def number_of_articulation_points(G, GName):
ArtNIdV = snap.TIntV()
snap.GetArtPoints(G, ArtNIdV)
articulation_points_in_graph = len(ArtNIdV)
print "Number of articulation points in {0}: {1}".format(
GName[:-10], articulation_points_in_graph)
def getArticulationPoints(Graph, node_to_g):
''' A vertex in an undirected connected graph is an articulation point (or cut vertex)
iff removing it (and edges through it) disconnects the graph.
Articulation points represent vulnerabilities in a connected network –
single points whose failure would split the network into 2 or more disconnected components.
They are useful for designing reliable networks. '''
prot_to_articulation_points = {}
ArtNIdV = snap.TIntV()
snap.GetArtPoints(Graph, ArtNIdV)
for node in ArtNIdV:
my_prot = node_to_g[node]
prot_to_articulation_points[my_prot] = True
return prot_to_articulation_points
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())
(average, variance))
#c Plot
snap.PlotShortPathDistr(fbsgel, "shortest_path_" + str(subgraph_name),
"shortest_path_" + str(subgraph_name))
#Q4
#a
print("Fraction of nodes in largest connected component:",
round(snap.GetMxSccSz(fbsgel), 4))
#b
EdgeBridgeV = snap.TIntPrV()
snap.GetEdgeBridges(fbsgel, EdgeBridgeV)
print("Number of edge bridges:", len(EdgeBridgeV))
#c
ArtNIdV = snap.TIntV()
snap.GetArtPoints(fbsgel, ArtNIdV)
print("Number of articulation points:", len(ArtNIdV))
#d Plot
snap.PlotSccDistr(fbsgel, "connected_comp_" + str(subgraph_name),
"connected_comp_" + str(subgraph_name))
#Q5
#a
print("Average clustering coefficient:", round(snap.GetClustCf(fbsgel, -1), 4))
#b
print("Number of triads:", snap.GetTriads(fbsgel, -1))
#c
RnId = fbsgel.GetRndNId(Rnd)
print("Clustering coefficient of random node " + str(RnId) + ":",
round(snap.GetNodeClustCf(fbsgel, RnId), 4))
#d
(effmean, effvar))
str1 = 'shortest_path_' + file_name
snap.PlotShortPathDistr(Graph1, str1, "Distribution of shortest path lengths")
#4.Components of the network
fraction = snap.GetMxSccSz(Graph1)
print("Fraction of nodes in largest connected component: %0.4f" % fraction)
V_edges = snap.TIntPrV()
snap.GetEdgeBridges(Graph1, V_edges)
edge_bridges = V_edges.Len()
print("Number of edge bridges: ", edge_bridges)
Art_points = snap.TIntV()
snap.GetArtPoints(Graph1, Art_points)
art = Art_points.Len()
print("Number of articulation points: ", art)
str2 = "connected_comp_" + file_name
snap.PlotSccDistr(Graph1, str2,
"Distribution of sizes of connected components")
#5.Connectivity and clustering in the network
avg_cc = snap.GetClustCf(Graph1, -1)
print("Average clustering coefficient: %0.4f" % avg_cc)
triads = snap.GetTriads(Graph1, -1)
print("Number of triads: ", triads)
random1 = Graph1.GetRndNId(Rnd)
node_cc = snap.GetNodeClustCf(Graph1, random1)
def get_articulation_points(graph):
articulation_points = snap.TIntV()
snap.GetArtPoints(graph, articulation_points)
return articulation_points
def graphStructure(elistName, elistPath):
"""
Calculate properties of the graph as given in the assignment
Args:
elistName (str) -> Input elist name
elistPath (pathlib.Path) -> Input elist using which graph needs to be built
Return:
RESULTS (dict) -> Dictionary containing results for different subparts of the assignment
"""
RESULTS = {}
subGraph = snap.LoadEdgeList(snap.PUNGraph, elistPath, 0, 1)
# Part 1 (Size of the network)
RESULTS['nodeCount'] = subGraph.GetNodes()
RESULTS['edgeCount'] = subGraph.GetEdges()
# Part 2 (Degree of nodes in the network)
maxDegree = 0
maxDegreeNodes = []
degree7Count = 0
for node in subGraph.Nodes():
if node.GetDeg() == 7:
degree7Count += 1
maxDegree = max(maxDegree, node.GetDeg())
for node in subGraph.Nodes():
if node.GetDeg() == maxDegree:
maxDegreeNodes.append(node.GetId())
plotFilename = f"deg_dist_{elistName}"
# Since it is an undirected graph, in/out degree is unimportant
snap.PlotOutDegDistr(subGraph, plotFilename)
RESULTS['maxDegree'] = maxDegree
RESULTS['maxDegreeNodes'] = ','.join(map(str, maxDegreeNodes))
RESULTS['degree7Count'] = degree7Count
# Part 3 (Paths in the network)
# Full Diameter Calculation
fullDiameters = {
10: snap.GetBfsFullDiam(subGraph, 10, False),
100: snap.GetBfsFullDiam(subGraph, 100, False),
1000: snap.GetBfsFullDiam(subGraph, 1000, False)
}
fullMean, fullVariance = meanVariance(fullDiameters.values())
fullDiameters['mean'] = fullMean
fullDiameters['variance'] = fullVariance
RESULTS['fullDiameters'] = fullDiameters
# Effective Diameter Calculation
effDiameters = {
10: snap.GetBfsEffDiam(subGraph, 10, False),
100: snap.GetBfsEffDiam(subGraph, 100, False),
1000: snap.GetBfsEffDiam(subGraph, 1000, False),
}
effMean, effVariance = meanVariance(effDiameters.values())
effDiameters['mean'] = effMean
effDiameters['variance'] = effVariance
RESULTS['effDiameters'] = effDiameters
plotFilename = f"shortest_path_{elistName}"
snap.PlotShortPathDistr(subGraph, plotFilename)
# Part 4 (Components of the network)
edgeBridges = snap.TIntPrV()
articulationPoints = snap.TIntV()
RESULTS['fractionLargestConnected'] = snap.GetMxSccSz(subGraph)
snap.GetEdgeBridges(subGraph, edgeBridges)
snap.GetArtPoints(subGraph, articulationPoints)
RESULTS['edgeBridges'] = len(edgeBridges)
RESULTS['articulationPoints'] = len(articulationPoints)
plotFilename = f"connected_comp_{elistName}"
snap.PlotSccDistr(subGraph, plotFilename)
# Part 5 (Connectivity and clustering in the network)
RESULTS['avgClusterCoefficient'] = snap.GetClustCf(subGraph, -1)
RESULTS['triadCount'] = snap.GetTriadsAll(subGraph, -1)[0]
nodeX = subGraph.GetRndNId(Rnd)
nodeY = subGraph.GetRndNId(Rnd)
RESULTS['randomClusterCoefficient'] = (nodeX,
snap.GetNodeClustCf(
subGraph, nodeX))
RESULTS['randomNodeTriads'] = (nodeY, snap.GetNodeTriads(subGraph, nodeY))
RESULTS['edgesTriads'] = snap.GetTriadEdges(subGraph)
plotFilename = f"clustering_coeff_{elistName}"
snap.PlotClustCf(subGraph, plotFilename)
return RESULTS
def is_articulation_point(G, n):
ArtNIdV = snap.TIntV()
snap.GetArtPoints(G, ArtNIdV)
return n in ArtNIdV
def main():
parentDir = os.getcwd()
os.chdir(parentDir + "/subgraphs")
sub_graph = snap.LoadEdgeList(snap.PUNGraph, sys.argv[1], 0, 1)
subGraphName = sys.argv[1].split(".")[0]
os.chdir(parentDir)
#### 1 ########
node_count = 0
for node in sub_graph.Nodes():
node_count = node_count + 1
printWithOutNewLine("Number of nodes:", node_count)
printWithOutNewLine("Number of edges:", snap.CntUniqBiDirEdges(sub_graph))
#### 2 ########
printWithOutNewLine("Number of nodes with degree=7:",
snap.CntDegNodes(sub_graph, 7))
rndMaxDegNId = snap.GetMxDegNId(sub_graph)
nodeDegPairs = snap.TIntPrV()
snap.GetNodeInDegV(sub_graph, nodeDegPairs)
maxDegVal = 0
for pair in nodeDegPairs:
if (pair.GetVal1() == rndMaxDegNId):
maxDegVal = pair.GetVal2()
break
maxDegNodes = []
for pair in nodeDegPairs:
if (pair.GetVal2() == maxDegVal):
maxDegNodes.append(pair.GetVal1())
print("Node id(s) with highest degree:", end=" ")
print(*maxDegNodes, sep=',')
#### 3 ########
sampledFullDiam = []
sampledFullDiam.append(snap.GetBfsFullDiam(sub_graph, 10, False))
sampledFullDiam.append(snap.GetBfsFullDiam(sub_graph, 100, False))
sampledFullDiam.append(snap.GetBfsFullDiam(sub_graph, 1000, False))
sampledFullDiamStats = []
sampledFullDiamStats.append(round(statistics.mean(sampledFullDiam), 4))
sampledFullDiamStats.append(round(statistics.variance(sampledFullDiam), 4))
printWithOutNewLine("Approximate full diameter by sampling 10 nodes:",
sampledFullDiam[0])
printWithOutNewLine("Approximate full diameter by sampling 100 nodes:",
sampledFullDiam[1])
printWithOutNewLine("Approximate full diameter by sampling 1000 nodes:",
sampledFullDiam[2])
print("Approximate full diameter (mean and variance):", end=" ")
print(*sampledFullDiamStats, sep=',')
sampledEffDiam = []
sampledEffDiam.append(round(snap.GetBfsEffDiam(sub_graph, 10, False), 4))
sampledEffDiam.append(round(snap.GetBfsEffDiam(sub_graph, 100, False), 4))
sampledEffDiam.append(round(snap.GetBfsEffDiam(sub_graph, 1000, False), 4))
sampledEffDiamStats = []
sampledEffDiamStats.append(round(statistics.mean(sampledEffDiam), 4))
sampledEffDiamStats.append(round(statistics.variance(sampledEffDiam), 4))
printWithOutNewLine("Approximate effective diameter by sampling 10 nodes:",
sampledEffDiam[0])
printWithOutNewLine(
"Approximate effective diameter by sampling 100 nodes:",
sampledEffDiam[1])
printWithOutNewLine(
"Approximate effective diameter by sampling 1000 nodes:",
sampledEffDiam[2])
print("Approximate effective diameter (mean and variance):", end=" ")
print(*sampledEffDiamStats, sep=',')
#### 4 ########
printWithOutNewLine("Fraction of nodes in largest connected component:",
round(snap.GetMxSccSz(sub_graph), 4))
bridgeEdges = snap.TIntPrV()
snap.GetEdgeBridges(sub_graph, bridgeEdges)
printWithOutNewLine("Number of edge bridges:", len(bridgeEdges))
articulationPoints = snap.TIntV()
snap.GetArtPoints(sub_graph, articulationPoints)
printWithOutNewLine("Number of articulation points:",
len(articulationPoints))
#### 5 ########
printWithOutNewLine("Average clustering coefficient:",
round(snap.GetClustCf(sub_graph, -1), 4))
printWithOutNewLine("Number of triads:", snap.GetTriads(sub_graph, -1))
randomNodeId = sub_graph.GetRndNId()
nodeIdCcfMap = snap.TIntFltH()
snap.GetNodeClustCf(sub_graph, nodeIdCcfMap)
print("Clustering coefficient of random node", end=" ")
print(randomNodeId, end=": ")
print(round(nodeIdCcfMap[randomNodeId], 4))
print("Number of triads random node", end=" ")
print(randomNodeId, end=" participates: ")
print(snap.GetNodeTriads(sub_graph, randomNodeId))
printWithOutNewLine(
"Number of edges that participate in at least one triad:",
snap.GetTriadEdges(sub_graph, -1))
#### plots ########
if not os.path.isdir('plots'):
os.makedirs('plots')
os.chdir(parentDir + "/plots")
plotsDir = os.getcwd()
snap.PlotOutDegDistr(sub_graph, subGraphName,
subGraphName + " Subgraph Degree Distribution")
snap.PlotShortPathDistr(
sub_graph, subGraphName,
subGraphName + " Subgraph Shortest Path Lengths Distribution")
snap.PlotSccDistr(
sub_graph, subGraphName,
subGraphName + " Subgraph Connected Components Size Distribution")
snap.PlotClustCf(
sub_graph, subGraphName,
subGraphName + " Subgraph Clustering Coefficient Distribution")
files = os.listdir(plotsDir)
for file in files:
if not file.endswith(".png"):
os.remove(os.path.join(plotsDir, file))
plots = os.listdir(plotsDir)
filePrefix = "filename"
for file in plots:
nameSplit = file.split(".")
if (len(nameSplit) == 2):
continue
if (nameSplit[0] == "ccf"):
filePrefix = "clustering_coeff_"
elif (nameSplit[0] == "outDeg"):
filePrefix = "deg_dist_"
elif (nameSplit[0] == "diam"):
filePrefix = "shortest_path_"
elif (nameSplit[0] == "scc"):
filePrefix = "connected_comp_"
os.rename(file, filePrefix + nameSplit[1] + "." + nameSplit[2])
os.chdir(parentDir)
EdgeV = snap.TIntPrV()
snap.GetEdgeBridges(p2p_gnutella04_subgraph, EdgeV)
edge_bridge = 0
for i in EdgeV:
edge_bridge = edge_bridge + 1
print "Number of edge bridges in p2p-Gnutella04-subgraph :" + str(
edge_bridge)
# Task 1.2.4.3
if (sub_graph_name == "soc-Epinions1-subgraph"):
# Calculating no of Articulation points
ArtNIdV = snap.TIntV()
snap.GetArtPoints(soc_epinions1_subgraph, ArtNIdV)
art_point = 0
for NI in ArtNIdV:
art_point = art_point + 1
print "Number of articulation points in soc-Epinions1-subgraph :" + str(
art_point)
if (sub_graph_name == "cit-HepPh-subgraph"):
# Calculating no of Articulation points
ArtNIdV = snap.TIntV()
snap.GetArtPoints(cit_heph_subgraph, ArtNIdV)
art_point = 0
for NI in ArtNIdV:
art_point = art_point + 1
"""
FOR FASTER COMPUTATION, UNCOMMENT THE FOLLOWING LINE AND COMMENT OUT LINE 107-125
"""
# snap.PlotShortPathDistr(G, "shortest_path_{}".format(graph_filename[:-6]), "Shortest Path Distribution ({})".format(graph_filename[:-6]))
# [4] Components of the network
SCC = snap.GetMxScc(G)
print("Fraction of nodes in largest connected component: {}".format(
round(SCC.GetNodes() / G.GetNodes(), 4)))
Edge_Bridge = snap.TIntPrV()
snap.GetEdgeBridges(G, Edge_Bridge)
print("Number of edge bridges: {}".format(len(Edge_Bridge)))
ArticulationPoint = snap.TIntV()
snap.GetArtPoints(G, ArticulationPoint)
print("Number of articulation points: {}".format(len(ArticulationPoint)))
CComp = snap.TIntPrV()
snap.GetSccSzCnt(G, CComp)
connected_component = {}
for comp in CComp:
connected_component[comp.GetVal1()] = comp.GetVal2()
# Plot Degree Distribution
plot_filename = 'connected comp_' + graph_filename[:-6] + '.png'
plot_filedir = os.path.join(plotpath, plot_filename)
plt.figure()
plt.scatter(list(connected_component.keys()),
list(connected_component.values()),
s=15)
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(G, NIdHubH, NIdAuthH)
write(NIdHubH, "hub.txt")
write(NIdAuthH, "auth.txt")
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
snap.GetBetweennessCentr(G, Nodes, Edges, 1.0)
write(Nodes, "between.txt")
rows = []
for i, node in enumerate(G.Nodes()):
if i % 10000 == 0:
print "on iteration {}".format(i)
nid = node.GetId()
ecc = snap.GetNodeEcc(G, nid)
clust = snap.GetNodeClustCf(G, nid)
rows.append([nid, ecc, clust])
with open(base + "ecc_clust.txt", 'w') as f:
for row in rows:
f.write(",".join(map(str, row)) + "\n")
ArtNIdV = snap.TIntV()
snap.GetArtPoints(G, ArtNIdV)
with open(base + "art.txt", "w") as f:
for NI in ArtNIdV:
f.write("{}\n".format(NI))
#Question 4
## Max Comp Fraction
MxConCompSize = sn.GetMxScc(graph).GetNodes()
print("Fraction of nodes in largest connected component: {:0.4f}".format(
MxConCompSize / graph.GetNodes()))
## Edge Bridges
edgeBridge = sn.TIntPrV()
sn.GetEdgeBridges(graph, edgeBridge)
print("Number of edge bridges: {}".format(len(edgeBridge)))
## Articulation Points
artPoints = sn.TIntV()
sn.GetArtPoints(graph, artPoints)
print("Number of articulation points: {}".format(len(artPoints)))
## Connected Components Distribution
sn.PlotSccDistr(graph, name, "Connected Component Distribution")
plotRemove("scc", "connected_comp", name)
#Question 5
## Clustering Coefficient
print("Average clustering coefficient: {:0.4f}".format(
sn.GetClustCf(graph)))
## Triads
print("Number of triads: {}".format(sn.GetTriads(graph)))
