def get_outlier_nodes(data, feat="deg", threshold=1e-3):
T = len(data)
n = len(data[0])
feature = np.empty((T, n))
for t in range(0, T):
if feat == "deg":
feature[t] = data[t].sum(axis=0)
elif feat == "cent":
feature[t] = bct.betweenness_wei(data[t])
elif feat == "cc":
feature[t] = bct.clustering_coef_wu(data[t])
elif feat == "assort":
feature[t] = bct.assortativity_wei(data[t])
diff = forward_diff(forward_diff(feature))
ind_vec = diff > threshold
print(ind_vec.sum(axis=None))
return ind_vec
# network measures of interest here
# global efficiency
ge = bct.efficiency_wei(thresh)
ge_s.append(ge)
# characteristic path length
cp = bct.charpath(thresh)
cp_s.append(cp[0])
# modularity
md = bct.modularity_louvain_und(thresh)
md_s.append(md[1])
# network measures of interest here
# global efficiency
at = bct.assortativity_wei(thresh)
at_s.append(at)
# modularity
tr = bct.transitivity_wu(thresh)
tr_s.append(tr)
df.at[(subject, session, task, conds[i], mask),
"assortativity"] = np.trapz(ge_s, dx=0.01)
df.at[(subject, session, task, conds[i], mask),
"transitivity"] = np.trapz(md_s, dx=0.01)
df.at[(subject, session, task, conds[i], mask),
"efficiency"] = np.trapz(ge_s, dx=0.01)
df.at[(subject, session, task, conds[i], mask),
"charpath"] = np.trapz(cp_s, dx=0.01)
df.at[(subject, session, task, conds[i], mask),
def main():
parser = _build_arg_parser()
args = parser.parse_args()
assert_inputs_exist(parser, [args.in_length_matrix, args.in_conn_matrix])
if args.verbose:
logging.basicConfig(level=logging.DEBUG)
if not args.append_json:
assert_outputs_exist(parser, args, args.out_json)
else:
logging.debug('Using --append_json, make sure to delete {} '
'before re-launching a group analysis.'.format(
args.out_json))
if args.append_json and args.overwrite:
parser.error('Cannot use the append option at the same time as '
'overwrite.\nAmbiguous behavior, consider deleting the '
'output json file first instead.')
conn_matrix = load_matrix_in_any_format(args.in_conn_matrix)
len_matrix = load_matrix_in_any_format(args.in_length_matrix)
if args.filtering_mask:
mask_matrix = load_matrix_in_any_format(args.filtering_mask)
conn_matrix *= mask_matrix
len_matrix *= mask_matrix
N = len_matrix.shape[0]
if args.avg_node_wise:
func_cast = avg_cast
else:
func_cast = list_cast
gtm_dict = {}
betweenness_centrality = bct.betweenness_wei(len_matrix) / ((N - 1) *
(N - 2))
gtm_dict['betweenness_centrality'] = func_cast(betweenness_centrality)
ci, gtm_dict['modularity'] = bct.modularity_louvain_und(conn_matrix,
seed=0)
gtm_dict['assortativity'] = bct.assortativity_wei(conn_matrix, flag=0)
gtm_dict['participation'] = func_cast(
bct.participation_coef_sign(conn_matrix, ci)[0])
gtm_dict['clustering'] = func_cast(bct.clustering_coef_wu(conn_matrix))
gtm_dict['nodal_strength'] = func_cast(bct.strengths_und(conn_matrix))
gtm_dict['local_efficiency'] = func_cast(
bct.efficiency_wei(len_matrix, local=True))
gtm_dict['global_efficiency'] = func_cast(bct.efficiency_wei(len_matrix))
gtm_dict['density'] = func_cast(bct.density_und(conn_matrix)[0])
# Rich club always gives an error for the matrix rank and gives NaN
with warnings.catch_warnings():
warnings.simplefilter("ignore")
tmp_rich_club = bct.rich_club_wu(conn_matrix)
gtm_dict['rich_club'] = func_cast(tmp_rich_club[~np.isnan(tmp_rich_club)])
# Path length gives an infinite distance for unconnected nodes
# All of this is simply to fix that
empty_connections = np.where(np.sum(len_matrix, axis=1) < 0.001)[0]
if len(empty_connections):
len_matrix = np.delete(len_matrix, empty_connections, axis=0)
len_matrix = np.delete(len_matrix, empty_connections, axis=1)
path_length_tuple = bct.distance_wei(len_matrix)
gtm_dict['path_length'] = func_cast(path_length_tuple[0])
gtm_dict['edge_count'] = func_cast(path_length_tuple[1])
if not args.avg_node_wise:
for i in empty_connections:
gtm_dict['path_length'].insert(i, -1)
gtm_dict['edge_count'].insert(i, -1)
if args.small_world:
gtm_dict['omega'], gtm_dict['sigma'] = omega_sigma(len_matrix)
if os.path.isfile(args.out_json) and args.append_json:
with open(args.out_json) as json_data:
out_dict = json.load(json_data)
for key in gtm_dict.keys():
if isinstance(out_dict[key], list):
out_dict[key].append(gtm_dict[key])
else:
out_dict[key] = [out_dict[key], gtm_dict[key]]
else:
out_dict = {}
for key in gtm_dict.keys():
out_dict[key] = [gtm_dict[key]]
with open(args.out_json, 'w') as outfile:
json.dump(out_dict,
outfile,
indent=args.indent,
sort_keys=args.sort_keys)
def process(data):
return bct.assortativity_wei(data)
def graph_estimates(cm, th):
#dictionary for storing our results
d = OrderedDict()
#thresholding moved here for other matrices than MatLab matrices
#removes negative weights
cm = bct.threshold_absolute(cm, 0.0)
cm = threshold_connected(cm, th)
#for binarizing the connectivity matrices,
#we work with weighted so this is turned off
#bin_cm = bct.binarize(cm)
#invert the connectivity for computing shortest paths
cm_inv = bct.invert(cm)
#modularity_und is found in modularity.py
modularity_und = bct.modularity_und(cm)
#the community_affiliation vector that gets input to some of the functions
community_affiliation = modularity_und[0]
#distance_wei and charpath is found in distance.py
distance_wei = bct.distance_wei(cm_inv)
charpath = bct.charpath(distance_wei[0], False, False)
#clustering_coef_wu is found in clustering.py
clustering_coef_wu = bct.clustering_coef_wu(cm)
avg_clustering_coef_wu = np.mean(clustering_coef_wu)
#assortativity_wei is found in core.py
d['assortativity_wei-r'] = bct.assortativity_wei(cm, flag=0)
#just taking the average of clustering_coef_wu
d['avg_clustering_coef_wu:C'] = avg_clustering_coef_wu
d['charpath-lambda'] = charpath[0]
#d['charpath-efficiency'] = charpath[1]
#d['charpath-ecc'] = charpath[2]
#d['charpath-radius'] = charpath[3]
#d['charpath-diameter'] = charpath[4]
d['clustering_coef_wu-C'] = clustering_coef_wu
d['efficiency_wei-Eglob'] = bct.efficiency_wei(cm)
#d['efficiency_wei-Eloc'] = bct.efficiency_wei(cm, True)
#d['modularity_und-ci'] = modularity_und[0]
d['modularity_und-Q'] = modularity_und[1]
d['small_worldness:S'] = compute_small_worldness(cm,
avg_clustering_coef_wu,
charpath[0])
#transitivity_wu can be found in clustering.py
d['transitivity_wu-T'] = bct.transitivity_wu(cm)
#EXAMPLES for local measures and binary measures. Comment in to use.
#VECTOR MEASURES
#d['betweenness_wei-BC'] = bct.betweenness_wei(cm_inv)
# d['module_degree_zscore-Z'] = bct.module_degree_zscore(cm, community_affiliation)
#d['degrees_und-deg'] = bct.degrees_und(cm)
#d['charpath-ecc'] = charpath[2]
#BINARIES
# d['clustering_coef_bu-C'] = bct.clustering_coef_bu(bin_cm)
# d['efficiency_bin-Eglob'] = bct.efficiency_bin(bin_cm)
# d['efficiency_bin-Eloc'] = bct.efficiency_bin(bin_cm, True)
# d['modularity_und_bin-ci'] = modularity_und_bin[0]
# d['modularity_und_bin-Q'] = modularity_und_bin[1]
# d['transitivity_bu-T'] = bct.transitivity_bu(bin_cm)
# d['betweenness_bin-BC'] = bct.betweenness_bin(bin_cm)
# modularity_und_bin = bct.modularity_und(bin_cm)
#d['participation_coef'] = bct.participation_coef(cm, community_affiliation)
######## charpath giving problems with ecc, radius and diameter
# np.seterr(invalid='ignore')
return d
def calc_graph_vector(filename, thresholds) :
'''
This function calculates graph measures for connectivity matrix loaded from textfile
and save results under the same name with additional superscript +'_GV' (in same dir
filename is located)
Input arguments:
filename(str): name of file containing connectivity matrix (txt extension)
thresholds(list): list containing thresholds of interest #
Kamil Bonna, 14.08.2018
'''
#--- check inputs
import os
if not os.path.exists(filename):
raise Exception('{} does not exist'.format(filename))
if type(thresholds) != list:
raise Exception('thresholds should be a list!')
import numpy as np
import bct
#=== inner variables
N_rep_louvain = 10 # number of Louvain algorithm repetitions
N_measures = 10 # number of graph measures
gamma = 1 # Louvain resolution parameter
#--- load matrix
A_raw = np.loadtxt(filename)
N = A_raw.shape[0] # number of nodes
M_sat = N*(N-1)/2 # max number of connections
#=== calculate output
graph_measures = np.zeros([ len(thresholds), N_measures ]) # create empty output matrix
for thr in range(len(thresholds)) :
#--- thresholding
A = bct.threshold_proportional( A_raw, p=thresholds[thr], copy=True );
A[np.nonzero(A<0)] = 0 # ensure only positive weights
M_act = A[np.nonzero(A>0)].shape[0] / 2 # actual number of nonzero connections
#--- calculate measures
#-- mean connection strenght
S = np.sum(A)/M_act
#-- connection strenght std
Svar = np.std(A[np.nonzero(A)])
#-- modularity
[M,Q] = bct.modularity_louvain_und(A, gamma)
for i in range(N_rep_louvain) :
[Mt,Qt] = bct.modularity_louvain_und(A, gamma)
if Qt > Q :
Q = Qt
M = Mt
#-- participation coefficient
P = np.mean(bct.participation_coef_sign(A, M))
#-- clustering
C = np.mean(bct.clustering_coef_wu(A))
#-- transitivity
T = bct.transitivity_wu(A)
#-- assortativity
Asso = bct.assortativity_wei(A)
#-- global & local efficiency
Eglo = bct.efficiency_wei(A)
Eloc = np.mean(bct.efficiency_wei(A, local=True))
#-- mean eigenvector centralit
Eig = np.mean(bct.eigenvector_centrality_und(A))
#--- write vector to matrix
graph_measures[thr] = [ S, Svar, Q, P, C, T, Asso, Eglo, Eloc, Eig ]
#=== save results to file
np.savetxt( filename[:-4]+'_GV.txt', graph_measures )