
def spec(self, name):
"""
Returns either the input corresponding to a fileset or field
field spec or a spec or parameter that has either
been passed to the study as an input or can be derived.
Parameters
----------
name : Str | BaseData | Parameter
An parameter, fileset or field or name of one
"""
if isinstance(name, (BaseData, Parameter)):
name = name.name
try:
spec = self._inputs[name]
except KeyError:
try:
spec = self._bound_specs[name]
except KeyError:
if name in self._data_specs:
raise ArcanaMissingDataException(
"Acquired (i.e. non-generated) fileset '{}' "
"was not supplied when the study '{}' was "
"initiated".format(name, self.name))
else:
try:
spec = self._param_specs[name]
except KeyError:
raise ArcanaNameError(
name, "'{}' is not a recognised spec name "
"for {} studies:\n{}.".format(
name, self.__class__.__name__,
'\n'.join(sorted(self.spec_names()))))
return spec
def sub_study_spec(cls, name):
try:
return cls._sub_study_specs[name]
except KeyError:
raise ArcanaNameError(
name, "'{}' not found in sub-studes ('{}')".format(
name, "', '".join(cls._sub_study_specs)))
def sub_study(self, name):
try:
return self._sub_studies[name]
except KeyError:
raise ArcanaNameError(
name, "'{}' not found in sub-studes ('{}')".format(
name, "', '".join(self._sub_studies)))
def parameter_spec(cls, name):
try:
return cls._param_specs[name]
except KeyError:
raise ArcanaNameError(
name, "No parameter spec named '{}' in {} (available: "
"'{}')".format(name, cls.__name__,
"', '".join(list(cls._param_specs.keys()))))
def _get_parameter(self, name):
try:
parameter = self._parameters[name]
except KeyError:
try:
parameter = self._param_specs[name]
except KeyError:
raise ArcanaNameError(
name, "Invalid parameter, '{}', in {} (valid '{}')".format(
name, self._param_error_location,
"', '".join(self.parameter_spec_names())))
return parameter
def map(self, name):
try:
return self._name_map[name]
except KeyError:
if name not in self.study_class.spec_names():
raise ArcanaNameError(
name,
"'{}' doesn't match any filesets, fields, parameters "
"in the study class {} ('{}')".format(
name, self.name, self.study_class.__name__,
"', '".join(self.study_class.spec_names())))
return self.apply_prefix(name)
def data_spec(cls, name):
"""
Return the fileset_spec, i.e. the template of the fileset expected to
be supplied or generated corresponding to the fileset_spec name.
Parameters
----------
name : Str
Name of the fileset_spec to return
"""
if isinstance(name, BaseData):
name = name.name
try:
return cls._data_specs[name]
except KeyError:
raise ArcanaNameError(
name, "No fileset spec named '{}' in {} (available: "
"'{}')".format(name, cls.__name__,
"', '".join(list(cls._data_specs.keys()))))
def field(self, name, study=None):
try:
return self._fields[(name, study)]
except KeyError:
available = [d.name for d in self.fields if d.from_study == study]
other_studies = [
d.from_study for d in self.fields if d.name == name
]
if other_studies:
msg = (
". NB: matching field(s) found for '{}' study(ies)".format(
name, other_studies))
else:
msg = ''
raise ArcanaNameError(
name, ("{} doesn't have a field named '{}' "
"(available '{}')".format(
self, name,
("for study '{}'" if study is not None else ''),
"', '".join(available), other_studies), msg))
def visit(self, id): # @ReservedAssignment
try:
return self._visits[id]
except KeyError:
raise ArcanaNameError(
id, ("{} doesn't have a visit named '{}'".format(self, id)))
def input(self, name):
try:
return self._inputs[name]
except KeyError:
raise ArcanaNameError(
name, "{} doesn't have an input named '{}'".format(self, name))
def __init__(self,
name,
repository,
processor,
inputs,
environment=None,
parameters=None,
subject_ids=None,
visit_ids=None,
enforce_inputs=True,
reprocess=False,
fill_tree=False):
try:
# This works for PY3 as the metaclass inserts it itself if
# it isn't provided
metaclass = type(self).__dict__['__metaclass__']
if not issubclass(metaclass, StudyMetaClass):
raise KeyError
except KeyError:
raise ArcanaUsageError(
"Need to have StudyMetaClass (or a sub-class) as "
"the metaclass of all classes derived from Study")
if isinstance(repository, basestring):
repository = DirectoryRepository(repository, depth=None)
if isinstance(processor, basestring):
processor = LinearProcessor(processor)
if environment is None:
environment = StaticEnvironment()
self._name = name
self._repository = repository
self._processor = processor.bind(self)
self._environment = environment
self._inputs = {}
self._subject_ids = subject_ids
self._visit_ids = visit_ids
self._tree = self.repository.cached_tree(subject_ids=subject_ids,
visit_ids=visit_ids,
fill=fill_tree)
if not self.subject_ids:
raise ArcanaUsageError(
"No subject IDs provided and destination repository "
"is empty")
if not self.visit_ids:
raise ArcanaUsageError(
"No visit IDs provided and destination repository "
"is empty")
self._reprocess = reprocess
# For recording which parameters are accessed
# during pipeline generation so they can be attributed to the
# pipeline after it is generated (and then saved in the
# provenance
self._pipeline_to_generate = None
self._referenced_parameters = None
# Set parameters
if parameters is None:
parameters = {}
elif not isinstance(parameters, dict):
# Convert list of parameters into dictionary
parameters = {o.name: o for o in parameters}
self._parameters = {}
for param_name, param in list(parameters.items()):
if not isinstance(param, Parameter):
param = Parameter(param_name, param)
try:
param_spec = self._param_specs[param_name]
except KeyError:
raise ArcanaNameError(
param_name,
"Provided parameter '{}' is not present in the "
"allowable parameters for {} classes ('{}')".format(
param_name,
type(self).__name__,
"', '".join(self.parameter_spec_names())))
param_spec.check_valid(param,
context='{}(name={})'.format(
type(self).__name__, name))
self._parameters[param_name] = param
# Convert inputs to a dictionary if passed in as a list/tuple
if not isinstance(inputs, dict):
inputs = {i.name: i for i in inputs}
# Add each "input fileset" checking to see whether the given
# fileset_spec name is valid for the study types
for inpt_name, inpt in list(inputs.items()):
try:
spec = self.data_spec(inpt_name)
except ArcanaNameError:
raise ArcanaNameError(
inpt.name,
"Input name '{}' isn't in data specs of {} ('{}')".format(
inpt.name, self.__class__.__name__,
"', '".join(self._data_specs)))
else:
if isinstance(spec, BaseFileset):
if isinstance(inpt, BaseField):
raise ArcanaUsageError(
"Passed field ({}) as input to fileset spec"
" {}".format(inpt, spec))
if spec.derived:
try:
# FIXME: should provide requirement manager to
# converter_from but it hasn't been implemented yet
spec.format.converter_from(inpt.format)
except ArcanaNoConverterError as e:
raise ArcanaNoConverterError(
"{}, which is requried to convert:\n{} "
"to\n{}.".format(e, inpt, spec))
else:
if inpt.format not in spec.valid_formats:
raise ArcanaUsageError(
"Cannot pass {} as an input to {} as it is "
"not in one of the valid formats ('{}')".
format(
inpt, spec,
"', '".join(f.name
for f in spec.valid_formats)))
elif not isinstance(inpt, BaseField):
raise ArcanaUsageError(
"Passed fileset ({}) as input to field spec {}".format(
inpt, spec))
self._inputs[inpt_name] = inpt.bind(self)
# "Bind" data specs in the class to the current study object
# this will allow them to prepend the study name to the name
# of the fileset
self._bound_specs = {}
for spec in self.data_specs():
if spec.name not in self.input_names:
if not spec.derived and spec.default is None:
# Emit a warning if an acquired fileset has not been
# provided for an "acquired fileset"
msg = (" acquired fileset '{}' was not given as"
" an input of {}.".format(spec.name, self))
if spec.optional:
logger.info('Optional' + msg)
else:
if enforce_inputs:
raise ArcanaMissingInputError(
'Non-optional' + msg + " Pipelines "
"depending on this fileset will not "
"run")
else:
self._bound_specs[spec.name] = spec.bind(self)
def __init__(self,
name,
repository,
processor,
inputs,
parameters=None,
**kwargs):
try:
# This works for PY3 as the metaclass inserts it itself if
# it isn't provided
metaclass = type(self).__dict__['__metaclass__']
if not issubclass(metaclass, MultiStudyMetaClass):
raise KeyError
except KeyError:
raise ArcanaUsageError(
"Need to set MultiStudyMetaClass (or sub-class) as "
"the metaclass of all classes derived from "
"MultiStudy")
super(MultiStudy, self).__init__(name,
repository,
processor,
inputs,
parameters=parameters,
**kwargs)
self._sub_studies = {}
for sub_study_spec in self.sub_study_specs():
sub_study_cls = sub_study_spec.study_class
# Map inputs, data_specs to the sub_study
mapped_inputs = {}
for data_name in sub_study_cls.data_spec_names():
mapped_name = sub_study_spec.map(data_name)
if mapped_name in self.input_names:
mapped_inputs[data_name] = self.input(mapped_name)
else:
try:
inpt = self.spec(mapped_name)
except ArcanaMissingDataException:
pass
else:
if inpt.derived:
mapped_inputs[data_name] = inpt
# Map parameters to the sub_study
mapped_parameters = {}
for param_name in sub_study_cls.parameter_spec_names():
mapped_name = sub_study_spec.map(param_name)
parameter = self._get_parameter(mapped_name)
mapped_parameters[param_name] = parameter
# Create sub-study
sub_study = sub_study_spec.study_class(
name + '_' + sub_study_spec.name,
repository,
processor,
mapped_inputs,
parameters=mapped_parameters,
enforce_inputs=False)
# Append to dictionary of sub_studies
if sub_study_spec.name in self._sub_studies:
raise ArcanaNameError(
sub_study_spec.name,
"Duplicate sub-study names '{}'".format(
sub_study_spec.name))
self._sub_studies[sub_study_spec.name] = sub_study