def computeGraphMetrics(GRep, GModel):
nddDiff = euclidDist(ndDist(GRep), ndDist(GModel))
knnDiff = euclidDist(knnDist(GRep), knnDist(GModel))
dkDiff = euclidDist(dkDist(GRep), dkDist(GModel))
ccDiff = euclidDist(ccDist(GRep), ccDist(GModel))
ASVals = (ASCoeff(GRep), ASCoeff(GModel))
MxWccVals = (snap.GetMxWcc(GRep).GetNodes(), snap.GetMxWcc(GModel).GetNodes())
effDVals = (snap.GetBfsEffDiam(GRep, 1000, False),
snap.GetBfsEffDiam(GModel, 1000, False))
return nddDiff, knnDiff, dkDiff, ccDiff, ASVals, MxWccVals, effDVals
def q1_3_grpah(Graph):
n_nodes = Graph.GetNodes()
MxWcc = snap.GetMxWcc(Graph)
MxScc = snap.GetMxScc(Graph)
n_MxWcc = MxWcc.GetNodes()
n_MxScc = MxScc.GetNodes()
print(" TOTAL : ", n_nodes)
print(" DISCONNECTED : ", n_nodes - n_MxWcc)
print(" SCC : ", n_MxScc)
SCC_nodes = []
for NI in MxScc.Nodes():
SCC_nodes.append(NI.GetId())
num_test = 100
random_sampled_scc = random.sample(SCC_nodes, num_test)
num_out = []
num_in = []
for i in range(0, num_test):
NodeId = random_sampled_scc[i]
BfsTreeOut = snap.GetBfsTree(Graph, NodeId, True, False)
BfsTreeIn = snap.GetBfsTree(Graph, NodeId, False, True)
num_out.append(BfsTreeOut.GetNodes()) # roughly SCC + OUT
num_in.append(BfsTreeIn.GetNodes()) # roughly SCC + IN
num_out.sort()
num_in.sort()
print(" OUT : ", num_out[-1] - n_MxScc)
print(" IN : ", num_in[-1] - n_MxScc)
num_tendrils = n_MxWcc - n_MxScc - (num_out[-1] - n_MxScc) - (num_in[-1] -
n_MxScc)
print(" TENDRILS+TUBES : ", num_tendrils)
def bowtie_components(graph, name):
"""Give sizes of DISCONNECTED, IN, OUT, SCC"""
results = {}
N = graph.GetNodes()
SCC = snap.GetMxScc(graph)
n = SCC.GetRndNId()
disc = N - snap.GetMxWcc(graph).GetNodes()
scc = SCC.GetNodes()
SCC_in = snap.GetBfsTree(graph, n, False, True)
SCC_out = snap.GetBfsTree(graph, n, True, False)
in1 = SCC_in.GetNodes() - scc
out = SCC_out.GetNodes() - scc
tt = N - disc - scc - in1 - out
results["a. SCC"] = scc
results["b. IN"] = in1
results["c. OUT"] = out
results["d. TENDRILS + TUBES"] = tt
results["e. DISCONNECTED"] = disc
print 'Total nodes in {} network: {}'.format(name, N)
print 'DISCONNECTED: {}'.format(disc)
print 'SCC: {}'.format(scc)
print 'IN: {}'.format(in1)
print 'OUT: {}'.format(out)
print 'TENDRILS + TUBES: {}'.format(tt)
return results
def SizeOfBowtieRegions(Graph, sccNodeID):
'''
Given a Graph with a BowTie structure as described in
http://snap.stanford.edu/class/cs224w-readings/broder00bowtie.pdf
and an sccNodeID of a node known to belong to the central SCC,
determines the size of each component.
returns: tuple of sizes (SCC, IN, OUT, TENDRILS, DISCONNECTED)
'''
totalNodes = Graph.GetNodes()
wcc = snap.GetMxWcc(Graph)
assert wcc.IsNode(sccNodeID)
wccNodes = wcc.GetNodes()
disconnectedNodes = totalNodes - wccNodes
scc = snap.GetMxScc(Graph)
# Sanity check the input.
assert scc.IsNode(sccNodeID)
sccNodes = scc.GetNodes()
sccAndOutNodes = snap.GetBfsTree(Graph, sccNodeID, True, False).GetNodes()
sccAndInNodes = snap.GetBfsTree(Graph, sccNodeID, False, True).GetNodes()
inNodes = sccAndInNodes - sccNodes
outNodes = sccAndOutNodes - sccNodes
tendrilNodes = wccNodes - (inNodes + outNodes + sccNodes)
nodes = (sccNodes, inNodes, outNodes, tendrilNodes, disconnectedNodes)
assert sum(nodes) == Graph.GetNodes()
return nodes
def initNetwork(self,Ajen,keyList):
self.Ajen=Ajen
self.keyList=keyList
self.myGraph = snap.TNEANet.New()
self.nid2id=dict()
self.id2nid=dict()
length=len(keyList)
for i in range(length):
theKey=keyList[i]
nid=self.myGraph.AddNode(i)
self.myGraph.AddStrAttrDatN(nid, theKey, 'key')
self.nid2id[nid]=theKey
self.id2nid[theKey]=nid
self.outputList=[]
for i in range(length):
for j in range(i+1,length):
if Ajen[i,j]>0:
eid=self.myGraph.AddEdge(i, j)
self.myGraph.AddFltAttrDatE(eid, Ajen[i,j], 'weigth')
# eid=self.myGraph.AddEdge(j, i)
# self.myGraph.AddFltAttrDatE(eid, Ajen[j,i], 'weigth')
self.outputList.append([keyList[i],keyList[j], Ajen[i,j]])
print '-original: '+str(self.myGraph.GetEdges())+' '+str(self.myGraph.GetNodes())
self.MxWcc = snap.GetMxWcc(self.myGraph)
print '-mxWcc: '+str(self.MxWcc.GetEdges())+' '+str(self.MxWcc.GetNodes())
def generate_steam_edge_list():
FIn = snap.TFIn("graph/steam.graph")
G = snap.TUNGraph.Load(FIn)
G = snap.GetMxWcc(G)
user_node_array = [] #88310
with open('graph/user_node.txt', 'r') as f:
for line in f:
user_node_array.append(int(line))
game_node_array = [] #10978
with open('graph/game_node.txt', 'r') as f:
for line in f:
game_node_array.append(int(line))
with open('graph/steam_edge_list.csv', 'w') as f:
writer = csv.writer(f, delimiter=',')
for edge in G.Edges():
# eid = edge.GetId()
id1 = edge.GetSrcNId()
id2 = edge.GetDstNId()
if id1 in user_node_array:
row = [str(id1), 'g' + str(id2)]
else:
row = [str(id2), 'g' + str(id1)]
writer.writerow(row)
def preproc_graph(filename):
''' get connected graph
I beleive this is done after we remap the nodes to
consecutive order in map_nodes_new.py
'''
print "Working on %s \n" % filename
print "Generating graph from edge list..."
# laod edge list into snap
Graph0 = snap.LoadEdgeList(snap.PUNGraph, filename, 0, 1, '\t')
# get edges
V0 = Graph0.GetNodes()
# delete zero degree nodes
snap.DelZeroDegNodes(Graph0)
print "Done generating graph!"
# get max weakly connected component
print "Generating connected graph..."
Graph = snap.GetMxWcc(Graph0)
V = Graph.GetNodes()
E = Graph.GetEdges()
print "Done generating graph with V = %i, E = %i!, V0 = %i" % (V, E, V0)
# get nodes included in weakly connected graph (which could be
# a proper subset of original set)
# Find one edge in graph and find all connected nodes
for EI in Graph.Edges():
conn_node = EI.GetSrcNId() # start with one edge
break # only need one edge since connected
CnCom = snap.TIntV()
snap.GetNodeWcc(Graph, conn_node, CnCom)
conn_node_ids = sort(array([node for node in CnCom]))
return Graph, conn_node_ids, V, E, V0
def main(version):
starttime = datetime.datetime.now()
codePath = sys.path[0]
s = codePath.split('\\')
workPath = s[0] + '\\' + s[1] + '\\' + s[
2] + '\\data\\flixster\\commondata\\' #f:\project\somproject
filePath1 = workPath + 'finalSocial' + version + '.txt'
# transfer node string to num 2131313 to 1
# use the index of list to represent the node
totalNodeList = []
G1 = snap.TUNGraph.New()
for line in open(filePath1):
if line == '':
break
linkPair = line[:-1].split('\t')
node1 = int(linkPair[0])
node2 = int(linkPair[1])
if node1 not in totalNodeList:
totalNodeList.append(node1)
if node2 not in totalNodeList:
totalNodeList.append(node2)
node1MapNum = totalNodeList.index(node1)
node2MapNum = totalNodeList.index(node2)
if not G1.IsNode(node1MapNum):
G1.AddNode(node1MapNum)
if not G1.IsNode(node2MapNum):
G1.AddNode(node2MapNum)
G1.AddEdge(node1MapNum, node2MapNum)
print 'get the max connected component...'
MxWcc = snap.GetMxWcc(G1)
print 'the max connected component node num is %d ' % MxWcc.GetNodes()
print MxWcc.GetEdges()
# filePath2=workPath+'finalUserID.txt'
# finalNodeList=[]
# for line in open(filePath2):
# if line=='':
# break
# nodeStr=line[:-1]
# node=int(nodeStr)
# nodeMapNum=totalNodeList.index(node)
# if MxWcc.IsNode(nodeMapNum):
# finalNodeList.append(node)
# print 'the final user num is %d' %len(finalNodeList)
FOut = snap.TFOut(workPath + 'finalSocial' + version + '.graph')
MxWcc.Save(FOut)
FOut.Flush()
print 'finished'
endtime = datetime.datetime.now()
print 'passed time is %d s' % (endtime - starttime).seconds
def main():
starttime = datetime.datetime.now()
codePath = sys.path[0]
s = codePath.split('\\')
workPath = s[0] + '\\' + s[1] + '\\' + s[
2] + '\\data\\baidu\\' #f:\project\somproject
# transfer node string to num 2131313 to 1
# use the index of list to represent the node
print 'use social data to build the graph... '
filePath1 = workPath + 'commondata\\rawSocial.txt'
totalNodeList = []
G1 = snap.TUNGraph.New()
for line in open(filePath1):
if line == '':
break
linkPair = line[:-1].split('\t')
node1 = int(linkPair[0])
node2 = int(linkPair[1])
if node1 not in totalNodeList:
totalNodeList.append(node1)
if node2 not in totalNodeList:
totalNodeList.append(node2)
node1MapNum = totalNodeList.index(node1)
node2MapNum = totalNodeList.index(node2)
if not G1.IsNode(node1MapNum):
G1.AddNode(node1MapNum)
if not G1.IsNode(node2MapNum):
G1.AddNode(node2MapNum)
G1.AddEdge(node1MapNum, node2MapNum)
print 'get the max connected component...'
MxWcc = snap.GetMxWcc(G1)
print 'the max connected component node num is %d ' % MxWcc.GetNodes()
print 'get user id in the max connected component... '
writer2 = open(workPath + 'commondata\\coreUserID.txt', 'w')
filePath2 = workPath + 'commondata\\rawCoreUserID.txt'
coreUserList = []
for line in open(filePath2):
if line == '':
break
nodeStr = line[:-1]
node = int(nodeStr)
nodeMapNum = totalNodeList.index(node)
if MxWcc.IsNode(nodeMapNum):
coreUserList.append(node)
nodeLine = str(node) + '\n'
writer2.write(nodeLine)
writer2.close()
print 'the core user num is %d' % len(coreUserList)
print 'finished'
endtime = datetime.datetime.now()
print 'passed time is %d s' % (endtime - starttime).seconds
def createGraph(nodes, edges):
G = snap.TUNGraph.New()
renumbered = {}
idToOsmid = {}
counter = 0
for osmid in edges:
refs = edges[osmid]
for i in xrange(0, len(refs) - 1):
start = refs[i]
end = refs[i+1]
# not all edges in a way are in nodes in the graph if at the boundary
if start not in nodes or end not in nodes:
continue
# if way is a road, add nodes if they haven't been added before
if start not in renumbered:
renumbered[start] = counter
idToOsmid[counter] = start
G.AddNode(counter)
counter += 1
if end not in renumbered:
renumbered[end] = counter
idToOsmid[counter] = end
G.AddNode(counter)
counter += 1
G.AddEdge(renumbered[start], renumbered[end])
G = snap.GetMxWcc(G)
return G, idToOsmid
def Q2_4():
epinions, email = loadNetworks()
for trial in xrange(TRIALS):
for (name, network) in [("Epinions", epinions), ("Email", email)]:
print("Probability of path for entire %s is %s." %
(name, ProbabilityOfPath(network)))
print("Probability of path in largest WCC of %s is %s." %
(name, ProbabilityOfPath(snap.GetMxWcc(network))))
def __init__(self, nodes, edges, edge_list=None):
if edge_list is None:
G = snap.GenRndGnm(snap.PUNGraph, nodes, edges)
self.graph = snap.GetMxWcc(G)
else:
self.graph = snap.LoadEdgeList(snap.PUNGraph, edge_list, 0, 1)
self.assignment = {}
self.max_type, self.min_type = None, None
def quick_properties(graph, name, dic_path):
"""Get quick properties of the graph "name". dic_path is the path of the dict {players: id} """
n_edges = graph.GetEdges()
n_nodes = graph.GetNodes()
print("##########")
print("Quick overview of {} Network".format(name))
print("##########")
print("{} Nodes, {} Edges").format(n_nodes, n_edges)
print("{} Self-edges ".format(snap.CntSelfEdges(graph)))
print("{} Directed edges, {} Undirected edges".format(
snap.CntUniqDirEdges(graph), snap.CntUniqUndirEdges(graph)))
print("{} Reciprocated edges".format(snap.CntUniqBiDirEdges(graph)))
print("{} 0-out-degree nodes, {} 0-in-degree nodes".format(
snap.CntOutDegNodes(graph, 0), snap.CntInDegNodes(graph, 0)))
node_in = graph.GetNI(snap.GetMxInDegNId(graph))
node_out = graph.GetNI(snap.GetMxOutDegNId(graph))
print("Maximum node in-degree: {}, maximum node out-degree: {}".format(
node_in.GetDeg(), node_out.GetDeg()))
print("###")
components = snap.TCnComV()
snap.GetWccs(graph, components)
max_wcc = snap.GetMxWcc(graph)
print "{} Weakly connected components".format(components.Len())
print "Largest Wcc: {} Nodes, {} Edges".format(max_wcc.GetNodes(),
max_wcc.GetEdges())
prankH = snap.TIntFltH()
snap.GetPageRank(graph, prankH)
sorted_prankH = sorted(prankH, key=lambda key: prankH[key], reverse=True)
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(graph, NIdHubH, NIdAuthH)
sorted_NIdHubH = sorted(NIdHubH,
key=lambda key: NIdHubH[key],
reverse=True)
sorted_NIdAuthH = sorted(NIdAuthH,
key=lambda key: NIdAuthH[key],
reverse=True)
with open(dic_path, 'rb') as dic_id:
mydict = pickle.load(dic_id)
print("3 most central players by PageRank scores: {}, {}, {}".format(
list(mydict.keys())[list(mydict.values()).index(sorted_prankH[0])],
list(mydict.keys())[list(mydict.values()).index(sorted_prankH[1])],
list(mydict.keys())[list(mydict.values()).index(
sorted_prankH[2])]))
print("Top 3 hubs: {}, {}, {}".format(
list(mydict.keys())[list(mydict.values()).index(
sorted_NIdHubH[0])],
list(mydict.keys())[list(mydict.values()).index(
sorted_NIdHubH[1])],
list(mydict.keys())[list(mydict.values()).index(
sorted_NIdHubH[2])]))
print("Top 3 authorities: {}, {}, {}".format(
list(mydict.keys())[list(mydict.values()).index(
sorted_NIdAuthH[0])],
list(mydict.keys())[list(mydict.values()).index(
sorted_NIdAuthH[1])],
list(mydict.keys())[list(mydict.values()).index(
sorted_NIdAuthH[2])]))
def max_wcc_info(edges_file, key_file, valuefn): print '\nLoading edge list...' G = snap.LoadEdgeList(snap.PUNGraph, edges_file, 0, 1) MaxWCC = snap.GetMxWcc(G) print '\nBuilding legend...' legend, full_lines = build_legends(key_file, valuefn, '\t') return MaxWCC, legend, full_lines
def main(args):
review_file = args.review
review_maxwcc_file = args.review_maxwcc
# load graph
G = snap.LoadEdgeList(snap.PUNGraph, review_file, 0, 1)
# get wcc
MxWcc = snap.GetMxWcc(G)
# save
snap.SaveEdgeList(MxWcc, review_maxwcc_file)
def get_connected_component(graph):
if isinstance(graph, snap.PNGraph):
lcc = snap.GetMxScc(graph)
# renumber the node numbers from 0 to the size-1
lcc = snap.ConvertGraph(snap.PNGraph, lcc, True)
elif isinstance(graph, snap.PUNGraph):
lcc = snap.GetMxWcc(graph)
# renumber the node numbers from 0 to the size-1
lcc = snap.ConvertGraph(snap.PUNGraph, lcc, True)
else:
raise NotAGraphError(graph)
return lcc
def processNetwork(Graph, id_to_groups):
with open("../../data/fastinf_graph_noweights_features.txt", "w+") as f:
f.write("RELATED GROUPS GRAPH:\n")
f.write('Edges: %d\n' % Graph.GetEdges())
f.write('Nodes: %d\n\n' % Graph.GetNodes())
MxWcc = snap.GetMxWcc(Graph)
f.write("MAX WCC:\n")
f.write('Edges: %f ' % MxWcc.GetEdges())
f.write('Nodes: %f \n' % MxWcc.GetNodes())
f.write('Node List: ')
for node in MxWcc.Nodes():
f.write('%d, ' % node.GetId())
f.write('\n')
for node in MxWcc.Nodes():
f.write('%s, ' % id_to_groups[node.GetId()])
f.write("\n\nALL WCCs:")
Components = snap.TCnComV()
snap.GetWccs(Graph, Components)
for i, CnCom in enumerate(Components):
if CnCom.Len() < 10: continue
f.write('\nWcc%d: ' % i)
for nodeid in CnCom:
f.write('%d, ' % nodeid)
MxScc = snap.GetMxScc(Graph)
f.write("\n\nMAX SCC:\n")
f.write('Edges: %f ' % MxScc.GetEdges())
f.write('Nodes: %f \n' % MxScc.GetNodes())
f.write('Node List: ')
for node in MxScc.Nodes():
f.write('%d, ' % node.GetId())
f.write('\n')
for node in MxScc.Nodes():
f.write('%s, ' % id_to_groups[node.GetId()])
f.write("\n\nALL SCCs:")
Components = snap.TCnComV()
snap.GetSccs(Graph, Components)
for i, CnCom in enumerate(Components):
if CnCom.Len() < 10: continue
f.write('\nScc%d: ' % i)
for nodeid in CnCom:
f.write('%d, ' % nodeid)
f.write('\n\nCLUSTERING AND COMMUNITIES:\n')
f.write('Clustering coefficient: %f\n' % snap.GetClustCf(Graph, -1))
f.write('Num Triads: %d\n' % snap.GetTriads(Graph, -1))
Nodes = snap.TIntV()
for node in Graph.Nodes():
Nodes.Add(node.GetId())
f.write('Modularity: %f' % snap.GetModularity(Graph, Nodes))
def enumerate_graphs(self, k):
for seq in itertools.product("01", repeat=k*(k-1)):
g = snap.TNGraph.New()
for i in range(k): g.AddNode(i)
for i,e in enumerate(seq):
if e=='1':
start_node = i/(k-1)
end_node = i % (k-1)
if end_node >= start_node:
end_node += 1
g.AddEdge(start_node, end_node)
if snap.GetMxWcc(g).GetNodes()==k:
yield g
def q2_3_util(dataset_name):
# G = load_graph("email")
G = load_graph(dataset_name)
MxWcc = snap.GetMxWcc(G)
total_size = G.GetNodes()
wcc_size = MxWcc.GetNodes()
disconnected_size = total_size - wcc_size
print 'Total size: ', total_size
print 'WCC size: ', wcc_size
print 'DISCONNECTED: ', disconnected_size
Rnd = snap.TRnd(42)
Rnd.Randomize()
MxScc = snap.GetMxScc(G)
scc_size = MxScc.GetNodes()
number_of_trials = 1
scc_plus_out = 0
scc_plus_in = 0
out_size = 0
in_size = 0
tendrils_plus_tubes = 0
for i in xrange(number_of_trials):
NId = MxScc.GetRndNId(Rnd)
# print 'Random node id', NId
outward_set = set()
BfsTree = snap.GetBfsTree(G, NId, True, False)
for EI in BfsTree.Edges():
outward_set.add(EI.GetDstNId())
scc_plus_out = max(scc_plus_out, len(outward_set))
out_size = max( out_size, scc_plus_out - scc_size)
#
inward_set = set()
BfsTree = snap.GetBfsTree(G, NId, False, True)
for EI in BfsTree.Edges():
inward_set.add(EI.GetDstNId())
scc_plus_in = max(scc_plus_in, len(inward_set))
in_size = max(in_size, scc_plus_in - scc_size)
tendrils_plus_tubes = max(tendrils_plus_tubes, wcc_size - in_size - out_size)
print 'IN: ', in_size
print 'scc_size', scc_size
print 'scc + out: ', scc_plus_out
print 'OUT: ', out_size
print 'scc + in: ', scc_plus_in
print 'TENDRILS + TUBES', tendrils_plus_tubes
print '------------------'
def calculateWccSimilarity(G, partition):
MxWcc = snap.GetMxWcc(G)
numNodes = MxWcc.GetNodes()
intersection = 0
total = 0
for NI in G.Nodes():
if NI.GetId() in partition[0]:
intersection += 1
total += 1
for NId in partition[0]:
if not G.IsNode(NId):
total += 1
Jaccard = intersection * 1.0 / total
return numNodes, Jaccard
def main():
network = snap.LoadEdgeList(
snap.PNEANet, "/Users/qingyuan/CS224W/stackoverflow-Java.txt", 0, 1)
Components = snap.TCnComV()
snap.GetWccs(network, Components)
print("The number of weakly connected components is %d" % Components.Len())
MxWcc = snap.GetMxWcc(network)
print(
"The number of edges is %d and the number of nodes is %d in the largest weakly connected component."
% (MxWcc.GetNodes(), MxWcc.GetEdges()))
PRankH = snap.TIntFltH()
snap.GetPageRank(network, PRankH)
PRankH.SortByDat(False)
num = 0
print(
"IDs of the top 3 most central nodes in the network by PagePank scores. "
)
for item in PRankH:
print(item, PRankH[item])
num += 1
if num == 3:
num = 0
break
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(network, NIdHubH, NIdAuthH)
NIdHubH.SortByDat(False)
print("IDs of the top 3 hubs in the network by HITS scores. ")
for item in NIdHubH:
print(item, NIdHubH[item])
num += 1
if num == 3:
num = 0
break
NIdAuthH.SortByDat(False)
print("IDs of top 3 authorities in the network by HITS scores. ")
for item in NIdAuthH:
print(item, NIdAuthH[item])
num += 1
if num == 3:
num = 0
break
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
def q2_3_aux(name):
G = load_graph(name)
SCC = snap.GetMxScc(G).GetNodes()
wcc = snap.GetMxWcc(G).GetNodes()
inexplosionVect = emIn if name == "email" else epIn
outexplosionVect = emOut if name == "email" else epOut
ineexpl = inexplosionVect[-1]
outeexpl = outexplosionVect[-1]
IN = ineexpl - SCC
OUT = outeexpl - SCC
DISCONNECTED = G.GetNodes()-wcc
TENDRILS_AND_TUBES = wcc - IN - OUT - SCC
print name,"DISCONNECTED:",DISCONNECTED,"IN:",IN,"OUT:",OUT,"SCC:",SCC,"TENDRILS + TUBES:",TENDRILS_AND_TUBES
return
def q3():
G = snap.LoadEdgeList(snap.PNGraph, "stackoverflow-Java.txt", 0, 1)
components = snap.TCnComV()
snap.GetWccs(G, components)
print("Number of WCC: ", components.Len())
MxComp = snap.GetMxWcc(G)
cnt_mxc_node = 0
cnt_mxc_edge = 0
for _ in MxComp.Nodes():
cnt_mxc_node += 1
for _ in MxComp.Edges():
cnt_mxc_edge += 1
print("Number of edges and nodes in MxWCC: ", cnt_mxc_node, ' ',
cnt_mxc_edge)
PRankH = snap.TIntFltH()
snap.GetPageRank(G, PRankH)
scores = []
for id in PRankH:
scores.append((PRankH[id], id))
res = sorted(scores, reverse=True)[:3]
print("IDs of top 3 PageRank scores: ", res)
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(G, NIdHubH, NIdAuthH)
scores = []
for id in NIdHubH:
scores.append((NIdHubH[id], id))
res = sorted(scores, reverse=True)[:3]
print("IDs of top 3 hubs by HITS scores: ", res)
scores = []
for id in NIdAuthH:
scores.append((NIdAuthH[id], id))
res = sorted(scores, reverse=True)[:3]
print("IDs of top 3 authorities by HITS scores: ", res)
def graph_cleaning(file_path):
Graph, H = load_graph(file_path)
Graph = snap.GetMxWcc(Graph)
snap.DelSelfEdges(Graph)
nodes_set = set()
for NI in Graph.Nodes():
nodes_set.add(NI.GetId())
with open(file_path, 'r') as f:
raw_list = f.read().split('\n')
edges_list = [edge_str.split() for edge_str in raw_list]
with open(file_path, 'w') as f:
print '-----clear'
with open(file_path, 'a') as f:
for edge in edges_list:
if len(edge) == 0:
continue
if H.GetKeyId(edge[0]) not in nodes_set:
continue
edge_cleaned = list()
for node in edge:
if H.GetKeyId(node) in nodes_set:
edge_cleaned.append(node)
f.write(' '.join(edge_cleaned) + '\n')
def stackoverflow():
g = snap.LoadEdgeList(snap.PNGraph, "stackoverflow-Java.txt", 0, 1)
components = snap.TCnComV()
snap.GetWccs(g, components)
print "Num connected comp = ", components.Len()
mxwcc = snap.GetMxWcc(g)
print "Num edges in largest = ", mxwcc.GetEdges()
print "Num nodes in largest = ", mxwcc.GetNodes()
rank = snap.TIntFltH()
snap.GetPageRank(g, rank)
rank.SortByDat(False)
count = 0
for node in rank:
if count >= 3:
break
count += 1
print "largest page rank score nodes = ", node, " (score = ", rank[node]
hubs = snap.TIntFltH()
auths = snap.TIntFltH()
snap.GetHits(g, hubs, auths)
hubs.SortByDat(False)
count = 0
for node in hubs:
if count >= 3:
break
count += 1
print "largest hub score nodes = ", node, " (score = ", hubs[node]
auths.SortByDat(False)
count = 0
for node in auths:
if count >= 3:
break
count += 1
print "largest auth score nodes = ", node, " (score = ", auths[node]
def partThree():
data_dir_StackOverFlow = './data/stackoverflow-Java.txt'
sofG = snap.LoadEdgeList(snap.PNGraph, data_dir_StackOverFlow, 0, 1, '\t')
Components = snap.TCnComV()
snap.GetWccs(sofG, Components)
print('1. The number of weakly connected components in the network.: '+str(Components.Len()))
MxWcc = snap.GetMxWcc(sofG)
num_node = MxWcc.GetNodes()
num_deg = MxWcc.GetEdges()
print('2. The number of edges is {} and the number of nodes is {}'.format(num_deg, num_node))
PRankH = snap.TIntFltH()
snap.GetPageRank(sofG, PRankH)
cnt = 0
print('3. ')
for item in PRankH:
cnt += 1
if cnt > 3:
break
print(item, PRankH[item])
print('4. ')
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(sofG, NIdHubH, NIdAuthH)
HubDict = {}
AuthDict = {}
for item in NIdHubH:
HubDict[item] = NIdHubH[item]
a = zip(HubDict.values(), HubDict.keys())
print(list(sorted(a, reverse=True))[:3])
for item in NIdAuthH:
AuthDict[item] = NIdAuthH[item]
b = zip(AuthDict.values(), AuthDict.keys())
print(list(sorted(b, reverse=True))[:3])
def analyze_graph(G):
WCC = snap.GetMxWcc(G)
SCC = snap.GetMxScc(G)
id = SCC.GetRndNId()
out_tree = snap.GetBfsTree(G, id, True, False)
in_tree = snap.GetBfsTree(G, id, False, True)
G_size = G.GetNodes()
SCC_size = SCC.GetNodes()
WCC_size = WCC.GetNodes()
DISCONNECTED_size = G_size - WCC_size
in_size = in_tree.GetNodes() - SCC_size
out_size = out_tree.GetNodes() - SCC_size
Tendril_size = G_size - SCC_size - DISCONNECTED_size - in_size - out_size
print 'Total Graph Size: %d' % G_size
print 'SCC Size: %d' % SCC_size
print 'WCC Size: %d' % WCC_size
print 'IN Size: %d' % in_size
print 'OUT Size: %d' % out_size
print 'DISCONNECTED Size: %d' % DISCONNECTED_size
print 'Tendril tube size (remaining): %d' % Tendril_size
print()
def per_graph(graph, name):
mxWcc = snap.GetMxWcc(graph)
mxScc = snap.GetMxScc(graph)
print ''
print 'Size analysis on {}'.format(name)
print 'Disconnected size = {}'.format(graph.GetNodes() - mxWcc.GetNodes())
print 'SCC size = {}'.format(mxScc.GetNodes())
trials = 200
avg_reached_out = 0
avg_reached_in = 0
for _ in range(trials):
nodeId = mxScc.GetRndNId()
avg_reached_out += snap.GetBfsTree(graph, nodeId, True, False).GetNodes()
avg_reached_in += snap.GetBfsTree(graph, nodeId, False, True).GetNodes()
scc_out = float(avg_reached_out) / trials
scc_in = float(avg_reached_in) / trials
out_sz = scc_out - mxScc.GetNodes()
in_sz = scc_in - mxScc.GetNodes()
print 'OUT size = {}'.format(out_sz)
print 'IN size = {}'.format(in_sz)
print 'Tendrils/Tubes size = {}'.format(mxWcc.GetNodes() - mxScc.GetNodes() - out_sz - in_sz)
#Load the stack overflow grap
G1 = snap.LoadEdgeList(snap.PNGraph, "stackoverflow-Java.txt", 0, 1)
#1. Get the list of all weakly connected components
Components = snap.TCnComV()
snap.GetWccs(G1, Components)
wccCount = 0
for Cc in Components:
wccCount = wccCount + 1
print "1. Number of Weakly Connected Components: ", wccCount
#2. Get The number of edges and the number
# of nodes in the largest weakly connected component
maxWcc = snap.GetMxWcc(G1)
EdgeCount = 0
NodeCount = 0
for E in maxWcc.Edges():
EdgeCount = EdgeCount + 1
for N in maxWcc.Nodes():
NodeCount = NodeCount + 1
print "2. Number of edges and nodes in largest wcc"
print "EdgeCount : ", EdgeCount
print "NodeCount : ", NodeCount
#3 Get The top 3 most central nodes in the network by PagePank scores
PRankH = snap.TIntFltH()
snap.GetPageRank(G1, PRankH)
