def getBasicInfo(strPath, net):
G = snap.LoadEdgeList(snap.PUNGraph,strPath,0,1)
GraphInfo = {}
GraphInfo['nodes'] = G.GetNodes()
GraphInfo['edges'] = G.GetEdges()
GraphInfo['zeroDegNodes'] = snap.CntDegNodes(G, 0)
GraphInfo['zeroInDegNodes'] = snap.CntInDegNodes(G, 0)
GraphInfo['zeroOutDegNodes'] = snap.CntOutDegNodes(G, 0)
GraphInfo['nonZeroIn-OutDegNodes'] = snap.CntNonZNodes(G)
GraphInfo['uniqueDirectedEdges'] = snap.CntUniqDirEdges(G)
GraphInfo['uniqueUndirectedEdges'] = snap.CntUniqUndirEdges(G)
GraphInfo['selfEdges'] = snap.CntSelfEdges(G)
GraphInfo['biDirEdges'] = snap.CntUniqBiDirEdges(G)
NTestNodes = 10
IsDir = False
GraphInfo['approxFullDiameter'] = snap.GetBfsEffDiam(G, NTestNodes, IsDir)
GraphInfo['90effectiveDiameter'] = snap.GetAnfEffDiam(G)
DegToCntV = snap.TIntPrV()
snap.GetDegCnt(G, DegToCntV)
sumofNode = G.GetNodes()
L = [item.GetVal1()*item.GetVal2() for item in DegToCntV]
GraphInfo['averageDegree'] = float(sum(L))/(sumofNode)
(DegreeCountMax ,Degree, DegreeCount, CluDegree, Clu) = getGraphInfo(G)
# creatNet(G,net)
return GraphInfo,DegreeCountMax , Degree, DegreeCount, CluDegree, Clu
def directed_get_densification(df):
years = sorted(df['year'].unique())
out_num_nodes = []
out_num_edges = []
out_anf_diameters = []
G = snap.TNEANet.New()
for year in years:
add_df_to_G(df[df['year'] == year], G, directed=True)
out_num_nodes.append(G.GetNodes())
out_num_edges.append(G.GetEdges())
out_anf_diameters.append(snap.GetAnfEffDiam(G))
return out_num_nodes, out_num_edges, out_anf_diameters, years
def cumulative_get_densification(df):
years = sorted(df['year'].unique())
out_num_nodes = []
out_num_edges = []
out_anf_diameters = []
G = snap.TUNGraph.New()
for year in years:
add_df_to_G(df[df['year'] == year], G)
out_num_nodes.append(G.GetNodes())
out_num_edges.append(G.GetEdges())
out_anf_diameters.append(snap.GetAnfEffDiam(G))
return out_num_nodes, out_num_edges, out_anf_diameters, years
def get_densification(df):
years = sorted(df['year'].unique())
out_num_nodes = []
out_num_edges = []
# out_bfs_diameters = []
out_anf_diameters = []
for year in years:
G = get_graph(df[df['year'] == year])
out_num_nodes.append(G.GetNodes())
out_num_edges.append(G.GetEdges())
scc = snap.GetMxScc(G)
out_anf_diameters.append(snap.GetAnfEffDiam(scc))
return out_num_nodes, out_num_edges, out_anf_diameters, years
def approx_neighborhood_function_statistics(G,
n_nodes,
n_approx=64,
approx_type=APPROX_BFS_IGRAPH):
aG = convert_networkx_to_SNAP(G)
print "convert to SNAP graph: DONE"
# TEST (fixed)
# s_Diam = 20 # youtube
# diameter s_Diam (lowerbound)
start = time.clock()
if approx_type == APPROX_ANF:
s_Diam = sn.GetAnfEffDiam(aG, False, 0.99, n_approx)
elif approx_type == APPROX_BFS:
s_Diam = sn.GetBfsFullDiam(aG, N_BFS, False) #
elif approx_type == APPROX_BFS_IGRAPH:
s_APD_i, s_EDiam_i, s_CL_i, s_Diam = bfs_samples(G) # _i: igraph
else:
print "Wrong <approx_type> !"
print "compute s_Diam, elapsed :", time.clock() - start
# average distance s_APD
DistNbrsV = sn.TIntFltKdV()
MxDist = int(math.ceil(s_Diam))
print "MxDist =", MxDist
start = time.clock()
sn.GetAnf(aG, DistNbrsV, MxDist, False, n_approx) # n_approx=32, 64...
print "GetAnf, elapsed :", time.clock() - start
# for item in DistNbrsV:
# print item.Key(), "-", item.Dat()
sum_APD = 0.0
dist_list = [] # list of pairs
for item in DistNbrsV:
dist_list.append([item.Key(), item.Dat()])
num_APD = dist_list[-1][1]
# WAY 2 - compute s_EDiam from dist_list
s_EDiam = 0
for i in range(len(dist_list)):
if dist_list[i][1] >= 0.9 * num_APD:
s_EDiam = dist_list[i][0]
break
for i in range(len(dist_list) - 1, 1,
-1): # do not subtract [0] from [1] !
dist_list[i][1] = dist_list[i][1] - dist_list[i - 1][
1] # compute differences
sum_APD += dist_list[i][0] * dist_list[i][1]
s_APD = sum_APD / num_APD
print "num_APD =", num_APD
# for s_PDD
print "s_PDD :"
d_list = []
for item in dist_list:
# print item[0], "-", item[1]
d_list.append(item[1])
print d_list
# WAY 1 - effective diameter s_EDiam ( SNAP)
# start = time.clock()
# if approx_type == APPROX_ANF:
# s_EDiam = sn.GetAnfEffDiam(aG, False, 0.9, n_approx) # 90%
# elif approx_type == APPROX_BFS:
# s_EDiam = sn.GetBfsEffDiam(aG, 1000, False)
# else:
# print "Wrong <approx_type> !"
# print "compute s_EDiam, elapsed :", time.clock() - start
# connectivity length s_CL
sum_CL = 0.0
for item in dist_list:
if item[0] > 0:
sum_CL += item[1] / item[0]
# s_CL = n_nodes*(n_nodes-1)/sum_CL
s_CL = num_APD / sum_CL
#
return s_APD, float(s_EDiam), s_CL, float(s_Diam), s_APD_i, float(
s_EDiam_i), s_CL_i, dist_list
diameter = []
inter_edges = []
intra_edges = []
inter_intra = []
disassort_degree = []
disassort_cluster = []
edge_connectivity = []
avg_path_length = []
robustness = []
for j in range(samp):
g1 = read("uniform_noise_railway_perm" + str(i) + str(j) +
".graphml").as_undirected()
clustering.append(g1.transitivity_undirected())
g1.write("temp.txt", format="edgelist")
G = snap.LoadEdgeList(snap.PUNGraph, "temp.txt", 0, 1)
effective_dia.append(snap.GetAnfEffDiam(G))
os.system("rm temp.txt")
diameter.append(g1.diameter())
disassort_degree.append(g1.assortativity_degree())
avg_path_length.append(g1.average_path_length())
original_d = inverse_distance(g1)
robustness.append(original_d / d_o)
edge_connectivity.append(g1.edge_connectivity())
inter_eg = 0.0
intra_eg = 0.0
ii = modularity(g1)
inter_edges.append(1.0 * ii[1])
intra_edges.append(1.0 * ii[0])
inter_intra.append(1.0 * ii[1] / ii[0])
out.write(