def extractnetstats(ID, NETWORK, thr, conn_model, est_path1, out_file=None):
import pynets
from pynets import netstats, thresholding
##Load and threshold matrix
in_mat = np.array(genfromtxt(est_path1))
in_mat = thresholding.autofix(in_mat)
##Get hyperbolic tangent of matrix if non-sparse (i.e. fischer r-to-z transform)
if conn_model == 'corr':
in_mat = np.arctanh(in_mat)
##Get dir_path
dir_path = os.path.dirname(os.path.realpath(est_path1))
##Assign Weight matrix
mat_wei = in_mat
##Load numpy matrix as networkx graph
G=nx.from_numpy_matrix(mat_wei)
##Create Binary matrix
#mat_bin = weight_conversion(in_mat, 'binarize')
##Load numpy matrix as networkx graph
#G_bin=nx.from_numpy_matrix(mat_bin)
##Create Length matrix
mat_len = thresholding.weight_conversion(in_mat, 'lengths')
##Load numpy matrix as networkx graph
G_len=nx.from_numpy_matrix(mat_len)
##Save gephi files
if NETWORK != None:
nx.write_graphml(G, dir_path + '/' + ID + '_' + NETWORK + '.graphml')
else:
nx.write_graphml(G, dir_path + '/' + ID + '.graphml')
###############################################################
########### Calculate graph metrics from graph G ##############
###############################################################
import random
import itertools
from itertools import permutations
from networkx.algorithms import degree_assortativity_coefficient, average_clustering, average_shortest_path_length, degree_pearson_correlation_coefficient, graph_number_of_cliques, transitivity, betweenness_centrality, rich_club_coefficient, eigenvector_centrality, communicability_centrality
from pynets.netstats import efficiency, global_efficiency, local_efficiency, create_random_graph, smallworldness_measure, smallworldness, modularity
##For non-nodal scalar metrics from networkx.algorithms library, add the name of the function to metric_list for it to be automatically calculated.
##For non-nodal scalar metrics from custom functions, add the name of the function to metric_list and add the function (with a G-only input) to the netstats module.
#metric_list = [global_efficiency, local_efficiency, smallworldness, degree_assortativity_coefficient, average_clustering, average_shortest_path_length, degree_pearson_correlation_coefficient, graph_number_of_cliques, transitivity]
metric_list = [global_efficiency, local_efficiency, degree_assortativity_coefficient, average_clustering, average_shortest_path_length, degree_pearson_correlation_coefficient, graph_number_of_cliques, transitivity]
##Iteratively run functions from above metric list
num_mets = len(metric_list)
net_met_arr = np.zeros([num_mets, 2], dtype='object')
j=0
for i in metric_list:
met_name = str(i).split('<function ')[1].split(' at')[0]
if NETWORK != None:
net_met = NETWORK + '_' + met_name
else:
net_met = met_name
try:
net_met_val = float(i(G))
except:
net_met_val = np.nan
net_met_arr[j,0] = net_met
net_met_arr[j,1] = net_met_val
print(net_met)
print(str(net_met_val))
print('\n')
j = j + 1
net_met_val_list = list(net_met_arr[:,1])
##Calculate modularity using the Louvain algorithm
[community_aff, modularity] = modularity(mat_wei)
##betweenness_centrality
try:
bc_vector = betweenness_centrality(G_len)
print('Extracting Betweeness Centrality vector for all network nodes...')
bc_vals = list(bc_vector.values())
bc_nodes = list(bc_vector.keys())
num_nodes = len(bc_nodes)
bc_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j=0
for i in range(num_nodes):
if NETWORK != None:
bc_arr[j,0] = NETWORK + '_' + str(bc_nodes[j]) + '_betw_cent'
print('\n' + NETWORK + '_' + str(bc_nodes[j]) + '_betw_cent')
else:
bc_arr[j,0] = 'WholeBrain_' + str(bc_nodes[j]) + '_betw_cent'
print('\n' + 'WholeBrain_' + str(bc_nodes[j]) + '_betw_cent')
try:
bc_arr[j,1] = bc_vals[j]
except:
bc_arr[j,1] = np.nan
print(str(bc_vals[j]))
j = j + 1
bc_val_list = list(bc_arr[:,1])
bc_arr[num_nodes,0] = NETWORK + '_MEAN_betw_cent'
nonzero_arr_betw_cent = np.delete(bc_arr[:,1], [0])
bc_arr[num_nodes,1] = np.mean(nonzero_arr_betw_cent)
print('\n' + 'Mean Betweenness Centrality across all nodes: ' + str(bc_arr[num_nodes,1]) + '\n')
except:
print('Betweeness Centrality calculation failed. Skipping...')
bc_val_list = []
pass
##eigenvector_centrality
try:
ec_vector = eigenvector_centrality(G_len)
print('Extracting Eigenvector Centrality vector for all network nodes...')
ec_vals = list(ec_vector.values())
ec_nodes = list(ec_vector.keys())
num_nodes = len(ec_nodes)
ec_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j=0
for i in range(num_nodes):
if NETWORK != None:
ec_arr[j,0] = NETWORK + '_' + str(ec_nodes[j]) + '_eig_cent'
print('\n' + NETWORK + '_' + str(ec_nodes[j]) + '_eig_cent')
else:
ec_arr[j,0] = 'WholeBrain_' + str(ec_nodes[j]) + '_eig_cent'
print('\n' + 'WholeBrain_' + str(ec_nodes[j]) + '_eig_cent')
try:
ec_arr[j,1] = ec_vals[j]
except:
ec_arr[j,1] = np.nan
print(str(ec_vals[j]))
j = j + 1
ec_val_list = list(ec_arr[:,1])
ec_arr[num_nodes,0] = NETWORK + '_MEAN_eig_cent'
nonzero_arr_eig_cent = np.delete(ec_arr[:,1], [0])
ec_arr[num_nodes,1] = np.mean(nonzero_arr_eig_cent)
print('\n' + 'Mean Eigenvector Centrality across all nodes: ' + str(ec_arr[num_nodes,1]) + '\n')
except:
print('Eigenvector Centrality calculation failed. Skipping...')
ec_val_list = []
pass
##communicability_centrality
try:
cc_vector = communicability_centrality(G_len)
print('Extracting Communicability Centrality vector for all network nodes...')
cc_vals = list(cc_vector.values())
cc_nodes = list(cc_vector.keys())
num_nodes = len(cc_nodes)
cc_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j=0
for i in range(num_nodes):
if NETWORK != None:
cc_arr[j,0] = NETWORK + '_' + str(cc_nodes[j]) + '_comm_cent'
print('\n' + NETWORK + '_' + str(cc_nodes[j]) + '_comm_cent')
else:
cc_arr[j,0] = 'WholeBrain_' + str(cc_nodes[j]) + '_comm_cent'
print('\n' + 'WholeBrain_' + str(cc_nodes[j]) + '_comm_cent')
try:
cc_arr[j,1] = cc_vals[j]
except:
cc_arr[j,1] = np.nan
print(str(cc_vals[j]))
j = j + 1
cc_val_list = list(cc_arr[:,1])
cc_arr[num_nodes,0] = NETWORK + '_MEAN_comm_cent'
nonzero_arr_comm_cent = np.delete(cc_arr[:,1], [0])
cc_arr[num_nodes,1] = np.mean(nonzero_arr_comm_cent)
print('\n' + 'Mean Communicability Centrality across all nodes: ' + str(cc_arr[num_nodes,1]) + '\n')
except:
print('Communicability Centrality calculation failed. Skipping...')
cc_val_list = []
pass
##rich_club_coefficient
try:
rc_vector = rich_club_coefficient(G, normalized=True)
print('Extracting Rich Club Coefficient vector for all network nodes...')
rc_vals = list(rc_vector.values())
rc_edges = list(rc_vector.keys())
num_edges = len(rc_edges)
rc_arr = np.zeros([num_edges + 1, 2], dtype='object')
j=0
for i in range(num_edges):
if NETWORK != None:
rc_arr[j,0] = NETWORK + '_' + str(rc_edges[j]) + '_rich_club'
print('\n' + NETWORK + '_' + str(rc_edges[j]) + '_rich_club')
else:
cc_arr[j,0] = 'WholeBrain_' + str(rc_nodes[j]) + '_rich_club'
print('\n' + 'WholeBrain_' + str(rc_nodes[j]) + '_rich_club')
try:
rc_arr[j,1] = rc_vals[j]
except:
rc_arr[j,1] = np.nan
print(str(rc_vals[j]))
j = j + 1
##Add mean
rc_val_list = list(rc_arr[:,1])
rc_arr[num_edges,0] = NETWORK + '_MEAN_rich_club'
nonzero_arr_rich_club = np.delete(rc_arr[:,1], [0])
rc_arr[num_edges,1] = np.mean(nonzero_arr_rich_club)
print('\n' + 'Mean Rich Club Coefficient across all edges: ' + str(rc_arr[num_edges,1]) + '\n')
except:
print('Rich Club calculation failed. Skipping...')
rc_val_list = []
pass
##Create a list of metric names for scalar metrics
metric_list_names = []
net_met_val_list_final = net_met_val_list
for i in net_met_arr[:,0]:
metric_list_names.append(i)
##Add modularity measure
try:
if NETWORK != None:
metric_list_names.append(NETWORK + '_Modularity')
else:
metric_list_names.append('WholeBrain_Modularity')
net_met_val_list_final.append(modularity)
except:
pass
##Add centrality and rich club measures
try:
for i in bc_arr[:,0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(bc_arr[:,1])
except:
pass
try:
for i in ec_arr[:,0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(ec_arr[:,1])
except:
pass
try:
for i in cc_arr[:,0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(cc_arr[:,1])
except:
pass
try:
for i in rc_arr[:,0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(rc_arr[:,1])
except:
pass
##Save metric names as pickle
try:
import cPickle
except ImportError:
import _pickle as cPickle
if NETWORK != None:
met_list_picke_path = os.path.dirname(os.path.abspath(est_path1)) + '/met_list_pickle_' + NETWORK
else:
met_list_picke_path = os.path.dirname(os.path.abspath(est_path1)) + '/met_list_pickle_WB'
cPickle.dump(metric_list_names, open(met_list_picke_path, 'wb'))
##Save results to csv
if 'inv' in est_path1:
if NETWORK != None:
out_path = dir_path + '/' + ID + '_' + NETWORK + '_net_mets_sps_cov_' + str(thr) + '.csv'
else:
out_path = dir_path + '/' + ID + '_net_mets_sps_cov_' + str(thr) + '.csv'
else:
if NETWORK != None:
out_path = dir_path + '/' + ID + '_' + NETWORK + '_net_mets_corr_' + str(thr) + '.csv'
else:
out_path = dir_path + '/' + ID + '_net_mets_corr_' + str(thr) + '.csv'
np.savetxt(out_path, net_met_val_list_final)
return(out_path)
def extractnetstats(ID,
network,
thr,
conn_model,
est_path,
mask,
out_file=None):
from pynets import thresholding, utils
pruning = True
##Load and threshold matrix
in_mat = np.array(np.genfromtxt(est_path))
in_mat = thresholding.autofix(in_mat)
##Normalize connectivity matrix (weights between 0-1)
in_mat = thresholding.normalize(in_mat)
##Get hyperbolic tangent of matrix if non-sparse (i.e. fischer r-to-z transform)
if conn_model == 'corr':
in_mat = np.arctanh(in_mat)
in_mat[np.isnan(in_mat)] = 0
in_mat[np.isinf(in_mat)] = 1
##Get dir_path
dir_path = os.path.dirname(os.path.realpath(est_path))
##Load numpy matrix as networkx graph
G_pre = nx.from_numpy_matrix(in_mat)
##Prune irrelevant nodes (i.e. nodes who are fully disconnected from the graph and/or those whose betweenness centrality are > 3 standard deviations below the mean)
if pruning == True:
[G_pruned, _, _] = most_important(G_pre)
else:
G_pruned = G_pre
##Make directed if sparse
if conn_model != 'corr' and conn_model != 'cov' and conn_model != 'tangent':
G_di = nx.DiGraph(G_pruned)
G_dir = G_di.to_directed()
G = G_pruned
else:
G = G_pruned
##Get corresponding matrix
in_mat = nx.to_numpy_array(G)
##Print graph summary
print('\n\nThreshold: ' + str(thr))
print('Source File: ' + str(est_path))
info_list = list(nx.info(G).split('\n'))[2:]
for i in info_list:
print(i)
try:
G_dir
print('Analyzing DIRECTED graph when applicable...')
except:
print('Graph is UNDIRECTED')
if conn_model == 'corr' or conn_model == 'cov' or conn_model == 'tangent':
if nx.is_connected(G) == True:
num_conn_comp = nx.number_connected_components(G)
print('Graph is CONNECTED with ' + str(num_conn_comp) +
' connected component(s)')
else:
print('Graph is DISCONNECTED')
print('\n')
##Create Length matrix
mat_len = thresholding.weight_conversion(in_mat, 'lengths')
##Load numpy matrix as networkx graph
G_len = nx.from_numpy_matrix(mat_len)
##Save G as gephi file
if mask:
if network:
nx.write_graphml(
G, dir_path + '/' + ID + '_' + network + '_' +
str(os.path.basename(mask).split('.')[0]) + '.graphml')
else:
nx.write_graphml(
G, dir_path + '/' + ID + '_' +
str(os.path.basename(mask).split('.')[0]) + '.graphml')
else:
if network:
nx.write_graphml(G,
dir_path + '/' + ID + '_' + network + '.graphml')
else:
nx.write_graphml(G, dir_path + '/' + ID + '.graphml')
###############################################################
########### Calculate graph metrics from graph G ##############
###############################################################
from networkx.algorithms import degree_assortativity_coefficient, average_clustering, average_shortest_path_length, degree_pearson_correlation_coefficient, graph_number_of_cliques, transitivity, betweenness_centrality, eigenvector_centrality, communicability_betweenness_centrality, clustering, degree_centrality
from pynets.netstats import average_local_efficiency, global_efficiency, local_efficiency, modularity_louvain_dir, smallworldness
##For non-nodal scalar metrics from custom functions, add the name of the function to metric_list and add the function (with a G-only input) to the netstats module.
metric_list = [
global_efficiency, average_local_efficiency, smallworldness,
degree_assortativity_coefficient, average_clustering,
average_shortest_path_length, degree_pearson_correlation_coefficient,
graph_number_of_cliques, transitivity
]
##Custom Weight Parameter
#custom_weight = 0.25
custom_weight = None
##Iteratively run functions from above metric list that generate single scalar output
num_mets = len(metric_list)
net_met_arr = np.zeros([num_mets, 2], dtype='object')
j = 0
for i in metric_list:
met_name = str(i).split('<function ')[1].split(' at')[0]
net_met = met_name
try:
if i is 'average_shortest_path_length':
try:
try:
net_met_val = float(i(G_dir))
print('Calculating from directed graph...')
except:
net_met_val = float(i(G))
except:
##case where G is not fully connected
net_met_val = float(
average_shortest_path_length_for_all(G))
if custom_weight is not None and i is 'degree_assortativity_coefficient' or i is 'global_efficiency' or i is 'average_local_efficiency' or i is 'average_clustering':
custom_weight_param = 'weight = ' + str(custom_weight)
try:
net_met_val = float(i(G_dir, custom_weight_param))
print('Calculating from directed graph...')
except:
net_met_val = float(i(G, custom_weight_param))
else:
try:
net_met_val = float(i(G_dir))
print('Calculating from directed graph...')
except:
net_met_val = float(i(G))
except:
net_met_val = np.nan
net_met_arr[j, 0] = net_met
net_met_arr[j, 1] = net_met_val
print(net_met)
print(str(net_met_val))
print('\n')
j = j + 1
net_met_val_list = list(net_met_arr[:, 1])
##Run miscellaneous functions that generate multiple outputs
##Calculate modularity using the Louvain algorithm
[community_aff, modularity] = modularity_louvain_dir(in_mat)
##Calculate core-periphery subdivision
[Coreness_vec, Coreness_q] = core_periphery_dir(in_mat)
##Local Efficiency
try:
try:
le_vector = local_efficiency(G_dir)
except:
le_vector = local_efficiency(G)
print('\nExtracting Local Efficiency vector for all network nodes...')
le_vals = list(le_vector.values())
le_nodes = list(le_vector.keys())
num_nodes = len(le_nodes)
le_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
le_arr[j, 0] = str(le_nodes[j]) + '_local_efficiency'
#print('\n' + str(le_nodes[j]) + '_local_efficiency')
try:
le_arr[j, 1] = le_vals[j]
except:
le_arr[j, 1] = np.nan
#print(str(le_vals[j]))
j = j + 1
le_arr[num_nodes, 0] = 'MEAN_local_efficiency'
nonzero_arr_le = np.delete(le_arr[:, 1], [0])
le_arr[num_nodes, 1] = np.mean(nonzero_arr_le)
print('Mean Local Efficiency across nodes: ' +
str(le_arr[num_nodes, 1]))
print('\n')
except:
pass
##Local Clustering
try:
cl_vector = clustering(G)
print('\nExtracting Local Clustering vector for all network nodes...')
cl_vals = list(cl_vector.values())
cl_nodes = list(cl_vector.keys())
num_nodes = len(cl_nodes)
cl_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
cl_arr[j, 0] = str(cl_nodes[j]) + '_local_clustering'
#print('\n' + str(cl_nodes[j]) + '_local_clustering')
try:
cl_arr[j, 1] = cl_vals[j]
except:
cl_arr[j, 1] = np.nan
#print(str(cl_vals[j]))
j = j + 1
cl_arr[num_nodes, 0] = 'MEAN_local_efficiency'
nonzero_arr_cl = np.delete(cl_arr[:, 1], [0])
cl_arr[num_nodes, 1] = np.mean(nonzero_arr_cl)
print('Mean Local Clustering across nodes: ' +
str(cl_arr[num_nodes, 1]))
print('\n')
except:
pass
##Degree centrality
try:
try:
dc_vector = degree_centrality(G_dir)
except:
dc_vector = degree_centrality(G)
print('\nExtracting Degree Centrality vector for all network nodes...')
dc_vals = list(dc_vector.values())
dc_nodes = list(dc_vector.keys())
num_nodes = len(dc_nodes)
dc_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
dc_arr[j, 0] = str(dc_nodes[j]) + '_degree_centrality'
#print('\n' + str(dc_nodes[j]) + '_degree_centrality')
try:
dc_arr[j, 1] = dc_vals[j]
except:
dc_arr[j, 1] = np.nan
#print(str(cl_vals[j]))
j = j + 1
dc_arr[num_nodes, 0] = 'MEAN_degree_centrality'
nonzero_arr_dc = np.delete(dc_arr[:, 1], [0])
dc_arr[num_nodes, 1] = np.mean(nonzero_arr_dc)
print('Mean Degree Centrality across nodes: ' +
str(dc_arr[num_nodes, 1]))
print('\n')
except:
pass
##Betweenness Centrality
try:
bc_vector = betweenness_centrality(G_len, normalized=True)
print(
'\nExtracting Betweeness Centrality vector for all network nodes...'
)
bc_vals = list(bc_vector.values())
bc_nodes = list(bc_vector.keys())
num_nodes = len(bc_nodes)
bc_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
bc_arr[j, 0] = str(bc_nodes[j]) + '_betweenness_centrality'
#print('\n' + str(bc_nodes[j]) + '_betw_cent')
try:
bc_arr[j, 1] = bc_vals[j]
except:
bc_arr[j, 1] = np.nan
#print(str(bc_vals[j]))
j = j + 1
bc_arr[num_nodes, 0] = 'MEAN_betw_cent'
nonzero_arr_betw_cent = np.delete(bc_arr[:, 1], [0])
bc_arr[num_nodes, 1] = np.mean(nonzero_arr_betw_cent)
print('Mean Betweenness Centrality across nodes: ' +
str(bc_arr[num_nodes, 1]))
print('\n')
except:
pass
##Eigenvector Centrality
try:
try:
ec_vector = eigenvector_centrality(G_dir, max_iter=1000)
except:
ec_vector = eigenvector_centrality(G, max_iter=1000)
print(
'\nExtracting Eigenvector Centrality vector for all network nodes...'
)
ec_vals = list(ec_vector.values())
ec_nodes = list(ec_vector.keys())
num_nodes = len(ec_nodes)
ec_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
ec_arr[j, 0] = str(ec_nodes[j]) + '_eigenvector_centrality'
#print('\n' + str(ec_nodes[j]) + '_eig_cent')
try:
ec_arr[j, 1] = ec_vals[j]
except:
ec_arr[j, 1] = np.nan
#print(str(ec_vals[j]))
j = j + 1
ec_arr[num_nodes, 0] = 'MEAN_eig_cent'
nonzero_arr_eig_cent = np.delete(ec_arr[:, 1], [0])
ec_arr[num_nodes, 1] = np.mean(nonzero_arr_eig_cent)
print('Mean Eigenvector Centrality across nodes: ' +
str(ec_arr[num_nodes, 1]))
print('\n')
except:
pass
##Communicability Centrality
try:
cc_vector = communicability_betweenness_centrality(G, normalized=True)
print(
'\nExtracting Communicability Centrality vector for all network nodes...'
)
cc_vals = list(cc_vector.values())
cc_nodes = list(cc_vector.keys())
num_nodes = len(cc_nodes)
cc_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
cc_arr[j, 0] = str(cc_nodes[j]) + '_communicability_centrality'
#print('\n' + str(cc_nodes[j]) + '_comm_cent')
try:
cc_arr[j, 1] = cc_vals[j]
except:
cc_arr[j, 1] = np.nan
#print(str(cc_vals[j]))
j = j + 1
cc_arr[num_nodes, 0] = 'MEAN_comm_cent'
nonzero_arr_comm_cent = np.delete(cc_arr[:, 1], [0])
cc_arr[num_nodes, 1] = np.mean(nonzero_arr_comm_cent)
print('Mean Communicability Centrality across nodes: ' +
str(cc_arr[num_nodes, 1]))
print('\n')
except:
pass
##Rich club coefficient
try:
rc_vector = rich_club_coefficient(G, normalized=True)
print(
'\nExtracting Rich Club Coefficient vector for all network nodes...'
)
rc_vals = list(rc_vector.values())
rc_edges = list(rc_vector.keys())
num_edges = len(rc_edges)
rc_arr = np.zeros([num_edges + 1, 2], dtype='object')
j = 0
for i in range(num_edges):
rc_arr[j, 0] = str(rc_edges[j]) + '_rich_club'
#print('\n' + str(rc_edges[j]) + '_rich_club')
try:
rc_arr[j, 1] = rc_vals[j]
except:
rc_arr[j, 1] = np.nan
#print(str(rc_vals[j]))
j = j + 1
##Add mean
rc_arr[num_edges, 0] = 'MEAN_rich_club'
nonzero_arr_rich_club = np.delete(rc_arr[:, 1], [0])
rc_arr[num_edges, 1] = np.mean(nonzero_arr_rich_club)
print('Mean Rich Club Coefficient across edges: ' +
str(rc_arr[num_edges, 1]))
print('\n')
except:
pass
##Create a list of metric names for scalar metrics
metric_list_names = []
net_met_val_list_final = net_met_val_list
for i in net_met_arr[:, 0]:
metric_list_names.append(i)
##Add modularity measure
try:
metric_list_names.append('Modularity')
net_met_val_list_final.append(modularity)
except:
pass
##Add Core/Periphery measure
try:
metric_list_names.append('Coreness')
net_met_val_list_final.append(Coreness_q)
except:
pass
##Add local efficiency measures
try:
for i in le_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(le_arr[:, 1])
except:
pass
##Add local clustering measures
try:
for i in cl_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(cl_arr[:, 1])
except:
pass
##Add centrality measures
try:
for i in dc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(dc_arr[:, 1])
except:
pass
try:
for i in bc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(bc_arr[:, 1])
except:
pass
try:
for i in ec_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(ec_arr[:, 1])
except:
pass
try:
for i in cc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(cc_arr[:, 1])
except:
pass
##Add rich club measure
try:
for i in rc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(rc_arr[:, 1])
except:
pass
##Save metric names as pickle
try:
import cPickle
except ImportError:
import _pickle as cPickle
if mask != None:
if network != None:
met_list_picke_path = os.path.dirname(os.path.abspath(
est_path)) + '/net_metric_list_' + network + '_' + str(
os.path.basename(mask).split('.')[0])
else:
met_list_picke_path = os.path.dirname(
os.path.abspath(est_path)) + '/net_metric_list_' + str(
os.path.basename(mask).split('.')[0])
else:
if network != None:
met_list_picke_path = os.path.dirname(
os.path.abspath(est_path)) + '/net_metric_list_' + network
else:
met_list_picke_path = os.path.dirname(
os.path.abspath(est_path)) + '/net_metric_list'
cPickle.dump(metric_list_names, open(met_list_picke_path, 'wb'))
##And save results to csv
out_path = utils.create_csv_path(ID, network, conn_model, thr, mask,
dir_path)
np.savetxt(out_path, net_met_val_list_final)
return (out_path)
def extractnetstats(ID,
network,
thr,
conn_model,
est_path,
roi,
prune,
node_size,
norm,
binary,
custom_weight=None):
"""
Function interface for performing fully-automated graph analysis.
Parameters
----------
ID : str
A subject id or other unique identifier.
network : str
Resting-state network based on Yeo-7 and Yeo-17 naming (e.g. 'Default') used to filter nodes in the study of
brain subgraphs.
thr : float
The value, between 0 and 1, used to threshold the graph using any variety of methods
triggered through other options.
conn_model : str
Connectivity estimation model (e.g. corr for correlation, cov for covariance, sps for precision covariance,
partcorr for partial correlation). sps type is used by default.
est_path : str
File path to the thresholded graph, conn_matrix_thr, saved as a numpy array in .npy format.
roi : str
File path to binarized/boolean region-of-interest Nifti1Image file.
prune : bool
Indicates whether to prune final graph of disconnected nodes/isolates.
node_size : int
Spherical centroid node size in the case that coordinate-based centroids
are used as ROI's.
norm : int
Indicates method of normalizing resulting graph.
binary : bool
Indicates whether to binarize resulting graph edges to form an
unweighted graph.
custom_weight : float
The edge attribute that holds the numerical value used as a weight.
If None, then each edge has weight 1. Default is None.
Returns
-------
out_path : str
Path to .csv file where graph analysis results are saved.
"""
import pandas as pd
import yaml
try:
import cPickle as pickle
except ImportError:
import _pickle as pickle
from pathlib import Path
from pynets import thresholding, utils
# Advanced options
fmt = 'edgelist_ssv'
est_path_fmt = "%s%s" % ('.', est_path.split('.')[-1])
# Load and threshold matrix
if est_path_fmt == '.txt':
in_mat_raw = np.array(np.genfromtxt(est_path))
else:
in_mat_raw = np.array(np.load(est_path))
# De-diagnal
in_mat = np.array(np.array(thresholding.autofix(in_mat_raw)))
# Normalize connectivity matrix
# Force edges to values between 0-1
if norm == 1:
in_mat = thresholding.normalize(in_mat)
# Apply log10
elif norm == 2:
in_mat = np.log10(in_mat)
else:
pass
# Correct nan's and inf's
in_mat[np.isnan(in_mat)] = 0
in_mat[np.isinf(in_mat)] = 1
# Get hyperbolic tangent (i.e. fischer r-to-z transform) of matrix if non-covariance
if (conn_model == 'corr') or (conn_model == 'partcorr'):
in_mat = np.arctanh(in_mat)
# Binarize graph
if binary is True:
in_mat = thresholding.binarize(in_mat)
# Get dir_path
dir_path = os.path.dirname(os.path.realpath(est_path))
# Load numpy matrix as networkx graph
G_pre = nx.from_numpy_matrix(in_mat)
# Prune irrelevant nodes (i.e. nodes who are fully disconnected from the graph and/or those whose betweenness
# centrality are > 3 standard deviations below the mean)
if prune == 1:
[G, _] = prune_disconnected(G_pre)
elif prune == 2:
[G, _] = most_important(G_pre)
else:
G = G_pre
# Get corresponding matrix
in_mat = np.array(nx.to_numpy_matrix(G))
# Saved pruned
if (prune != 0) and (prune is not None):
final_mat_path = "%s%s%s" % (est_path.split(est_path_fmt)[0],
'_pruned_mat', est_path_fmt)
utils.save_mat(in_mat, final_mat_path, fmt)
# Print graph summary
print("%s%.2f%s" % ('\n\nThreshold: ', 100 * float(thr), '%'))
print("%s%s" % ('Source File: ', est_path))
info_list = list(nx.info(G).split('\n'))[2:]
for i in info_list:
print(i)
if nx.is_connected(G) is True:
frag = False
print('Graph is connected...')
else:
frag = True
print('Warning: Graph is fragmented...\n')
# Create Length matrix
mat_len = thresholding.weight_conversion(in_mat, 'lengths')
# Load numpy matrix as networkx graph
G_len = nx.from_numpy_matrix(mat_len)
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# # # # Calculate global and local metrics from graph G # # # #
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
import community
from networkx.algorithms import degree_assortativity_coefficient, average_clustering, average_shortest_path_length, degree_pearson_correlation_coefficient, graph_number_of_cliques, transitivity, betweenness_centrality, eigenvector_centrality, communicability_betweenness_centrality, clustering, degree_centrality, rich_club_coefficient, sigma
from pynets.stats.netstats import average_local_efficiency, global_efficiency, participation_coef, participation_coef_sign, diversity_coef_sign
# For non-nodal scalar metrics from custom functions, add the name of the function to metric_list and add the
# function (with a G-only input) to the netstats module.
metric_list_glob = [
global_efficiency, average_local_efficiency,
degree_assortativity_coefficient, average_clustering,
average_shortest_path_length, degree_pearson_correlation_coefficient,
graph_number_of_cliques, transitivity, sigma
]
metric_list_comm = ['louvain_modularity']
# with open("%s%s" % (str(Path(__file__).parent), '/global_graph_measures.yaml'), 'r') as stream:
# try:
# metric_dict_global = yaml.load(stream)
# metric_list_global = metric_dict_global['metric_list_global']
# print("%s%s%s" % ('\n\nCalculating global measures:\n', metric_list_global, '\n\n'))
# except FileNotFoundError:
# print('Failed to parse global_graph_measures.yaml')
with open(
"%s%s" %
(str(Path(__file__).parent), '/nodal_graph_measures.yaml'),
'r') as stream:
try:
metric_dict_nodal = yaml.load(stream)
metric_list_nodal = metric_dict_nodal['metric_list_nodal']
print("%s%s%s" % ('\n\nCalculating nodal measures:\n',
metric_list_nodal, '\n\n'))
except FileNotFoundError:
print('Failed to parse nodal_graph_measures.yaml')
# Note the use of bare excepts in preceding blocks. Typically, this is considered bad practice in python. Here,
# we are exploiting it intentionally to facilitate uninterrupted, automated graph analysis even when algorithms are
# undefined. In those instances, solutions are assigned NaN's.
# Iteratively run functions from above metric list that generate single scalar output
num_mets = len(metric_list_glob)
net_met_arr = np.zeros([num_mets, 2], dtype='object')
j = 0
for i in metric_list_glob:
met_name = str(i).split('<function ')[1].split(' at')[0]
net_met = met_name
try:
try:
net_met_val = raw_mets(G, i, custom_weight)
except:
print("%s%s%s" %
('WARNING: ', net_met, ' failed for graph G.'))
net_met_val = np.nan
except:
print("%s%s%s" %
('WARNING: ', str(i), ' is undefined for graph G'))
net_met_val = np.nan
net_met_arr[j, 0] = net_met
net_met_arr[j, 1] = net_met_val
print(net_met)
print(str(net_met_val))
print('\n')
j = j + 1
net_met_val_list = list(net_met_arr[:, 1])
# Create a list of metric names for scalar metrics
metric_list_names = []
net_met_val_list_final = net_met_val_list
for i in net_met_arr[:, 0]:
metric_list_names.append(i)
# Run miscellaneous functions that generate multiple outputs
# Calculate modularity using the Louvain algorithm
if 'louvain_modularity' in metric_list_comm:
try:
ci = community.best_partition(G)
modularity = community.community_louvain.modularity(ci, G)
metric_list_names.append('modularity')
net_met_val_list_final.append(modularity)
except:
print('Louvain modularity calculation is undefined for graph G')
pass
# Participation Coefficient by louvain community
if 'participation_coefficient' in metric_list_nodal:
try:
if ci is None:
raise KeyError(
'Participation coefficient cannot be calculated for graph G in the absence of a '
'community affiliation vector')
if len(in_mat[in_mat < 0.0]) > 0:
pc_vector = participation_coef_sign(in_mat, ci)
else:
pc_vector = participation_coef(in_mat, ci)
print(
'\nExtracting Participation Coefficient vector for all network nodes...'
)
pc_vals = list(pc_vector)
pc_edges = list(range(len(pc_vector)))
num_edges = len(pc_edges)
pc_arr = np.zeros([num_edges + 1, 2], dtype='object')
j = 0
for i in range(num_edges):
pc_arr[j, 0] = "%s%s" % (str(pc_edges[j]), '_partic_coef')
try:
pc_arr[j, 1] = pc_vals[j]
except:
print("%s%s%s" %
('Participation coefficient is undefined for node ',
str(j), ' of graph G'))
pc_arr[j, 1] = np.nan
j = j + 1
# Add mean
pc_arr[num_edges, 0] = 'average_participation_coefficient'
nonzero_arr_partic_coef = np.delete(pc_arr[:, 1], [0])
pc_arr[num_edges, 1] = np.mean(nonzero_arr_partic_coef)
print("%s%s" % ('Mean Participation Coefficient across edges: ',
str(pc_arr[num_edges, 1])))
for i in pc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(pc_arr[:,
1])
except:
print('Participation coefficient cannot be calculated for graph G')
pass
# Diversity Coefficient by louvain community
if 'diversity_coefficient' in metric_list_nodal:
try:
if ci is None:
raise KeyError(
'Diversity coefficient cannot be calculated for graph G in the absence of a community '
'affiliation vector')
[dc_vector, _] = diversity_coef_sign(in_mat, ci)
print(
'\nExtracting Diversity Coefficient vector for all network nodes...'
)
dc_vals = list(dc_vector)
dc_edges = list(range(len(dc_vector)))
num_edges = len(dc_edges)
dc_arr = np.zeros([num_edges + 1, 2], dtype='object')
j = 0
for i in range(num_edges):
dc_arr[j, 0] = "%s%s" % (str(dc_edges[j]), '_diversity_coef')
try:
dc_arr[j, 1] = dc_vals[j]
except:
print("%s%s%s" %
('Diversity coefficient is undefined for node ',
str(j), ' of graph G'))
dc_arr[j, 1] = np.nan
j = j + 1
# Add mean
dc_arr[num_edges, 0] = 'average_diversity_coefficient'
nonzero_arr_diversity_coef = np.delete(dc_arr[:, 1], [0])
dc_arr[num_edges, 1] = np.mean(nonzero_arr_diversity_coef)
print("%s%s" % ('Mean Diversity Coefficient across edges: ',
str(dc_arr[num_edges, 1])))
for i in dc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(dc_arr[:,
1])
except:
print('Diversity coefficient cannot be calculated for graph G')
pass
# Local Efficiency
if 'local_efficiency' in metric_list_nodal:
try:
le_vector = local_efficiency(G)
print(
'\nExtracting Local Efficiency vector for all network nodes...'
)
le_vals = list(le_vector.values())
le_nodes = list(le_vector.keys())
num_nodes = len(le_nodes)
le_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
le_arr[j, 0] = "%s%s" % (str(le_nodes[j]), '_local_efficiency')
try:
le_arr[j, 1] = le_vals[j]
except:
print(
"%s%s%s" % ('Local efficiency is undefined for node ',
str(j), ' of graph G'))
le_arr[j, 1] = np.nan
j = j + 1
le_arr[num_nodes, 0] = 'average_local_efficiency_nodewise'
nonzero_arr_le = np.delete(le_arr[:, 1], [0])
le_arr[num_nodes, 1] = np.mean(nonzero_arr_le)
print("%s%s" % ('Mean Local Efficiency across nodes: ',
str(le_arr[num_nodes, 1])))
for i in le_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(le_arr[:,
1])
except:
print('Local efficiency cannot be calculated for graph G')
pass
# Local Clustering
if 'local_clustering' in metric_list_nodal:
try:
cl_vector = clustering(G)
print(
'\nExtracting Local Clustering vector for all network nodes...'
)
cl_vals = list(cl_vector.values())
cl_nodes = list(cl_vector.keys())
num_nodes = len(cl_nodes)
cl_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
cl_arr[j, 0] = "%s%s" % (str(cl_nodes[j]), '_local_clustering')
try:
cl_arr[j, 1] = cl_vals[j]
except:
print(
"%s%s%s" % ('Local clustering is undefined for node ',
str(j), ' of graph G'))
cl_arr[j, 1] = np.nan
j = j + 1
cl_arr[num_nodes, 0] = 'average_local_efficiency_nodewise'
nonzero_arr_cl = np.delete(cl_arr[:, 1], [0])
cl_arr[num_nodes, 1] = np.mean(nonzero_arr_cl)
print("%s%s" % ('Mean Local Clustering across nodes: ',
str(cl_arr[num_nodes, 1])))
for i in cl_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(cl_arr[:,
1])
except:
print('Local clustering cannot be calculated for graph G')
pass
# Degree centrality
if 'degree_centrality' in metric_list_nodal:
try:
dc_vector = degree_centrality(G)
print(
'\nExtracting Degree Centrality vector for all network nodes...'
)
dc_vals = list(dc_vector.values())
dc_nodes = list(dc_vector.keys())
num_nodes = len(dc_nodes)
dc_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
dc_arr[j,
0] = "%s%s" % (str(dc_nodes[j]), '_degree_centrality')
try:
dc_arr[j, 1] = dc_vals[j]
except:
print(
"%s%s%s" % ('Degree centrality is undefined for node ',
str(j), ' of graph G'))
dc_arr[j, 1] = np.nan
j = j + 1
dc_arr[num_nodes, 0] = 'average_degree_cent'
nonzero_arr_dc = np.delete(dc_arr[:, 1], [0])
dc_arr[num_nodes, 1] = np.mean(nonzero_arr_dc)
print("%s%s" % ('Mean Degree Centrality across nodes: ',
str(dc_arr[num_nodes, 1])))
for i in dc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(dc_arr[:,
1])
except:
print('Degree centrality cannot be calculated for graph G')
pass
# Betweenness Centrality
if 'betweenness_centrality' in metric_list_nodal:
try:
bc_vector = betweenness_centrality(G_len, normalized=True)
print(
'\nExtracting Betweeness Centrality vector for all network nodes...'
)
bc_vals = list(bc_vector.values())
bc_nodes = list(bc_vector.keys())
num_nodes = len(bc_nodes)
bc_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
bc_arr[j, 0] = "%s%s" % (str(
bc_nodes[j]), '_betweenness_centrality')
try:
bc_arr[j, 1] = bc_vals[j]
except:
print("%s%s%s" %
('Betweeness centrality is undefined for node ',
str(j), ' of graph G'))
bc_arr[j, 1] = np.nan
j = j + 1
bc_arr[num_nodes, 0] = 'average_betweenness_centrality'
nonzero_arr_betw_cent = np.delete(bc_arr[:, 1], [0])
bc_arr[num_nodes, 1] = np.mean(nonzero_arr_betw_cent)
print("%s%s" % ('Mean Betweenness Centrality across nodes: ',
str(bc_arr[num_nodes, 1])))
for i in bc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(bc_arr[:,
1])
except:
print('Betweenness centrality cannot be calculated for graph G')
pass
# Eigenvector Centrality
if 'eigenvector_centrality' in metric_list_nodal:
try:
ec_vector = eigenvector_centrality(G, max_iter=1000)
print(
'\nExtracting Eigenvector Centrality vector for all network nodes...'
)
ec_vals = list(ec_vector.values())
ec_nodes = list(ec_vector.keys())
num_nodes = len(ec_nodes)
ec_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
ec_arr[j, 0] = "%s%s" % (str(
ec_nodes[j]), '_eigenvector_centrality')
try:
ec_arr[j, 1] = ec_vals[j]
except:
print("%s%s%s" %
('Eigenvector centrality is undefined for node ',
str(j), ' of graph G'))
ec_arr[j, 1] = np.nan
j = j + 1
ec_arr[num_nodes, 0] = 'average_eigenvector_centrality'
nonzero_arr_eig_cent = np.delete(ec_arr[:, 1], [0])
ec_arr[num_nodes, 1] = np.mean(nonzero_arr_eig_cent)
print("%s%s" % ('Mean Eigenvector Centrality across nodes: ',
str(ec_arr[num_nodes, 1])))
for i in ec_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(ec_arr[:,
1])
except:
print('Eigenvector centrality cannot be calculated for graph G')
pass
# Communicability Centrality
if 'communicability_centrality' in metric_list_nodal:
try:
cc_vector = communicability_betweenness_centrality(G,
normalized=True)
print(
'\nExtracting Communicability Centrality vector for all network nodes...'
)
cc_vals = list(cc_vector.values())
cc_nodes = list(cc_vector.keys())
num_nodes = len(cc_nodes)
cc_arr = np.zeros([num_nodes + 1, 2], dtype='object')
j = 0
for i in range(num_nodes):
cc_arr[j, 0] = "%s%s" % (str(
cc_nodes[j]), '_communicability_centrality')
try:
cc_arr[j, 1] = cc_vals[j]
except:
print("%s%s%s" %
('Communicability centrality is undefined for node ',
str(j), ' of graph G'))
cc_arr[j, 1] = np.nan
j = j + 1
cc_arr[num_nodes, 0] = 'average_communicability_centrality'
nonzero_arr_comm_cent = np.delete(cc_arr[:, 1], [0])
cc_arr[num_nodes, 1] = np.mean(nonzero_arr_comm_cent)
print("%s%s" % ('Mean Communicability Centrality across nodes: ',
str(cc_arr[num_nodes, 1])))
for i in cc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(cc_arr[:,
1])
except:
print(
'Communicability centrality cannot be calculated for graph G')
pass
# Rich club coefficient
if 'rich_club_coefficient' in metric_list_nodal:
try:
rc_vector = rich_club_coefficient(G, normalized=True)
print(
'\nExtracting Rich Club Coefficient vector for all network nodes...'
)
rc_vals = list(rc_vector.values())
rc_edges = list(rc_vector.keys())
num_edges = len(rc_edges)
rc_arr = np.zeros([num_edges + 1, 2], dtype='object')
j = 0
for i in range(num_edges):
rc_arr[j, 0] = "%s%s" % (str(rc_edges[j]), '_rich_club')
try:
rc_arr[j, 1] = rc_vals[j]
except:
print("%s%s%s" %
('Rich club coefficient is undefined for node ',
str(j), ' of graph G'))
rc_arr[j, 1] = np.nan
j = j + 1
# Add mean
rc_arr[num_edges, 0] = 'average_rich_club_coefficient'
nonzero_arr_rich_club = np.delete(rc_arr[:, 1], [0])
rc_arr[num_edges, 1] = np.mean(nonzero_arr_rich_club)
print("%s%s" % ('Mean Rich Club Coefficient across edges: ',
str(rc_arr[num_edges, 1])))
for i in rc_arr[:, 0]:
metric_list_names.append(i)
net_met_val_list_final = net_met_val_list_final + list(rc_arr[:,
1])
except:
print('Rich club coefficient cannot be calculated for graph G')
pass
if roi:
met_list_picke_path = "%s%s%s%s" % (
os.path.dirname(os.path.abspath(est_path)), '/net_met_list', "%s" %
("%s%s%s" % ('_', network, '_') if network else "_"),
os.path.basename(roi).split('.')[0])
else:
if network:
met_list_picke_path = "%s%s%s" % (os.path.dirname(
os.path.abspath(est_path)), '/net_met_list_', network)
else:
met_list_picke_path = "%s%s" % (os.path.dirname(
os.path.abspath(est_path)), '/net_met_list')
pickle.dump(metric_list_names, open(met_list_picke_path, 'wb'), protocol=2)
# And save results to csv
out_path = utils.create_csv_path(ID, network, conn_model, thr, roi,
dir_path, node_size)
np.savetxt(out_path, net_met_val_list_final, delimiter='\t')
if frag is True:
out_path_neat = "%s%s" % (out_path.split('.csv')[0], '_frag_neat.csv')
else:
out_path_neat = "%s%s" % (out_path.split('.csv')[0], '_neat.csv')
df = pd.DataFrame.from_dict(dict(
zip(metric_list_names, net_met_val_list_final)),
orient='index').transpose()
df.to_csv(out_path_neat, index=False)
return out_path