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 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])]))
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
OutDegV = snap.TIntPrV()
snap.GetNodeOutDegV(graph, OutDegV)
count_od = 0
for item in OutDegV:
if (item.GetVal2() > 10):
count_od = count_od + 1
print "Count of nodes with more than 10 outgoing edges %d" % count_od
#no of nodes with in-degree greater than 10
InDegV = snap.TIntPrV()
snap.GetNodeInDegV(graph, InDegV)
count_in = 0
print snap.CntUniqDirEdges(g)
print '\n'
# cc=0;
# ug=snap.ConvertGraph(snap.PUNGraph,g);
# for e in ug.Edges():
# if(e.GetSrcNId()!=e.GetDstNId()):
# cc=cc+1;
# print cc;
# print "\n";
print snap.CntUniqUndirEdges(g)
print '\n'
# print c-cc;
# print "\n";
print snap.CntUniqBiDirEdges(g)
print '\n'
c = 0
for n in g.Nodes():
if (n.GetOutDeg() == 0):
c = c + 1
print c
print "\n"
c = 0
for n in g.Nodes():
if (n.GetInDeg() == 0):
c = c + 1
print c
print "\n"
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
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)
from twython import Twython
import sys
if __name__ == '__main__':
CONSUMER_KEY, CONSUMER_SECRET = open('twitapikeys.txt').read().split()[:2]
twitterapi = Twython(CONSUMER_KEY, CONSUMER_SECRET)
filename = sys.argv[1]
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
# if src == dst:
# self_loop_v_cnt += 1
# else:
# direct_edge_cnt += 1
# Answer 2:
print('There are {} self-loop nodes'.format(snap.CntSelfEdges(G1)))
# 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:
wiki = snap.LoadEdgeList(snap.PNGraph, "wiki-Vote.txt", 0, 1, '\t')
# number of nodes
print("Node number:", wiki.GetNodes())
# 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
import snap
if __name__ == "__main__":
print("Loading graph...")
FIn = snap.TFIn("results/snap-follow.graph")
graph = snap.TNGraph.Load(FIn)
bidirectional = snap.CntUniqBiDirEdges(graph)
print("Bidirectional Edges:", bidirectional)
print("Total Edges:", graph.GetEdges())
print("Reciprocated Ratio:", float(bidirectional) / graph.GetEdges())
def numUniqueBidirectionalEdges(self):
return snap.CntUniqBiDirEdges(self.rawGraph)