def connected_components(self):
"""returns a labelling of the domain into connected components
"""
if self.topology is not None:
return wgraph_from_coo_matrix(self.topology).cc()
else:
return []
def connected_components(self):
"""returns a labelling of the domain into connected components
"""
if self.topology is not None:
return wgraph_from_coo_matrix(self.topology).cc()
else:
return []
def reduce_coo_matrix(mat, mask):
"""Reduce a supposedly coo_matrix to the vertices in the mask
Parameters
----------
mat: sparse coo_matrix,
input matrix
mask: boolean array of shape mat.shape[0],
desired elements
"""
G = wgraph_from_coo_matrix(mat)
K = G.subgraph(mask)
if K is None:
return None
return K.to_coo_matrix()
def reduce_coo_matrix(mat, mask):
"""Reduce a supposedly coo_matrix to the vertices in the mask
Parameters
----------
mat: sparse coo_matrix,
input matrix
mask: boolean array of shape mat.shape[0],
desired elements
"""
G = wgraph_from_coo_matrix(mat)
K = G.subgraph(mask)
if K is None:
return None
return K.to_coo_matrix()
def _bsa_dpmm(hrois, prior_h0, subjects, coords, sigma, prevalence_pval,
prevalence_threshold, dof=10, alpha=.5, n_iter=1000, burnin=100,
algorithm='density'):
""" Estimation of the population level model of activation density using
dpmm and inference
Parameters
----------
hrois: list of nipy.labs.spatial_models.hroi.HierarchicalROI instances
representing individual ROIs
Let nr be the number of terminal regions across subjects
prior_h0: array of shape (nr)
mixture-based prior probability
that the terminal regions are true positives
subjects: array of shape (nr)
subject index associated with the terminal regions
coords: array of shape (nr, coord.shape[1])
coordinates of the of the terminal regions
sigma: float > 0,
expected cluster scatter in the common space in units of coord
prevalence_pval: float in the [0,1] interval, optional
p-value of the prevalence test
prevalence_threshold: float in the rannge [0,nsubj]
null hypothesis on region prevalence
dof: float > 0, optional,
degrees of freedom of the prior
alpha: float > 0, optional,
creation parameter of the DPMM
niter: int, optional,
number of iterations of the DPMM
burnin: int, optional,
number of iterations of the DPMM
algorithm: {'density', 'co_occurrence'}, optional,
algorithm used in the DPMM inference
Returns
-------
landmarks: instance of sbf.LandmarkRegions
that describes the ROIs found in inter-subject inference
If no such thing can be defined landmarks is set to None
hrois: List of nipy.labs.spatial_models.hroi.HierarchicalROI instances
representing individual ROIs
"""
from nipy.algorithms.graph.field import field_from_coo_matrix_and_data
domain = hrois[0].domain
n_subjects = len(hrois)
landmarks = None
density = np.zeros(domain.size)
if len(subjects) < 1:
return landmarks, hrois
null_density = 1. / domain.local_volume.sum()
# prepare the DPMM
dim = domain.em_dim
prior_precision = 1. / (sigma ** 2) * np.ones((1, dim))
# n_iter = number of iterations to estimate density
if algorithm == 'density':
density, post_proba = _dpmm(
coords, alpha, null_density, dof, prior_precision, prior_h0,
subjects, domain.coord, n_iter=n_iter, burnin=burnin)
# associate labels with coords
Fbeta = field_from_coo_matrix_and_data(domain.topology, density)
_, label = Fbeta.custom_watershed(0, null_density)
midx = np.array([np.argmin(np.sum((domain.coord - coord_) ** 2, 1))
for coord_ in coords])
components = label[midx]
elif algorithm == 'co-occurrence':
post_proba, density, co_clustering = _dpmm(
coords, alpha, null_density, dof, prior_precision, prior_h0,
subjects, n_iter=n_iter, burnin=burnin, co_clust=True)
contingency_graph = wgraph_from_coo_matrix(co_clustering)
if contingency_graph.E > 0:
contingency_graph.remove_edges(contingency_graph.weights > .5)
components = contingency_graph.cc()
components[density < null_density] = components.max() + 1 +\
np.arange(np.sum(density < null_density))
else:
raise ValueError('Unknown algorithm')
# append some information to the hroi in each subject
for subject in range(n_subjects):
bfs = hrois[subject]
if bfs is None:
continue
if bfs.k == 0:
bfs.set_roi_feature('label', np.array([]))
continue
leaves_pos = [bfs.select_id(k) for k in bfs.get_leaves_id()]
# save posterior proba
post_proba_ = np.zeros(bfs.k)
post_proba_[leaves_pos] = post_proba[subjects == subject]
bfs.set_roi_feature('posterior_proba', post_proba_)
# save prior proba
prior_proba = np.zeros(bfs.k)
prior_proba[leaves_pos] = 1 - prior_h0[subjects == subject]
bfs.set_roi_feature('prior_proba', prior_proba)
# assign labels to ROIs
roi_label = - np.ones(bfs.k).astype(np.int)
roi_label[leaves_pos] = components[subjects == subject]
# when parent regions has similarly labelled children,
# include it also
roi_label = bfs.make_forest().propagate_upward(roi_label)
bfs.set_roi_feature('label', roi_label)
# derive the group-level landmarks
# with a threshold on the number of subjects
# that are represented in each one
landmarks, new_labels = build_landmarks(
domain, coords, subjects, np.array(components), 1 - prior_h0,
prevalence_pval, prevalence_threshold, sigma)
# relabel the regions
_update_hroi_labels(hrois, new_labels)
return landmarks, hrois
def bsa_dpmm2(bf, gf0, sub, gfc, dmax, thq, ths, verbose):
""" Estimation of the population level model of activation density using
dpmm and inference
Parameters
----------
bf list of nipy.labs.spatial_models.hroi.HierarchicalROI instances
representing individual ROIs
let nr be the number of terminal regions across subjects
gf0, array of shape (nr)
the mixture-based prior probability
that the terminal regions are false positives
sub, array of shape (nr)
the subject index associated with the terminal regions
gfc, array of shape (nr, coord.shape[1])
the coordinates of the of the terminal regions
dmax float>0:
expected cluster std in the common space in units of coord
thq = 0.5 (float in the [0,1] interval)
p-value of the prevalence test
ths=0, float in the rannge [0,nsubj]
null hypothesis on region prevalence that is rejected during inference
verbose=0, verbosity mode
Returns
-------
crmap: array of shape (nnodes):
the resulting group-level labelling of the space
LR: a instance of sbf.LandmarkRegions that describes the ROIs found
in inter-subject inference
If no such thing can be defined LR is set to None
bf: List of nipy.labs.spatial_models.hroi.Nroi instances
representing individual ROIs
Coclust: array of shape (nr,nr):
co-labelling matrix that gives for each pair of inputs
how likely they are in the same class according to the model
"""
dom = bf[0].domain
n_subj = len(bf)
crmap = - np.ones(dom.size, np.int)
LR = None
p = np.zeros(dom.size)
if len(sub) < 1:
return crmap, LR, bf, p
sub = np.concatenate(sub).astype(np.int)
gfc = np.concatenate(gfc)
gf0 = np.concatenate(gf0)
# prepare the DPMM
g0 = 1. / (np.sum(dom.local_volume))
g1 = g0
prior_precision = 1. / (dmax * dmax) * np.ones((1, dom.em_dim), np.float)
dof = 10
burnin = 100
nis = 300
q, p, CoClust = dpmm(gfc, .5, g0, g1, dof, prior_precision, 1 - gf0,
sub, burnin, nis=nis, co_clust=True)
cg = wgraph_from_coo_matrix(CoClust)
if cg.E > 0:
cg.remove_edges(cg.weights > .5)
u = cg.cc()
u[p < g0] = u.max() + 1 + np.arange(np.sum(p < g0))
if verbose:
cg.show(gfc)
# append some information to the hroi in each subject
for s in range(n_subj):
bfs = bf[s]
if bfs is not None:
leaves = np.asarray(
[bfs.select_id(id) for id in bfs.get_leaves_id()])
us = - np.ones(bfs.k).astype(np.int)
lq = np.zeros(bfs.k)
lq[leaves] = q[sub == s]
bfs.set_roi_feature('posterior_proba', lq)
lq = np.zeros(bfs.k)
lq[leaves] = 1 - gf0[sub == s]
bfs.set_roi_feature('prior_proba', lq)
us[leaves] = u[sub == s]
# when parent regions has similarly labelled children,
# include it also
us = bfs.make_forest().propagate_upward(us)
bfs.set_roi_feature('label', us)
# derive the group-level landmarks
# with a threshold on the number of subjects
# that are represented in each one
LR, nl = build_LR(bf, thq, ths, dmax, verbose=verbose)
# make a group-level map of the landmark position
crmap = - np.ones(dom.size)
# not implemented at the moment
return crmap, LR, bf, CoClust
def _bsa_dpmm(hrois,
prior_h0,
subjects,
coords,
sigma,
prevalence_pval,
prevalence_threshold,
dof=10,
alpha=.5,
n_iter=1000,
burnin=100,
algorithm='density'):
""" Estimation of the population level model of activation density using
dpmm and inference
Parameters
----------
hrois: list of nipy.labs.spatial_models.hroi.HierarchicalROI instances
representing individual ROIs
Let nr be the number of terminal regions across subjects
prior_h0: array of shape (nr)
mixture-based prior probability
that the terminal regions are true positives
subjects: array of shape (nr)
subject index associated with the terminal regions
coords: array of shape (nr, coord.shape[1])
coordinates of the of the terminal regions
sigma: float > 0,
expected cluster scatter in the common space in units of coord
prevalence_pval: float in the [0,1] interval, optional
p-value of the prevalence test
prevalence_threshold: float in the rannge [0,nsubj]
null hypothesis on region prevalence
dof: float > 0, optional,
degrees of freedom of the prior
alpha: float > 0, optional,
creation parameter of the DPMM
niter: int, optional,
number of iterations of the DPMM
burnin: int, optional,
number of iterations of the DPMM
algorithm: {'density', 'co_occurrence'}, optional,
algorithm used in the DPMM inference
Returns
-------
landmarks: instance of sbf.LandmarkRegions
that describes the ROIs found in inter-subject inference
If no such thing can be defined landmarks is set to None
hrois: List of nipy.labs.spatial_models.hroi.HierarchicalROI instances
representing individual ROIs
"""
from nipy.algorithms.graph.field import field_from_coo_matrix_and_data
domain = hrois[0].domain
n_subjects = len(hrois)
landmarks = None
density = np.zeros(domain.size)
if len(subjects) < 1:
return landmarks, hrois
null_density = 1. / domain.local_volume.sum()
# prepare the DPMM
dim = domain.em_dim
prior_precision = 1. / (sigma**2) * np.ones((1, dim))
# n_iter = number of iterations to estimate density
if algorithm == 'density':
density, post_proba = _dpmm(coords,
alpha,
null_density,
dof,
prior_precision,
prior_h0,
subjects,
domain.coord,
n_iter=n_iter,
burnin=burnin)
# associate labels with coords
Fbeta = field_from_coo_matrix_and_data(domain.topology, density)
_, label = Fbeta.custom_watershed(0, null_density)
midx = np.array([
np.argmin(np.sum((domain.coord - coord_)**2, 1))
for coord_ in coords
])
components = label[midx]
elif algorithm == 'co-occurrence':
post_proba, density, co_clustering = _dpmm(coords,
alpha,
null_density,
dof,
prior_precision,
prior_h0,
subjects,
n_iter=n_iter,
burnin=burnin,
co_clust=True)
contingency_graph = wgraph_from_coo_matrix(co_clustering)
if contingency_graph.E > 0:
contingency_graph.remove_edges(contingency_graph.weights > .5)
components = contingency_graph.cc()
components[density < null_density] = components.max() + 1 +\
np.arange(np.sum(density < null_density))
else:
raise ValueError('Unknown algorithm')
# append some information to the hroi in each subject
for subject in range(n_subjects):
bfs = hrois[subject]
if bfs is None:
continue
if bfs.k == 0:
bfs.set_roi_feature('label', np.array([]))
continue
leaves_pos = [bfs.select_id(k) for k in bfs.get_leaves_id()]
# save posterior proba
post_proba_ = np.zeros(bfs.k)
post_proba_[leaves_pos] = post_proba[subjects == subject]
bfs.set_roi_feature('posterior_proba', post_proba_)
# save prior proba
prior_proba = np.zeros(bfs.k)
prior_proba[leaves_pos] = 1 - prior_h0[subjects == subject]
bfs.set_roi_feature('prior_proba', prior_proba)
# assign labels to ROIs
roi_label = -np.ones(bfs.k).astype(np.int)
roi_label[leaves_pos] = components[subjects == subject]
# when parent regions has similarly labelled children,
# include it also
roi_label = bfs.make_forest().propagate_upward(roi_label)
bfs.set_roi_feature('label', roi_label)
# derive the group-level landmarks
# with a threshold on the number of subjects
# that are represented in each one
landmarks, new_labels = build_landmarks(domain, coords, subjects,
np.array(components), 1 - prior_h0,
prevalence_pval,
prevalence_threshold, sigma)
# relabel the regions
_update_hroi_labels(hrois, new_labels)
return landmarks, hrois
def cc_array_mask(mask, size_threshold):
"""Filter the mask to keep only connected components above a given size"""
graph = wgraph_from_coo_matrix(grid_domain_from_binary_array(mask).topology)
mask[mask] = cc_mask(graph, mask[mask], size_threshold)
return mask
def bsa_dpmm2(bf, gf0, sub, gfc, dmax, thq, ths, verbose):
""" Estimation of the population level model of activation density using
dpmm and inference
Parameters
----------
bf list of nipy.labs.spatial_models.hroi.HierarchicalROI instances
representing individual ROIs
let nr be the number of terminal regions across subjects
gf0, array of shape (nr)
the mixture-based prior probability
that the terminal regions are false positives
sub, array of shape (nr)
the subject index associated with the terminal regions
gfc, array of shape (nr, coord.shape[1])
the coordinates of the of the terminal regions
dmax float>0:
expected cluster std in the common space in units of coord
thq = 0.5 (float in the [0,1] interval)
p-value of the prevalence test
ths=0, float in the rannge [0,nsubj]
null hypothesis on region prevalence that is rejected during inference
verbose=0, verbosity mode
Returns
-------
crmap: array of shape (nnodes):
the resulting group-level labelling of the space
LR: a instance of sbf.LandmarkRegions that describes the ROIs found
in inter-subject inference
If no such thing can be defined LR is set to None
bf: List of nipy.labs.spatial_models.hroi.Nroi instances
representing individual ROIs
Coclust: array of shape (nr,nr):
co-labelling matrix that gives for each pair of inputs
how likely they are in the same class according to the model
"""
dom = bf[0].domain
n_subj = len(bf)
crmap = -np.ones(dom.size, np.int)
LR = None
p = np.zeros(dom.size)
if len(sub) < 1:
return crmap, LR, bf, p
sub = np.concatenate(sub).astype(np.int)
gfc = np.concatenate(gfc)
gf0 = np.concatenate(gf0)
# prepare the DPMM
g0 = 1. / (np.sum(dom.local_volume))
g1 = g0
prior_precision = 1. / (dmax * dmax) * np.ones((1, dom.em_dim), np.float)
dof = 10
burnin = 100
nis = 300
q, p, CoClust = dpmm(gfc,
.5,
g0,
g1,
dof,
prior_precision,
1 - gf0,
sub,
burnin,
nis=nis,
co_clust=True)
cg = wgraph_from_coo_matrix(CoClust)
if cg.E > 0:
cg.remove_edges(cg.weights > .5)
u = cg.cc()
u[p < g0] = u.max() + 1 + np.arange(np.sum(p < g0))
if verbose:
cg.show(gfc)
# append some information to the hroi in each subject
for s in range(n_subj):
bfs = bf[s]
if bfs is not None:
leaves = np.asarray(
[bfs.select_id(id) for id in bfs.get_leaves_id()])
us = -np.ones(bfs.k).astype(np.int)
lq = np.zeros(bfs.k)
lq[leaves] = q[sub == s]
bfs.set_roi_feature('posterior_proba', lq)
lq = np.zeros(bfs.k)
lq[leaves] = 1 - gf0[sub == s]
bfs.set_roi_feature('prior_proba', lq)
us[leaves] = u[sub == s]
# when parent regions has similarly labelled children,
# include it also
us = bfs.make_forest().propagate_upward(us)
bfs.set_roi_feature('label', us)
# derive the group-level landmarks
# with a threshold on the number of subjects
# that are represented in each one
LR, nl = build_LR(bf, thq, ths, dmax, verbose=verbose)
# make a group-level map of the landmark position
crmap = -np.ones(dom.size)
# not implemented at the moment
return crmap, LR, bf, CoClust