def test_number_of_cliques(self):
G=self.G
assert_equal(nx.graph_number_of_cliques(G),5)
assert_equal(nx.graph_number_of_cliques(G,cliques=self.cl),5)
assert_equal(nx.number_of_cliques(G,1),1)
assert_equal(list(nx.number_of_cliques(G,[1]).values()),[1])
assert_equal(list(nx.number_of_cliques(G,[1,2]).values()),[1, 2])
assert_equal(nx.number_of_cliques(G,[1,2]),{1: 1, 2: 2})
assert_equal(nx.number_of_cliques(G,2),2)
assert_equal(nx.number_of_cliques(G),
{1: 1, 2: 2, 3: 1, 4: 2, 5: 1,
6: 2, 7: 1, 8: 1, 9: 1, 10: 1, 11: 1})
assert_equal(nx.number_of_cliques(G,cliques=self.cl),
{1: 1, 2: 2, 3: 1, 4: 2, 5: 1,
6: 2, 7: 1, 8: 1, 9: 1, 10: 1, 11: 1})
def draw_graph(G):
# an example using Graph as a weighted network.
# __author__ = """Aric Hagberg ([email protected])"""
try:
import matplotlib.pyplot as plt
except:
raise
elarge = [(u, v) for (u, v, d) in G.edges(data=True) if d['weight'] > 0.5]
esmall = [(u, v) for (u, v, d) in G.edges(data=True) if d['weight'] <= 0.5]
pos = nx.spring_layout(G) # positions for all nodes
# nodes
nx.draw_networkx_nodes(G, pos, node_size=200)
# edges
nx.draw_networkx_edges(G, pos, edgelist=elarge, width=0.4)
nx.draw_networkx_edges(G,
pos,
edgelist=esmall,
width=0.4,
alpha=0.6,
style='dashed')
# labels
nx.draw_networkx_labels(G, pos, font_size=6, font_family='sans-serif')
print 'number of cliques/clusters:', nx.graph_number_of_cliques(G)
print 'time:', time.time() - start
plt.show()
def draw_graph(G): # an example using Graph as a weighted network. # __author__ = """Aric Hagberg ([email protected])""" try: import matplotlib.pyplot as plt except: raise elarge = [(u,v) for (u,v,d) in G.edges(data = True) if d['weight'] > 0.5] esmall = [(u,v) for (u,v,d) in G.edges(data = True) if d['weight'] <= 0.5] pos = nx.spring_layout(G) # positions for all nodes # nodes nx.draw_networkx_nodes(G, pos, node_size = 200) # edges nx.draw_networkx_edges(G, pos, edgelist = elarge, width = 0.4) nx.draw_networkx_edges(G, pos, edgelist = esmall, width = 0.4, alpha = 0.6, style = 'dashed') # labels nx.draw_networkx_labels(G, pos, font_size = 6, font_family = 'sans-serif') print 'number of cliques/clusters:', nx.graph_number_of_cliques(G) print 'time:', time.time() - start plt.show()
def netstats_simple(graph):
G = graph
if nx.is_connected(G):
d = nx.diameter(G)
r = nx.radius(G)
else:
d = 'NA - graph is not connected' #should be calculatable on unconnected graph - see example code for hack
r = 'NA - graph is not connected'
#using dictionary to pack values and variablesdot, eps, ps, pdf break equally
result = {#"""single value measures"""
'nn': G.number_of_nodes(),
'ne': G.number_of_edges(),
'd': d,
'r': r,
'conn': nx.number_connected_components(G),
'asp': nx.average_shortest_path_length(G),
# """number of the largest clique"""
'cn': nx.graph_clique_number(G),
# """number of maximal cliques"""
'mcn': nx.graph_number_of_cliques(G),
# """transitivity - """
'tr': nx.transitivity(G),
#cc = nx.clustering(G) """clustering coefficient"""
'avgcc': nx.average_clustering(G) }
# result['d'] = nx.diameter(G)
print result
return result
def Cliques(P, tipo, ruta):
RUTA = ruta + '/NetWX/files/'
path = Path(RUTA)
path.mkdir(parents=True, exist_ok=True)
graph_clique_num = []
graph_number_of_cliqs = []
graph_find_cliques = []
for i in range(len(P)):
graph_clique_num.append(graph_clique_number(P[i]))
graph_number_of_cliqs.append(graph_number_of_cliques(P[i]))
graph_find_cliques.append(find_cliques(P[i]))
graph_clique_num = DataFrame(graph_clique_num)
graph_number_of_cliqs = DataFrame(graph_number_of_cliqs)
graph_find_cliques = DataFrame(graph_find_cliques)
graph_clique_num.to_csv(RUTA + tipo + " - clique num.txt",
sep='\t',
header=None,
index=False)
graph_number_of_cliqs.to_csv(RUTA + tipo + " - number of maxcliques.txt",
sep='\t',
header=None,
index=False)
graph_find_cliques.to_csv(RUTA + tipo + " - find cliques.txt",
sep='\t',
header=None,
index=False)
def calculatecliques(network):
'''
Returns the number of maximal cliques in G.
'''
try:
n = nx.graph_number_of_cliques(network)
except:
n = 0
return n
def computeOneFile(file, aln_net):
global max_clique_dict
global full_score_dict
file_root = file.split('/')[-1].split('.')[0]
score_dict = prepareScoreDict(file_root)
coev_net = nx.read_graphml(file)
cliques = list(nx.find_cliques(coev_net))
max_clique_dict[file_root] = nx.graph_number_of_cliques(coev_net)
# print file_root
# print max_clique_dict[file_root]
for clique in cliques:
flag = False
res_count_dict = {}
for res in clique:
if res in list(nx.nodes(aln_net)):
for neighbor in list(nx.all_neighbors(aln_net, res)):
prot = neighbor.split('-')[0]
if prot not in res_count_dict.keys():
res_count_dict[prot] = 1
else:
res_count_dict[prot] += 1
else:
flag = True
break
if flag:
max_clique_dict[file_root] -= 1
continue
for key, value in res_count_dict.items():
if value == len(clique):
if np.isnan(score_dict[key]):
score_dict[key] = 1
else:
score_dict[key] += 1
full_score_dict[file_root] = score_dict
def getGraphVector(gGraph):
print("Extracting graph feature vector...")
mRes = np.asarray([
len(gGraph.edges()),
len(gGraph.nodes()),
getMeanDegreeCentrality(gGraph),
nx.graph_number_of_cliques(gGraph),
nx.number_connected_components(gGraph),
nx.average_node_connectivity(gGraph),
getAvgShortestPath(gGraph)
])
print("Extracting graph feature vector... Done.")
return mRes
def test_number_of_cliques(self):
G = self.G
assert nx.graph_number_of_cliques(G) == 5
assert nx.graph_number_of_cliques(G, cliques=self.cl) == 5
assert nx.number_of_cliques(G, 1) == 1
assert list(nx.number_of_cliques(G, [1]).values()) == [1]
assert list(nx.number_of_cliques(G, [1, 2]).values()) == [1, 2]
assert nx.number_of_cliques(G, [1, 2]) == {1: 1, 2: 2}
assert nx.number_of_cliques(G, 2) == 2
assert (nx.number_of_cliques(G) ==
{1: 1, 2: 2, 3: 1, 4: 2, 5: 1,
6: 2, 7: 1, 8: 1, 9: 1, 10: 1, 11: 1})
assert (nx.number_of_cliques(G, nodes=list(G)) ==
{1: 1, 2: 2, 3: 1, 4: 2, 5: 1,
6: 2, 7: 1, 8: 1, 9: 1, 10: 1, 11: 1})
assert (nx.number_of_cliques(G, nodes=[2, 3, 4]) ==
{2: 2, 3: 1, 4: 2})
assert (nx.number_of_cliques(G, cliques=self.cl) ==
{1: 1, 2: 2, 3: 1, 4: 2, 5: 1,
6: 2, 7: 1, 8: 1, 9: 1, 10: 1, 11: 1})
assert (nx.number_of_cliques(G, list(G), cliques=self.cl) ==
{1: 1, 2: 2, 3: 1, 4: 2, 5: 1,
6: 2, 7: 1, 8: 1, 9: 1, 10: 1, 11: 1})
def obtenerValores(dirigido, noDirigido):
# variables locales
datos = []
m = 0
c = 0
dm = 0
com = 0
# 1; orden - ambas
#print("orden")
datos.append(str(dirigido.order()))
# 2; tamaño - dirigida
#print("tamaño")
datos.append(str(dirigido.size()))
# 3; densidad, dirigida
#print("densidad")
datos.append(str(nx.density(dirigido)))
# 4; grado promedio - dirigido
#print("grado promedio")
datos.append(str((dirigido.size()) / (dirigido.order())))
# 5; diametro - no dirigido
#print("diametro")
datos.append(str(nx.diameter(noDirigido)))
# 6; radio - no dirigido
#print("radio")
datos.append(str(nx.radius(noDirigido)))
# 7; tamaño de clique mas grande - no dirigida
#print("clique mas grande")
datos.append(str(nx.graph_clique_number(noDirigido)))
# 8; numero de cliques maximales - no dirigida
#print("cliques maximales")
datos.append(str(nx.graph_number_of_cliques(noDirigido)))
# 9; global reaching centrality - dirigido
#print("reachability")
datos.append(str(nx.global_reaching_centrality(dirigido)))
# 10; clustering coefficient - dirigida
#print("clustering")
datos.append(str(nx.average_clustering(dirigido)))
# 11; transitividad - dirigida
#print("transitivity")
datos.append(str(nx.transitivity(dirigido)))
# 12; 13; 14; datos MODC: modularidad, dependencia minima, total de comunidades - no dirigido
#print("MODC")
(m, dm, com) = MODC(noDirigido, True)
datos.append(str(m))
datos.append(str(dm))
datos.append(str(com))
# fin de funcion
return (datos)
def _graph(self, graph):
"""Generate graph-based attributes."""
graph_attr = pd.DataFrame()
graph_attr['number_of_nodes'] = [nx.number_of_nodes(graph)]
graph_attr['number_of_edges'] = [nx.number_of_edges(graph)]
graph_attr['number_of_selfloops'] = [nx.number_of_selfloops(graph)]
graph_attr['graph_number_of_cliques'] = [
nx.graph_number_of_cliques(graph)
]
graph_attr['graph_clique_number'] = [nx.graph_clique_number(graph)]
graph_attr['density'] = [nx.density(graph)]
graph_attr['transitivity'] = [nx.transitivity(graph)]
graph_attr['average_clustering'] = [nx.average_clustering(graph)]
graph_attr['radius'] = [nx.radius(graph)]
graph_attr['is_tree'] = [1 if nx.is_tree(graph) else 0]
graph_attr['wiener_index'] = [nx.wiener_index(graph)]
return graph_attr
def clique(self):
import config
graphs = config.graph
file = open('clique.txt', 'w')
clique_string = [
"This txt file will show you the finding of cliques in your network.\n\n"
+
"Description : In complex network, a clique is a maximal subset of the vertices or nodes in an undirected network such that every member\n"
+
"of the set is connected by an edge or link to every other node." +
"The meaning of 'maximal' here means there is no other vertex or node in the network that can be added to the subset while keeping or preserving\n"
+
"the property that every vertex or node is connected to every other.\n"
]
file.write(clique_string[0])
max_clique = list(nx.make_max_clique_graph(graphs))
max_clique_str = str(max_clique)
max_clique_string = [
"Maximal Cliques:\n-The maximal cliques and treats these cliques as nodes.\n -These nodes in a [] are connected if they have common members in the original graph.\n"
+ "-" + max_clique_str + '\n'
]
file.write(max_clique_string[0])
all_maximal_cliques = str(list(nx.find_cliques(graphs)))
all_maximal_cliques_string = [
"Cliques:\n-The possible cliques in the network.\n" + "-" +
all_maximal_cliques + '\n'
]
file.write(all_maximal_cliques_string[0])
number_of_maximum_clique = str(nx.graph_number_of_cliques(graphs))
number_of_node_in_largest_clique = str(nx.graph_clique_number(graphs))
clique_number_string = [
"Basic statistic of cliques in network:\n-The (largest) number of cliques in the network:"
+ number_of_maximum_clique + "\n" +
"-The number of nodes in the largest clique in the network:" +
number_of_node_in_largest_clique
]
file.write(clique_number_string[0])
file.close() # this must add or only display a empty txt
import os
os.system("notepad.exe clique.txt")
def _graph(self):
"""Generate graph-based attributes."""
self.graph_attr['number_of_nodes'] = [nx.number_of_nodes(self.graph)]
self.graph_attr['number_of_edges'] = [nx.number_of_edges(self.graph)]
self.graph_attr['number_of_selfloops'] = [
nx.number_of_selfloops(self.graph)
]
self.graph_attr['graph_number_of_cliques'] = [
nx.graph_number_of_cliques(self.graph)
]
self.graph_attr['graph_clique_number'] = [
nx.graph_clique_number(self.graph)
]
self.graph_attr['density'] = [nx.density(self.graph)]
self.graph_attr['transitivity'] = [nx.transitivity(self.graph)]
self.graph_attr['average_clustering'] = [
nx.average_clustering(self.graph)
]
self.graph_attr['radius'] = [nx.radius(self.graph)]
self.graph_attr['is_tree'] = [1 if nx.is_tree(self.graph) else 0]
self.graph_attr['wiener_index'] = [nx.wiener_index(self.graph)]
return self.graph_attr
def main():
test = PSNG(generate_three_party_list(7, "normal"), 0.25)
test.dynamic_network_formation()
print(nx.degree_centrality(test.social_network))
print(nx.average_clustering(test.social_network))
print(nx.graph_number_of_cliques(test.social_network))
colour_map = []
for i in test.social_network:
if (test.social_network.node[i]['attr'][0] < 0.5):
colour_map.append('blue')
elif (test.social_network.node[i]['attr'][0] > 0.5):
colour_map.append('green')
else:
colour_map.append('orange')
nx.draw(test.social_network, node_color=colour_map, alpha=0.9, node_size=500, with_labels=True)
plt.show()
graphs_len[gr] = gtem
graphs_lists[gr] = ttem
graphh = G.subgraph(graphs[gr])
if len(graphh.nodes()) > 1 and len(graphh.edges()) > 0:
cliques_edges.append(graphh.edges())
cliques_nodes.append(graphh.nodes())
if len(colors_to_select) == 0:
colors_to_select = list(colors_list)
color = random.choice(colors_to_select)
colors_to_select.remove(color)
colors_of_edges.append((color))
nodes_color_alpha.append(0.4)
edges_color_alpha.append(0.6)
edge_width_l.append(4.0)
lvl2 = []
for i in range(nx.graph_number_of_cliques(G)):
lvl2.append(graphs_len[i])
print str(" ")
print 'ΚΛΙΚΕΣ ΣΕ ΜΗ ΚΑΤΕΥΘΥΝΟΜΕΝΟΥΣ ΓΡΑΦΟΥΣ'
# print 'CLIQUES IN UNDIRECTED GRAPHS'
print str(" ")
print 'Ο γράφος είναι:'
# print 'The graph is:'
graph_name = str(G.name) + str(lvl2)
print graph_name
print str(" ")
print 'Το σύνολο όλων των κλικών του γράφου G:'
# print 'The set of all maximal cliques in graph G is:'
def main(graph_name):
H = nx.read_gml(graph_name)
for node in H.nodes(): # i remove self loops
if node in H.neighbors(node):
if len(H.neighbors(node)) > 1:
H.remove_edge(node, node)
else:
H.remove_node(node)
# for node in H.nodes():
# if H.node[node]['weigh_ins'] <5: #Adherent filter
# H.remove_node(node)
# print node, "is going down"
G = nx.connected_component_subgraphs(H)[0] # Giant component
print "size of the GC:", len(
G.nodes()) #, "after filtering for adherence!!"
#dir=graph_name.split("full_")[0]
#dir=graph_name.split("master")[0]
#dir=graph_name.split("method3_")[0]
#dir=graph_name.split("method3_adh")[0]
dir = graph_name.split("friends")[0]
dir = dir + "roles/"
time_in_system = 50 #minimum amount of time in the sytem for a user to be included in the statistics
#name=graph_name.split('data/')[1]
#name=graph_name.split('method3_50/interim/')[1]
#name=graph_name.split('network_all_users/')[1]
name = graph_name.split('5_points_network_2010/data/')[1]
name = name.split('.gml')[0]
name0 = dir + name + "_overlap_R6s_averages_" + str(
time_in_system) + "days_exclude_R6s.dat"
file0 = open(name0, 'wt')
file0.close()
contador = 0
name12 = dir + name + "_slopes_for_the_fits_average_weight_change.dat"
file = open(name12, 'wt')
file.close()
####for the Isolated Clusters:
list_GC_nodes = []
for n in G.nodes():
list_GC_nodes.append(n)
# print G.node[n]['percentage_weight_change']
# print "# users GC:",len(list_GC_nodes),"total:",len(H.nodes())
list_weight_changes_not_GC = []
for n in H.nodes():
if n not in list_GC_nodes:
#print n,"not in GC"
list_weight_changes_not_GC.append(
float(H.node[n]['percentage_weight_change']))
#print "# users not in GC:",len(list_weight_changes_not_GC)
# who="not_GC"
#Nbins=18
#histograma(list_weight_changes_not_GC,Nbins,dir,name,who)
###########################
list_R6s = [] # collect the R6 of the system
list_R6s_label = []
list_R6s_percent_weight_change = []
for node in G.nodes():
if str(G.node[node]['role']) == "R6":
list_R6s.append(node)
list_R6s_label.append(G.node[node]['label'])
list_R6s_percent_weight_change.append(
float(G.node[node]['percentage_weight_change']))
name00 = dir + name + "R6s_and_top_tens_averages_" + str(
time_in_system) + "days_exclude_R6s.dat"
file0 = open(name00, 'at')
print >> file0, "R6s", numpy.mean(
list_R6s_percent_weight_change), numpy.std(
list_R6s_percent_weight_change)
file0.close()
# print "\n\n R6s:\n"
# for i in list_R6s_label:
# print i
# studying the possible cumulative effect of more than one R6 on the population:
for node in G.nodes():
cont = 0
for n in G.neighbors(node):
if str(G.node[n]['role']) == "R6":
cont += 1
G.node[node]["R6_overlap"] = int(cont)
##### weight change for people not connected to any R6s:####
list_weight_changes_no_neighbors = []
for node in G.nodes():
interseccion = list(set(G.neighbors(node)) & set(list_R6s))
# print node, "intersection:",intersection,len(intersection)
# print "because", list_R6s, "and ",G.neighbors(node)
# raw_input()
if len(interseccion) == 0:
list_weight_changes_no_neighbors.append(
G.node[node]['percentage_weight_change'])
# print len(list_weight_changes_no_neighbors),"no_neighbors"
who = "no_neigbors_R6s"
Nbins = 18
histograma(list_weight_changes_no_neighbors, Nbins, dir, name, who)
# mood test
mood = stats.mood(list_weight_changes_no_neighbors,
list_weight_changes_not_GC)
print "mood test for", who, "against not_GC:", mood
########
# K-S test:
ks = stats.ks_2samp(list_weight_changes_no_neighbors,
list_weight_changes_not_GC)
print "KS test for", who, "against not_GC:", ks
name00 = "ks_results.dat"
file0 = open(dir + name00, 'at')
print >> file0, "KS test for", who, "of", graph_name, "against not_GC:", ks
file0.close()
#############################################
#average percentage weight change as a function of the size of the largest CLIQUE the node belongs to:
absolute_max = 1
for i in G.nodes():
maximo = 1
list2 = nx.cliques_containing_node(G, i)
# print i, list2
for elem in list2:
# print elem,len(elem,)
if len(elem) > maximo:
maximo = len(elem)
# print "\n",maximo
G.node[i]['max_clique_size'] = maximo
if absolute_max < maximo:
absolute_max = maximo
#print absolute_max
lista = list(
nx.find_cliques(G)) # crea una lista de cliques (lista de listas)
max_clique = nx.graph_clique_number(G) #finds out max size clique
num_tot_clique = nx.graph_number_of_cliques(
G) #finds out total number of cliques
# count number of 2, 3, 4, 5, 6 and 7cliques:
num_2cliques = 0
num_3cliques = 0
num_4cliques = 0
num_5cliques = 0
num_6cliques = 0
num_7cliques = 0
num_8cliques = 0
num_9cliques = 0
for element in lista:
if len(element) == 2:
num_2cliques = num_2cliques + 1
elif len(element) == 3:
num_3cliques = num_3cliques + 1
elif len(element) == 4:
num_4cliques = num_4cliques + 1
elif len(element) == 5:
num_5cliques = num_5cliques + 1
elif len(element) == 6:
num_6cliques = num_6cliques + 1
elif len(element) == 7:
num_7cliques = num_7cliques + 1
elif len(element) == 8:
num_8cliques = num_8cliques + 1
elif len(element) == 9:
num_9cliques = num_9cliques + 1
# print " 2: ",num_2cliques, " 3: ",num_3cliques, " 4: ",num_4cliques, " 5: ",num_5cliques, " 6: ",num_6cliques, " 7: ",num_7cliques, " 8: ",num_8cliques, " 9: ",num_9cliques, " max_clique_size:",max_clique, " num_tot_cliques:", num_tot_clique
name33 = dir + name + "_percent_weight_change_vs_largest_clique_size.dat"
file11 = open(name33, 'wt')
file11.close()
list_of_lists_for_bootstrap = []
x_positions_fit = []
y_positions_fit = []
cum_size_set = float(len(G.nodes()))
tot_nodes = []
for clique_size in range(1, max_clique):
clique_size = clique_size + 1
print clique_size
num_users_set = cum_size_set
percent_weight_change_that_clique_size = []
for n in G.nodes():
if G.node[n]['max_clique_size'] == clique_size:
percent_weight_change_that_clique_size.append(
float(G.node[n]['percentage_weight_change']))
tot_nodes.append(float(G.node[n]['percentage_weight_change']))
cum_size_set -= 1.0
file11 = open(name33, 'at')
print >> file11, clique_size, len(
percent_weight_change_that_clique_size), num_users_set / float(
len(G.nodes())), numpy.mean(
percent_weight_change_that_clique_size), numpy.std(
percent_weight_change_that_clique_size)
file11.close()
if len(x_positions_fit) <= 7:
x_positions_fit.append(clique_size)
y_positions_fit.append(
numpy.mean(percent_weight_change_that_clique_size))
list_of_lists_for_bootstrap.append(
percent_weight_change_that_clique_size)
slope, intercept, Corr_coef, p_value, std_err = stats.linregress(
x_positions_fit, y_positions_fit) # least squeares polinomial fit
print "result linear. fit for clique size dependency:"
print "slope:", slope, "intercept:", intercept, "Corr_coef:", Corr_coef, "p_value:", p_value, "std_err:", std_err
name11 = dir + name + "_fits_clique_size.dat"
file11 = open(name11, 'wt')
for i in range(len(x_positions_fit)):
print >> file11, x_positions_fit[
i], intercept + x_positions_fit[i] * slope
print >> file11, "\n\n", "y=", intercept, "+", slope, "*x",
print "Bootstrap for clique size:\n"
mean_slope, standard_dev = bootstrap(x_positions_fit[0],
x_positions_fit[-1],
list_of_lists_for_bootstrap)
zscore = (slope - mean_slope) / standard_dev
print >> file11, "bootstrap:\n", "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
print x_positions_fit[0], x_positions_fit[
-1], "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
file11.close()
contador += 1
file = open(name12, 'at')
print >> file, contador, mean_slope, standard_dev, "largest_clique_size"
file.close()
#######################################
#####dose effect of the R6s independently########
name11 = dir + name + "_dose_eff_indepently_only_one_R6_" + str(
time_in_system) + "days_exclude_R6s.dat"
file11 = open(name11, 'at')
print >> file11, 0, "average_no_neighbors", "average_no_neighbors", "average_no_neighbors", len(
list_weight_changes_no_neighbors
), numpy.mean(list_weight_changes_no_neighbors), numpy.std(
list_weight_changes_no_neighbors
) # the first line of the file is actually for no_neighbors, the rest, for one_and_only_one
file11.close()
file11 = open(name11, 'wt')
file11.close()
cont = 1
list_all = []
list_all_nodes = []
for R6 in list_R6s:
list_weight_changes = []
for n in G.neighbors(R6):
if (G.node[n]['role'] != "R6") and (G.node[n]["R6_overlap"] == 1):
list_weight_changes.append(
float(G.node[n]['percentage_weight_change']))
if n not in list_all_nodes:
list_all_nodes.append(n)
list_all.append(
float(G.node[n]['percentage_weight_change']))
if len(list_weight_changes) > 0:
file11 = open(name11, 'at')
print >> file11, cont, G.node[R6]['role'], G.node[R6][
'label'], len(
G.neighbors(R6)), len(list_weight_changes), numpy.mean(
list_weight_changes), numpy.std(list_weight_changes)
file11.close()
# print cont,G.node[R6]['role'],G.node[R6]['label'], len(G.neighbors(R6)),len(list_weight_changes),numpy.mean(list_weight_changes),numpy.std(list_weight_changes)
cont = cont + 1
else:
# file11=open(name11, 'at')
#print >> file11,cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes)
#file11.close()
# print cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes)
cont = cont + 1
who = "one_and_only_one_R6s"
Nbins = 18
histograma(list_all, Nbins, dir, name, who)
####################################
print "\n\n"
list_of_lists_for_bootstrap = []
x_positions_fit = []
y_positions_fit = []
averages_larger5_x = []
averages_larger5_y = []
norm = 0.0
cum_size_set = float(len(G.nodes())) - float(len(list_R6s))
for r in range(len(list_R6s) + 1):
# list_BMI_changes=[]
list_weight_changes = []
list_percentage_weight_changes = []
list_activities = []
num_users_set = cum_size_set
for node in G.nodes():
if int(G.node[node]["R6_overlap"]) == r:
if G.node[node]["role"] == "R6": # i exclude the R6s
pass
else:
if int(G.node[node]['time_in_system']) > time_in_system:
# list_BMI_changes.append(float(G.node[node]['final_BMI'])-float(G.node[node]['initial_BMI']))
list_weight_changes.append(
float(G.node[node]['weight_change']))
list_percentage_weight_changes.append(
float(G.node[node]['percentage_weight_change']))
list_activities.append(
float(G.node[node]['activity']) /
float(G.node[node]['time_in_system']))
cum_size_set -= 1.0
if len(list_percentage_weight_changes) > 0:
# average_BMI_change=numpy.mean(list_BMI_changes)
average_weight_change = numpy.mean(list_weight_changes)
average_percentage_weight_change = numpy.mean(
list_percentage_weight_changes)
average_activity = numpy.mean(list_activities)
#deviation_BMI=numpy.std(list_BMI_changes)
deviation_weight = numpy.std(list_weight_changes)
deviation_percentage_weight = numpy.std(
list_percentage_weight_changes)
deviation_activity = numpy.std(list_activities)
#print out
file0 = open(name0, 'at')
print >> file0, r, len(
list_percentage_weight_changes
), num_users_set / float(
len(G.nodes())
), average_percentage_weight_change, deviation_percentage_weight, average_weight_change, deviation_weight, average_activity, deviation_activity
file0.close()
if r <= 5:
x_positions_fit.append(r)
y_positions_fit.append(average_percentage_weight_change)
list_of_lists_for_bootstrap.append(
list_percentage_weight_changes)
# else:
# aux_x=r*len(list_percentage_weight_changes)
# averages_larger5_x.append(aux_x)
# aux_y=average_percentage_weight_change*len(list_percentage_weight_changes)
# averages_larger5_y.append(aux_y)
#norm+=float(len(list_percentage_weight_changes))
# x_positions_fit.append(numpy.mean(averages_larger5_x)/norm)
# y_positions_fit.append(numpy.mean(averages_larger5_y)/norm)
slope, intercept, Corr_coef, p_value, std_err = stats.linregress(
x_positions_fit, y_positions_fit) # least squeares polinomial fit
print "result linear. fit for dose eff.:"
print "slope:", slope, "intercept:", intercept, "Corr_coef:", Corr_coef, "p_value:", p_value, "std_err:", std_err
name11 = dir + name + "_fits_dose_eff_R6.dat"
file11 = open(name11, 'wt')
for i in range(len(x_positions_fit)):
print >> file11, x_positions_fit[
i], intercept + x_positions_fit[i] * slope
print >> file11, "\n\n", "y=", intercept, "+", slope, "*x",
print "Bootstrap for dose eff. R6s:\n"
mean_slope, standard_dev = bootstrap(x_positions_fit[0],
x_positions_fit[-1],
list_of_lists_for_bootstrap)
zscore = (slope - mean_slope) / standard_dev
print >> file11, "bootstrap:\n", "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
print x_positions_fit[0], x_positions_fit[
-1], "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
file11.close()
contador += 1
file = open(name12, 'at')
print >> file, contador, mean_slope, standard_dev, "dose_eff"
file.close()
#### averages for every R6's egonetwork:#########
cont = 1
list_all_ = []
list_all_nodes_ = []
for node in list_R6s:
neighbors = G.neighbors(node) #a list of nodes
average_BMI_change = 0.0
list_BMI_changes = []
average_weight_change = 0.0
list_weight_changes = []
average_percentage_weight_change = 0.0
list_percentage_weight_changes = []
average_activity = 0.0 # ojo! sera dividida por el numero de dias!!!!!
list_activities = []
for n in G.neighbors(node):
if int(G.node[n]['time_in_system']) > time_in_system:
# list_BMI_changes.append(float(G.node[n]['final_BMI'])-float(G.node[n]['initial_BMI']))
list_weight_changes.append(float(G.node[n]['weight_change']))
list_percentage_weight_changes.append(
float(G.node[n]['percentage_weight_change']))
list_activities.append(
float(G.node[n]['activity']) /
float(G.node[n]['time_in_system']))
if n not in list_all_nodes_:
list_all_nodes_.append(n)
list_all_.append(
float(G.node[n]['percentage_weight_change']))
#averages
average_weight_change = numpy.mean(list_weight_changes)
# average_BMI_change=numpy.mean(list_BMI_changes)
average_activity = numpy.mean(list_activities)
average_percentage_weight_change = numpy.mean(
list_percentage_weight_changes)
#standard deviation
#deviation_BMI=numpy.std(list_BMI_changes)
deviation_weight = numpy.std(list_weight_changes)
deviation_percentage_weight = numpy.std(list_percentage_weight_changes)
deviation_activity = numpy.std(list_activities)
#print out
name2 = dir + name + "_ego_R6s_average_weight_change_" + str(
time_in_system) + "days.dat"
file2 = open(name2, 'at')
print >> file2, cont, G.node[node]['role'], G.node[node]['label'], len(
G.neighbors(node)), average_weight_change, deviation_weight
file2.close()
name22 = dir + name + "_ego_R6s_average_percentage_weight_change_" + str(
time_in_system) + "days.dat"
file22 = open(name22, 'at')
print >> file22, cont, G.node[node]['role'], G.node[node][
'label'], len(
G.neighbors(node)
), average_percentage_weight_change, deviation_percentage_weight
file22.close()
name3 = dir + name + "_ego_R6s_average_activity_" + str(
time_in_system) + "days.dat"
file3 = open(name3, 'at')
print >> file3, cont, G.node[node]['role'], G.node[node]['label'], len(
G.neighbors(node)), average_activity, deviation_activity
file3.close()
cont = cont + 1
who = "R6s_egonetworks_all"
Nbins = 18
histograma(list_all_, Nbins, dir, name, who)
# print "intersection:",len(set(list_all_)&set(list_all)),len(list_all_),len(list_all)
#############just checking what happens if we remove the 40155 guy
##### percent weight change vs. role:
list_roles = ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]
file = open(dir + name + "_percentage_weight_change_vs_role", 'wt')
cont = 1
for role in list_roles:
list_weight_changes_role = []
for n in G.nodes():
if G.node[n]['role'] == role:
list_weight_changes_role.append(
G.node[n]['percentage_weight_change'])
print >> file, cont, role, len(list_weight_changes_role), numpy.mean(
list_weight_changes_role), numpy.std(list_weight_changes_role)
cont += 1
file.close()
#############################
############## percentage weight change vs k
x_positions_fit = []
y_positions_fit = []
cum_size_set = float(len(G.nodes()))
list_of_lists_for_bootstrap = []
list_k = []
for n in G.nodes():
list_k.append(len(G.neighbors(n)))
max_k = max(list_k)
file = open(dir + name + "_percentage_weight_change_vs_k.dat", 'wt')
max_k = max_k + 1
for k in range(1, max_k):
num_users_set = cum_size_set
list_percent_weight_change_k = []
for n in G.nodes():
if len(G.neighbors(n)) == k:
list_percent_weight_change_k.append(
G.node[n]['percentage_weight_change'])
cum_size_set -= 1.0
if len(list_percent_weight_change_k) > 0:
print >> file, k, len(
list_percent_weight_change_k), num_users_set / float(
len(G.nodes())), numpy.mean(
list_percent_weight_change_k), numpy.std(
list_percent_weight_change_k)
if len(x_positions_fit) <= 7:
x_positions_fit.append(k)
y_positions_fit.append(
numpy.mean(list_percent_weight_change_k))
list_of_lists_for_bootstrap.append(
list_percent_weight_change_k)
slope, intercept, Corr_coef, p_value, std_err = stats.linregress(
x_positions_fit, y_positions_fit) # least squeares polinomial fit
print "result linear. fit for degree dependency:"
print "slope:", slope, "intercept:", intercept, "Corr_coef:", Corr_coef, "p_value:", p_value, "std_err:", std_err
file.close()
name11 = dir + name + "_fits_degree.dat"
file11 = open(name11, 'wt')
for i in range(len(x_positions_fit)):
print >> file11, x_positions_fit[
i], intercept + x_positions_fit[i] * slope
print >> file11, "\n\n", "y=", intercept, "+", slope, "*x",
print "Bootstrap for degree:\n"
mean_slope, standard_dev = bootstrap(x_positions_fit[0],
x_positions_fit[-1],
list_of_lists_for_bootstrap)
zscore = (slope - mean_slope) / standard_dev
print >> file11, "bootstrap:\n", "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
print x_positions_fit[0], x_positions_fit[
-1], "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
file11.close()
contador += 1
file = open(name12, 'at')
print >> file, contador, mean_slope, standard_dev, "degree"
file.close()
########################################
new_name = graph_name.split(".gml")[0]
new_name = new_name + "_adherent_num_R6s_largest_clique.gml"
nx.write_gml(G, new_name)
def calculate(network):
try:
n = nx.graph_number_of_cliques(network)
except:
n = 0
return n
def compute_features(self):
g = rbc(self.graph)
# Basic stats
self.add_feature(
"number_of_edges",
lambda graph: graph.number_of_edges(),
"Number of edges in Jaccard similarity graph",
InterpretabilityScore(5),
function_args=g,
)
self.add_feature(
"number_of_edges_no_selfloops",
lambda graph: remove_selfloops(graph).number_of_edges(),
"Number of edges, not including selfloops, in Jaccard similarity graph",
InterpretabilityScore(5),
function_args=g,
)
self.add_feature(
"connectance",
lambda graph: nx.density(graph),
"Connectance of Jaccard similarity graph",
InterpretabilityScore(5),
function_args=g,
)
self.add_feature(
"diameter",
lambda graph: nx.diameter(ensure_connected(graph)),
"Diameter of Jaccard similarity graph",
InterpretabilityScore(5),
function_args=g,
)
self.add_feature(
"radius",
lambda graph: nx.radius(ensure_connected(graph)),
"Radius of Jaccard similarity graph",
InterpretabilityScore(5),
function_args=g,
)
# Assortativity
self.add_feature(
"degree_assortativity_coeff",
lambda graph: nx.degree_assortativity_coefficient(graph),
"Similarity of connections in Jaccard similarity graph with respect to the node degree",
InterpretabilityScore(4),
function_args=g,
)
# Cliques
self.add_feature(
"graph_clique_number",
lambda graph: nx.graph_clique_number(graph),
"The size of the largest clique in the Jaccard similarity graph",
InterpretabilityScore(3),
function_args=g,
)
self.add_feature(
"num_max_cliques",
lambda graph: nx.graph_number_of_cliques(graph),
"The number of maximal cliques in the Jaccard similarity graph",
InterpretabilityScore(3),
function_args=g,
)
# Clustering
self.add_feature(
"transitivity",
lambda graph: nx.transitivity(graph),
"Transitivity of the graph",
InterpretabilityScore(4),
function_args=g,
)
# Components
self.add_feature(
"is_connected",
lambda graph: nx.is_connected(graph) * 1,
"Whether the Jaccard similarity graph is connected or not",
InterpretabilityScore(5),
function_args=g,
)
self.add_feature(
"num_connected_components",
lambda graph: nx.number_connected_components(graph),
"The number of connected components",
InterpretabilityScore(5),
function_args=g,
)
self.add_feature(
"largest_connected_component",
lambda graph: ensure_connected(graph).number_of_nodes(),
"The size of the largest connected component",
InterpretabilityScore(4),
function_args=g,
)
# Efficiency
self.add_feature(
"global_efficiency",
lambda graph: nx.global_efficiency(graph),
"The global efficiency",
InterpretabilityScore(4),
function_args=g,
)
# Node connectivity
self.add_feature(
"node_connectivity",
lambda graph: nx.node_connectivity(graph),
"Node connectivity",
InterpretabilityScore(4),
function_args=g,
)
self.add_feature(
"edge_connectivity",
lambda graph: nx.edge_connectivity(graph),
"Edge connectivity",
InterpretabilityScore(4),
function_args=g,
)
G = nx.Graph()
for i in range(8):
G.add_node(i + 1)
G.add_edge(1, 2)
G.add_edge(1, 3)
G.add_edge(2, 3)
G.add_edge(4, 5)
G.add_edge(4, 6)
G.add_edge(5, 6)
G.add_edge(1, 6)
G.add_edge(2, 6)
G.add_edge(3, 6)
G.add_edge(7, 8)
nx.draw(G)
plt.show()
cliques = list(nx.find_cliques(G))
print("Number", nx.graph_number_of_cliques(G))
for clique in cliques:
print("Hello, world!")
print(cliques)
# %%
count_fliter = 3
# 此值會過濾掉留言者對作者留言次數過低的樣本，網軍此值理論上比一般人高
sum_fliter = 5
# 此值會過濾掉留言者總留言次數過低的樣本
percentage_fliter = 0.3
# 此值會過濾掉留言者對作者留言機率過低的樣本，網軍此值理論上比一般人高
G = nx.Graph()
G.add_nodes_from(
get_nodelist(data, count_fliter, sum_fliter, percentage_fliter))
G.add_edges_from(
get_edgelist(data, count_fliter, sum_fliter, percentage_fliter))
nx.graph_number_of_cliques(G)
partition = community.best_partition(G)
pos = nx.spring_layout(G)
plt.figure(figsize=(8, 8), dpi=300)
plt.axis('off')
nx.draw_networkx_nodes(G,
pos,
node_size=20,
cmap=plt.cm.RdYlBu,
node_color=list(partition.values()),
label=get_nodelist(data, count_fliter, sum_fliter,
percentage_fliter))
nx.draw_networkx_edges(G, pos, alpha=0.3)
nx.write_gexf(G, r'E:\\research\\data\\圖庫\\test.gexf')
def main(graph_name):
H = nx.read_gml(graph_name)
for node in H.nodes(): # i remove self loops
if node in H.neighbors(node):
if len(H.neighbors(node))>1:
H.remove_edge(node,node)
else:
H.remove_node(node)
for node in H.nodes():
if H.node[node]['weigh_ins'] <5: #Adherent filter
H.remove_node(node)
# print node, "is going down"
G= nx.connected_component_subgraphs(H)[0] # Giant component
print "final size of the GC:",len(G.nodes())
#dir=graph_name.split("fr")[0]
#dir=graph_name.split("master")[0]
#dir=graph_name.split("method3_")[0]
dir=graph_name.split("engaged_")[0]
dir=dir+"roles/"
print dir
time_in_system=100 #minimum amount of time in the sytem for a user to be included in the statistics
#name=graph_name.split('data/')[1]
name=graph_name.split('method3/')[1]
print name
name=name.split('.gml')[0]
print name
print dir+name
name0=dir+name+"_overlap_R6s_averages_"+str(time_in_system)+"days_exclude_R6s_clinically_signif.dat"
file0=open(name0, 'wt')
file0.close()
####for the Isolated Clusters:
list_GC_nodes=[]
for n in G.nodes():
list_GC_nodes.append(n)
# print G.node[n]['percentage_weight_change']
# print "# users GC:",len(list_GC_nodes),"total:",len(H.nodes())
list_weight_changes_not_GC=[]
for n in H.nodes():
if n not in list_GC_nodes:
#print n,"not in GC"
list_weight_changes_not_GC.append(float(H.node[n]['percentage_weight_change']))
#print "# users not in GC:",len(list_weight_changes_not_GC)
who="not_GC"
Nbins=18
histograma(list_weight_changes_not_GC,Nbins,dir,name,who)
###########################
list_R6s=[] # collect the R6 of the system
list_R6s_label=[]
list_R6s_percent_weight_change=[]
for node in G.nodes() :
if str(G.node[node]['role']) == "R6" :
list_R6s.append(node)
list_R6s_label.append(G.node[node]['label'])
list_R6s_percent_weight_change.append(float(G.node[node]['percentage_weight_change']))
name00=dir+name+"R6s_and_top_tens_averages_"+str(time_in_system)+"days_exclude_R6s_clinically_signif.dat"
file0=open(name00, 'at')
print >> file0,"R6s",numpy.mean(list_R6s_percent_weight_change),numpy.std(list_R6s_percent_weight_change)
file0.close()
# print "\n\n R6s:\n"
# for i in list_R6s_label:
# print i
# studying the possible cumulative effect of more than one R6 on the population:
for node in G.nodes():
cont=0
for n in G.neighbors(node):
if str(G.node[n]['role']) == "R6" :
cont+=1
G.node[node]["R6_overlap"]=int(cont)
##### weight change for people not connected to any R6s:####
list_weight_changes_no_neighbors=[]
for node in G.nodes():
interseccion=list(set(G.neighbors(node)) & set(list_R6s))
# print node, "intersection:",intersection,len(intersection)
# print "because", list_R6s, "and ",G.neighbors(node)
# raw_input()
if len(interseccion)==0:
list_weight_changes_no_neighbors.append(G.node[node]['percentage_weight_change'])
# print len(list_weight_changes_no_neighbors),"no_neighbors"
who="no_neigbors_R6s"
Nbins=18
histograma(list_weight_changes_no_neighbors,Nbins,dir,name,who)
# mood test
mood=stats.mood(list_weight_changes_no_neighbors,list_weight_changes_not_GC)
print "mood test for",who, "against not_GC:",mood
########
# K-S test:
ks=stats.ks_2samp(list_weight_changes_no_neighbors,list_weight_changes_not_GC)
print "KS test for",who, "against not_GC:",ks
name00="ks_results_clinically_signif.dat"
file0=open(dir+name00, 'at')
print >> file0, "KS test for",who,"of",graph_name, "against not_GC:",ks
file0.close()
#############################################
#average percentage weight change as a function of the size of the largest CLIQUE the node belongs to:
absolute_max=1
for i in G.nodes():
maximo=1
list2=nx.cliques_containing_node(G, i)
# print i, list2
for elem in list2:
# print elem,len(elem,)
if len(elem) > maximo:
maximo=len(elem)
# print "\n",maximo
G.node[i]['max_clique_size']=maximo
if absolute_max < maximo:
absolute_max = maximo
print absolute_max
lista=list(nx.find_cliques(G)) # crea una lista de cliques (lista de listas)
max_clique=nx.graph_clique_number(G) #finds out max size clique
num_tot_clique=nx.graph_number_of_cliques(G) #finds out total number of cliques
# count number of 2, 3, 4, 5, 6 and 7cliques:
num_2cliques=0
num_3cliques=0
num_4cliques=0
num_5cliques=0
num_6cliques=0
num_7cliques=0
num_8cliques=0
num_9cliques=0
for element in lista:
if len(element)==2:
num_2cliques=num_2cliques +1
elif len(element)==3:
num_3cliques=num_3cliques+1
elif len(element)==4:
num_4cliques=num_4cliques+1
elif len(element)==5:
num_5cliques=num_5cliques+1
elif len(element)==6:
num_6cliques=num_6cliques+1
elif len(element)==7:
num_7cliques=num_7cliques+1
elif len(element)==8:
num_8cliques=num_8cliques+1
elif len(element)==9:
num_9cliques=num_9cliques+1
print " 2: ",num_2cliques, " 3: ",num_3cliques, " 4: ",num_4cliques, " 5: ",num_5cliques, " 6: ",num_6cliques, " 7: ",num_7cliques, " 8: ",num_8cliques, " 9: ",num_9cliques, " max_clique_size:",max_clique, " num_tot_cliques:", num_tot_clique
name33=dir+name+"_percent_weight_change_vs_largest_clique_size_clinically_signif.dat"
file11=open(name33, 'wt')
file11.close()
cum_size_set=float(len(G.nodes()))
tot_nodes=[]
for clique_size in range(max_clique):
clique_size=clique_size+1
num_users_clinically_signif=0.0
num_users_set=cum_size_set
percent_weight_change_that_clique_size=[]
for n in G.nodes():
if G.node[n]['max_clique_size']==clique_size:
percent_weight_change_that_clique_size.append(float(G.node[n]['percentage_weight_change']))
tot_nodes.append(float(G.node[n]['percentage_weight_change']))
cum_size_set-=1.0
if G.node [n]['percentage_weight_change']<=-5.0:
num_users_clinically_signif+=1.0
try:
file11=open(name33, 'at')
print >> file11,clique_size,len(percent_weight_change_that_clique_size),num_users_set/float(len(G.nodes())),num_users_clinically_signif/len(percent_weight_change_that_clique_size),numpy.mean(percent_weight_change_that_clique_size),numpy.std(percent_weight_change_that_clique_size)
file11.close()
except ZeroDivisionError:
file11=open(name33, 'at')
print >> file11,clique_size,len(percent_weight_change_that_clique_size),num_users_set/float(len(G.nodes())),0.0 ,numpy.mean(percent_weight_change_that_clique_size),numpy.std(percent_weight_change_that_clique_size)
file11.close()
#######################################
#####dose effect of the R6s independently########
name11=dir+name+"_dose_eff_indepently_only_one_R6_"+str(time_in_system)+"days_exclude_R6s.dat"
file11=open(name11, 'at')
print >> file11,0,"average_no_neighbors","average_no_neighbors","average_no_neighbors",len(list_weight_changes_no_neighbors),numpy.mean(list_weight_changes_no_neighbors),numpy.std(list_weight_changes_no_neighbors) # the first line of the file is actually for no_neighbors, the rest, for one_and_only_one
file11.close()
file11=open(name11, 'wt')
file11.close()
cont=1
list_all=[]
list_all_nodes=[]
for R6 in list_R6s:
list_weight_changes=[]
for n in G.neighbors(R6):
if (G.node[n]['role'] != "R6") and ( G.node[n]["R6_overlap"]==1) :
list_weight_changes.append(float(G.node[n]['percentage_weight_change']))
if n not in list_all_nodes:
list_all_nodes.append(n)
list_all.append(float(G.node[n]['percentage_weight_change']))
if len(list_weight_changes)>0:
file11=open(name11, 'at')
print >> file11,cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes),numpy.mean(list_weight_changes),numpy.std(list_weight_changes)
file11.close()
# print cont,G.node[R6]['role'],G.node[R6]['label'], len(G.neighbors(R6)),len(list_weight_changes),numpy.mean(list_weight_changes),numpy.std(list_weight_changes)
cont=cont+1
else:
# file11=open(name11, 'at')
#print >> file11,cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes)
#file11.close()
# print cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes)
cont=cont+1
who="one_and_only_one_R6s"
Nbins=18
histograma(list_all,Nbins,dir,name,who)
####################################
cum_size_set=float(len(G.nodes()))-float(len(list_R6s))
for r in range(len(list_R6s)+1):
# list_BMI_changes=[]
list_weight_changes=[]
list_percentage_weight_changes=[]
list_activities=[]
num_users_clinically_signif=0.0
num_users_set=cum_size_set
for node in G.nodes():
if int(G.node[node]["R6_overlap"])==r:
if G.node[node]["role"]== "R6": # i exclude the R6s
pass
else:
if int(G.node[node]['time_in_system']) > time_in_system:
# list_BMI_changes.append(float(G.node[node]['final_BMI'])-float(G.node[node]['initial_BMI']))
list_weight_changes.append(float(G.node[node]['weight_change']))
list_percentage_weight_changes.append(float(G.node[node]['percentage_weight_change']))
list_activities.append(float(G.node[node]['activity'])/float(G.node[node]['time_in_system']))
cum_size_set-=1.0
if G.node [node]['percentage_weight_change']<=-5.0:
num_users_clinically_signif+=1.0
if len(list_percentage_weight_changes)>0:
# average_BMI_change=numpy.mean(list_BMI_changes)
average_weight_change=numpy.mean(list_weight_changes)
average_percentage_weight_change=numpy.mean(list_percentage_weight_changes)
average_activity=numpy.mean(list_activities)
#deviation_BMI=numpy.std(list_BMI_changes)
deviation_weight=numpy.std(list_weight_changes)
deviation_percentage_weight=numpy.std(list_percentage_weight_changes)
deviation_activity=numpy.std(list_activities)
#print out
try:
file0=open(name0, 'at')
print >> file0,r,len(list_percentage_weight_changes),num_users_set/float(len(G.nodes())),num_users_clinically_signif/len(list_percentage_weight_changes),average_percentage_weight_change,deviation_percentage_weight,average_weight_change,deviation_weight,average_activity,deviation_activity
file0.close()
except ZeroDivisionError:
file11=open(name33, 'at')
print >> file11,clique_size,len(percent_weight_change_that_clique_size),num_users_set/float(len(G.nodes())),0.0 ,numpy.mean(percent_weight_change_that_clique_size),numpy.std(percent_weight_change_that_clique_size)
file11.close()
#### averages for every R6's egonetwork:#########
cont=1
list_all_=[]
list_all_nodes_=[]
for node in list_R6s:
neighbors=G.neighbors(node)#a list of nodes
average_BMI_change=0.0
list_BMI_changes=[]
average_weight_change=0.0
list_weight_changes=[]
average_percentage_weight_change=0.0
list_percentage_weight_changes=[]
average_activity=0.0 # ojo! sera dividida por el numero de dias!!!!!
list_activities=[]
for n in G.neighbors(node):
if int(G.node[n]['time_in_system']) > time_in_system:
# list_BMI_changes.append(float(G.node[n]['final_BMI'])-float(G.node[n]['initial_BMI']))
list_weight_changes.append(float(G.node[n]['weight_change']))
list_percentage_weight_changes.append(float(G.node[n]['percentage_weight_change']))
list_activities.append(float(G.node[n]['activity'])/float(G.node[n]['time_in_system']))
if n not in list_all_nodes_:
list_all_nodes_.append(n)
list_all_.append(float(G.node[n]['percentage_weight_change']))
#averages
average_weight_change=numpy.mean(list_weight_changes)
# average_BMI_change=numpy.mean(list_BMI_changes)
average_activity=numpy.mean(list_activities)
average_percentage_weight_change=numpy.mean(list_percentage_weight_changes)
#standard deviation
#deviation_BMI=numpy.std(list_BMI_changes)
deviation_weight=numpy.std(list_weight_changes)
deviation_percentage_weight=numpy.std(list_percentage_weight_changes)
deviation_activity=numpy.std(list_activities)
#print out
name2=dir+name+"_ego_R6s_average_weight_change_"+str(time_in_system)+"days.dat"
file2=open(name2, 'at')
print >> file2,cont,G.node[node]['role'],G.node[node]['label'],len(G.neighbors(node)),average_weight_change,deviation_weight
file2.close()
name22=dir+name+"_ego_R6s_average_percentage_weight_change_"+str(time_in_system)+"days.dat"
file22=open(name22, 'at')
print >> file22,cont,G.node[node]['role'],G.node[node]['label'],len(G.neighbors(node)),average_percentage_weight_change,deviation_percentage_weight
file22.close()
name3=dir+name+"_ego_R6s_average_activity_"+str(time_in_system)+"days.dat"
file3=open(name3, 'at')
print >> file3,cont,G.node[node]['role'],G.node[node]['label'],len(G.neighbors(node)),average_activity,deviation_activity
file3.close()
cont=cont+1
who="R6s_egonetworks_all"
Nbins=18
histograma(list_all_,Nbins,dir,name,who)
# print "intersection:",len(set(list_all_)&set(list_all)),len(list_all_),len(list_all)
#############just checking what happens if we remove the 40155 guy
##### percent weight change vs. role:
list_roles=["R1","R2","R3","R4","R5","R6","R7"]
file = open(dir+name+"_percentage_weight_change_vs_role",'wt')
cont=1
for role in list_roles:
list_weight_changes_role=[]
for n in G.nodes():
if G.node[n]['role']==role:
list_weight_changes_role.append(G.node[n]['percentage_weight_change'])
print >> file, cont, role, len(list_weight_changes_role),numpy.mean(list_weight_changes_role),numpy.std(list_weight_changes_role)
cont+=1
file.close()
#############################
############## percentage weight change vs k
cum_size_set=float(len(G.nodes()))
list_k=[]
for n in G.nodes():
list_k.append(len(G.neighbors(n)))
max_k=max(list_k)
file = open(dir+name+"_percentage_weight_change_vs_k_clinically_signif.dat",'wt')
max_k=max_k+1
for k in range(1,max_k):
num_users_clinically_signif=0.0
num_users_set=cum_size_set
list_percent_weight_change_k=[]
for n in G.nodes():
if len(G.neighbors(n))==k:
list_percent_weight_change_k.append(G.node[n]['percentage_weight_change'])
cum_size_set-=1.0
if G.node [n]['percentage_weight_change']<=-5.0:
num_users_clinically_signif+=1.0
if len(list_percent_weight_change_k)>0:
try:
print >> file,k, len(list_percent_weight_change_k),num_users_set/float(len(G.nodes())),num_users_clinically_signif/len(list_percent_weight_change_k),numpy.mean(list_percent_weight_change_k),numpy.std(list_percent_weight_change_k)
except ZeroDivisionError:
file11=open(name33, 'at')
print >> file11,clique_size,len(percent_weight_change_that_clique_size),num_users_set/float(len(G.nodes())),0.0 ,numpy.mean(percent_weight_change_that_clique_size),numpy.std(percent_weight_change_that_clique_size)
file11.close()
file.close()
print "-------------------------------------" print "Find cliques of the graph" print "-------------------------------------" cliques = list(nx.find_cliques(G)) print cliques print "-------------------------------------" print "Compute clique number - size of the largest clique" print "-------------------------------------" graphCliqueNumber = nx.graph_clique_number(G, cliques) print graphCliqueNumber print "-------------------------------------" print "Compute number of maximal ciiques" print "-------------------------------------" graphNumberOfCliques = nx.graph_number_of_cliques(G, cliques) print graphNumberOfCliques print "-------------------------------------" print "Compute size of largest maximal clique containing a given node" print "-------------------------------------" maximalCliqueSizePerNode = nx.node_clique_number(G) print maximalCliqueSizePerNode print "-------------------------------------" print "Compute number of maximal cliques for each node" print "-------------------------------------" noOfMaximalCliquesPerNode = nx.number_of_cliques(G) print noOfMaximalCliquesPerNode
# diameter(b)
# This will work only for graphs that are connected
diameter = -1
if numberConnectedComponents == 1:
diameter = nx.diameter(b)
#print(diameter, sizeMaxClique)
# The maximum clique is returned as a set of nodes
# max_clique(b)
maxClique = naa.max_clique(b)
sizeMaxClique = len(maxClique)
print (diameter, sizeMaxClique)
# The dominating set is returned as a set of nodes
# min_weighted_dominating_set(b)
minDominatingSet = naa.min_weighted_dominating_set(b)
sizeMinDominatingSet = len(minDominatingSet)
# The number of maximal cliques in the graph
# graph_number_of_cliques(b)
numberOfCliques = nx.graph_number_of_cliques(b)
print (numberConnectedComponents,diameter,sizeMaxClique,sizeMinDominatingSet,numberOfCliques)
print("Katz centrality for Hollywood")
nbest_centrality(H, nx.katz_centrality_numpy, 10, "katz")
T = nx.ego_graph(G, "Twitter")
E = nx.ego_graph(G, "Earth")
# # Examine degree distributions with histograms
sns.distplot([G.degree(v) for v in G.nodes()], norm_hist=True)
plt.show()
sns.distplot([H.degree(v) for v in H.nodes()], norm_hist=True)
plt.show()
sns.distplot([T.degree(v) for v in T.nodes()], norm_hist=True)
plt.show()
sns.distplot([E.degree(v) for v in E.nodes()], norm_hist=True)
plt.show()
print("Baleen Entity Graph")
print("Transitivity: {}".format(nx.transitivity(G)))
print("Average clustering coefficient: {}".format(
nx.average_clustering(G)))
print("Number of cliques: {}".format(nx.graph_number_of_cliques(G)))
print("Hollywood Ego Graph")
print("Transitivity: {}".format(nx.transitivity(H)))
print("Average clustering coefficient: {}".format(
nx.average_clustering(H)))
print("Number of cliques: {}".format(nx.graph_number_of_cliques(H)))
def output_graphmetrics(pathadd,paths,file_name,data_dir):
'''
output_graphmetrics()
Calculates graph theory metrics from package NetworkX, stores in file and
outputs in .csv file.
'''
# Graph package
#print outputGraphMetrics
#if outputGraphMetrics:
try:
import networkx as nx
except ImportError:
raise ImportError, "NetworkX required."
pathG = nx.Graph()
# Get nrows and columns
nrows = len(pathadd)
ncols = len(pathadd[0])
# Now loop through pathadd rows
for irow in xrange(nrows):
# Begin loop through pathadd columns
for icol in xrange(ncols):
# Skip -9999. values
if pathadd[irow][icol] != -9999.0:
# Get spot node number
nodenumber = ncols*irow+icol
# Add node to pathG
pathG.add_node(nodenumber)
# Check neighbors for edges all 8 conditions
# Count 0,1,2,3,4,5,6,7 in counter-clockwise
# around center cell starting 0 in lower
# left corner
# Left top corner:
if irow == 0 and icol == 0:
# Get neighbors: spot 1
if pathadd[irow+1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 2
if pathadd[irow+1][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 3
if pathadd[irow][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Right top corner
elif irow == 0 and icol == ncols-1:
# Get neighbors: spot 1
if pathadd[irow+1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 7
if pathadd[irow][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 0
if pathadd[irow+1][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Left bottom corner
elif irow == nrows-1 and icol == 0:
# Get neighbors: spot 5
if pathadd[irow-1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 4
if pathadd[irow-1][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 3
if pathadd[irow][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Right bottom corner
elif irow == nrows-1 and icol == ncols-1:
# Get neighbors: spot 5
if pathadd[irow-1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 7
if pathadd[irow][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 6
if pathadd[irow-1][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Top side
elif irow == 0 and icol != 0 and icol != ncols-1:
# Get neighbors: spot 7
if pathadd[irow][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 0
if pathadd[irow+1][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 1
if pathadd[irow+1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 2
if pathadd[irow+1][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 3
if pathadd[irow][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Left side
elif icol == 0 and irow != 0 and irow != nrows-1:
# Get neighbors -spots 1,2,3,4,5
# Get neighbors: spot 1
if pathadd[irow+1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 2
if pathadd[irow+1][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 3
if pathadd[irow][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 4
if pathadd[irow-1][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 5
if pathadd[irow-1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Right side
elif icol == ncols-1 and irow != 0 and irow != nrows-1:
# Get neighbors - spots 0,1,5,6,7
# Get neighbors: spot 0
if pathadd[irow+1][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 1
if pathadd[irow+1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 5
if pathadd[irow-1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 6
if pathadd[irow-1][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 7
if pathadd[irow][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Bottom side:
elif irow == nrows-1 and icol != 0 and icol != ncols-1:
# Get neighbors - spots 3,4,5,6,7
# Get neighbors: spot 3
if pathadd[irow][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 4
if pathadd[irow-1][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 5
if pathadd[irow-1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 6
if pathadd[irow-1][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 7
if pathadd[irow][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Everything else:
else:
# Get neighbors: spot 0
if pathadd[irow+1][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 1
if pathadd[irow+1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 2
if pathadd[irow+1][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow+1)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 3
if pathadd[irow][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 4
if pathadd[irow-1][icol+1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol+1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 5
if pathadd[irow-1][icol] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+icol
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 6
if pathadd[irow-1][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow-1)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Get neighbors: spot 7
if pathadd[irow][icol-1] != -9999.:
# Then get egde number
edgenumber = ncols*(irow)+(icol-1)
# Then add edge to pathG
pathG.add_edge(nodenumber,edgenumber)
# Calculate properties from path lengths: min, max, average
pathlen = []
for i in xrange(len(paths)):
pathlen.append(paths[i][2])
# Create file to write info to
try:
fout = open(data_dir+file_name, 'w')
except(IOerror,OSerror) as e:
print("UNICOROutputs %s, error%s"(filename,e))
sys.exit(-1)
# Write header information
fout.write('Minimum Path Length,')
fout.write(str(min(pathlen))+'\n')
fout.write('Maximum Path Length,')
fout.write(str(max(pathlen))+'\n')
fout.write('Average Path Length,')
fout.write(str(sum(pathlen)/len(paths))+'\n')
fout.write('Density of Graph,')
fout.write(str(nx.density(pathG))+'\n')
fout.write('Number of nodes,')
fout.write(str(nx.number_of_nodes(pathG))+'\n')
fout.write('Number of edges,')
fout.write(str(nx.number_of_edges(pathG))+'\n')
fout.write('Is the graph a bipartite,')
fout.write(str(nx.is_bipartite(pathG))+'\n')
fout.write('Size of the largest clique,')
fout.write(str(nx.graph_clique_number(pathG))+'\n')
fout.write('Number of maximal cliques,')
fout.write(str(nx.graph_number_of_cliques(pathG))+'\n')
fout.write('Transitivity,')
fout.write(str(nx.transitivity(pathG))+'\n')
fout.write('Average clustering coefficient,')
fout.write(str(nx.average_clustering(pathG))+'\n')
fout.write('Test graph connectivity,')
fout.write(str(nx.is_connected(pathG))+'\n')
fout.write('Number of connected components,')
fout.write(str(nx.number_connected_components(pathG))+'\n')
fout.write('Consists of a single attracting component,')
fout.write(str(nx.is_attracting_component(pathG))+'\n')
if nx.is_attracting_component(pathG) == True:
fout.write('Number of attracting components,')
fout.write(str(nx.number_attracting_components(pathG))+'\n')
if nx.is_connected(pathG):
fout.write('Center,')
fout.write(str(nx.center(pathG))+'\n')
fout.write('Diameter,')
fout.write(str(nx.diameter(pathG))+'\n')
#fout.write('Eccentricity,')
#fout.write(str(nx.eccentricity(pathG))+'\n')
fout.write('Periphery,')
fout.write(str(nx.periphery(pathG))+'\n')
fout.write('Radius,')
fout.write(str(nx.radius(pathG))+'\n')
fout.write('Degree assortativity,')
fout.write(str(nx.degree_assortativity(pathG))+'\n')
fout.write('Degree assortativity Pearsons r,')
fout.write(str(nx.degree_pearsonr(pathG))+'\n')
# Close file
fout.close
del(pathG)
# End::output_graphmetrics()
G1 = 0
S1 = G1 / G.number_of_nodes()
s1_alpha.append(S1)
plt.ylabel('S2') # = ' + str(S1))
plt.xlabel('linking length [Mpc]')
plt.plot(ll, s1_alpha)
plt.ylim([0, 0.05])
## plot max clique size vs ll in bottom left
plt.subplot(2, 2, 3)
max_clq_sz.append(nx.graph_clique_number(G))
plt.ylabel('Max Clique Size') # = ' + str(S1))
plt.xlabel('linking length [Mpc]')
plt.plot(ll, max_clq_sz)
## plot # of maximal cliques vs ll in bottom right
plt.subplot(2, 2, 4)
max_clq_num.append(nx.graph_number_of_cliques(G))
plt.ylabel('Number of Maximal Cliques') # = ' + str(S1))
plt.xlabel('linking length [Mpc]')
plt.plot(ll, max_clq_num)
np.save('rgg-data/z_radii', ll)
np.save('rgg-data/z_alpha', alpha)
np.save('rgg-data/z_S1', s_alpha)
np.save('rgg-data/z_S2', s1_alpha)
np.save('rgg-data/z_mcs', max_clq_sz)
np.save('rgg-data/z_mnc', max_clq_num)
plt.savefig('rgg-data/rgg.png')
graphs_len[gr] = gtem
graphs_lists[gr] = ttem
graphh = G.subgraph(graphs[gr])
if len(graphh.nodes()) > 1 and len(graphh.edges()) > 0:
cliques_edges.append(graphh.edges())
cliques_nodes.append(graphh.nodes())
if len(colors_to_select) == 0:
colors_to_select = list(colors_list)
color = random.choice(colors_to_select)
colors_to_select.remove(color)
colors_of_edges.append((color))
nodes_color_alpha.append(0.4)
edges_color_alpha.append(0.6)
edge_width_l.append(4.0)
lvl2 = []
for i in range(nx.graph_number_of_cliques(G)):
lvl2.append(graphs_len[i])
print str(" ")
print "ΚΛΙΚΕΣ ΣΕ ΜΗ ΚΑΤΕΥΘΥΝΟΜΕΝΟΥΣ ΓΡΑΦΟΥΣ"
# print 'CLIQUES IN UNDIRECTED GRAPHS'
print str(" ")
print "Ο γράφος είναι:"
# print 'The graph is:'
graph_name = str(G.name) + str(lvl2)
print graph_name
print str(" ")
print "Το σύνολο όλων των κλικών του γράφου G:"
# print 'The set of all maximal cliques in graph G is:'
def num_max_cliques(graph):
"""num_max_cliques"""
return nx.graph_number_of_cliques(jaccard_similarity(graph))
def clique_v0(filename, threshold):
#自底向上
windowGraph = {}
cliqueGraph = {}
windowGraph[49] = nx.Graph()
cliqueGraph[49] = nx.DiGraph()
data = pd.read_csv(filename, index_col = 0, sep = '\t' )
#df = data[data.columns[0]].sort_values(ascending = False) # 默认是最小在前 若要降序 ascending = False
df = data[data.columns[0]].sort_values(ascending = False)
t=1
term = 183
dic_term = {}
#dic_cliques = {}
for i in range(0, df.shape[0]):
if df[i] == t :
node_1, node_2 = df.index[i].split('_')
windowGraph[49].add_edge(node_1, node_2)
else :
# find cliques when threshold = t
print i
print 'number_of_cliques(windowGraph):',nx.graph_number_of_cliques(windowGraph[49])
for cliques in sorted(list(nx.find_cliques(windowGraph[49])), key=lambda x:len(x)) : #cliques sorted by size of each clique
print 'cliques size:' , len(cliques)
gene_set = set()
term_set = set()
if sorted(cliques) not in dic_term.values() : #[1,2,3]=[1,2,3] [2,1,3]!=[1,2,3]
#this clique is new then a term is generated for this clique
cliqueGraph[49].add_node(term, annotation = cliques, windowsize = [49])# generate a term
# find child
for key,value in sorted(dic_term.items(), key=lambda d:d[0], reverse = True): # sorted by term id 854,853,852,851...
if set(value).issubset(cliques) :
old_size = len(gene_set) #old size
gene_set |= set(value) #add term genes
if len(gene_set) > old_size : #new size > old size
term_set.add(key) # add useful term
if len(set(cliques).intersection(gene_set)) ==len(cliques) : #gene_set == cliques
print term, 'all link to terms',gene_set.difference(cliques)
for child in term_set :
cliqueGraph[49].add_edge(term, child)
print term, child
break
else:
continue
if gene_set.issubset(cliques) and len(gene_set)<len(cliques):
#print len(gene_set), len(cliques)
#link to term
for child_term in term_set :
print 'some', term, child_term
cliqueGraph[49].add_edge(term, child_term)
# link to gene
#print term,'some link to genes'
for child_gene in set(cliques)-gene_set:
#print term, child_gene
cliqueGraph[49].add_edge(term, child_gene)
dic_term[term] = sorted(cliques)
term = term +1
else :
continue
t = df[i]
if not t==-1:
node_1, node_2 = df.index[i].split('_')
windowGraph[49].add_edge(node_1, node_2)
print 'dic_term',len(dic_term)
print 'windowGraph[49].size()',windowGraph[49].size(), windowGraph[49].number_of_nodes()
print 'cliqueGraph[49].size()',cliqueGraph[49].size(), cliqueGraph[49].number_of_nodes()
'''
#output files
fw = open ('49ontology_edges_v2.txt', 'w')
fw2 = open('49ontology_term_annotation_v2.txt', 'w')
fw3 = open('49ontology_term_annotation_v2a.txt', 'w')
fw.write('parent' +'\t' +'child' +'\n')
fw2.write('TermId' +'\t' + ' GeneSize'+ '\t' +'Gene'+'\n')
fw3.write('TermId' +'\t' + ' GeneSize'+ '\t' +'Gene'+'\n')
for i in sorted(cliqueGraph[49].edges(), key=lambda d:d[0]) :
fw.write(str(i[0]) + '\t' + str(i[1]) +'\n')
for i in dic_term :
fw2.write(str(i) +'\t'+ str(len(dic_term[i])) + '\t' + ','.join(dic_term[i])+ '\n')
# input the annotation of each term by nodes attribute---annotation
for i in sorted(cliqueGraph[49].nodes()):
try :
fw3.write(str(i) + '\t'+ str(len(cliqueGraph[49].node[i]['annotation'])) + '\t'+ ' '.join(cliqueGraph[49].node[i]['annotation']) +'\n')
except :
continue
fw.close()
fw2.close()
fw3.close()
'''
print 'windowGraph[49].size()',windowGraph[49].size(), windowGraph[49].number_of_nodes()
print 'cliqueGraph[49].size()',cliqueGraph[49].size(), cliqueGraph[49].number_of_nodes()
print 'nx.graph_clique_number(windowGraph[49]):',nx.graph_clique_number(windowGraph[49])
print 'number_of_cliques(windowGraph):',nx.graph_number_of_cliques(windowGraph[49])
def clique2(filename, threshold):
#自底向上
'''
data = pd.read_csv(filename, index_col = 0, sep = '\t' )
windowGraph = {} # generate window graph
cliqueGraph = {} # generate term
for i in range(0, data.shape[1]):
# Declare windowGraph and cliqueGraph for each column(window)
windowGraph[i] = nx.Graph()
cliqueGraph[i] = nx.Graph()
term = 1
lastIndex = []
while threshold >=0:
df = data[data[data.columns[i]]>=threshold][data.columns[i]]
newIndex = df.index.difference(lastIndex)
#Update windowGraph
for edge in range(0, len(newIndex)):
node_1, node_2 = newIndex[edge].split('_')
windowGraph[i].add_edge(node_1, node_2)
#Update cliqueGraph
for cliques in sorted(list(nx.find_cliques(windowGraph[i]))) :
for node in cliques :
cliqueGraph[i].add_edge(term, node)
term = term +1
lastIndex = df.index
threshold = threshold-0.2
print 'window', i, windowGraph[i].size(), windowGraph[i].number_of_nodes()
'''
windowGraph = {}
cliqueGraph = {}
windowGraph[49] = nx.Graph()
cliqueGraph[49] = nx.DiGraph()
data = pd.read_csv(filename, index_col=0, sep='\t')
#df = data[data.columns[0]].sort_values(ascending = False) # 默认是最小在前 若要降序 ascending = False
df = data[data.columns[0]].sort_values(ascending=False)
t = 1
term = 183
dic_term = {}
#dic_cliques = {}
for i in range(0, df.shape[0]):
if df[i] == t:
node_1, node_2 = df.index[i].split('_')
windowGraph[49].add_edge(node_1, node_2)
else:
# find cliques when threshold = t
#print i
#print 'number_of_cliques(windowGraph):',nx.graph_number_of_cliques(windowGraph[49])
for cliques in sorted(list(nx.find_cliques(windowGraph[49])),
key=lambda x: len(x)
): #cliques sorted by size of each clique
gene_set = set()
term_set = set()
if sorted(cliques) not in dic_term.values(
): #[1,2,3]=[1,2,3] [2,1,3]!=[1,2,3]
#this clique is new then a term is generated for this clique
cliqueGraph[49].add_node(term,
annotation=cliques,
windowsize=[49
]) # generate a term
# find child
#print 'cliques size:' , len(cliques)
for key, value in sorted(
dic_term.items(), key=lambda d: d[0], reverse=True
): # sorted by term id 854,853,852,851...
if set(value).issubset(cliques):
old_size = len(gene_set) #old size
gene_set |= set(value) #add term genes
if len(gene_set) > old_size: #new size > old size
term_set.add(key) # add useful term
if len(set(cliques).intersection(gene_set)) == len(
cliques): #gene_set == cliques
#print term, 'all link to terms',gene_set.difference(cliques)
for child in term_set:
cliqueGraph[49].add_edge(term, child)
#print term, child
break
else:
continue
if gene_set.issubset(
cliques) and len(gene_set) < len(cliques):
#print len(gene_set), len(cliques)
#link to term
for child_term in term_set:
#print 'some', term, child_term
cliqueGraph[49].add_edge(term, child_term)
# link to gene
#print term,'some link to genes'
for child_gene in set(cliques) - gene_set:
#print term, child_gene
cliqueGraph[49].add_edge(term, child_gene)
dic_term[term] = sorted(cliques)
term = term + 1
else:
continue
t = df[i]
if not t == -1:
node_1, node_2 = df.index[i].split('_')
windowGraph[49].add_edge(node_1, node_2)
print 'dic_term', len(dic_term)
print 'windowGraph[49].size()', windowGraph[49].size(
), windowGraph[49].number_of_nodes()
print 'cliqueGraph[49].size()', cliqueGraph[49].size(
), cliqueGraph[49].number_of_nodes()
print 'term:', term
print 'Before '
print 'windowGraph[49].size()', windowGraph[49].size(
), windowGraph[49].number_of_nodes()
print 'cliqueGraph[49].size()', cliqueGraph[49].size(
), cliqueGraph[49].number_of_nodes()
#find terms not root but do not have a parent
print 'find terms which is not root but do not have a parent:'
degree_0_terms = []
for i in cliqueGraph[49].nodes():
if cliqueGraph[49].in_degree(i) == 0:
degree_0_terms.append(i)
print 'degree 0 terms: ', degree_0_terms
# link these terms to a sutible parent
for term_id in sorted(degree_0_terms): #从小到大 从当前向后查找
for fp in range(term_id + 1, term):
if set(dic_term[term_id]).issubset(dic_term[fp]):
cliqueGraph[49].add_edge(fp, term_id)
break
#output files
fw = open('49ontology_edges_v3.txt', 'w')
fw2 = open('49ontology_term_annotation_v3.txt', 'w')
fw3 = open('49ontology_term_annotation_v3a.txt', 'w')
fw.write('parent' + '\t' + 'child' + '\n')
fw2.write('TermId' + '\t' + ' GeneSize' + '\t' + 'Gene' + '\n')
fw3.write('TermId' + '\t' + ' GeneSize' + '\t' + 'Gene' + '\n')
for i in sorted(cliqueGraph[49].edges(), key=lambda d: d[0]):
fw.write(str(i[0]) + '\t' + str(i[1]) + '\n')
for i in dic_term:
fw2.write(
str(i) + '\t' + str(len(dic_term[i])) + '\t' +
','.join(dic_term[i]) + '\n')
# input the annotation of each term by nodes attribute---annotation
for i in sorted(cliqueGraph[49].nodes()):
try:
fw3.write(
str(i) + '\t' +
str(len(cliqueGraph[49].node[i]['annotation'])) + '\t' +
' '.join(cliqueGraph[49].node[i]['annotation']) + '\n')
except:
continue
fw.close()
fw2.close()
fw3.close()
print 'After:'
print 'windowGraph[49].size()', windowGraph[49].size(
), windowGraph[49].number_of_nodes()
print 'cliqueGraph[49].size()', cliqueGraph[49].size(
), cliqueGraph[49].number_of_nodes()
print 'nx.graph_clique_number(windowGraph[49]):', nx.graph_clique_number(
windowGraph[49])
print 'number_of_cliques(windowGraph):', nx.graph_number_of_cliques(
windowGraph[49])
# -*- coding: utf-8 -*-
"""
AFRS - Trabalho 4
Author: Gonçalo Peres
Date: 2019/02/02
"""
import networkx as nx
g = nx.read_gml('dolphins.gml')
clique = nx.graph_number_of_cliques(g)
print(clique)
graph = nx.Graph()
graph.add_nodes_from(corr_df.index)
weights = squareform(corr_df.fillna(0).values)
edges_between = list( combinations( corr_df.index, 2))
for n in range(len(weights)):
edge_weight = weights[n]
if edge_weight >= 0.7:
node1 = edges_between[n][0]
node2 = edges_between[n][1]
graph.add_edge(node1, node2, weight = edge_weight)
nx.graph_number_of_cliques(graph)
print nx.info(graph)
out = open('graph.dimacs', 'wb')
for line in graph.degree(weight='weight').iteritems():
out.write('n %s %f\n' %line)
for line in graph.edges():
out.write('e %s %s\n' %line)
cliques = nx.find_cliques(graph)
cliques = list(cliques)
a = smaller_df.as_matrix()
color_intensity = []
node_sizes = []
graph_degree = graph.degree(weight='weight')
#from networkx.algorithms import bipartite #print bipartite.is_bipartite(goarn_network) from networkx import find_cliques cliques = list(find_cliques(goarn_network)) bigg= max(cliques, key=lambda l: len(l)) print bigg print nx.graph_number_of_cliques(goarn_network, cliques) # #print nx.eigenvector_centrality(goarn_network) H=nx.connected_component_subgraphs(goarn_network)[0] print(nx.average_shortest_path_length(H)) # #def trim_nodes(goarn_network,d): # """ returns a copy of G without # the nodes with a degree less than d """ # Gt = goarn_network.copy() # dn = nx.degree(Gt) # for n in Gt.nodes(): # if dn[n] <= d:
import networkx as nx
G = nx.read_edgelist('soc-sign-bitcoinotc.csv', delimiter=',', nodetype=int, data=(('weight', int), ('timestamp', float)), encoding="utf-8")
core_number = nx.core_number(G)
k_core = nx.k_core(G)
enumerate_cliques = nx.enumerate_all_cliques(G)
find_cliques = nx.find_cliques(G) # all maximal cliques
graph_clique_number = nx.graph_clique_number(G) # all maximal cliques
graph_number_of_cliques = nx.graph_number_of_cliques(G) # all maximal cliques
edge_betweenness_centrality = nx.edge_betweenness_centrality(G)
print("Core number for each node: ", core_number)
print("K-core: ", k_core)
print("Cliques: ", enumerate_cliques)
print("All maximal cliques: ", find_cliques)
print("Graph clique number - size of the largest clique for the graph: ", graph_clique_number)
print("Number of maximal cliques in the graph: ", graph_number_of_cliques)
print("Edge betweenness: ", edge_betweenness_centrality)
import networkx as nx import mfa import numpy as np G = nx.Graph() G.add_edge(0, 2, weight=1) G.add_edge(0, 3, weight=1) G.add_edge(1, 2, weight=1) G.add_edge(1, 3, weight=1) nodes = G.number_of_nodes() edges = G.number_of_edges() deg_assort = nx.degree_pearson_correlation_coefficient(G) apl = nx.average_shortest_path_length(G) num_cliq = nx.graph_number_of_cliques(G) diameter = nx.diameter(G) Q = [q for q in range(-10,11,1)] lst = [nodes, edges, deg_assort, apl, num_cliq, diameter] ntau = mfa.NFD(G, Q) al_list, fal_list = mfa.nspectrum(ntau, Q) q_list, dim_list = mfa.ndimension(ntau, Q) lst.extend(al_list) lst.extend(fal_list) lst.extend(q_list) lst.extend(dim_list) print(lst)
def main():
initial_period = 1
final_period = 250
filename3 = "../Results/Time_evol_network_metrics_monthly___.dat"
file3 = open(filename3, 'wt')
file3.close()
#header: period N L GC avg_degree std_degree max_k avg_pos_w std_pos_w avg_neg_w std_neg_w max_pos_w min_pos_w max_neg_w min_neg_w
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
# max_shell avg_shortest_path max_clique avg_betweenness std_betweenness
# 16 17 18 19 20
list_network_month_files = []
period = initial_period
while period <= final_period:
list_network_month_files.append(
"../Results/Supply_network_slicing_monthly_period_" + str(period) +
"_no_network_metrics.pickle")
period += 1
list_network_month_files.append(
"../Results/Supply_network_1985_2005_no_network_metrics.pickle")
########## i read input pickle network
for filename in list_network_month_files:
G = pickle.load(open(filename, 'rb'))
if len(G.nodes()) > 1:
print "\n\nloaded pickle file for the network:", filename
try:
period = filename.split("period_")[1].split(
".pickle")[0].split("_no_network_metrics")[0]
except IndexError:
period = filename.split("Supply_network_")[1].split(
"_no_network_metrics.pickle")[0]
# print G.nodes(data=True)
#raw_input()
N = len(G.nodes())
L = len(G.edges())
GC = nx.connected_component_subgraphs(G)[0]
print "period", period
print " N:", N, "L:", L, "GC:", len(GC.nodes())
####### degree
print "degrees:"
list_k = []
for node in G.nodes():
#list_k.append(len(G.neighbors(node)))
list_k.append(G.degree(node))
avg_degree = numpy.mean(list_k)
std_degree = numpy.std(list_k)
print " <k>:", avg_degree, "+/-", std_degree
path_name_h = "../Results/degree_distribution_period" + str(
period) + ".dat"
histograma_gral.histogram(list_k, path_name_h)
max_k = max(list_k)
print " max_k:", max_k
######### weights
print "weights:"
list_pos_w = []
list_neg_w = []
for edge in G.edges():
list_pos_w.append(G.edge[edge[0]][edge[1]]["pos_weight"])
list_neg_w.append(-1. *
(G.edge[edge[0]][edge[1]]["neg_weight"]))
avg_pos_w = numpy.mean(list_pos_w)
std_pos_w = numpy.std(list_pos_w)
print " pos. weight:", avg_pos_w, "+/-", std_pos_w
# print >> file3, numpy.mean(list_pos_w), numpy.std(list_pos_w),
avg_neg_w = numpy.mean(list_neg_w)
std_neg_w = numpy.std(list_neg_w)
print " neg. weight:", numpy.mean(list_neg_w), "+/-", numpy.std(
list_neg_w)
path_name_h = "../Results/weight_pos_trans_distribution_period" + str(
period) + ".dat"
histograma_gral.histogram(list_pos_w, path_name_h)
path_name_h = "../Results/weight_neg_trans_distribution_period" + str(
period) + ".dat"
histograma_gral.histogram(list_neg_w, path_name_h)
max_pos_w = max(list_pos_w)
min_pos_w = min(list_pos_w)
max_neg_w = max(list_neg_w)
min_neg_w = min(list_neg_w)
print " max_pos_w:", max_pos_w, " min_pos_w:", min_pos_w
print " max_neg_w:", -1. * max_neg_w, " min_neg_w:", -1. * min_neg_w
######### k-shell decomposition
print "k-shell structure:"
# i need to make a copy and remove the self-loops from that before i can proceed
G_for_kshell = nx.Graph(G.subgraph(G.nodes()))
list_edges_to_remove = []
for edge in G_for_kshell.edges():
if edge[0] == edge[1]:
list_edges_to_remove.append(edge)
for edge in list_edges_to_remove:
G_for_kshell.remove_edge(edge[0], edge[1])
max_shell = 0
cont_zeros = 0
for i in range(max_k):
size_shell = len(
nx.k_shell(G_for_kshell, k=i, core_number=None))
print " ", i, size_shell
if size_shell == 0:
cont_zeros += 1
else:
max_shell = i
if cont_zeros >= 10:
break
print "max shell:", max_shell
######### connected components
print "connected components:"
max_con_comp = 0
list_sizes = []
for item in sorted(nx.connected_components(G),
key=len,
reverse=True):
size = len(item)
list_sizes.append(size)
if size > max_con_comp:
max_con_comp = size
# print "list sizes of connected components:",list_sizes
path_name_h = "../Results/connected_components_distribution_period" + str(
period) + ".dat"
histograma_gral.histogram(list_sizes, path_name_h)
########## avg. path lenght
avg_shortest_path = nx.average_shortest_path_length(GC)
print "average shortest path within GC:", avg_shortest_path
######## max. clique size
absolute_max = 1
for i in G.nodes():
maximo = 1
list2 = nx.cliques_containing_node(G, i)
# print i, list2
for elem in list2:
# print elem,len(elem,)
if len(elem) > maximo:
maximo = len(elem)
# print "\n",maximo
G.node[i]['max_clique_size'] = maximo
if absolute_max < maximo:
absolute_max = maximo
lista = list(nx.find_cliques(
G)) # crea una lista de cliques (lista de listas)
max_clique = nx.graph_clique_number(G) #finds out max size clique
num_tot_clique = nx.graph_number_of_cliques(
G) #finds out total number of cliques
print "max. clique size:", max_clique
print "calculating betweenness centrality..."
#for item in nx.betweenness_centrality(G, k=None, normalized=True, weight=None, endpoints=False, seed=None):
dict_betweenness = nx.betweenness_centrality(G,
k=None,
normalized=True,
weight=None,
endpoints=False,
seed=None)
list_betweenness = []
for node in G.nodes():
betw = dict_betweenness[node]
list_betweenness.append(betw)
avg_betweenness = numpy.mean(list_betweenness)
std_betweenness = numpy.std(list_betweenness)
print "avg centrality:", avg_betweenness, std_betweenness
path_name_h = "../Results/betweenness_distribution_period" + str(
period) + ".dat"
histograma_bines_gral.histograma_bins_norm(list_betweenness, 10,
path_name_h)
print
print
file3 = open(filename3, 'at')
print >> file3, period, N, L, len(
GC.nodes()
), avg_degree, std_degree, max_k, avg_pos_w, std_pos_w, -1. * avg_neg_w, std_neg_w, max_pos_w, min_pos_w, -1. * max_neg_w, -1. * min_neg_w, max_shell, avg_shortest_path, max_clique, avg_betweenness, std_betweenness
file3.close()
print "written:", filename3
def calculate_cliques(self, G):
gcn = nx.graph_clique_number(G)
nofc = nx.graph_number_of_cliques(G)
return gcn, nofc
#%%
net.degree_assortativity_coefficient(EliteNet_giant)
#%%
net.attribute_assortativity_coefficient(EliteNet_giant, 'multi')
#%%
# coloring the nodes by attribute:
color_map = plt.get_cmap("cool")
valuesForColors = [n[1]['multi'] for n in EliteNet_giant.nodes(data=True)]
net.draw(EliteNet_giant,
node_color=valuesForColors,
cmap=color_map,
with_labels=True)
#%%
len([a for a in net.enumerate_all_cliques(EliteNet_giant)])
#%%
net.graph_number_of_cliques(EliteNet_giant)
#%%
for a in net.find_cliques(EliteNet_giant):
print(a)
#%%
net.graph_clique_number(EliteNet_giant)
#%%
[
c for c in net.find_cliques(EliteNet_giant)
if len(c) == net.graph_clique_number(EliteNet_giant)
]
#%%
import community
parts = community.best_partition(EliteNet_giant)
parts
#%%