def omni_embed(pop_array):
variance_threshold = VarianceThreshold(threshold=0.05)
diags = np.array([np.triu(pop_array[i]) for i in range(len(pop_array))])
diags_red = diags.reshape(diags.shape[0], diags.shape[1] * diags.shape[2])
var_thr = variance_threshold.fit(diags_red.T)
graphs_ix_keep = var_thr.get_support(indices=True)
pop_array_red = [pop_array[i] for i in graphs_ix_keep]
# Omnibus embedding -- random dot product graph (rdpg)
print("%s%s%s" % ('Embedding ensemble for atlas: ', atlas, '...'))
omni = OmnibusEmbed(check_lcc=False)
try:
omni_fit = omni.fit_transform(pop_array_red)
mds = ClassicalMDS()
mds_fit = mds.fit_transform(omni_fit)
except:
omni_fit = omni.fit_transform(pop_array)
mds = ClassicalMDS()
mds_fit = mds.fit_transform(omni_fit)
# Transform omnibus tensor into dissimilarity feature
dir_path = os.path.dirname(graph_path)
out_path = "%s%s%s%s%s%s" % (dir_path, '/', list(flatten(ID))[0], '_omnetome_', atlas, '.npy')
print('Saving...')
np.save(out_path, mds_fit)
del mds, mds_fit, omni, omni_fit
return
def flatten(l):
import collections
for el in l:
if isinstance(
el, collections.Iterable) and not isinstance(el, (str, bytes)):
for ell in flatten(el):
yield ell
else:
yield el
def pass_meta_outs(conn_model_iterlist, est_path_iterlist, network_iterlist, node_size_iterlist, thr_iterlist,
prune_iterlist, ID_iterlist, roi_iterlist, norm_iterlist, binary_iterlist, embed=True,
multimodal=False):
from pynets.utils import build_omnetome, flatten
"""
:param conn_model_iterlist:
:param est_path_iterlist:
:param network_iterlist:
:param node_size_iterlist:
:param thr_iterlist:
:param prune_iterlist:
:param ID_iterlist:
:param roi_iterlist:
:param norm_iterlist:
:param binary_iterlist:
:return:
"""
if embed is True:
build_omnetome(list(flatten(est_path_iterlist)), list(flatten(ID_iterlist))[0], multimodal)
return conn_model_iterlist, est_path_iterlist, network_iterlist, node_size_iterlist, thr_iterlist, prune_iterlist, ID_iterlist, roi_iterlist, norm_iterlist, binary_iterlist
def collect_pandas_df(network, ID, net_pickle_mt_list, plot_switch,
multi_nets):
from pynets.utils import collect_pandas_df_make, flatten
net_pickle_mt_list = list(flatten(net_pickle_mt_list))
if multi_nets is not None:
net_pickle_mt_list_nets = net_pickle_mt_list
for network in multi_nets:
net_pickle_mt_list = list(
set([i for i in net_pickle_mt_list_nets if network in i]))
collect_pandas_df_make(net_pickle_mt_list, ID, network,
plot_switch)
else:
collect_pandas_df_make(net_pickle_mt_list, ID, network, plot_switch)
return
def collect_pandas_df(network, ID, net_pickle_mt_list, plot_switch, multi_nets, multimodal):
"""
:param network:
:param ID:
:param net_pickle_mt_list:
:param plot_switch:
:param multi_nets:
:return:
"""
from pynets.utils import collect_pandas_df_make, flatten
func_models = ['corr', 'sps', 'cov', 'partcorr', 'QuicGraphicalLasso', 'QuicGraphicalLassoCV',
'QuicGraphicalLassoEBIC', 'AdaptiveQuicGraphicalLasso']
struct_models = ['csa', 'tensor', 'csd']
net_pickle_mt_list = list(flatten(net_pickle_mt_list))
if multi_nets is not None:
net_pickle_mt_list_nets = net_pickle_mt_list
for network in multi_nets:
net_pickle_mt_list = list(set([i for i in net_pickle_mt_list_nets if network in i]))
if multimodal is True:
net_pickle_mt_list_dwi = list(set([i for i in net_pickle_mt_list if i.split('metrics_')[1].split('_')[0]
in struct_models]))
collect_pandas_df_make(net_pickle_mt_list_dwi, ID, network, plot_switch)
net_pickle_mt_list_func = list(set([i for i in net_pickle_mt_list if
i.split('metrics_')[1].split('_')[0] in func_models]))
collect_pandas_df_make(net_pickle_mt_list_func, ID, network, plot_switch)
else:
collect_pandas_df_make(net_pickle_mt_list, ID, network, plot_switch)
else:
if multimodal is True:
net_pickle_mt_list_dwi = list(set([i for i in net_pickle_mt_list if i.split('metrics_')[1].split('_')[0] in
struct_models]))
collect_pandas_df_make(net_pickle_mt_list_dwi, ID, network, plot_switch)
net_pickle_mt_list_func = list(set([i for i in net_pickle_mt_list if i.split('metrics_')[1].split('_')[0]
in func_models]))
collect_pandas_df_make(net_pickle_mt_list_func, ID, network, plot_switch)
else:
collect_pandas_df_make(net_pickle_mt_list, ID, network, plot_switch)
return