def __init__(self):
super(PatternSnipeLabeling, self).__init__()
self.add_trait(
'graphs',
traits.List(traits.File(output=False), desc='graphs to classify'))
self.add_trait(
'traindata_file',
traits.File(output=False,
desc='file (.json) storing the data extracted'
' from the training base graphs'))
self.add_trait(
'param_file',
traits.File(output=False,
desc='file (.json) storing the hyperparameters'
' (OPM number, patch sizes)'))
self.add_trait(
'num_cpu',
traits.Int(
1,
output=False,
optional=True,
desc='number of processes that can be used to parallel the'
' calculations'))
self.add_trait(
'result_file',
traits.File(output=True,
desc='file (.csv) with predicted class (y_pred)'
' for each of the input graphs'))
def __init__(self):
super(ErrorComputation, self).__init__()
self.add_trait('t1mri', traits.File(output=False, desc='MRI scan'))
self.add_trait(
'true_graph',
traits.File(output=False,
desc='corresponding graph manually labeled'))
self.add_trait(
'labeled_graphs',
traits.List(
traits.File(output=False),
desc='corresponding set of graphs automatically labeled'))
self.add_trait(
'sulci_side_list',
traits.List(
traits.Str(output=False),
desc='list of sulci (e.g. S.C._right) considered to compute the'
' error rates. It is not supposed to contain the labels'
' "unknown", "ventricle_left" and "ventricle_right".'))
self.add_trait(
'error_file',
traits.File(
output=True,
desc=
'file (.csv) storing the error rates for each labeled graph'))
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
# Directories
base_dir = Directory(os.path.abspath('.'),mandatory=True, desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True, desc="Location where the BIP will store the results")
# Subjects
subjects = traits.List(traits.Str, mandatory=True, usedefault=True,
desc="Subject id's. Note: These MUST match the subject id's in the \
Freesurfer directory. For simplicity, the subject id's should \
also match with the location of individual functional files.")
fwhm=traits.List(traits.Float())
inputs_template = traits.String('%s/preproc/output/fwhm_%s/*.nii.gz')
meanfunc_template = traits.String('%s/preproc/mean/*_mean.nii.gz')
fsl_mat_template = traits.String('%s/preproc/bbreg/*.mat')
unwarped_brain_template = traits.String('%s/smri/unwarped_brain/*.nii*')
affine_transformation_template = traits.String('%s/smri/affine_transformation/*.nii*')
warp_field_template = traits.String('%s/smri/warped_field/*.nii*')
#Normalization
standard_transform_template = traits.File(mandatory=True,desc='Standard template to warp to')
standard_warp_field_template = traits.String()
standard_affine_transformation_template = traits.String()
standard_norm_template = traits.File()
standard_warp_field_template = traits.File()
standard_affine_transformation_template = traits.File()
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
# Buttons
check_func_datagrabber = Button("Check")
def __init__(self):
super(PatternSVMTraining, self).__init__()
self.add_trait(
'graphs',
traits.List(traits.File(output=False),
desc='training base graphs'))
self.add_trait(
'pattern',
traits.Str(output=False,
desc='vertex name representing the'
' searched pattern'))
self.add_trait(
'names_filter',
traits.ListStr(
output=False,
desc='list of vertex names used for the registration'
' of the patches'))
self.add_trait(
'step_1',
traits.Bool(
True,
output=False,
optional=True,
desc='perform the data extraction step from the graphs'))
self.add_trait(
'step_2',
traits.Bool(True,
output=False,
optional=True,
desc='perform the hyperparameter tuning step'
' (C, gamma, initial translations)'))
self.add_trait(
'step_3',
traits.Bool(True,
output=False,
optional=True,
desc='perform the model training step'))
self.add_trait(
'traindata_file',
traits.File(output=True,
desc='file (.json) storing the data extracted'
' from the training base graphs'))
self.add_trait(
'param_file',
traits.File(output=True,
desc='file (.json) storing the hyperparameters'
' (C, gamma, initial tranlations)'))
self.add_trait(
'clf_file',
traits.File(output=True,
desc='file (.sav) storing the trained SVM classifier'))
self.add_trait(
'scaler_file',
traits.File(output=True, desc='file (.sav) storing the scaler'))
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
desc = traits.Str(desc='Workflow description')
# Directories
base_dir = Directory(os.path.abspath('.'),mandatory=True, desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(os.path.abspath('.'),mandatory=True, desc="Location where the BIP will store the results")
field_dir = Directory(desc="Base directory of field-map data (Should be subject-independent) \
Set this value to None if you don't want fieldmap distortion correction")
surf_dir = Directory(mandatory=True, desc= "Freesurfer subjects directory")
# Subjects
subjects= traits.List(traits.Str, mandatory=True, usedefault=True,
desc="Subject id's. Note: These MUST match the subject id's in the \
Freesurfer directory. For simplicity, the subject id's should \
also match with the location of individual functional files.")
func_template = traits.String('%s/functional.nii.gz')
run_datagrabber_without_submitting = traits.Bool(desc="Run the datagrabber without \
submitting to the cluster")
timepoints_to_remove = traits.Int(0,usedefault=True)
do_slicetiming = Bool(True, usedefault=True, desc="Perform slice timing correction")
SliceOrder = traits.List(traits.Int)
order = traits.Enum('motion_slicetime','slicetime_motion',use_default=True)
TR = traits.Float(mandatory=True, desc = "TR of functional")
motion_correct_node = traits.Enum('nipy','fsl','spm','afni',
desc="motion correction algorithm to use",
usedefault=True,)
csf_prob = traits.File(desc='CSF_prob_map')
grey_prob = traits.File(desc='grey_prob_map')
white_prob = traits.File(desc='white_prob_map')
# Artifact Detection
norm_thresh = traits.Float(1, min=0, usedefault=True, desc="norm thresh for art")
z_thresh = traits.Float(3, min=0, usedefault=True, desc="z thresh for art")
# Smoothing
fwhm = traits.Float(6.0,usedefault=True)
save_script_only = traits.Bool(False)
check_func_datagrabber = Button("Check")
def _check_func_datagrabber_fired(self):
subs = self.subjects
for s in subs:
if not os.path.exists(os.path.join(self.base_dir,self.func_template % s)):
print "ERROR", os.path.join(self.base_dir,self.func_template % s), "does NOT exist!"
break
else:
print os.path.join(self.base_dir,self.func_template % s), "exists!"
def __init__(self):
super(PatternSnipeTraining, self).__init__()
self.add_trait(
'graphs',
traits.List(traits.File(output=False),
desc='training base graphs'))
self.add_trait(
'pattern',
traits.Str(output=False,
desc='vertex name representing the'
' searched pattern'))
self.add_trait(
'names_filter',
traits.ListStr(output=False,
desc='list of vertex names defining the region of'
' interest'))
self.add_trait(
'num_cpu',
traits.Int(
1,
output=False,
optional=True,
default=1,
desc='number of processes that can be used to parallel the'
' calculations'))
self.add_trait(
'step_1',
traits.Bool(
True,
output=False,
optional=True,
desc='perform the data extraction step from the graphs'))
self.add_trait(
'step_2',
traits.Bool(True,
output=False,
optional=True,
desc='perform the hyperparameter tuning step'
' (OPM number, patch sizes)'))
self.add_trait(
'traindata_file',
traits.File(output=True,
desc='file (.json) storing the data extracted'
' from the training base graphs'))
self.add_trait(
'param_file',
traits.File(output=True,
desc='file (.json) storing the hyperparameters'
' (OPM number, patch sizes)'))
class config(HasTraits):
uuid = traits.Str(desc="UUID")
# Directories
working_dir = Directory(mandatory=True, desc="Location of the Nipype working directory")
base_dir = Directory(os.path.abspath('.'),mandatory=True, desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True, desc="Location where the BIP will store the results")
crash_dir = Directory(mandatory=False, desc="Location to store crash files")
# Execution
run_using_plugin = Bool(False, usedefault=True, desc="True to run pipeline with plugin, False to run serially")
plugin = traits.Enum("PBS", "MultiProc", "SGE", "Condor",
usedefault=True,
desc="plugin to use, if run_using_plugin=True")
plugin_args = traits.Dict({"qsub_args": "-q many"},
usedefault=True, desc='Plugin arguments.')
test_mode = Bool(False, mandatory=False, usedefault=True,
desc='Affects whether where and if the workflow keeps its \
intermediary files. True to keep intermediary files. ')
timeout = traits.Float(14.0)
# Subjects
#subjects = traits.List(traits.Str, mandatory=True, usedefault=True,
# desc="Subject id's. Note: These MUST match the subject id's in the \
# Freesurfer directory. For simplicity, the subject id's should \
# also match with the location of individual functional files.")
#fwhm=traits.List(traits.Float())
#copes_template = traits.String('%s/preproc/output/fwhm_%s/cope*.nii.gz')
#varcopes_template = traits.String('%s/preproc/output/fwhm_%s/varcope*.nii.gz')
#contrasts = traits.List(traits.Str,desc="contrasts")
datagrabber = traits.Instance(Data, ())
# Regression
design_csv = traits.File(desc="design .csv file")
reg_contrasts = traits.Code(desc="function named reg_contrasts which takes in 0 args and returns contrasts")
#Normalization
norm_template = traits.File(mandatory=True,desc='Template of files')
#Correction:
run_correction = traits.Bool(False)
z_threshold = traits.Float(2.3)
connectivity = traits.Int(25)
do_randomize = traits.Bool(False)
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
# Buttons
check_func_datagrabber = Button("Check")
class Process1(Process):
'''
This silly process concatenates in an output file the input file and the other int input parameter. Not very useful, for sure.
'''
param_a = traits.File(output=False, desc='input param A')
param_b = traits.Int(desc='another parameter B')
param_c = traits.File(output=True, desc='output param C')
def _run_process(self):
with open(self.param_c, 'w') as f:
print('output file:', file=f)
with open(self.param_b) as sf:
f.write(sf.read())
print('param B:', self.param_b, file=f)
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
# Directories
base_dir = Directory(
os.path.abspath('.'),
mandatory=True,
desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True,
desc="Location where the BIP will store the results")
save_script_only = traits.Bool(False)
# Subjects
#subjects = traits.List(traits.Str, mandatory=True, usedefault=True,
# desc="Subject id's. Note: These MUST match the subject id's in the \
# Freesurfer directory. For simplicity, the subject id's should \
# also match with the location of individual functional files.")
#fwhm=traits.List(traits.Float())
#copes_template = traits.String('%s/preproc/output/fwhm_%s/cope*.nii.gz')
#varcopes_template = traits.String('%s/preproc/output/fwhm_%s/varcope*.nii.gz')
#contrasts = traits.List(traits.Str,desc="contrasts")
datagrabber = traits.Instance(Data, ())
# Regression
design_csv = traits.File(desc="design .csv file")
reg_contrasts = traits.Code(
desc=
"function named reg_contrasts which takes in 0 args and returns contrasts"
)
run_mode = traits.Enum("flame1", "ols", "flame12")
#Normalization
norm_template = traits.File(desc='Template of files')
use_mask = traits.Bool(False)
mask_file = traits.File()
#Correction:
run_correction = traits.Bool(False)
p_threshold = traits.Float(0.05)
z_threshold = traits.Float(2.3)
connectivity = traits.Int(26)
do_randomize = traits.Bool(False)
num_iterations = traits.Int(5000)
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
# Buttons
check_func_datagrabber = Button("Check")
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
desc = traits.Str(desc='Workflow description')
# Directories
working_dir = Directory(mandatory=True,
desc="Location of the Nipype working directory")
base_dir = Directory(
exists=True,
desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True,
desc="Location where the BIP will store the results")
field_dir = Directory(
exists=True,
desc="Base directory of field-map data (Should be subject-independent) \
Set this value to None if you don't want fieldmap distortion correction"
)
crash_dir = Directory(mandatory=False,
desc="Location to store crash files")
json_sink = Directory(mandatory=False, desc="Location to store json_files")
surf_dir = Directory(mandatory=True, desc="Freesurfer subjects directory")
# Subjects
subjects = traits.List(
traits.Str,
mandatory=True,
usedefault=True,
desc=
"Subject id's. These subjects must match the ones that have been run in your preproc config"
)
preproc_config = traits.File(desc="preproc config file")
debug = traits.Bool(True)
#Preprocessing Info
use_custom_ROI_list_file = Bool(
False,
usedefault=True,
desc=
"True to limit the produced TSNR table to a more selective list of ROIs"
)
custom_ROI_list_file = traits.File(
desc="Enter the full path to your customized FreeSurferColorLUT.txt")
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
save_script_only = traits.Bool(False)
class config(HasTraits):
uuid = traits.Str(desc="UUID")
desc = traits.Str(desc="Workflow Description")
# Directories
working_dir = Directory(mandatory=True, desc="Location of the Nipype working directory")
sink_dir = Directory(os.path.abspath('.'), mandatory=True, desc="Location where the BIP will store the results")
crash_dir = Directory(mandatory=False, desc="Location to store crash files")
surf_dir = Directory(mandatory=True, desc= "Freesurfer subjects directory")
save_script_only = traits.Bool(False)
# Execution
run_using_plugin = Bool(False, usedefault=True, desc="True to run pipeline with plugin, False to run serially")
plugin = traits.Enum("PBS", "MultiProc", "SGE", "Condor",
usedefault=True,
desc="plugin to use, if run_using_plugin=True")
plugin_args = traits.Dict({"qsub_args": "-q many"},
usedefault=True, desc='Plugin arguments.')
test_mode = Bool(False, mandatory=False, usedefault=True,
desc='Affects whether where and if the workflow keeps its \
intermediary files. True to keep intermediary files. ')
timeout = traits.Float(14.0)
subjects = traits.List(desc="subjects")
split_files = traits.List(traits.File(),desc="""list of split files""")
# First Level
#advanced_options
use_advanced_options = Bool(False)
advanced_options = traits.Code()
class config(HasTraits):
# Directories
working_dir = Directory(mandatory=True, desc="Location of the Nipype working directory")
base_dir = Directory(mandatory=True, desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True, desc="Location where the BIP will store the results")
crash_dir = Directory(mandatory=False, desc="Location to store crash files")
# Execution
run_using_plugin = Bool(False, usedefault=True, desc="True to run pipeline with plugin, False to run serially")
plugin = traits.Enum("PBS", "PBSGraph","MultiProc", "SGE", "Condor",
usedefault=True,
desc="plugin to use, if run_using_plugin=True")
plugin_args = traits.Dict({"qsub_args": "-q many"},
usedefault=True, desc='Plugin arguments.')
test_mode = Bool(False, mandatory=False, usedefault=True,
desc='Affects whether where and if the workflow keeps its \
intermediary files. True to keep intermediary files. ')
timeout = traits.Float(14.0)
#Subjects
subjects= traits.List(traits.Str, mandatory=True, usedefault=True,
desc="Subject id's. Bips expects dicoms to be organized by subject id's")
dicom_dir_template = traits.String('%s/dicoms/')
#Conversion Options
embed_meta = traits.Bool(True)
info_only = traits.Bool(True)
no_moco = traits.Bool(False,desc="only convert non-moco files")
use_heuristic = traits.Bool(False)
heuristic_file = traits.File(desc="heuristic file")
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
# Directories
base_dir = Directory(os.path.abspath('.'),mandatory=True, desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True, desc="Location where the BIP will store the results")
datagrabber = traits.Instance(Data, ())
run_mode = traits.Enum("flame1","ols","flame12")
save_script_only = traits.Bool(False)
#Normalization
brain_mask = traits.File(mandatory=True,desc='Brain Mask')
name_of_project = traits.String("group_analysis",usedefault=True)
do_randomize = traits.Bool(True)
num_iterations = traits.Int(5000)
#Correction:
run_correction = traits.Bool(True)
z_threshold = traits.Float(2.3)
p_threshold = traits.Float(0.05)
connectivity = traits.Int(26)
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
# Buttons
check_func_datagrabber = Button("Check")
class config(HasTraits):
uuid = traits.Str(desc="UUID")
desc = traits.Str(desc='Workflow description')
# Directories
working_dir = Directory(mandatory=True, desc="Location of the Nipype working directory")
sink_dir = Directory(mandatory=True, desc="Location where the BIP will store the results")
crash_dir = Directory(mandatory=False, desc="Location to store crash files")
# Execution
run_using_plugin = Bool(False, usedefault=True, desc="True to run pipeline with plugin, False to run serially")
plugin = traits.Enum("PBS", "PBSGraph","MultiProc", "SGE", "Condor",
usedefault=True,
desc="plugin to use, if run_using_plugin=True")
plugin_args = traits.Dict({"qsub_args": "-q many"},
usedefault=True, desc='Plugin arguments.')
test_mode = Bool(False, mandatory=False, usedefault=True,
desc='Affects whether where and if the workflow keeps its \
intermediary files. True to keep intermediary files. ')
# Subjects
subjects= traits.List(traits.Str, mandatory=True, usedefault=True,
desc="Subject id's. Note: These MUST match the subject id's in the \
Freesurfer directory. For simplicity, the subject id's should \
also match with the location of individual functional files.")
# Preprocessing info
preproc_config = traits.File(desc="preproc json file")
#Advanced
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
save_script_only = traits.Bool(False)
def createOption(name, initialValue):
"""creates an option with a boolean attribute as the value, type should be the result of type(value)"""
option = Option(name=name)
if type(initialValue) is bool:
option.add_trait("value", traits.Bool(initialValue))
elif type(initialValue) is int:
option.add_trait("value", traits.Int(initialValue))
elif type(initialValue) is float:
option.add_trait("value", traits.Float(initialValue))
elif type(initialValue) is str:
option.add_trait("value", traits.File(initialValue))
# # need to modify the view, not sure how to make this more elegantly
option.traits_view = traitsui.View(
traitsui.HGroup(
traitsui.Item("name",
style="readonly",
springy=True,
show_label=False),
traitsui.Item(
"value",
show_label=False,
springy=True,
editor=traitsui.FileEditor(dialog_style='save'))))
else:
logger.warning(
"unrecognised option type ({}) in processor. Using traits.Any Editor and value"
.format(type(initialValue)))
option.add_trait("value", traits.Any(initialValue))
return option
class InputData(T.HasTraits):
dwi_images = nifti_file
fa_file = nifti_file
bvec_file = T.File(filter=['*.bvec'])
bvec_orientation = T.String('IMG', minlen=3, maxlen=3)
min_signal = T.Float(1)
@T.on_trait_change('dwi_images')
def update_files(self):
dir, file = path.split(self.dwi_images)
base = string.split(file, path.extsep, 1)[0]
if self.fa_file == '':
self.fa_file = path.join(dir, base + '_fa.nii.gz')
if self.bvec_file == '':
self.bvec_file = path.join(dir, base + '.bvec')
def read_data(self):
data_img = nib.load(self.dwi_images)
affine = data_img.get_affine()
voxel_size = data_img.get_header().get_zooms()
voxel_size = voxel_size[:3]
fa_img = nib.load(self.fa_file)
assert data_img.shape[:-1] == fa_img.shape
bvec, bval = read_bvec_file(self.bvec_file)
data_ornt = nib.io_orientation(affine)
if self.bvec_orientation != 'IMG':
bvec = reorient_vectors(bvec, self.bvec_orientation, data_ornt)
fa = fa_img.get_data()
data = data_img.get_data()
return data, voxel_size, affine, fa, bvec, bval
def __init__(self,
pipeline,
name,
input_names=['inputs'],
output_names=['output_%d'],
input_types=None):
in_traits = []
out_traits = [{'name': 'lengths', 'optional': True}]
if input_types:
ptypes = input_types
else:
ptypes = [traits.File(traits.Undefined, output=False)] \
* len(input_names)
self.input_types = ptypes
for tr in input_names:
in_traits.append({'name': tr, 'optional': False})
super(MapNode, self).__init__(pipeline, name, in_traits, out_traits)
for tr, ptype in zip(input_names, ptypes):
self.add_trait(tr, traits.List(ptype, output=False))
self.add_trait(
'lengths',
traits.List(traits.Int(),
output=True,
optional=True,
desc='lists lengths'))
self.input_names = input_names
self.output_names = output_names
self.lengths = [0] * len(input_names)
self.set_callbacks()
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
desc = traits.Str(desc='Workflow description')
# Directories
base_dir = Directory(
exists=True,
desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True,
desc="Location where the BIP will store the results")
field_dir = Directory(
exists=True,
desc="Base directory of field-map data (Should be subject-independent) \
Set this value to None if you don't want fieldmap distortion correction"
)
surf_dir = Directory(mandatory=True, desc="Freesurfer subjects directory")
save_script_only = traits.Bool(False)
# Subjects
datagrabber = traits.Instance(Data, ())
TR = traits.Float(6.0)
preproc_config = traits.File(desc="preproc config file")
json_name = traits.String('preproc_metrics')
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
class config(HasTraits):
uuid = traits.Str(desc="UUID")
desc = traits.Str(desc='Workflow description')
# Directories
working_dir = Directory(mandatory=True,
desc="Location of the Nipype working directory")
base_dir = Directory(
exists=True,
desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True,
desc="Location where the BIP will store the results")
field_dir = Directory(
exists=True,
desc="Base directory of field-map data (Should be subject-independent) \
Set this value to None if you don't want fieldmap distortion correction"
)
crash_dir = Directory(mandatory=False,
desc="Location to store crash files")
json_sink = Directory(mandatory=False, desc="Location to store json_files")
surf_dir = Directory(mandatory=True, desc="Freesurfer subjects directory")
# Execution
run_using_plugin = Bool(
False,
usedefault=True,
desc="True to run pipeline with plugin, False to run serially")
plugin = traits.Enum("PBS",
"PBSGraph",
"MultiProc",
"SGE",
"Condor",
usedefault=True,
desc="plugin to use, if run_using_plugin=True")
plugin_args = traits.Dict({"qsub_args": "-q many"},
usedefault=True,
desc='Plugin arguments.')
test_mode = Bool(
False,
mandatory=False,
usedefault=True,
desc='Affects whether where and if the workflow keeps its \
intermediary files. True to keep intermediary files. '
)
# Subjects
subjects = traits.List(
traits.Str,
mandatory=True,
usedefault=True,
desc=
"Subject id's. These subjects must match the ones that have been run in your preproc config"
)
preproc_config = traits.File(desc="preproc config file")
debug = traits.Bool(True)
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
class config(HasTraits):
uuid = traits.Str(desc="UUID")
# Directories
working_dir = Directory(mandatory=True,
desc="Location of the Nipype working directory")
base_dir = Directory(
os.path.abspath('.'),
mandatory=True,
desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True,
desc="Location where the BIP will store the results")
crash_dir = Directory(mandatory=False,
desc="Location to store crash files")
# Execution
run_using_plugin = Bool(
False,
usedefault=True,
desc="True to run pipeline with plugin, False to run serially")
plugin = traits.Enum("PBS",
"MultiProc",
"SGE",
"Condor",
usedefault=True,
desc="plugin to use, if run_using_plugin=True")
plugin_args = traits.Dict({"qsub_args": "-q many"},
usedefault=True,
desc='Plugin arguments.')
test_mode = Bool(
False,
mandatory=False,
usedefault=True,
desc='Affects whether where and if the workflow keeps its \
intermediary files. True to keep intermediary files. '
)
timeout = traits.Float(14.0)
datagrabber = traits.Instance(Data, ())
run_mode = traits.Enum("flame1", "ols", "flame12")
save_script_only = traits.Bool(False)
#Normalization
brain_mask = traits.File(mandatory=True, desc='Brain Mask')
name_of_project = traits.String("group_analysis", usedefault=True)
do_randomize = traits.Bool(True)
num_iterations = traits.Int(5000)
#Correction:
run_correction = traits.Bool(True)
z_threshold = traits.Float(2.3)
p_threshold = traits.Float(0.05)
connectivity = traits.Int(26)
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
# Buttons
check_func_datagrabber = Button("Check")
def __init__(self):
super(LabelResample, self).__init__()
self.add_trait('input_image', traits.File(
output=False, desc='Labelled image to transform'))
self.add_trait('transformation', traits.File(
output=False, optional=True, desc='Transformation file .trm'))
self.add_trait('sx', traits.Float(-1, output=False,
desc='Output resolution (X axis)'))
self.add_trait('sy', traits.Float(-1, output=False,
desc='Output resolution (Y axis)'))
self.add_trait('sz', traits.Float(-1, output=False,
desc='Output resolution (Z axis)'))
self.add_trait('background', traits.Int(0, output=False,
desc='Background value/label'))
self.add_trait('output_image', traits.File(
output=False, desc='file (.json) storing the hyperparameters'
' (cutting threshold)'))
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
# Directories
base_dir = Directory(
os.path.abspath('.'),
mandatory=True,
desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True,
desc="Location where the BIP will store the results")
surf_dir = Directory(
desc="freesurfer directory. subject id's should be the same")
save_script_only = traits.Bool(False)
# DataGrabber
datagrabber = traits.Instance(Data, ())
# segstats
use_reg = traits.Bool(True)
inverse_reg = traits.Bool(True)
use_standard_label = traits.Bool(
False, desc="use same label file for all subjects")
label_file = traits.File()
use_annotation = traits.Bool(
False,
desc=
"use same annotation file for all subjects (will warp to subject space"
)
use_subject_annotation = traits.Bool(
False,
desc="you need to change datragrabber to\
have outputs lh_annotation and rh_annotation"
)
annot_space = traits.String("fsaverage5",
desc="subject space of annot file")
lh_annotation = traits.File()
rh_annotation = traits.File()
color_table_file = traits.Enum("Default", "Color_Table", "GCA_color_table",
"None")
color_file = traits.File()
proj = traits.BaseTuple(("frac", 0, 1, 0.1), traits.Enum("abs", "frac"),
traits.Float(), traits.Float(), traits.Float())
statname = traits.Str('segstats1', desc="description of the segstat")
def __init__(self):
super(PatternDeepLabeling, self).__init__()
self.add_trait(
'graphs',
traits.List(traits.File(output=False), desc='graphs to classify'))
self.add_trait(
'model_file',
traits.File(output=False,
desc='file (.mdsm) storing neural network parameters'))
self.add_trait(
'param_file',
traits.File(output=False,
desc='file (.json) storing the hyperparameters'
' (bounding_box, learning rate and momentum)'))
self.add_trait(
'result_file',
traits.File(output=True,
desc='file (.csv) with predicted class (y_pred)'
' for each of the input graphs'))
def build_node(cls, pipeline, name, conf_controller):
t = None
if conf_controller.param_type == 'Str':
t = traits.Str(traits.Undefined)
elif conf_controller.param_type == 'File':
t = traits.File(traits.Undefined)
elif conf_controller.param_type not in (None, traits.Undefined):
t = getattr(traits, conf_controller.param_type)()
node = CrossValidationFoldNode(pipeline, name, input_type=t)
return node
class config(HasTraits):
uuid = traits.Str(desc="UUID")
# Directories
working_dir = Directory(mandatory=True, desc="Location of the Nipype working directory")
base_dir = Directory(os.path.abspath('.'),mandatory=True, desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True, desc="Location where the BIP will store the results")
crash_dir = Directory(mandatory=False, desc="Location to store crash files")
# Execution
run_using_plugin = Bool(False, usedefault=True, desc="True to run pipeline with plugin, False to run serially")
plugin = traits.Enum("PBS", "MultiProc", "SGE", "Condor",
usedefault=True,
desc="plugin to use, if run_using_plugin=True")
plugin_args = traits.Dict({"qsub_args": "-q many"},
usedefault=True, desc='Plugin arguments.')
test_mode = Bool(False, mandatory=False, usedefault=True,
desc='Affects whether where and if the workflow keeps its \
intermediary files. True to keep intermediary files. ')
timeout = traits.Float(14.0)
# Subjects
datagrabber = traits.Instance(Data, ())
#Normalization
norm_template = traits.File(mandatory=True,desc='Template to warp to')
use_nearest = traits.Bool(False,desc="use nearest neighbor interpolation")
do_segment = traits.Bool(True)
surf_dir = traits.Directory()
moving_images_4D = traits.Bool(True, usedefault=True, desc="True if your moving image inputs \
are time series images, False if they are 3-dimensional")
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
save_script_only = traits.Bool(False)
# Buttons
check_func_datagrabber = Button("Check")
def _check_func_datagrabber_fired(self):
subs = self.subjects
template = [self.inputs_template,
self.meanfunc_template,
self.fsl_mat_template,
self.unwarped_brain_template,
self.affine_transformation_template,
self.warp_field_template]
for s in subs:
for t in template:
try:
temp = glob(os.path.join(self.base_dir,t%s))
except TypeError:
temp = []
for f in self.fwhm:
temp.append(glob(os.path.join(self.base_dir,t%(s,f))))
print temp
def edition_widget(engine, environment):
''' Edition GUI for FSL config - see
:class:`~capsul.qt_gui.widgets.settings_editor.SettingsEditor`
'''
from soma.qt_gui.controller_widget import ScrollControllerWidget
from soma.controller import Controller
import types
import traits.api as traits
def validate_config(widget):
controller = widget.controller_widget.controller
with widget.engine.settings as session:
conf = session.config('fsl', widget.environment)
values = {'config_id': 'fsl'}
for k in ('directory', 'config', 'prefix'):
value = getattr(controller, k)
if value is traits.Undefined:
value = None
values[k] = value
if conf is None:
session.new_config('fsl', widget.environment, values)
else:
for k, value in values.items():
if k == 'config_id':
continue
setattr(conf, k, values[k])
controller = Controller()
controller.add_trait(
'directory',
traits.Directory(traits.Undefined,
desc='Directory where FSL is installed'))
controller.add_trait(
'config',
traits.File(traits.Undefined,
output=False,
desc='Parameter to specify the fsl.sh path'))
controller.add_trait(
'prefix',
traits.String(traits.Undefined, desc='Prefix to add to FSL commands'))
conf = engine.settings.select_configurations(environment, {'fsl': 'any'})
if conf:
fconf = conf.get('capsul.engine.module.fsl', {})
controller.directory = fconf.get('directory', traits.Undefined)
controller.config = fconf.get('config', traits.Undefined)
controller.prefix = fconf.get('prefix', traits.Undefined)
widget = ScrollControllerWidget(controller, live=True)
widget.engine = engine
widget.environment = environment
widget.accept = types.MethodType(validate_config, widget)
return widget
def build_node(cls, pipeline, name, conf_controller):
t = None
if conf_controller.param_type == 'Str':
t = traits.Str(traits.Undefined)
elif conf_controller.param_type == 'File':
t = traits.File(traits.Undefined)
elif conf_controller.param_type not in (None, traits.Undefined):
t = getattr(traits, conf_controller.param_type)()
node = CVFilterNode(pipeline, name, conf_controller.is_output,
input_type=t)
return node
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
# Directories
base_dir = Directory(
os.path.abspath('.'),
mandatory=True,
desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True,
desc="Location where the BIP will store the results")
save_script_only = traits.Bool(False)
datagrabber = traits.Instance(Data, ())
# Regression
run_one_sample_T_test = traits.Bool(True)
run_regression = traits.Bool()
design_csv = traits.File(desc="design .csv file")
reg_contrasts = traits.Code(
desc=
"function named reg_contrasts which takes in 0 args and returns contrasts"
)
use_regressors = traits.Bool()
estimation_method = traits.Enum('Classical', 'Bayesian', 'Bayesian2')
include_intercept = traits.Bool(True)
#Normalization
norm_template = traits.File(desc='Template of files')
use_mask = traits.Bool(False)
mask_file = traits.File(desc='already binarized mask file to use')
#Correction:
p_threshold = traits.Float(0.05)
height_threshold = traits.Float(0.05)
min_cluster_size = traits.Int(25)
# Advanced Options
use_advanced_options = traits.Bool()
advanced_script = traits.Code()
# Buttons
check_func_datagrabber = Button("Check")
class config(BaseWorkflowConfig):
uuid = traits.Str(desc="UUID")
# Directories
base_dir = Directory(
os.path.abspath('.'),
mandatory=True,
desc='Base directory of data. (Should be subject-independent)')
sink_dir = Directory(mandatory=True,
desc="Location where the BIP will store the results")
surf_dir = Directory(
desc="freesurfer directory. subject id's should be the same")
save_script_only = traits.Bool(False)
# Data
subject_id = traits.String()
contrast = traits.File()
mask_contrast = traits.File()
use_contrast_mask = traits.Bool(True)
reg_file = traits.File()
mean_image = traits.File()
background_thresh = traits.Float(0.5)
roi = traits.List(
['superiortemporal', 'bankssts'],
traits.Enum('superiortemporal', 'bankssts', 'caudalanteriorcingulate',
'caudalmiddlefrontal', 'corpuscallosum', 'cuneus',
'entorhinal', 'fusiform', 'inferiorparietal',
'inferiortemporal', 'isthmuscingulate', 'lateraloccipital',
'lateralorbitofrontal', 'lingual', 'medialorbitofrontal',
'middletemporal', 'parahippocampal', 'paracentral',
'parsopercularis', 'parsorbitalis', 'parstriangularis',
'pericalcarine', 'postcentral', 'posteriorcingulate',
'precentral', 'precuneus', 'rostralanteriorcingulate',
'rostralmiddlefrontal', 'superiorfrontal',
'superiorparietal', 'supramarginal', 'frontalpole',
'temporalpole', 'transversetemporal', 'insula'),
usedefault=True) #35 freesurfer regions,
thresh = traits.Float(1.5)
def __init__(self):
super(PatternSVMLabeling, self).__init__()
self.add_trait(
'graphs',
traits.List(traits.File(output=False), desc='graphs to classify'))
self.add_trait(
'clf_file',
traits.File(output=False,
desc='file (.sav) storing the trained SVM'
' classifier'))
self.add_trait(
'scaler_file',
traits.File(output=False, desc='file (.sav) storing the scaler'))
self.add_trait(
'param_file',
traits.File(output=False,
desc='file (.json) storing the hyperparameters'
' (C, gamma, initial tranlations)'))
self.add_trait(
'result_file',
traits.File(output=True,
desc='file (.csv) with predicted class (y_pred)'
' for each of the input graphs'))
