def f():
snap = self.snap
ret = []
ComponentDist = snap.TIntPr64V()
snap.GetSccSzCnt(self.graph, ComponentDist)
for comp in ComponentDist:
ret.append((comp.GetVal1(), comp.GetVal2()))
return ret
def _get_SCC(Graph, H, output_path):
ComponentDist = snap.TIntPrV()
snap.GetSccSzCnt(Graph, ComponentDist)
dataset = list()
for comp in ComponentDist:
scc = dict()
scc['size'] = comp.GetVal1()
scc['freq'] = comp.GetVal2()
dataset.append(scc)
dataset = pd.DataFrame(dataset)
dataset = dataset[['size', 'freq']]
dataset.sort('size', ascending=0, inplace=True)
dataset.to_csv(output_path, index=False, encoding='utf-8')
def fraction_of_nodes_in_largest_connected_component(G, GName):
ComponentDist = snap.TIntPrV()
snap.GetSccSzCnt(G, ComponentDist)
highest_nodes_in_connected_comp = 0
for comp in ComponentDist:
highest_nodes_in_connected_comp = max(comp.GetVal1(),
highest_nodes_in_connected_comp)
print "Fraction of nodes in largest connected component in {0}: {1}".format(
GName[:-10],
(float(str(highest_nodes_in_connected_comp)) / G.GetNodes()))
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 computeNumberOfStronglyConnectedComponentsPerSize(graph, outFile, fill):
logger.info("Computing Strongly Connected Components Per Component Size")
fw_cc = open(outFile, 'w')
CntV = snap.TIntPrV()
fw_cc.write('Size of SCC\tNumber of SCCs\n')
snap.GetSccSzCnt(graph, CntV)
last = 0
array = []
for p in CntV:
if (fill & p.GetVal1() - last > 1):
for i in range(last + 1, p.GetVal1()):
fw_cc.write(str(i) + '\t' + str(0) + '\n')
fw_cc.write(str(p.GetVal1()) + '\t' + str(p.GetVal2()) + '\n')
array.append({"x": p.GetVal1(), "y": p.GetVal2()})
last = p.GetVal1()
with open(outFile + '.json', 'w') as file:
json.dump(array, file)
logger.info("Number of Strongly Connected Components Per Component Size!")
logger.info(
"Number of Strongly Connected Components Per Component Size Exported to "
+ outFile)
import snap
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")
# [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)
plt.xlabel("Size of Connected Components")
plt.ylabel("Number of components")
plt.title("Connected Component Distribution ({})".format(graph_filename[:-6]))
plt.savefig(plot_filedir)
repliesgraph = snap.LoadEdgeList(snap.PNGraph, filename, 0, 1)
snap.PrintInfo(repliesgraph, "Twitter replies network")
print
#reciprocity
num_dir_edges = snap.CntUniqDirEdges(repliesgraph)
print "{0:.2f}% of directed edges are reciprocal".format(
snap.CntUniqBiDirEdges(repliesgraph) * 2 * 100 / num_dir_edges)
#clustering coefficient
print "The clustering coefficient is {0:.2f}%".format(
snap.GetClustCf(repliesgraph) * 100)
#strongly and weakly connected components
CntV = snap.TIntPrV()
snap.GetSccSzCnt(repliesgraph, CntV)
num_cc = 0
for p in CntV:
print "{0} strongly connected component(s) of size {1}".format(
p.GetVal2(), p.GetVal1())
num_cc += p.GetVal2()
print num_cc, "total strongly connected components"
print
snap.GetWccSzCnt(repliesgraph, CntV)
num_cc = 0
for p in CntV:
print "{0} weakly connected component(s) of size {1}".format(
p.GetVal2(), p.GetVal1())
num_cc += p.GetVal2()
print num_cc, "total weakly connected components"
def GraphComponentDistributionDict(G):
''' return a dict of cardinality : number of strongly-connected components
with that size in the graph G.'''
ComponentDist = snap.TIntPrV()
snap.GetSccSzCnt(G, ComponentDist)
return {comp.GetVal1(): comp.GetVal2() for comp in ComponentDist}
def main():
Component = snap.TIntPrV()
#loading the real world graph
realWorld = snap.LoadEdgeList(snap.PUNGraph, "CA-HepTh.txt", 0, 1)
#deleting the self-edges from the graph
snap.DelSelfEdges(realWorld)
#calling the function
wikiVotingNetwork()
#Taking number of nodes in a graph from real world network
n = realWorld.GetNodes()
#Generating an Undirected Graph
G = snap.TUNGraph.New()
#Taking number of edges in a graph from user
e = int(raw_input('Enter the number of Random Edges : '))
p = float(
raw_input('Enter the Probability of Edges between Nodes from 0-1 : '))
#Generating Number of Nodes
for i in range(n):
#Adding Nodes into the graph
G.AddNode(i)
#calling the function
erdosRenyi(G, p)
#Printing the Clustering
print 'Erdos Renyi Clustering Co-efficient: ', clustCoefficient(G)
diam = snap.GetBfsFullDiam(G, 9877, False)
#printing the diameter
print 'Erdos Renyi Diameter: ', diam
#plotting the graph
snap.PlotOutDegDistr(G, "Erdos-Renyi",
"Un-Directed graph - Out-Degree Distribution")
snap.GetSccSzCnt(G, Component)
for comp in Component:
#printing number of strongly connected components with size
print "Size: %d - Number of Connected Component in Erdos-Renyi: %d" % (
comp.GetVal1(), comp.GetVal2())
#printing fraction of nodes and edges
print "Fraction of Nodes and Edges in Erdos Renyi: ", snap.GetMxSccSz(G)
#Drawing a Erdos Renyi Graph
snap.DrawGViz(G, snap.gvlDot, "erdosRenyi1.png", "Erdos Renyi")
#calling the function
smallWorldRandomNetwork(G, e)
#printing the clustering coefficient
print 'Small World Random Network Clustering Co-efficient: ', clustCoefficient(
G)
diam = snap.GetBfsFullDiam(G, 9877, False)
#printing the diameter
print 'Small World Random Network Diameter: ', diam
snap.GetSccSzCnt(G, Component)
for comp in Component:
#printing number of strongly connected components with size
print "Size: %d - Number of Connected Component in Small World: %d" % (
comp.GetVal1(), comp.GetVal2())
#fraction of nodes and edges in small world
print "Fraction of Nodes and Edges in Small World: ", snap.GetMxSccSz(G)
#plotting the graph
snap.PlotOutDegDistr(G, "Small-World",
"Un-Directed graph - Out-Degree Distribution")
#drawinf the graph
snap.DrawGViz(G, snap.gvlDot, "smallWorld1.png",
"Small World Random Network")
#calculating the clustering co-efficient
print 'Real World Random Network Clustering Co-efficient: ', clustCoefficient(
realWorld)
diam = snap.GetBfsFullDiam(G, 9877, False)
print 'Real World Random Network Diameter: ', diam
snap.GetSccSzCnt(realWorld, Component)
for comp in Component:
#printing number of strongly connected components with size
print "Size: %d - Number of Weekly Connected Component in Real World: %d" % (
comp.GetVal1(), comp.GetVal2())
#printing fraction of nodes and edges
print "Fraction of Nodes and Edges in Small World: ", snap.GetMxSccSz(
realWorld)
#plotting the real world network graph
snap.PlotOutDegDistr(realWorld, "real-World",
"Un-Directed graph - Out-Degree Distribution")
#Drawing Real WOrld Graph
snap.DrawGViz(realWorld, snap.gvlDot, "realWorld.png",
"Real World Random Network")
def get_graph_overview(G, Gd=None):
'''
G here is an undirected graph
'''
# degree distribution
CntV = snap.TIntPrV()
snap.GetOutDegCnt(G, CntV)
deg_x, deg_y = [], []
max_deg = 0
for item in CntV:
max_deg = max(max_deg, item.GetVal1())
deg_x.append(item.GetVal1())
deg_y.append(item.GetVal2())
# print item.GetVal1(), item.GetVal2()
print 'max_deg = ', max_deg
deg_cnt = np.zeros(max_deg + 1)
for item in CntV:
deg_cnt[item.GetVal1()] = item.GetVal2()
print deg_cnt
# plt.loglog(deg_x, deg_y)
# plt.xlabel('Degree of nodes')
# plt.ylabel('Number of nodes')
# plt.savefig('Giu_deg_dist.png')
# plt.clf()
# clustering coefficient distribution
cf = snap.GetClustCf(G)
print 'average cf =', cf
NIdCCfH = snap.TIntFltH()
snap.GetNodeClustCf(G, NIdCCfH)
ccf_sum = np.zeros(max_deg + 1)
for item in NIdCCfH:
ccf_sum[G.GetNI(item).GetDeg()] += NIdCCfH[item]
# print item, NIdCCfH[item]
ccf_x, ccf_y = [], []
for i in range(max_deg + 1):
if deg_cnt[i] != 0:
ccf_sum[i] /= deg_cnt[i]
ccf_x.append(i)
ccf_y.append(ccf_sum[i])
print ccf_y
# plt.loglog(ccf_x, ccf_y)
# plt.xlabel('Degree of nodes')
# plt.ylabel('Average clustering coefficient of nodes with the degree')
# plt.savefig('Giu_ccf_dist.png')
# plt.clf()
# snap.PlotClustCf(G, 'investor_network', 'Distribution of clustering coefficients')
# diameter and shortest path distribution
diam = snap.GetBfsFullDiam(G, 100)
print diam
# snap.PlotShortPathDistr(G, 'investor_network', 'Distribution of shortest path length')
# rewired_diams = []
# for i in range(100):
# print 'rewire: ', i
# G_config = rewire_undirected_graph(G)
# rewired_diams.append(snap.GetBfsFullDiam(G_config, 400))
# print rewired_diams
# print 'null model diam mean: ', np.mean(rewired_diams)
# print 'null model diam std: ', np.std(rewired_diams)
# wcc and scc size distribution
WccSzCnt = snap.TIntPrV()
snap.GetWccSzCnt(G, WccSzCnt)
print 'Distribution of wcc:'
for item in WccSzCnt:
print item.GetVal1(), item.GetVal2()
if Gd != None:
print 'Distribution of scc:'
ComponentDist = snap.TIntPrV()
snap.GetSccSzCnt(Gd, ComponentDist)
for item in ComponentDist:
print item.GetVal1(), item.GetVal2()
import snap
import numpy as np
import matplotlib.pyplot as plt
if __name__ == "__main__":
print("Loading graph...")
FIn = snap.TFIn("results/snap-follow.graph")
graph = snap.TNGraph.Load(FIn)
print("Finding strongly connected components...")
dist = snap.TIntPrV()
snap.GetSccSzCnt(graph, dist)
sccs = [(comp.GetVal1(), comp.GetVal2()) for comp in dist]
print("Finding weakly connected components...")
dist = snap.TIntPrV()
snap.GetWccSzCnt(graph, dist)
wccs = [(comp.GetVal1(), comp.GetVal2()) for comp in dist]
print("Number of SCCs:", sum(scc[1] for scc in sccs))
print("Number of WCCs:", sum(wcc[1] for wcc in wccs))
plt.scatter([scc[0] for scc in sccs], [scc[1] for scc in sccs], s=4, label = 'WCC Distribution')
plt.scatter([wcc[0] for wcc in wccs], [wcc[1] for wcc in wccs], s=4, label = 'SCC Distribution')
plt.yscale('log')
plt.xscale('log')
plt.title('WCC / SCC Size Distribution')
plt.xlabel('Component Size')
dic_path = "../datasets/chess/chess_ids.pkl"
with open(dic_path, 'rb') as dic_id:
mydict = pickle.load(dic_id)
chess_graph = load.load_global("chess")
graphs = [fencing_graph, tm_graph, tf_graph, chess_graph]
names = ["Fencing Network", "Men's Tennis Network", "Women's Tennis Network", "Chess Network"]
print 'names:', names
print 'nodes:', [graph.GetNodes() for graph in graphs]
print 'edges:', [graph.GetEdges() for graph in graphs]
print 'mxscc:', [snap.GetMxScc(graph).GetNodes() for graph in graphs]
print 'max degree:', [graph.GetNI(snap.GetMxDegNId(graph)).GetDeg() for graph in graphs]
comp_dists = [snap.TIntPrV() for graph in graphs]
scc_counts = [snap.GetSccSzCnt(graph, comp_dists[i]) for i, graph in enumerate(graphs)]
print 'Strongly Connected Components'
for i, comp_dist in enumerate(comp_dists):
print names[i]
for comp in comp_dist:
print 'size:', comp.GetVal1(), 'count:', comp.GetVal2()
p_ranks = [snap.TIntFltH() for graph in graphs]
[snap.GetPageRank(graph, p_ranks[i]) for i, graph in enumerate(graphs)]
pr_ys = [sorted([p_rank[x] for x in p_rank]) for p_rank in p_ranks]
i_pr_ys = [[sum(pr_y[:i+1]) for i in range(len(pr_y))] for pr_y in pr_ys]
pr_xs = [[float(i+1)/len(pr_y) for i in range(len(pr_y))] for pr_y in pr_ys]
plt.figure()
[plt.plot(pr_xs[i], i_pr_ys[i], '.', markersize=4) for i in range(len(graphs))]
plt.title("Cumulative PageRank vs. Node Fraction")
