def calculate_centrality(graph):
cl_unweighted = gt.closeness(graph)
cl_distance = gt.closeness(graph, weight=graph.ep.Distance)
bt_unweighted, ep = gt.betweenness(graph)
bt_distance, ep = gt.betweenness(graph, weight=graph.ep.Distance)
f = open('cl_unweighted.txt', 'w+')
f = open('cl_unweighted.txt', 'r+')
f.writelines(["%s\n" % item for item in cl_unweighted.a])
f = open('cl_distance.txt', 'w+')
f = open('cl_distance.txt', 'r+')
f.writelines(["%s\n" % item for item in cl_distance.a])
f = open('bt_unweighted.txt', 'w+')
f = open('bt_unweighted.txt', 'r+')
f.writelines(["%s\n" % item for item in bt_unweighted.a])
f = open('bt_distance.txt', 'w+')
f = open('bt_distance.txt', 'r+')
f.writelines(["%s\n" % item for item in bt_distance.a])
with open('results.csv', 'wb') as results:
writer = csv.writer(results, delimiter=',')
header = [
'Name', 'Type', 'Longitude', 'Latitude', 'Closeness_Unweighted',
'Closeness_Distance', 'Betweenness_Unweighted',
'Betweenness_Distance'
]
writer.writerow(header)
for v in graph.vertices():
row = [
graph.vp.name[v], graph.vp.Type[v], graph.vp.Longitude[v],
graph.vp.Latitude[v], cl_unweighted[v], cl_distance[v],
bt_unweighted[v], bt_distance[v]
]
writer.writerow(row)
def graph_measures(graph: gt.Graph) -> pd.DataFrame:
def get_attrs(attrs):
return (attrs[1][0], attrs[1][1][1], attrs[0])
def append_val(key, prop, v):
measures[key][0].append(prop[v])
_, vp_authority, vp_hub = gt.hits(graph)
measures = {
key: ([], prop)
for key, prop in {
'tp_group': graph.vp.group_name,
'tp_author': graph.vp.username,
'tn_degree_in': graph.degree_property_map('in'),
'tn_degree_out': graph.degree_property_map('out'),
'tn_degree_total': graph.degree_property_map('total'),
'tn_pagerank': gt.pagerank(graph),
'tn_betweenness': gt.betweenness(graph)[0],
'tn_closeness': gt.closeness(graph),
'tn_eigenvector': gt.eigenvector(graph)[1],
'tn_authority': vp_authority,
'tn_hub': vp_hub,
'tn_lcc': gt.local_clustering(graph)
}.items()
}
for attrs in product(graph.vertices(), measures.items()):
append_val(*get_attrs(attrs))
return pd.DataFrame(
dict(map(lambda item: (item[0], item[1][0]),
measures.items()))).fillna(0)
def generate_report(self, analysis_type, out_file):
if type(out_file) != str or out_file == "":
print("Invalid output path.")
exit(1)
data = None
if analysis_type == "total_degree":
pass
elif analysis_type == "in_degree":
pass
elif analysis_type == "out_degree":
pass
elif analysis_type == "closeness":
data = gt.closeness(self.G, weight=self.e_weights)
elif analysis_type == "betweenness":
vp, ep = gt.betweenness(self.G, weight=self.e_weights)
else:
print('Invalid analysis type, select from:')
print('total_degree')
print('in_degree')
print('out_degree')
print('closeness')
print('betweenness')
exit(1)
#data = dict(sorted(data.items(), key=operator.itemgetter(1), reverse=True))
f = open(out_file, 'w')
for v in self.G.vertices():
print(self.v_labels[v], vp[v], file=f)
f.close()
def closeness(rankCommands, Graph, conn, cur):
gt.openmp_set_num_threads(4) #enable 4 threads for runing algorithm
before_time = time.time()
c = gt.closeness(Graph.g)
values = c.get_array()
idCl = dict()
for each in Graph.g.vertices():
if numpy.isnan(values[each]):
idCl[Graph.indexIdDict[each]] = 0.0
else:
idCl[Graph.indexIdDict[each]] = values[each]
print "Total handling time is: ", (time.time() - before_time)
slist = sorted(idCl, key=lambda key: idCl[key], reverse=True)
createTable(rankCommands, slist, idCl, conn, cur)
def closeness(rankCommands, Graph, conn, cur):
gt.openmp_set_num_threads(4) #enable 4 threads for runing algorithm
before_time = time.time()
c = gt.closeness(Graph.g)
values = c.get_array()
idCl = dict()
for each in Graph.g.vertices():
if numpy.isnan(values[each]):
idCl[Graph.indexIdDict[each]] = 0.0
else:
idCl[Graph.indexIdDict[each]] = values[each]
print "Total handling time is: ", (time.time() - before_time)
slist = sorted(idCl, key = lambda key: idCl[key], reverse = True)
createTable(rankCommands, slist, idCl, conn, cur)
def calculate_centrality(graph):
print 'calculate closeness'
cl_time = gt.closeness(graph,weight=graph.ep.Time)
f = open('cl_time_adjusted.txt', 'w+')
f = open('cl_time_adjusted.txt', 'r+')
f.writelines(["%s\n" % item for item in cl_time.a])
with open('results_time_adjusted.csv','wb') as results:
writer = csv.writer(results,delimiter=',')
header = ['Name','Type','Longitude','Latitude','Closeness_Time']
writer.writerow(header)
for v in graph.vertices():
row = [graph.vp.name[v],graph.vp.Type[v],graph.vp.Longitude[v],graph.vp.Latitude[v],cl_time[v]]
writer.writerow(row)
def g_centrality_correlations(g):
dgr = g.degree_property_map('total').a
dgr = dgr / (g.num_vertices() - 1)
btn = gt.betweenness(g, norm=True)[0].a
cln = gt.closeness(g, norm=True, harmonic=False).a
egn = gt.eigenvector(g)[1].a
return dict(
# dgr=dgr,
# btn=btn,
# cln=cln,
# egn=egn,
db_p=stats.pearsonr(dgr, btn),
dc_p=stats.pearsonr(dgr, cln),
de_p=stats.pearsonr(dgr, egn),
db_s=stats.spearmanr(dgr, btn),
dc_s=stats.spearmanr(dgr, cln),
de_s=stats.spearmanr(dgr, egn),
db_k=stats.kendalltau(dgr, btn),
dc_k=stats.kendalltau(dgr, cln),
de_k=stats.kendalltau(dgr, egn))
def process(name, g):
# Properties
vp_pos = gt.sfdp_layout(g)
vp_deg = g.degree_property_map('total')
vp_deg_log = g.new_vp('double')
vp_deg_log.a = np.log10(vp_deg.a)
vp_cls = gt.closeness(g)
vp_page = gt.pagerank(g)
vp_btw, ep_btw = gt.betweenness(g, norm=False)
# Colormaps
for cmap in [
'viridis', 'plasma', 'inferno', 'YlGnBu', 'Blues', 'Greys',
'Greens', 'Oranges'
]:
draw_graph(g,
vp_pos,
f'{name}.prop=deg.color={cmap}.png',
vp_color=vp_deg,
vcmap=cmap)
draw_graph(g,
vp_pos,
f'{name}.prop=deg_log.color={cmap}.png',
vp_color=vp_deg_log,
vcmap=cmap)
draw_graph(g,
vp_pos,
f'{name}.prop=cls.color={cmap}.png',
vp_color=vp_cls,
vcmap=cmap)
draw_graph(g,
vp_pos,
f'{name}.prop=page.color={cmap}.png',
vp_color=vp_page,
vcmap=cmap)
draw_graph(g,
vp_pos,
f'{name}.prop=btw.color={cmap}.png',
vp_color=vp_btw,
vcmap=cmap)
# Construct dicts for D3-style JSON
nodes = []
for u in g.vertices():
p = vp_pos[u]
nodes.append({
'x': p[0],
'y': p[1],
'deg': vp_deg[u],
'deg_log': vp_deg_log[u],
'cls': vp_cls[u],
'page': vp_page[u],
'btw': vp_btw[u],
})
vp_idx = g.vertex_index
links = [{
'source': vp_idx[e.source()],
'target': vp_idx[e.target()],
} for e in g.edges()]
# Save D3 style JSON
d = {'nodes': nodes, 'links': links}
with open(f'{name}.json', 'w') as f:
json.dump(d, f)
import graph_tool.all as gtool
gr = gtool.collection.data["polblogs"]
gr = gtool.GraphView(gr, vfilt=gtool.label_largest_component(gr))
cness = gtool.closeness(gr)
gtool.graph_draw(gr,
pos=gr.vp["pos"],
vertex_fill_color=cness,
vertex_size=gtool.prop_to_size(cness, mi=5, ma=15),
vorder=cness,
vcmap=matplotlib.cm.gist_heat,
output="political_closeness.pdf")
betweenness = GT.betweenness(g)[0].get_array()
plt.title("Betweenness distribution")
plt.ylabel('#Nodes')
plt.xlabel('Betweenness coefficient')
plt.bar(*float_distribution(betweenness, 40), width=(max(betweenness)-min(betweenness))/50)
plt.savefig(f"img/betweenness_dist.png", format='png')
plt.close()
print(f"top {TOP} betweenness nodes: {get_top(betweenness, TOP)}")
del betweenness
#############
# Closeness #
#############
closeness = GT.closeness(GT.extract_largest_component(g), norm=False, harmonic=True).get_array()
plt.title("Closeness distribution")
plt.ylabel('#Nodes')
plt.xlabel('Closeness coefficient')
plt.bar(*float_distribution(closeness, 40), width=(max(closeness)-min(closeness))/50)
plt.savefig(f"img/closeness_dist.png", format='png')
plt.close()
print(f"top {TOP} closeness nodes: {get_top(closeness, TOP)}")
del closeness
##############
# Clustering #
##############
clustering = list(GT.local_clustering(g))
def harmonic_centrality(g):
return gt.closeness(g, harmonic=True).get_array()
dist, ends = gt.pseudo_diameter(g_friend_LC)
print('(Pseudo-) Diameter: ', dist) # 14.0
#print('(Pseudo-) Diameter start:', ends[0], 'end:', ends[1]) # start: 1275 end: 37966
print(
"\n\nDeskriptives Friendship Network - Largest Component specific - (Pseudo-) Diameter -done\n"
)
#-- Closeness Distribution of Largest Component --#
if descClose_bool == True:
print("\n\n#-- Closeness Distribution --#\n")
vprop_closeness = gt.closeness(g_friend_LC)
g_friend_LC.vp.closeness = vprop_closeness
close_array = np.array(vprop_closeness.a)
close_array_index_LC = np.where(close_array != 0)
close_array_LC = close_array[close_array_index_LC]
print("Avg Closeness Centrality: ",
sum(close_array_LC) / len(close_array_LC)) # 0.2769106346214449
print("Median Closeness Centrality: ",
np.median(close_array_LC)) # 0.27148728827604496
print("Mode Closeness Centrality: ",
stats.mode(close_array_LC)) # 0.2712535187945024
plt.hist(
weight_map[e] = 1. * common_votes / len(dep1[5:])
edges[(dep1[4],dep2[4])] = [weight_map[e], dep1, dep2] # adds for debuging
except Exception, e:
print str(e)
# conventional centrality analysis
# degree
degree = g.degree_property_map('total', weight = weight_map)
# vertice betweeness
betweeness = gt.betweenness(g, weight = weight_map)
# closeness
closeness = gt.closeness(g, weight = weight_map)
# Katz
katz = gt.katz(g, weight = weight_map)
# Pagerank
pagerank = gt.pagerank(g, weight = weight_map)
metrics = ['name', 'diap', 'betweenness', 'closeness', 'degree', 'katz', 'pagerank']
df = pd.DataFrame(zip(vertex_to_name.values(), diap, degree.a.tolist(), betweeness[0].a.tolist(), closeness.a.tolist(), katz.a.tolist(),
pagerank.a.tolist()), columns = metrics)
df.sort('pagerank', ascending=True)[:30]
ctrlity_frame = [df_eigen_centrality, df_harmnic_centrality, df_betweenness_centrality, df_degree_centrality]
ctrlity_merged = reduce(lambda left,right: pd.merge(left, right, on=['ctry', 'year'],
how='inner'), ctrlity_frame).fillna('0')
ctrlity_merged.to_csv("/content/drive/MyDrive/G11-MEA-Diffusion/dataMEA_Ctrlity/ctrlity_output.csv")
"""### visualization"""
#eigenvector centrality
ee, x = gt.eigenvector(gt_2018_univ)
x.a /= (x.a*10 - 0.7)/0.04 # follow the formula in the book
gt.graph_draw(gt_2018_univ, vertex_fill_color=x, vcmap=matplotlib.cm.gist_earth, vorder=x) #
gc = gt.GraphView(gt_2018_univ, vfilt=gt.label_largest_component(gt_2018_univ))
c = gt.closeness(gc)
c.a /= c.a / 232
gt.graph_draw(gc, vertex_fill_color=c, vcmap=matplotlib.cm.Oranges, vorder=c)
#betweenness centrality
bv, be = betweenness(gt_2018_univ)
graph_draw(gt_2018_univ, pos=None, vertex_fill_color=bv, vcmap=matplotlib.cm.summer)
deg = gt_2018_univ.degree_property_map("total")
gt.graph_draw(gt_2018_univ, vertex_fill_color=deg, vorder=deg)
# https://colab.research.google.com/github/count0/colab-gt/blob/master/colab-gt.ipynb#scrollTo=6km1lWMF2kAm
!apt-get install
g = gt.GraphView(g, vfilt=gt.label_largest_component(g), directed=False)
g = gt.Graph(g, prune=True)
# chequea que todo sea como "debe ser"
print('chequeando...', args.file)
print('vertices', g.num_vertices()) # numero de vertices
print('edges', g.num_edges()) # numero de links
weight = g.ep['weight']
width = gt.prop_to_size(weight, ma=.5)
# seteo de algunas argumentos de la creacion del grafo
pos = g.vp['pos_sfdp_infomap']
vcl = gt.closeness(g, weight=weight)
vsize = gt.prop_to_size(vcl)
vorder = -vsize.a
df = pd.DataFrame({'node': list(g.vertices()), 'closeness': list(vcl)})
df.sort_values(by='closeness', inplace=True, ascending=False)
print(df.head(15))
print('drawing...')
# dibuja el grafico en el archivo filename.png
gt.graph_draw(
g,
pos,
output_size=(500, 400),
vertex_size=vsize,
vertex_fill_color=vsize,
gCoocNode = nx.Graph()
gCoocNode = gCooc
gtgCooc = nx2gt_module.nx2gt(gCooc)
CoocEdgeWeight = gtgCooc.edge_properties['weight']
CoocVertexId = gtgCooc.vertex_properties['id']
CoocVertexIter = gtgCooc.vertices()
print("4")
CoocBetween, ep = gt.betweenness(gtgCooc, weight=CoocEdgeWeight, norm=True)
print("5")
#ee, CoocEigen = gt.eigenvector(gtgCooc, weight=CoocEdgeWeight)
print("6")
#ee, CoocAuthority, CoocHub = gt.hits(gtgCooc, weight =CoocEdgeWeight)
#CoocPagerank = gt.pagerank(gtgCooc, weight =CoocEdgeWeight)
CoocCloseness = gt.closeness(gtgCooc, weight=CoocEdgeWeight)
print("7")
CoocKatz = gt.katz(gtgCooc, weight=CoocEdgeWeight)
CoocClustering = gt.local_clustering(gtgCooc)
print("8")
CoocDegree = gtgCooc.degree_property_map("total", weight=CoocEdgeWeight)
print("9")
print("where")
print("A")
print len(nodeList)
print("B")
tempCoocList = []
for i in CoocVertexIter:
temp = (str(j_id), CoocVertexId[i], CoocDegree[i], CoocBetween[i],