def analyzeMisc(FNGraph):
# LCC, average distances, clustering
t1 = time.time()
print "Started calculating miscellaneous network statistics:"
print '\tPercentage of nodes in LCC in Football network: %.3f' % (snap.GetMxWccSz(FNGraph) * 100.0)
GraphClustCoeff = snap.GetClustCf (FNGraph, -1)
print "\tClustering coefficient: %.3f" % GraphClustCoeff
diam = snap.GetBfsFullDiam(FNGraph, 1432, False)
print "\tNetwork diameter: %.3f\n" % diam
print "\tCalculating average distance..."
avgDist = 0
iter1 = 0
allNodes1 = FNGraph.GetNodes()
for NI in FNGraph.Nodes():
if(iter1 % 100 == 0):
print "\t\tCalculated for %d nodes" % iter1
NIdToDistH = snap.TIntH()
snap.GetShortPath(FNGraph, NI.GetId(), NIdToDistH)
singleDistSum = 0
for item in NIdToDistH:
singleDistSum += NIdToDistH[item]
avgDist += (1.0/allNodes1) * float(singleDistSum)/(allNodes1-1)
iter1 += 1
print "\tNetwork average distance: %.3f" % avgDist
print "\nFinished calculating in %f seconds\n" % (time.time() - t1)
def benchmark_neanet(Graph):
'''
Perform benchmark tests for Directed Attribute Graphs
'''
results = {}
results['num_nodes'] = Graph.GetNodes()
results['num_edges'] = Graph.GetEdges()
for degree in range(0, 11):
num = snap.NodesGTEDegree(Graph, degree)
percent_deg = float(num) / results['num_nodes']
results['deg_gte_%d' % degree] = num
results['deg_gte_%d_percent' % degree] = percent_deg
# Check for over-weighted nodes
results['max_degree'] = snap.MxDegree(Graph)
num = snap.NodesGTEDegree(Graph, results['max_degree'])
results['max_degree_num'] = num
results['max_wcc_percent'] = snap.GetMxWccSz(Graph) \
/ results['num_nodes']
results['max_scc_percent'] = snap.GetMxSccSz(Graph).GetNodes() \
/ results['num_nodes']
return results
def get_robustness(file_path, LSCC_output_path, LWCC_output_path):
frac_list = [
0.0001, 0.001, 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9
]
Graph, H = load_graph(file_path)
InDegV = snap.TIntPrV()
snap.GetNodeInDegV(Graph, InDegV)
OutDegV = snap.TIntPrV()
snap.GetNodeOutDegV(Graph, OutDegV)
degree = dict()
for item in InDegV:
ID = item.GetVal1()
InDeg = item.GetVal2()
degree[ID] = InDeg
for item in OutDegV:
ID = item.GetVal1()
OutDeg = item.GetVal2()
degree[ID] += OutDeg
sorted_degree = sorted(degree.items(), key=itemgetter(1), reverse=True)
tot = len(sorted_degree)
pos = [int(tot * frac) for frac in frac_list]
print pos
cur = 0
LSCC_robust = list()
LWCC_robust = list()
for i in range(tot):
Graph.DelNode(sorted_degree[i][0])
if i == pos[cur] - 1:
LSCC_frac = snap.GetMxSccSz(Graph)
LWCC_frac = snap.GetMxWccSz(Graph)
singleton_frac = 1.0 - 1.0 * snap.CntNonZNodes(
Graph) / Graph.GetNodes()
LSCC_robust.append({
'removed': frac_list[cur],
'singleton': singleton_frac,
'middle': 1.0 - singleton_frac - LSCC_frac,
'LSCC': LSCC_frac
})
LWCC_robust.append({
'removed': frac_list[cur],
'singleton': singleton_frac,
'middle': 1.0 - singleton_frac - LWCC_frac,
'LWCC': LWCC_frac
})
cur += 1
if cur >= len(pos):
break
LSCC_robust = pd.DataFrame(LSCC_robust)
LSCC_robust = LSCC_robust[['removed', 'singleton', 'middle', 'LSCC']]
LSCC_robust.to_csv(LSCC_output_path, index=False, encoding='utf-8')
LWCC_robust = pd.DataFrame(LWCC_robust)
LWCC_robust = LWCC_robust[['removed', 'singleton', 'middle', 'LWCC']]
LWCC_robust.to_csv(LWCC_output_path, index=False, encoding='utf-8')
def print_components(G):
"""
Prints the fraction of nodes in the largest component of subgraph G
Also prints the number of edge bridges and articulation points
"""
print("Fraction of nodes in largest connected component:", round(snap.GetMxWccSz(G), 4))
EdgeV = snap.TIntPrV()
snap.GetEdgeBridges(G, EdgeV)
print("Number of edge bridges:", EdgeV.Len())
ArtNIdV = snap.TIntV()
snap.GetArtPoints(G, ArtNIdV)
print("Number of articulation points:", ArtNIdV.Len())
def wikiVotingNetwork():
Component = snap.TIntPrV()
#Loding the graph
Wiki = snap.LoadEdgeList(snap.PNGraph, "Wiki-Vote.txt", 0, 1)
#Printing Number of Nodes in the Graph
print "Number of Nodes: ", Wiki.GetNodes()
#Printing Number of Edges in the Graph
print "Number of Edges: ", Wiki.GetEdges()
#Printing Number of Directed Edges in the Graph
print "Number of Directed Edges: ", snap.CntUniqDirEdges(Wiki)
#Printing Number of Un-Directed Edges in the Graph
print "Number of Undirected Edges: ", snap.CntUniqUndirEdges(Wiki)
#Printing Number of Directed Edges in the Graph
print "Number of Self-Edges: ", snap.CntSelfEdges(Wiki)
#Printing Number of Zero InDeg Nodes in the Graph
print "Number of Zero InDeg Nodes: ", snap.CntInDegNodes(Wiki, 0)
#Printing Number of Zero OutDeg Nodes in the Graph
print "Number of Zero OutDeg Nodes: ", snap.CntOutDegNodes(Wiki, 0)
#Printing Node ID with maximum degree in the Graph
print "Node ID with maximum degree: ", snap.GetMxDegNId(Wiki)
snap.GetSccSzCnt(Wiki, Component)
for comp in Component:
#printing number of strongly connected components with size
print "Size: %d - Number of Strongly Connected Components: %d" % (
comp.GetVal1(), comp.GetVal2())
#printing size of largest connected components
print "Size of largest connected component: ", snap.GetMxSccSz(Wiki)
snap.GetWccSzCnt(Wiki, Component)
for comp in Component:
#printing number of weekly connected components with size
print "Size: %d - Number of Weekly Connected Component Wikipedia: %d" % (
comp.GetVal1(), comp.GetVal2())
#printing size of weekly connected components
print "Size of Weakly connected component: ", snap.GetMxWccSz(Wiki)
#plotting out-degree distribution
snap.PlotOutDegDistr(Wiki, "wiki-analysis",
"Directed graph - Out-Degree Distribution")
def analyzeMisc(FNGraph):
# LCC, average distances, clustering
tStart = time.time()
print "[Network Analyzr] Started calculating miscellaneous network statistics..."
LCCPercentage = snap.GetMxWccSz(FNGraph) * 100.0
print '\t[Network Analyzr] Percentage of nodes in LCC: %.3f' % LCCPercentage
clusteringCoefficient = snap.GetClustCf (FNGraph, -1)
print "\t[Network Analyzr] Clustering coefficient: %.3f" % clusteringCoefficient
diameter= snap.GetBfsFullDiam(FNGraph, 1432, False)
print "\t[Network Analyzr] Network diameter: %.3f\n" % diameter
# Average distance
print "\t[Network Analyzr] Calculating average distance..."
i = 0
avgDist = 0
nodes = FNGraph.GetNodes()
for sourceNode in FNGraph.Nodes():
if i % 100 == 0 and utils.mode == 'debug':
print "\t\tCalculated for %d nodes" % i
NIdToDistH = snap.TIntH()
snap.GetShortPath(FNGraph, sourceNode.GetId(), NIdToDistH)
distanceSum = 0
for destinationNode in NIdToDistH:
distanceSum += NIdToDistH[destinationNode]
avgDist += (1.0 / nodes) * float(distanceSum) / (nodes - 1)
i += 1
print "\t[Network Analyzr] Network average distance: %.3f" % avgDist
timeSpent = time.time() - tStart
print "\n[Network Analyzr] Finished calculating in %f seconds\n" % timeSpent
def analyze(graph):
n = graph.GetNodes()
m = graph.GetEdges()
maxSCCsize = snap.GetMxSccSz(graph)
maxWCCsize = snap.GetMxWccSz(graph)
avgDegree = (m * float(2)) / n
# estimate power law exponent
degs = []
degCounts = []
DegToCntV = snap.TIntPrV()
snap.GetDegCnt(graph, DegToCntV)
for item in DegToCntV:
degs.append(item.GetVal1())
degCounts.append(item.GetVal2())
xMin = min(degs) - 0.5
m = graph.GetNodes()
alphaMLLE = 1 + (m / (sum([np.log(i / xMin) * degCounts[degs.index(i)] for i in degs])))
# erdos-renyi clustering coefficient
graphER = snap.GenRndGnm(snap.PUNGraph, n, m)
avgClustCoeffER = snap.GetClustCf(graphER, -1)
# average shortest path
graphWCC = snap.GetMxWcc(graph)
avgClustCoeff = snap.GetClustCf(graphWCC, -1)
numSamples = min(graphWCC.GetNodes(), 617) # all nodes or sample size
Rnd = snap.TRnd(42)
Rnd.Randomize()
shortPathList = []
for i in xrange(numSamples):
s = graphWCC.GetRndNId(Rnd)
NIdToDistH = snap.TIntH()
snap.GetShortPath(graphWCC, s, NIdToDistH)
for item in NIdToDistH:
shortPathList.append(NIdToDistH[item])
avgShortPath = np.mean(shortPathList)
return avgClustCoeff, maxSCCsize, maxWCCsize, avgDegree, alphaMLLE, avgClustCoeffER, avgShortPath
# return nodes in the same weakly connected component as node 1
CnCom = snap.TInt64V()
snap.GetNodeWcc(G, 1, CnCom)
print("CnCom.Len() = %d" % (CnCom.Len()))
# get nodes in weakly connected components
WCnComV = snap.TCnComV()
snap.GetWccs(G, WCnComV)
for i in range(0, WCnComV.Len()):
print("WCnComV[%d].Len() = %d" % (i, WCnComV[i].Len()))
for j in range(0, WCnComV[i].Len()):
print("WCnComV[%d][%d] = %d" % (i, j, WCnComV[i][j]))
# get the size of the maximum weakly connected component
MxWccSz = snap.GetMxWccSz(G)
print("MxWccSz = %.5f" % (MxWccSz))
# get the graph with the largest weakly connected component
GMx = snap.GetMxWcc(G)
print("GMx: GetNodes() = %d, GetEdges() = %d" %
(GMx.GetNodes(), GMx.GetEdges()))
# get strongly connected components
SCnComV = snap.TCnComV()
snap.GetSccs(G, SCnComV)
for i in range(0, SCnComV.Len()):
print("SCnComV[%d].Len() = %d" % (i, SCnComV[i].Len()))
# get the graph representing the largest bi-connected component
GMxBi = snap.GetMxBiCon(G)
G = snap.LoadEdgeList(snap.PNGraph, "Wiki-Vote.txt", 0, 1)
snap.PrintInfo(G, "votes Stats", "votes-info.txt", False)
# Node ID with maximum degree
NId1 = snap.GetMxDegNId(G)
print("Node ID with Maximum-Degree: %d" % NId1)
# Number of Strongly connected components
ComponentDist = snap.TIntPrV()
snap.GetSccSzCnt(G, ComponentDist)
for comp in ComponentDist:
print("Size: %d - Number of Components: %d" %
(comp.GetVal1(), comp.GetVal2()))
# Size of largest strongly connected component
print("Strongly Connected Component - Maximum size:", snap.GetMxSccSz(G))
# Number of Weakly Connected Components
CompDist = snap.TIntPrV()
snap.GetWccSzCnt(G, CompDist)
for comp in CompDist:
print("Size: %d - Number of Components: %d" %
(comp.GetVal1(), comp.GetVal2()))
# Size of largest weakly connected component
print("Weakly Connected Component - Maximum size:", snap.GetMxWccSz(G))
# Plot of Outdegree Distribution
snap.PlotOutDegDistr(G, "Wiki Votes", "Wiki-Votes Out Degree")