def test_snap(self):
"""Test that snap.py installed correctly.
"""
import snap
num_nodes = 20
# Generate different undirected graphs
full_graph = snap.GenFull(snap.PUNGraph, num_nodes)
star_graph = snap.GenStar(snap.PUNGraph, num_nodes)
random_graph = snap.GenRndGnm(snap.PUNGraph, num_nodes, num_nodes * 3)
# Basic statistics on the graphs
self.assertEqual(snap.CntInDegNodes(full_graph, num_nodes - 1), num_nodes)
self.assertEqual(snap.CntOutDegNodes(full_graph, num_nodes - 1), num_nodes)
self.assertEqual(snap.GetMxInDegNId(star_graph), 0)
self.assertEqual(snap.GetMxOutDegNId(star_graph), 0)
# Iterator
degree_to_count = snap.TIntPrV()
snap.GetInDegCnt(full_graph, degree_to_count)
# There should be only one entry (num_nodes - 1, num_nodes)
for item in degree_to_count:
self.assertEqual(num_nodes - 1, item.GetVal1())
self.assertEqual(num_nodes, item.GetVal2())
# Rewiring
rewired_graph = snap.GenRewire(random_graph)
for n1 in random_graph.Nodes():
for n2 in rewired_graph.Nodes():
if n1.GetId() == n2.GetId():
self.assertEqual(n1.GetOutDeg() + n1.GetInDeg(),
n2.GetOutDeg() + n2.GetInDeg())
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 degree_distribution_graphs():
InDegV = snap.TIntPrV()
snap.GetNodeInDegV(G, InDegV)
a = np.arange(1, snap.CntNonZNodes(G) - snap.CntInDegNodes(G, 0) + 2)
i = 0
for item in InDegV:
if item.GetVal2() > 0:
i = i + 1
a[i] = item.GetVal2()
bars, bins = np.histogram(a, bins=np.arange(1, max(a)))
plt.hist(bars, bins)
plt.grid()
plt.show()
plt.loglog(bins[0:-1], bars)
plt.ylabel('# users per degree')
plt.xlabel('in-degree')
plt.grid()
plt.show()
plt.loglog(bins[0:-1], sum(bars) - np.cumsum(bars))
plt.ylabel('# users with degree larger or equal than x')
plt.xlabel('in-degree')
plt.grid()
plt.show()
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 partOneAndTwo(WikiG):
# WikiG.Dump()
print('1. Number of nodes: '+str(WikiG.GetNodes()))
selfloop_cnt = 0
for node in WikiG.Nodes():
# print(node.GetId())
if WikiG.IsEdge(node.GetId(), node.GetId()):
selfloop_cnt += 1
print('2. Self loop Node: {}'.format(selfloop_cnt))
cnt_dir = snap.CntUniqDirEdges(WikiG)
print('3. The number of directed edges: {}'.format(cnt_dir))
cnt_undir = snap.CntUniqUndirEdges(WikiG)
print("4. The number of unique undirected edges is %d" % cnt_undir)
print("5. The number of reciprocated edges is %d" % (cnt_dir - cnt_undir))
cnt_in = snap.CntInDegNodes(WikiG, 0)
print("6. The number of nodes of zero out-degree is %d" % cnt_in)
cnt_out = snap.CntOutDegNodes(WikiG, 0)
print("7. The number of nodes of zero in-degree is %d" % cnt_out)
cnt_deg_above_10 = 0
cnt_deg_less_10 = 0
for node in WikiG.Nodes():
if node.GetOutDeg() > 10:
cnt_deg_above_10 += 1
if node.GetInDeg() < 10:
cnt_deg_less_10 += 1
print("8. The number of nodes with more than 10 outgoing edges is %d" % cnt_deg_above_10)
print("9. The number of nodes with fewer than 10 incoming edges is %d" % cnt_deg_less_10)
# Part 2
out_file_name = 'wiki'
snap.PlotInDegDistr(WikiG, out_file_name, "Directed graph - in-degree Distribution")
snap.PlotOutDegDistr(WikiG, out_file_name, "Directed graph - out-degree Distribution")
InDegDistr = np.loadtxt("inDeg."+out_file_name+".tab")
InDegDistr = InDegDistr[InDegDistr[:, 0] > 0]
OutDegDistr = np.loadtxt("OutDeg."+out_file_name+".tab")
# print(OutDegDistr.shape)
OutDegDistr = OutDegDistr[OutDegDistr[:, 0] > 0]
# print(OutDegDistr.shape)
coff = np.polyfit(np.log10(OutDegDistr)[:, 0], np.log10(OutDegDistr)[:, 1], 1)
print(coff)
plt.figure()
plt.subplot(211)
plt.loglog(InDegDistr[:, 0], InDegDistr[:, 1])
plt.title('In deg Distr')
plt.subplot(212)
plt.loglog(OutDegDistr[:, 0], OutDegDistr[:, 1])
plt.loglog(OutDegDistr[:, 0], np.power(10, coff[1])*np.power(OutDegDistr[:, 0], coff[0]))
plt.title('Out deg Distr & Last-Square Reg Line in log-log plot')
plt.show()
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 power_law_fit():
InDegV = snap.TIntPrV()
snap.GetNodeInDegV(G, InDegV)
a = np.arange(1, snap.CntNonZNodes(G) - snap.CntInDegNodes(G, 0) + 2)
fit = pl.Fit(a)
pl.plot_pdf(a, color='r')
fig2 = fit.plot_pdf(color='b', linewidth=2)
# power-law exponent
print("Power Law Data\n")
print("Power Law Exponential:", fit.alpha)
print("Min value for X:", fit.xmin)
print("Kolmogorov-Smirnov test:", fit.D)
# comparison of data and Pl-fits of pdf (blue) and ccdf (red)"
figCCDF = fit.plot_pdf(color='b', linewidth=2)
fit.power_law.plot_pdf(color='b', linestyle='--', ax=figCCDF)
fit.plot_ccdf(color='r', linewidth=2, ax=figCCDF)
fit.power_law.plot_ccdf(color='r', linestyle='--', ax=figCCDF)
####
figCCDF.set_ylabel(u"p(X), p(X≥x)")
figCCDF.set_xlabel(r"in-degree")
schema.Add(snap.TStrTAttrPr("srcID", snap.atStr))
schema.Add(snap.TStrTAttrPr("dstID", snap.atStr))
sample_table = snap.TTable.LoadSS(schema, graphfilename, context, "\t",
snap.TBool(False))
# graph will be an object of type snap.PNGraph
graph = snap.ToGraph(snap.PNGraph, sample_table, "srcID", "dstID",
snap.aaFirst)
#no of nodes
Count = snap.CntNonZNodes(graph)
print "Count of nodes with degree greater than 0 is %d" % Count
#no of edges
Count = snap.CntOutDegNodes(graph, 0)
print "Count of nodes with out-degree 0 is %d" % Count
#no of nodes with zero in-degree
Count = snap.CntInDegNodes(graph, 0)
print "Count of nodes with in-degree 0 is %d" % Count
#no of directed edges
Count = snap.CntUniqDirEdges(graph)
print "Count of directed edges is %d" % Count
#no of undirected edges
Count = snap.CntUniqUndirEdges(graph)
print "Count of undirected edges is %d" % Count
#no of self edges
Count = snap.CntSelfEdges(graph)
print "Count of self edges is %d" % Count
#no of unique bi-directional/reciprocated edges
Count = snap.CntUniqBiDirEdges(graph)
print "Count of unique bidirectional edges is %d" % Count
#no of nodes with out-degree greater than 10
def quick_properties(graph, name, dic_path):
"""Get quick properties of the graph "name". dic_path is the path of the dict {players: id} """
results = {}
n_edges = graph.GetEdges()
n_nodes = graph.GetNodes()
n_self_edges = snap.CntSelfEdges(graph)
n_directed_edges, n_undirected_edges = snap.CntUniqDirEdges(
graph), snap.CntUniqUndirEdges(graph)
n_reciprocated_edges = snap.CntUniqBiDirEdges(graph)
n_zero_out_nodes, n_zero_in_nodes = snap.CntOutDegNodes(
graph, 0), snap.CntInDegNodes(graph, 0)
max_node_in = graph.GetNI(snap.GetMxInDegNId(graph)).GetDeg()
max_node_out = graph.GetNI(snap.GetMxOutDegNId(graph)).GetDeg()
components = snap.TCnComV()
snap.GetWccs(graph, components)
max_wcc = snap.GetMxWcc(graph)
results["a. Nodes"] = n_nodes
results["b. Edges"] = n_edges
results["c. Self-edges"] = n_self_edges
results["d. Directed edges"] = n_directed_edges
results["e. Undirected edges"] = n_undirected_edges
results["f. Reciprocated edges"] = n_reciprocated_edges
results["g. 0 out-degree nodes"] = n_zero_out_nodes
results["h. 0 in-degree nodes"] = n_zero_in_nodes
results["i. Maximum node out-degree"] = max_node_out
results["j. Maximum node in-degree"] = max_node_in
results["k. Weakly connected components"] = components.Len()
results["l. Nodes, edges of largest WCC"] = (max_wcc.GetNodes(),
max_wcc.GetEdges())
print("##########")
print("Quick overview of {} Network".format(name))
print("##########")
print("{} Nodes, {} Edges".format(n_nodes, n_edges))
print("{} Self-edges ".format(n_self_edges))
print("{} Directed edges, {} Undirected edges".format(
n_directed_edges, n_undirected_edges))
print("{} Reciprocated edges".format(n_reciprocated_edges))
print("{} 0-out-degree nodes, {} 0-in-degree nodes".format(
n_zero_out_nodes, n_zero_in_nodes))
print("Maximum node in-degree: {}, maximum node out-degree: {}".format(
max_node_in, max_node_out))
print("###")
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(
name_from_index(sorted_prankH, 0, mydict),
name_from_index(sorted_prankH, 1, mydict),
name_from_index(sorted_prankH, 2, mydict)))
print("Top 3 hubs: {}, {}, {}".format(
name_from_index(sorted_NIdHubH, 0, mydict),
name_from_index(sorted_NIdHubH, 1, mydict),
name_from_index(sorted_NIdHubH, 2, mydict)))
print("Top 3 authorities: {}, {}, {}".format(
name_from_index(sorted_NIdAuthH, 0, mydict),
name_from_index(sorted_NIdAuthH, 1, mydict),
name_from_index(sorted_NIdAuthH, 2, mydict)))
results["m. Three top PageRank"] = (name_from_index(
sorted_prankH, 0, mydict), name_from_index(
sorted_prankH, 1,
mydict), name_from_index(sorted_prankH, 2, mydict))
results["n. Three top hubs"] = (name_from_index(
sorted_NIdHubH, 0,
mydict), name_from_index(sorted_NIdHubH, 1, mydict),
name_from_index(
sorted_NIdHubH, 2, mydict))
results["o. Three top authorities"] = (name_from_index(
sorted_NIdAuthH, 0,
mydict), name_from_index(sorted_NIdAuthH, 1, mydict),
name_from_index(
sorted_NIdAuthH, 2, mydict))
return results
# 1.4
print("The number of undirected edges is %s." % (
snap.CntUniqUndirEdges(wikiGraph)))
# 1.5
print("The number of reciprocated edges is %s." % (
snap.CntUniqDirEdges(wikiGraph) - snap.CntUniqUndirEdges(wikiGraph)))
# 1.6
print("The number of nodes of zero out-degree is %s." % (
snap.CntOutDegNodes(wikiGraph, 0)))
# 1.7
print("The number of nodes of zero in-degree is %s." % (
snap.CntInDegNodes(wikiGraph, 0)))
# 1.8
outDegreeToCount = snap.TIntPrV()
snap.GetOutDegCnt(wikiGraph, outDegreeToCount)
numNodesLargeOutDegree = sum([item.GetVal2()
for item in outDegreeToCount
if item.GetVal1() > DEGREE_BOUNDARY])
print("The number of nodes with more than %s outgoing edges is %s." % (
DEGREE_BOUNDARY, numNodesLargeOutDegree))
# 1.9
inDegreeCount = snap.TIntPrV()
snap.GetInDegCnt(wikiGraph, inDegreeCount)
numNodesSmallInDegree = sum([item.GetVal2()
for item in inDegreeCount
# Answer 3:
print('Thre are {} directed edges'.format(snap.CntUniqDirEdges(G1)))
# Answer 4:
print('There are {} undirect edges'.format(snap.CntUniqUndirEdges(G1)))
# Answer 5:
print('There are {} reciprocated edges'.format(snap.CntUniqBiDirEdges(G1)))
# Answer 6:
print('There are {} nodes having 0 out-degree'.format(
snap.CntOutDegNodes(G1, 0)))
# Answer 7:
print('There are {} nodes having 0 in-degree'.format(
snap.CntInDegNodes(G1, 0)))
# Answer 8:
DegToCntV = snap.TIntPrV()
snap.GetOutDegCnt(G1, DegToCntV)
Out10_cnt = 0
for item in DegToCntV:
if item.GetVal1() > 10:
Out10_cnt += 1
print('There are {} nodes having >10 out-degree'.format(Out10_cnt))
# Answer 9:
DegToCntV = snap.TIntPrV()
snap.GetInDegCnt(G1, DegToCntV)
In10_cnt = 0
for item in DegToCntV:
DegToCntV = snap.TIntPrV()
snap.GetDegCnt(Graph, DegToCntV)
N = Graph.GetNodes()
X, Y = [item.GetVal1() for item in DegToCntV
], [np.true_divide(item.GetVal2(), N) for item in DegToCntV]
############################################################################
return X, Y
G = snap.LoadEdgeList(snap.PNGraph, "team_data_bipartite.csv", 0, 1, ",")
# if the graph is loan id to user id, Out/In deg count, and set item.GetVal2() to zero
print "Loan nodes: %d" % (snap.CntInDegNodes(G, 0))
print "Lender nodes: %d" % (snap.CntOutDegNodes(G, 0))
print "Loan-Lender Edges: %d" % (G.GetEdges())
OutDegV = snap.TIntPrV()
snap.GetNodeOutDegV(G, OutDegV)
# Lender = [item.GetVal1() for item in OutDegV if item.GetVal2() == 0]
#
# NG = snap.TUNGraph.New()
# j = 0
# for i in Lender:
# print j
# if not NG.IsNode(i):
# NG.AddNode(i)
# NodeVec = snap.TIntV()
# number of self-edge
print("Self Edges:", snap.CntSelfEdges(wiki))
# number of directed edges
print("Directed Edges:", wiki.GetEdges() - snap.CntSelfEdges(wiki))
# number of undirected edges (A->B and B->A counts a single undirected edge)
print("Undirected Edges:", snap.CntUniqUndirEdges(wiki))
# number of reciprocated edges
print("Reciprocated Edges:", snap.CntUniqBiDirEdges(wiki))
# nubmber of nodes of zero out-degree
print("# of zero out-degree:", snap.CntOutDegNodes(wiki, 0))
# number of nodes of zero in-degree
print("# of zero in-degree:", snap.CntInDegNodes(wiki, 0))
# number of nodes with out-degree > 10
count = 0
for i in range(11):
count += snap.CntOutDegNodes(wiki, i)
temp = wiki.GetNodes() - count
print("Nodes with out-degree > 10:", temp)
# number of nodes with in-degree < 10
count = 0
for i in range(10):
count += snap.CntInDegNodes(wiki, i)
print("Nodes with in-degree < 10:", count)
def ratioIndeg1(G):
return snap.CntInDegNodes(G, 1) / float(G.GetNodes())
