def test_surface_voxel_query_engine(self):
vol_shape = (10, 10, 10, 1)
vol_affine = np.identity(4)
vol_affine[0, 0] = vol_affine[1, 1] = vol_affine[2, 2] = 5
vg = volgeom.VolGeom(vol_shape, vol_affine)
# make the surfaces
sphere_density = 10
outer = surf.generate_sphere(sphere_density) * 25. + 15
inner = surf.generate_sphere(sphere_density) * 20. + 15
vs = volsurf.VolSurfMaximalMapping(vg, inner, outer)
radius = 10
for fallback, expected_nfeatures in ((True, 1000), (False, 183)):
voxsel = surf_voxel_selection.voxel_selection(vs, radius)
qe = SurfaceVoxelsQueryEngine(voxsel,
fallback_euclidian_distance=fallback)
m = _Voxel_Count_Measure()
sl = Searchlight(m, queryengine=qe)
data = np.random.normal(size=vol_shape)
img = nb.Nifti1Image(data, vol_affine)
ds = fmri_dataset(img)
sl_map = sl(ds)
counts = sl_map.samples
assert_true(np.all(np.logical_and(5 <= counts, counts <= 18)))
assert_equal(sl_map.nfeatures, expected_nfeatures)
def _get_seed_means(self, measure, queryengine, dataset, seed_indices):
# Computing seed data as mean timeseries in each SL
seed_data = Searchlight(measure, queryengine=queryengine,
nproc=self.params.nproc, roi_ids=seed_indices)
seed_data = seed_data(dataset)
zscore(seed_data, chunks_attr=None)
return seed_data
def _seed_means(self, measure, queryengine, ds, seed_indices):
# Seed data is the mean timeseries for each searchlight
seed_data = Searchlight(measure, queryengine=queryengine,
nproc=self.nproc, roi_ids=np.concatenate(seed_indices).copy())
if isinstance(ds,np.ndarray):
ds = Dataset(ds)
seed_data = seed_data(ds)
zscore(seed_data.samples, chunks_attr=None)
return seed_data
def test_niml_dset_voxsel(self):
if not externals.exists('nibabel'):
return
# This is actually a bit of an integration test.
# It tests storing and retrieving searchlight results.
# Imports are inline here so that it does not mess up the header
# and makes the other unit tests more modular
# XXX put this in a separate file?
from mvpa2.misc.surfing import volgeom, surf_voxel_selection, queryengine
from mvpa2.measures.searchlight import Searchlight
from mvpa2.support.nibabel import surf
from mvpa2.measures.base import Measure
from mvpa2.datasets.mri import fmri_dataset
class _Voxel_Count_Measure(Measure):
# used to check voxel selection results
is_trained = True
def __init__(self, dtype, **kwargs):
Measure.__init__(self, **kwargs)
self.dtype = dtype
def _call(self, dset):
return self.dtype(dset.nfeatures)
sh = (20, 20, 20)
vg = volgeom.VolGeom(sh, np.identity(4))
density = 20
outer = surf.generate_sphere(density) * 10. + 5
inner = surf.generate_sphere(density) * 5. + 5
intermediate = outer * .5 + inner * .5
xyz = intermediate.vertices
radius = 50
sel = surf_voxel_selection.run_voxel_selection(radius, vg, inner,
outer)
qe = queryengine.SurfaceVerticesQueryEngine(sel)
for dtype in (int, float):
sl = Searchlight(_Voxel_Count_Measure(dtype), queryengine=qe)
ds = fmri_dataset(vg.get_empty_nifti_image(1))
r = sl(ds)
_, fn = tempfile.mkstemp('.niml.dset', 'dset')
niml_dset.write(fn, r)
rr = niml_dset.read(fn)
os.remove(fn)
assert_array_equal(r.samples, rr.samples)
def test_1d_multispace_searchlight(self):
ds = Dataset([np.arange(6)])
ds.fa['coord1'] = np.repeat(np.arange(3), 2)
# add a second space to the dataset
ds.fa['coord2'] = np.tile(np.arange(2), 3)
measure = lambda x: "+".join([str(x) for x in x.samples[0]])
# simply select each feature once
res = Searchlight(measure,
IndexQueryEngine(coord1=Sphere(0), coord2=Sphere(0)),
nproc=1)(ds)
assert_array_equal(res.samples, [['0', '1', '2', '3', '4', '5']])
res = Searchlight(measure,
IndexQueryEngine(coord1=Sphere(0), coord2=Sphere(1)),
nproc=1)(ds)
assert_array_equal(res.samples,
[['0+1', '0+1', '2+3', '2+3', '4+5', '4+5']])
res = Searchlight(measure,
IndexQueryEngine(coord1=Sphere(1), coord2=Sphere(0)),
nproc=1)(ds)
assert_array_equal(res.samples,
[['0+2', '1+3', '0+2+4', '1+3+5', '2+4', '3+5']])
def test_agreement_surface_volume(self):
'''test agreement between volume-based and surface-based
searchlights when using euclidean measure'''
# import runner
def sum_ds(ds):
return np.sum(ds)
radius = 3
# make a small dataset with a mask
sh = (10, 10, 10)
msk = np.zeros(sh)
for i in xrange(0, sh[0], 2):
msk[i, :, :] = 1
vg = volgeom.VolGeom(sh, np.identity(4), mask=msk)
# make an image
nt = 6
img = vg.get_masked_nifti_image(6)
ds = fmri_dataset(img, mask=msk)
# run the searchlight
sl = sphere_searchlight(sum_ds, radius=radius)
m = sl(ds)
# now use surface-based searchlight
v = volsurf.from_volume(ds)
source_surf = v.intermediate_surface
node_msk = np.logical_not(np.isnan(source_surf.vertices[:, 0]))
# check that the mask matches with what we used earlier
assert_array_equal(msk.ravel() + 0., node_msk.ravel() + 0.)
source_surf_nodes = np.nonzero(node_msk)[0]
sel = surf_voxel_selection.voxel_selection(
v,
float(radius),
source_surf=source_surf,
source_surf_nodes=source_surf_nodes,
distance_metric='euclidean')
qe = queryengine.SurfaceVerticesQueryEngine(sel)
sl = Searchlight(sum_ds, queryengine=qe)
r = sl(ds)
# check whether they give the same results
assert_array_equal(r.samples, m.samples)
def test_surface_voxel_query_engine(self):
vol_shape = (10, 10, 10, 1)
vol_affine = np.identity(4)
vol_affine[0, 0] = vol_affine[1, 1] = vol_affine[2, 2] = 5
vg = volgeom.VolGeom(vol_shape, vol_affine)
# make the surfaces
sphere_density = 10
outer = surf.generate_sphere(sphere_density) * 25. + 15
inner = surf.generate_sphere(sphere_density) * 20. + 15
vs = volsurf.VolSurfMaximalMapping(vg, inner, outer)
radius = 10
for fallback, expected_nfeatures in ((True, 1000), (False, 183)):
voxsel = surf_voxel_selection.voxel_selection(vs, radius)
qe = SurfaceVoxelsQueryEngine(voxsel,
fallback_euclidean_distance=fallback)
# test i/o and ensure that the loaded instance is trained
if externals.exists('h5py'):
fd, qefn = tempfile.mkstemp('qe.hdf5', 'test')
os.close(fd)
h5save(qefn, qe)
qe = h5load(qefn)
os.remove(qefn)
m = _Voxel_Count_Measure()
sl = Searchlight(m, queryengine=qe)
data = np.random.normal(size=vol_shape)
img = nb.Nifti1Image(data, vol_affine)
ds = fmri_dataset(img)
sl_map = sl(ds)
counts = sl_map.samples
assert_true(np.all(np.logical_and(5 <= counts, counts <= 18)))
assert_equal(sl_map.nfeatures, expected_nfeatures)
def test_add_center_fa(self):
# just a smoke test pretty much
ds = datasets['3dsmall'].copy()
# check that we do not mark anything as center whenever there is none
def check_no_center(ds):
assert (not np.any(ds.fa.center))
return 1.0
# or just a single center in our case
def check_center(ds):
assert (np.sum(ds.fa.center) == 1)
return 1.0
for n, check in [(HollowSphere(1, 0), check_no_center),
(Sphere(0), check_center), (Sphere(1), check_center)]:
Searchlight(check,
IndexQueryEngine(myspace=n),
add_center_fa='center')(ds)
# and no changes to original ds data, etc
assert_array_equal(datasets['3dsmall'].fa.keys(), ds.fa.keys())
assert_array_equal(datasets['3dsmall'].samples, ds.samples)
def compute_seed_means(measure, queryengine, ds, roi_ids):
"""
Parameters:
----------
measure: a PyMVPA measure passed to the Searchlight.
queryengine: a trained PyMVPA SurfaceQueryEngine.
ds: a single PyMVPA dataset (samples: timeseries, features: vertices)
roi_ids: the vertex indices where each searchlight will be centered.
Returns:
--------
seed_data: dataset with the mean timeseries for a searchlight centered on each ROI_id.
"""
# Seed data is the mean timeseries for each searchlight
seed_data = Searchlight(measure, queryengine=queryengine,
nproc=1, roi_ids=roi_ids.copy())
if isinstance(ds,np.ndarray):
ds = Dataset(ds)
seed_data = seed_data(ds)
zscore(seed_data.samples, chunks_attr=None)
return seed_data
def test_surf_voxel_selection(self):
vol_shape = (10, 10, 10)
vol_affine = np.identity(4)
vol_affine[0, 0] = vol_affine[1, 1] = vol_affine[2, 2] = 5
vg = volgeom.VolGeom(vol_shape, vol_affine)
density = 10
outer = surf.generate_sphere(density) * 25. + 15
inner = surf.generate_sphere(density) * 20. + 15
vs = volsurf.VolSurfMaximalMapping(vg, outer, inner)
nv = outer.nvertices
# select under variety of parameters
# parameters are distance metric (dijkstra or euclidean),
# radius, and number of searchlight centers
params = [('d', 1., 10), ('d', 1., 50), ('d', 1., 100), ('d', 2., 100),
('e', 2., 100), ('d', 2., 100), ('d', 20, 100),
('euclidean', 5, None), ('dijkstra', 10, None)]
# function that indicates for which parameters the full test is run
test_full = lambda x: len(x[0]) > 1 or x[2] == 100
expected_labs = ['grey_matter_position', 'center_distances']
voxcount = []
tested_double_features = False
for param in params:
distance_metric, radius, ncenters = param
srcs = range(0, nv, nv // (ncenters or nv))
sel = surf_voxel_selection.voxel_selection(
vs,
radius,
source_surf_nodes=srcs,
distance_metric=distance_metric)
# see how many voxels were selected
vg = sel.volgeom
datalin = np.zeros((vg.nvoxels, 1))
mp = sel
for k, idxs in mp.iteritems():
if idxs is not None:
datalin[idxs] = 1
voxcount.append(np.sum(datalin))
if test_full(param):
assert_equal(np.sum(datalin), np.sum(sel.get_mask()))
assert_true(len('%s%r' % (sel, sel)) > 0)
# see if voxels containing inner and outer
# nodes were selected
for sf in [inner, outer]:
for k, idxs in mp.iteritems():
xyz = np.reshape(sf.vertices[k, :], (1, 3))
linidx = vg.xyz2lin(xyz)
# only required if xyz is actually within the volume
assert_equal(linidx in idxs, vg.contains_lin(linidx))
# check that it has all the attributes
labs = sel.aux_keys()
assert_true(all([lab in labs for lab in expected_labs]))
if externals.exists('h5py'):
# some I/O testing
fd, fn = tempfile.mkstemp('.h5py', 'test')
os.close(fd)
h5save(fn, sel)
sel2 = h5load(fn)
os.remove(fn)
assert_equal(sel, sel2)
else:
sel2 = sel
# check that mask is OK even after I/O
assert_array_equal(sel.get_mask(), sel2.get_mask())
# test I/O with surfaces
# XXX the @tempfile decorator only supports a single filename
# hence this method does not use it
fd, outerfn = tempfile.mkstemp('outer.asc', 'test')
os.close(fd)
fd, innerfn = tempfile.mkstemp('inner.asc', 'test')
os.close(fd)
fd, volfn = tempfile.mkstemp('vol.nii', 'test')
os.close(fd)
surf.write(outerfn, outer, overwrite=True)
surf.write(innerfn, inner, overwrite=True)
img = sel.volgeom.get_empty_nifti_image()
img.to_filename(volfn)
sel3 = surf_voxel_selection.run_voxel_selection(
radius,
volfn,
innerfn,
outerfn,
source_surf_nodes=srcs,
distance_metric=distance_metric)
outer4 = surf.read(outerfn)
inner4 = surf.read(innerfn)
vsm4 = vs = volsurf.VolSurfMaximalMapping(vg, inner4, outer4)
# check that two ways of voxel selection match
sel4 = surf_voxel_selection.voxel_selection(
vsm4,
radius,
source_surf_nodes=srcs,
distance_metric=distance_metric)
assert_equal(sel3, sel4)
os.remove(outerfn)
os.remove(innerfn)
os.remove(volfn)
# compare sel3 with other selection results
# NOTE: which voxels are precisely selected by sel can be quite
# off from those in sel3, as writing the surfaces imposes
# rounding errors and the sphere is very symmetric, which
# means that different neighboring nodes are selected
# to select a certain number of voxels.
sel3cmp_difference_ratio = [(sel, .2), (sel4, 0.)]
for selcmp, ratio in sel3cmp_difference_ratio:
nunion = ndiff = 0
for k in selcmp.keys():
p = set(sel3.get(k))
q = set(selcmp.get(k))
nunion += len(p.union(q))
ndiff += len(p.symmetric_difference(q))
assert_true(float(ndiff) / float(nunion) <= ratio)
# check searchlight call
# as of late Aug 2012, this is with the fancy query engine
# as implemented by Yarik
mask = sel.get_mask()
keys = None if ncenters is None else sel.keys()
dset_data = np.reshape(np.arange(vg.nvoxels), vg.shape)
dset_img = nb.Nifti1Image(dset_data, vg.affine)
dset = fmri_dataset(samples=dset_img, mask=mask)
qe = queryengine.SurfaceVerticesQueryEngine(
sel,
# you can optionally add additional
# information about each near-disk-voxels
add_fa=['center_distances', 'grey_matter_position'])
# test i/o ensuring that when loading it is still trained
if externals.exists('h5py'):
fd, qefn = tempfile.mkstemp('qe.hdf5', 'test')
os.close(fd)
h5save(qefn, qe)
qe = h5load(qefn)
os.remove(qefn)
assert_false('ERROR' in repr(qe)) # to check if repr works
voxelcounter = _Voxel_Count_Measure()
searchlight = Searchlight(
voxelcounter,
queryengine=qe,
roi_ids=keys,
nproc=1,
enable_ca=['roi_feature_ids', 'roi_center_ids'])
sl_dset = searchlight(dset)
selected_count = sl_dset.samples[0, :]
mp = sel
for i, k in enumerate(sel.keys()):
# check that number of selected voxels matches
assert_equal(selected_count[i], len(mp[k]))
assert_equal(searchlight.ca.roi_center_ids, sel.keys())
assert_array_equal(sl_dset.fa['center_ids'], qe.ids)
# check nearest node is *really* the nearest node
allvx = sel.get_targets()
intermediate = outer * .5 + inner * .5
for vx in allvx:
nearest = sel.target2nearest_source(vx)
xyz = intermediate.vertices[nearest, :]
sqsum = np.sum((xyz - intermediate.vertices)**2, 1)
idx = np.argmin(sqsum)
assert_equal(idx, nearest)
if not tested_double_features: # test only once
# see if we have multiple features for the same voxel, we would get them all
dset1 = dset.copy()
dset1.fa['dset'] = [1]
dset2 = dset.copy()
dset2.fa['dset'] = [2]
dset_ = hstack((dset1, dset2), 'drop_nonunique')
dset_.sa = dset1.sa
# dset_.a.imghdr = dset1.a.imghdr
assert_true('imghdr' in dset_.a.keys())
assert_equal(dset_.a['imghdr'].value,
dset1.a['imghdr'].value)
roi_feature_ids = searchlight.ca.roi_feature_ids
sl_dset_ = searchlight(dset_)
# and we should get twice the counts
assert_array_equal(sl_dset_.samples, sl_dset.samples * 2)
# compare old and new roi_feature_ids
assert (len(roi_feature_ids) == len(
searchlight.ca.roi_feature_ids))
nfeatures = dset.nfeatures
for old, new in zip(roi_feature_ids,
searchlight.ca.roi_feature_ids):
# each new ids should comprise of old ones + (old + nfeatures)
# since we hstack'ed two datasets
assert_array_equal(
np.hstack([(x, x + nfeatures) for x in old]), new)
tested_double_features = True
# check whether number of voxels were selected is as expected
expected_voxcount = [22, 93, 183, 183, 183, 183, 183, 183, 183]
assert_equal(voxcount, expected_voxcount)
def test_voxel_selection(self):
'''Compare surface and volume based searchlight'''
'''
Tests to see whether results are identical for surface-based
searchlight (just one plane; Euclidean distnace) and volume-based
searchlight.
Note that the current value is a float; if it were int, it would
specify the number of voxels in each searchlight'''
radius = 10.
'''Define input filenames'''
epi_fn = os.path.join(pymvpa_dataroot, 'bold.nii.gz')
maskfn = os.path.join(pymvpa_dataroot, 'mask.nii.gz')
'''
Use the EPI datafile to define a surface.
The surface has as many nodes as there are voxels
and is parallel to the volume 'slice'
'''
vg = volgeom.from_any(maskfn, mask_volume=True)
aff = vg.affine
nx, ny, nz = vg.shape[:3]
'''Plane goes in x and y direction, so we take these vectors
from the affine transformation matrix of the volume'''
plane = surf.generate_plane(aff[:3, 3], aff[:3, 0], aff[:3, 1], nx, ny)
'''
Simulate pial and white matter as just above and below
the central plane
'''
normal_vec = aff[:3, 2]
outer = plane + normal_vec
inner = plane + -normal_vec
'''
Combine volume and surface information
'''
vsm = volsurf.VolSurfMaximalMapping(vg, outer, inner)
'''
Run voxel selection with specified radius (in mm), using
Euclidean distance measure
'''
surf_voxsel = surf_voxel_selection.voxel_selection(vsm,
radius,
distance_metric='e')
'''Define the measure'''
# run_slow=True would give an actual cross-validation with meaningful
# accuracies. Because this is a unit-test only the number of voxels
# in each searchlight is tested.
run_slow = False
if run_slow:
meas = CrossValidation(GNB(),
OddEvenPartitioner(),
errorfx=lambda p, t: np.mean(p == t))
postproc = mean_sample
else:
meas = _Voxel_Count_Measure()
postproc = lambda x: x
'''
Surface analysis: define the query engine, cross validation,
and searchlight
'''
surf_qe = SurfaceVerticesQueryEngine(surf_voxsel)
surf_sl = Searchlight(meas, queryengine=surf_qe, postproc=postproc)
'''
new (Sep 2012): also test 'simple' queryengine wrapper function
'''
surf_qe2 = disc_surface_queryengine(radius,
maskfn,
inner,
outer,
plane,
volume_mask=True,
distance_metric='euclidean')
surf_sl2 = Searchlight(meas, queryengine=surf_qe2, postproc=postproc)
'''
Same for the volume analysis
'''
element_sizes = tuple(map(abs, (aff[0, 0], aff[1, 1], aff[2, 2])))
sph = Sphere(radius, element_sizes=element_sizes)
kwa = {'voxel_indices': sph}
vol_qe = IndexQueryEngine(**kwa)
vol_sl = Searchlight(meas, queryengine=vol_qe, postproc=postproc)
'''The following steps are similar to start_easy.py'''
attr = SampleAttributes(
os.path.join(pymvpa_dataroot, 'attributes_literal.txt'))
mask = surf_voxsel.get_mask()
dataset = fmri_dataset(samples=os.path.join(pymvpa_dataroot,
'bold.nii.gz'),
targets=attr.targets,
chunks=attr.chunks,
mask=mask)
if run_slow:
# do chunkswise linear detrending on dataset
poly_detrend(dataset, polyord=1, chunks_attr='chunks')
# zscore dataset relative to baseline ('rest') mean
zscore(dataset,
chunks_attr='chunks',
param_est=('targets', ['rest']))
# select class face and house for this demo analysis
# would work with full datasets (just a little slower)
dataset = dataset[np.array(
[l in ['face', 'house'] for l in dataset.sa.targets],
dtype='bool')]
'''Apply searchlight to datasets'''
surf_dset = surf_sl(dataset)
surf_dset2 = surf_sl2(dataset)
vol_dset = vol_sl(dataset)
surf_data = surf_dset.samples
surf_data2 = surf_dset2.samples
vol_data = vol_dset.samples
assert_array_equal(surf_data, surf_data2)
assert_array_equal(surf_data, vol_data)
def test_voxel_selection_alternative_calls(self):
# Tests a multitude of different searchlight calls
# that all should yield exactly the same results.
#
# Calls differ by whether the arguments are filenames
# or data objects, whether values are specified explicityly
# or set to the default implicitly (using None).
# and by different calls to run the voxel selection.
#
# This method does not test for mask functionality.
# define the volume
vol_shape = (10, 10, 10, 3)
vol_affine = np.identity(4)
vol_affine[0, 0] = vol_affine[1, 1] = vol_affine[2, 2] = 5
# four versions: array, nifti image, file name, fmri dataset
volarr = np.ones(vol_shape)
volimg = nb.Nifti1Image(volarr, vol_affine)
# There is a detected problem with elderly NumPy's (e.g. 1.6.1
# on precise on travis) leading to segfaults while operating
# on memmapped volumes being forwarded to pprocess.
# Thus just making it compressed volume for those cases
suf = '.gz' \
if externals.exists('pprocess') and externals.versions['numpy'] < '1.6.2' \
else ''
fd, volfn = tempfile.mkstemp('vol.nii' + suf, 'test')
os.close(fd)
volimg.to_filename(volfn)
volds = fmri_dataset(volfn)
fd, volfngz = tempfile.mkstemp('vol.nii.gz', 'test')
os.close(fd)
volimg.to_filename(volfngz)
voldsgz = fmri_dataset(volfngz)
# make the surfaces
sphere_density = 10
# two versions: Surface and file name
outer = surf.generate_sphere(sphere_density) * 25. + 15
inner = surf.generate_sphere(sphere_density) * 20. + 15
intermediate = inner * .5 + outer * .5
nv = outer.nvertices
fd, outerfn = tempfile.mkstemp('outer.asc', 'test')
os.close(fd)
fd, innerfn = tempfile.mkstemp('inner.asc', 'test')
os.close(fd)
fd, intermediatefn = tempfile.mkstemp('intermediate.asc', 'test')
os.close(fd)
for s, fn in zip([outer, inner, intermediate],
[outerfn, innerfn, intermediatefn]):
surf.write(fn, s, overwrite=True)
# searchlight radius (in mm)
radius = 10.
# dataset used to run searchlight on
ds = fmri_dataset(volfn)
# simple voxel counter (run for each searchlight position)
m = _Voxel_Count_Measure()
# number of voxels expected in each searchlight
r_expected = np.array([[
18, 9, 10, 9, 9, 9, 9, 10, 9, 9, 9, 9, 11, 11, 11, 11, 10, 10, 10,
9, 10, 11, 9, 10, 10, 8, 7, 8, 8, 8, 9, 10, 12, 12, 11, 7, 7, 8, 5,
9, 11, 11, 12, 12, 9, 5, 8, 7, 7, 12, 12, 13, 12, 12, 7, 7, 8, 5,
9, 12, 12, 13, 11, 9, 5, 8, 7, 7, 11, 12, 12, 11, 12, 10, 10, 11,
9, 11, 12, 12, 12, 12, 16, 13, 16, 16, 16, 17, 15, 17, 17, 17, 16,
16, 16, 18, 16, 16, 16, 16, 18, 16
]])
params = dict(intermediate_=(intermediate, intermediatefn, None),
center_nodes_=(None, range(nv)),
volume_=(volimg, volfn, volds, volfngz, voldsgz),
surf_src_=('filename', 'surf'),
volume_mask_=(None, True, 0, 2),
call_method_=("qe", "rvs", "gam"))
combis = _cartprod(params) # compute all possible combinations
combistep = 17 #173
# some fine prime number to speed things up
# if this value becomes too big then not all
# cases are covered
# the unit test tests itself whether all values
# occur at least once
tested_params = dict()
def val2str(x):
return '%r:%r' % (type(x), x)
for i in xrange(0, len(combis), combistep):
combi = combis[i]
intermediate_ = combi['intermediate_']
center_nodes_ = combi['center_nodes_']
volume_ = combi['volume_']
surf_src_ = combi['surf_src_']
volume_mask_ = combi['volume_mask_']
call_method_ = combi['call_method_']
# keep track of which values were used -
# so that this unit test tests itself
for k in combi.keys():
if not k in tested_params:
tested_params[k] = set()
tested_params[k].add(val2str(combi[k]))
if surf_src_ == 'filename':
s_i, s_m, s_o = inner, intermediate, outer
elif surf_src_ == 'surf':
s_i, s_m, s_o = innerfn, intermediatefn, outerfn
else:
raise ValueError('this should not happen')
if call_method_ == "qe":
# use the fancy query engine wrapper
qe = disc_surface_queryengine(radius,
volume_,
s_i,
s_o,
s_m,
source_surf_nodes=center_nodes_,
volume_mask=volume_mask_)
sl = Searchlight(m, queryengine=qe)
r = sl(ds).samples
elif call_method_ == 'rvs':
# use query-engine but build the
# ingredients by hand
vg = volgeom.from_any(volume_, volume_mask_)
vs = volsurf.VolSurfMaximalMapping(vg, s_i, s_o)
sel = surf_voxel_selection.voxel_selection(
vs,
radius,
source_surf=s_m,
source_surf_nodes=center_nodes_)
qe = SurfaceVerticesQueryEngine(sel)
sl = Searchlight(m, queryengine=qe)
r = sl(ds).samples
elif call_method_ == 'gam':
# build everything from the ground up
vg = volgeom.from_any(volume_, volume_mask_)
vs = volsurf.VolSurfMaximalMapping(vg, s_i, s_o)
sel = surf_voxel_selection.voxel_selection(
vs,
radius,
source_surf=s_m,
source_surf_nodes=center_nodes_)
mp = sel
ks = sel.keys()
nk = len(ks)
r = np.zeros((1, nk))
for i, k in enumerate(ks):
r[0, i] = len(mp[k])
# check if result is as expected
assert_array_equal(r_expected, r)
# clean up
all_fns = [volfn, volfngz, outerfn, innerfn, intermediatefn]
map(os.remove, all_fns)
for k, vs in params.iteritems():
if not k in tested_params:
raise ValueError("Missing key: %r" % k)
for v in vs:
vstr = val2str(v)
if not vstr in tested_params[k]:
raise ValueError("Missing value %r for %s" %
(tested_params[k], k))
def run(args):
if os.path.isfile(args.payload) and args.payload.endswith('.py'):
measure = script2obj(args.payload)
elif args.payload == 'cv':
if args.cv_learner is None or args.cv_partitioner is None:
raise ValueError(
'cross-validation payload requires --learner and --partitioner'
)
# get CV instance
measure = get_crossvalidation_instance(
args.cv_learner, args.cv_partitioner, args.cv_errorfx,
args.cv_sampling_repetitions, args.cv_learner_space,
args.cv_balance_training, args.cv_permutations,
args.cv_avg_datafold_results, args.cv_prob_tail)
else:
raise RuntimeError("this should not happen")
ds = arg2ds(args.data)
if not args.ds_preproc_fx is None:
ds = args.ds_preproc_fx(ds)
# setup neighborhood
# XXX add big switch to allow for setting up surface-based neighborhoods
from mvpa2.misc.neighborhood import IndexQueryEngine
qe = IndexQueryEngine(**dict(args.neighbors))
# determine ROIs
rids = None # all by default
aggregate_fx = args.aggregate_fx
if args.roi_attr is not None:
# first figure out which roi features should be processed
if len(args.roi_attr) == 1 and args.roi_attr[0] in ds.fa.keys():
# name of an attribute -> pull non-zeroes
rids = ds.fa[args.roi_attr[0]].value.nonzero()[0]
else:
# an expression?
from .cmd_select import _eval_attr_expr
rids = _eval_attr_expr(args.roi_attr, ds.fa).nonzero()[0]
seed_ids = None
if args.scatter_rois is not None:
# scatter_neighborhoods among available ids if was requested
from mvpa2.misc.neighborhood import scatter_neighborhoods
attr, nb = args.scatter_rois
coords = ds.fa[attr].value
if rids is not None:
# select only those which were chosen by ROI
coords = coords[rids]
_, seed_ids = scatter_neighborhoods(nb, coords)
if aggregate_fx is None:
# no custom one given -> use default "fill in" function
aggregate_fx = _fill_in_scattered_results
if args.enable_ca is None:
args.enable_ca = ['roi_feature_ids']
elif 'roi_feature_ids' not in args.enable_ca:
args.enable_ca += ['roi_feature_ids']
if seed_ids is None:
roi_ids = rids
else:
if rids is not None:
# we had to sub-select by scatterring among available rids
# so we would need to get original ids
roi_ids = rids[seed_ids]
else:
# scattering happened on entire feature-set
roi_ids = seed_ids
verbose(
3, 'Attempting %i ROI analyses' %
((roi_ids is None) and ds.nfeatures or len(roi_ids)))
from mvpa2.measures.searchlight import Searchlight
sl = Searchlight(measure,
queryengine=qe,
roi_ids=roi_ids,
nproc=args.nproc,
results_backend=args.multiproc_backend,
results_fx=aggregate_fx,
enable_ca=args.enable_ca,
disable_ca=args.disable_ca)
# XXX support me too!
# add_center_fa
# tmp_prefix
# nblocks
# null_dist
# run
res = sl(ds)
if (seed_ids is not None) and ('mapper' in res.a):
# strip the last mapper link in the chain, which would be the seed ID selection
res.a['mapper'] = res.a.mapper[:-1]
# XXX create more output
# and store
ds2hdf5(res, args.output, compression=args.hdf5_compression)
return res
