def clust_coef(self):
snap.PlotClustCf(self.graph, "Clust_Coef",
"Graph Clustering Coefficient")
img = mpimg.imread("ccf.Clust_Coef.png")
plt.figure()
imgplot = plt.imshow(img)
plt.show()
def PlotVisual(G1):
snap.PlotInDegDistr(G1, "Facebook", "Facebook In Degree")
snap.PlotWccDistr(G1, "Facebook", "Facebook - wcc distributaion")
snap.PlotSccDistr(G1, "Facebook", "Facebook - scc distributaion")
snap.PlotClustCf(G1, "Facebook", "Facebook - clustering coefficient")
snap.PlotKCoreNodes(G1, "Facebook", "Facebook - k-core nodes")
snap.PlotKCoreEdges(G1, "Facebook", "Facebook - k-core edges")
def print_ccf_distri(G, GName):
filename = "ccf." + GName[:-10] + ".png"
snap.PlotClustCf(G, GName[:-10], GName[:-10] + " - clustering coefficient")
print "Clustering coefficient distribution of {0} is in: {1}".format(
GName[:-10], filename)
def plotClustCf(graph):
path = 'temp'
os.chdir(path)
fileName = 'clust_coeff'
snap.PlotClustCf(graph, fileName, "Clustering Coefficient")
base = os.path.join(path, 'ccf.' + fileName)
os.chdir('..')
return os.path.abspath(base + '.png')
def clustering_coefficient_plot(G):
"""
Saves the clustering coefficient distribution plot of the subgraph G
The file is saved in the directory './plots/clustering_coeff_<subgraph_name>.png'
"""
snap.PlotClustCf(G, sys.argv[-1], f"Clustering Coefficient Distribution in {sys.argv[-1]}")
try:
os.mkdir('./plots')
except:
pass
os.rename(f'ccf.{sys.argv[-1]}.png', f'./plots/clustering_coeff_{sys.argv[-1]}.png')
os.remove(f'ccf.{sys.argv[-1]}.plt')
os.remove(f'ccf.{sys.argv[-1]}.tab')
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
from graph import * import snap # plot deg dist snap.PlotInDegDistr(graph, "InDegDist", flnme+" in-degree distribution") snap.PlotOutDegDistr(graph, "OutDegDist", flnme+" out-degree distribution") # plot connected components dist snap.PlotSccDistr(graph, "SccDist", flnme+" strongly connected components distribution") snap.PlotWccDistr(graph, "WccDist", flnme+" weakly connected components distribution") # plot cluster coefficient snap.PlotClustCf(graph, "ClustCoef", flnme+" clustering coefficient")
# print("node: %d centrality: %f" % (node, Nodes[node]))
# for edge in Edges:
# print("edge: (%d, %d) centrality: %f" % (edge.GetVal1(), edge.GetVal2(), Edges[edge]))
Graph = snap.GenRndGnm(snap.PNGraph, 10, 20)
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
snap.GetBetweennessCentr(Graph, Nodes, Edges, 1.0)
for node in Nodes:
print("node: %d centrality: %f" % (node, Nodes[node]))
for edge in Edges:
print("edge: (%d, %d) centrality: %f" % (edge.GetVal1(), edge.GetVal2(), Edges[edge]))
snap.PlotClustCf(Graph, "example", "Directed graph - clustering coefficient")
snap.DrawGViz(Graph, snap.gvlDot, "graph.png", "graph 1")
Image('graph.png')
NIdColorH = snap.TIntStrH()
NIdColorH[0] = "green"
NIdColorH[1] = "red"
NIdColorH[2] = "purple"
NIdColorH[3] = "blue"
NIdColorH[4] = "yellow"
Network = snap.GenRndGnm(snap.PNEANet, 5, 10)
snap.DrawGViz(Network, snap.gvlSfdp, "network.png", "graph 3", True, NIdColorH)
Image('network.png')
UGraph = snap.GenRndGnm(snap.PUNGraph, 10, 40)
snap.DrawGViz(UGraph, snap.gvlNeato, "graph_undirected.png", "graph 2", True)
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)
nde_cnt_freq_liberal.update({x: freq})
for x in set(conservative_deg_nds):
freq = conservative_deg_nds.count(x)
nde_cnt_freq_conservative.update({x: freq})
print("Average in Degree " + str(avg_in_degree / graph.GetNodes()))
print("Average out Degree " + str(avg_out_degree / graph.GetNodes()))
print("Liberal Nodes " + str(no_liberal))
print("Conservative Nodes " + str(no_conservative))
print("Density of graph " + str(graph.GetEdges() / (graph.GetNodes() *
(graph.GetNodes() - 1))))
snap.PlotClustCf(graph, "cluster_plot",
"Polblog Directed graph - clustering coefficient")
fig, axs = plt.subplots(3)
x_val = list(nde_cnt_freq_conservative.keys())
y_val = list(nde_cnt_freq_conservative.values())
axs[0].plot(x_val, y_val)
axs[0].set_ylabel("Frequency of that degree ")
axs[0].set_title("Degree of the conservative nodes")
x_val = list(nde_cnt_freq_liberal.keys())
y_val = list(nde_cnt_freq_liberal.values())
axs[1].plot(x_val, y_val)
axs[1].set_ylabel("Frequency of that degree ")
axs[1].set_title("Degree of the liberal nodes")
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)
print("Clustering coefficient of random node %d: %0.4f" % (random1, node_cc))
random2 = Graph1.GetRndNId(Rnd)
node_triads = snap.GetNodeTriads(Graph1, random2)
print("Number of triads random node %d participates: %d" %
(random2, node_triads))
triad_edges = snap.GetTriadEdges(Graph1, -1)
print("Number of edges that participate in at least one triad: ", triad_edges)
str3 = "clustering_coeff_" + file_name
snap.PlotClustCf(Graph1, str3, "The distribution of clustering coefficient")
def compute_graph_statistics(graph_path, overwrite, compute_betweenness=False):
graph_abs_path = os.path.abspath(graph_path)
graph_name = os.path.basename(graph_abs_path).replace(".graph", "")
fin = snap.TFIn(graph_abs_path)
graph = snap.TNEANet.Load(fin)
# rebuild the id => pkg dictionary
id_pkg_dict = {}
for node in graph.Nodes():
id_pkg_dict[node.GetId()] = graph.GetStrAttrDatN(node.GetId(), "pkg")
directory = os.path.dirname(os.path.abspath(graph_path))
json_path = os.path.join(directory, graph_name + "_statistics.json")
if os.path.isfile(json_path):
with open(json_path, "r") as f:
statistics = json.load(f, object_pairs_hook=OrderedDict)
else:
statistics = OrderedDict()
# snap.py doesn't suport absolute paths for some operations. Let's cd to the directory
os.chdir(directory)
# general statistics
output = os.path.join(directory, graph_name + "_main_statistics.txt")
if not os.path.isfile(output) or overwrite:
print("{0} Computing general statistics".format(datetime.datetime.now()))
snap.PrintInfo(graph, "Play Store Graph -- main statistics", output, False)
# info about the nodes with the max in degree
if "max_in_degree" not in statistics or overwrite:
print("{0} Computing max indegree".format(datetime.datetime.now()))
max_in_deg_id = snap.GetMxInDegNId(graph)
iterator = graph.GetNI(max_in_deg_id)
max_in_deg = iterator.GetInDeg()
max_in_deg_pkg = graph.GetStrAttrDatN(max_in_deg_id, "pkg")
statistics["max_in_degree"] = max_in_deg
statistics["max_in_degree_id"] = max_in_deg_id
statistics["max_in_degree_pkg"] = max_in_deg_pkg
# info about the nodes with the max out degree
if "max_out_degree" not in statistics or overwrite:
print("{0} Computing max outdegree".format(datetime.datetime.now()))
max_out_deg_id = snap.GetMxOutDegNId(graph)
iterator = graph.GetNI(max_out_deg_id)
max_out_deg = iterator.GetOutDeg()
max_out_deg_pkg = graph.GetStrAttrDatN(max_out_deg_id, "pkg")
statistics["max_out_degree"] = max_out_deg
statistics["max_out_degree_id"] = max_out_deg_id
statistics["max_out_degree_pkg"] = max_out_deg_pkg
# pagerank statistics
output = graph_name + "_topNpagerank.eps"
if not os.path.isfile(output) or "top_n_pagerank" not in statistics or overwrite:
print("{0} Computing top 20 nodes with highest pagerank".format(datetime.datetime.now()))
data_file = graph_name + "_pageranks"
prank_hashtable = snap.TIntFltH()
if not os.path.isfile(data_file) or overwrite:
# Damping Factor: 0.85, Convergence difference: 1e-4, MaxIter: 100
snap.GetPageRank(graph, prank_hashtable, 0.85)
fout = snap.TFOut(data_file)
prank_hashtable.Save(fout)
else:
fin = snap.TFIn(data_file)
prank_hashtable.Load(fin)
top_n = get_top_nodes_from_hashtable(prank_hashtable)
top_n.sort(key=itemgetter(1))
if "top_n_pagerank" not in statistics or overwrite:
top_n_labeled = []
for pair in top_n:
top_n_labeled.append((id_pkg_dict[pair[0]], pair[1]))
statistics["top_n_pagerank"] = list(reversed(top_n_labeled))
if not os.path.isfile(output) or overwrite:
# let's build a subgraph induced on the top 20 pagerank nodes
subgraph = get_subgraph(graph, [x[0] for x in top_n])
labels_dict = get_labels_subset(id_pkg_dict, subgraph)
values = snap_hashtable_to_dict(prank_hashtable, [x[0] for x in top_n])
plot_subgraph_colored(subgraph, labels_dict, values, "PageRank",
"Play Store Graph - top 20 PageRank nodes", output, "autumn_r")
# betweeness statistics
output = graph_name + "_topNbetweenness.eps"
if compute_betweenness and (not os.path.isfile(output) or "betweenness" not in statistics or overwrite):
print("{0} Computing top 20 nodes with highest betweenness".format(datetime.datetime.now()))
data_file1 = graph_name + "_node_betweenness"
data_file2 = graph_name + "_edge_betweenness"
node_betwenness_hashtable = snap.TIntFltH()
edge_betwenness_hashtable = snap.TIntPrFltH()
if not os.path.isfile(data_file1) or not os.path.isfile(data_file2) or overwrite:
snap.GetBetweennessCentr(graph, node_betwenness_hashtable, edge_betwenness_hashtable, 0.85, True)
fout = snap.TFOut(data_file1)
node_betwenness_hashtable.Save(fout)
fout = snap.TFOut(data_file2)
edge_betwenness_hashtable.Save(fout)
else:
fin = snap.TFIn(data_file1)
node_betwenness_hashtable.Load(fin)
fin = snap.TFIn(data_file2)
edge_betwenness_hashtable.Load(fin) # unused, as now
top_n = get_top_nodes_from_hashtable(node_betwenness_hashtable)
top_n.sort(key=itemgetter(1))
if "top_n_betweenness" not in statistics or overwrite:
top_n_labeled = []
for pair in top_n:
top_n_labeled.append((id_pkg_dict[pair[0]], pair[1]))
statistics["top_n_betweenness"] = list(reversed(top_n_labeled))
if not os.path.isfile(output) or overwrite:
# let's build a subgraph induced on the top 20 betweenness nodes
subgraph = get_subgraph(graph, [x[0] for x in top_n])
labels_dict = get_labels_subset(id_pkg_dict, subgraph)
values = snap_hashtable_to_dict(node_betwenness_hashtable, [x[0] for x in top_n])
plot_subgraph_colored(subgraph, labels_dict, values, "Betweenness",
"Play Store Graph - top 20 Betweenness nodes", output)
# HITS statistics
output_hub = graph_name + "_topNhitshubs.eps"
output_auth = graph_name + "_topNhitsauth.eps"
if not os.path.isfile(output_hub) or not os.path.isfile(output_auth) or "top_n_hits_hubs" not in statistics \
or "top_n_hits_authorities" not in statistics or overwrite:
print("{0} Computing top 20 HITS hubs and auths".format(datetime.datetime.now()))
data_file1 = graph_name + "_hits_hubs"
data_file2 = graph_name + "_hits_auth"
hubs_hashtable = snap.TIntFltH()
auth_hashtable = snap.TIntFltH()
if not os.path.isfile(data_file1) or not os.path.isfile(data_file2) or overwrite:
# MaxIter = 20
snap.GetHits(graph, hubs_hashtable, auth_hashtable, 20)
fout = snap.TFOut(data_file1)
hubs_hashtable.Save(fout)
fout = snap.TFOut(data_file2)
auth_hashtable.Save(fout)
else:
fin = snap.TFIn(data_file1)
hubs_hashtable.Load(fin)
fin = snap.TFIn(data_file2)
auth_hashtable.Load(fin)
top_n_hubs = get_top_nodes_from_hashtable(hubs_hashtable)
top_n_hubs.sort(key=itemgetter(1))
if "top_n_hits_hubs" not in statistics or overwrite:
top_n_labeled = []
for pair in top_n_hubs:
top_n_labeled.append((id_pkg_dict[pair[0]], pair[1]))
statistics["top_n_hits_hubs"] = list(reversed(top_n_labeled))
top_n_auth = get_top_nodes_from_hashtable(auth_hashtable)
top_n_auth.sort(key=itemgetter(1))
if "top_n_hits_authorities" not in statistics or overwrite:
top_n_labeled = []
for pair in top_n_auth:
top_n_labeled.append((id_pkg_dict[pair[0]], pair[1]))
statistics["top_n_hits_authorities"] = list(reversed(top_n_labeled))
if not os.path.isfile(output_hub) or not os.path.isfile(output_auth) or overwrite:
nodes_subset = set()
for pair in top_n_hubs:
nodes_subset.add(pair[0])
for pair in top_n_auth:
nodes_subset.add(pair[0])
# let's build a subgraph induced on the top N HITS auths and hubs nodes
subgraph = get_subgraph(graph, nodes_subset)
labels_dict = get_labels_subset(id_pkg_dict, subgraph)
values = snap_hashtable_to_dict(hubs_hashtable, nodes_subset)
values2 = snap_hashtable_to_dict(auth_hashtable, nodes_subset)
plot_subgraph_colored(subgraph, labels_dict, values, "HITS - Hub Index",
"Play Store Graph - top 20 HITS hubs + top 20 HITS authorities", output_hub, "bwr")
plot_subgraph_colored(subgraph, labels_dict, values2, "HITS - Authority Index",
"Play Store Graph - top 20 HITS hubs + top 20 HITS authorities", output_auth,
"bwr_r")
# indegree histogram
output = graph_name + "_indegree"
if not os.path.isfile("inDeg." + output + ".plt") or not os.path.isfile(
"inDeg." + output + ".tab") or not os.path.isfile("inDeg." + output + ".png") or overwrite:
print("{0} Computing indegree distribution".format(datetime.datetime.now()))
snap.PlotInDegDistr(graph, output, "Play Store Graph - in-degree Distribution")
# outdegree histogram
output = graph_name + "_outdegree"
if not os.path.isfile("outDeg." + output + ".plt") or not os.path.isfile(
"outDeg." + output + ".tab") or not os.path.isfile(
"outDeg." + output + ".png") or overwrite:
print("{0} Computing outdegree distribution".format(datetime.datetime.now()))
snap.PlotOutDegDistr(graph, output, "Play Store Graph - out-degree Distribution")
# strongly connected components print
output = graph_name + "_scc"
if not os.path.isfile("scc." + output + ".plt") or not os.path.isfile(
"scc." + output + ".tab") or not os.path.isfile("scc." + output + ".png") or overwrite:
print("{0} Computing scc distribution".format(datetime.datetime.now()))
snap.PlotSccDistr(graph, output, "Play Store Graph - strongly connected components distribution")
# weakly connected components print
output = graph_name + "_wcc"
if not os.path.isfile("wcc." + output + ".plt") or not os.path.isfile(
"wcc." + output + ".tab") or not os.path.isfile("wcc." + output + ".png") or overwrite:
print("{0} Computing wcc distribution".format(datetime.datetime.now()))
snap.PlotWccDistr(graph, output, "Play Store Graph - weakly connected components distribution")
# clustering coefficient distribution
output = graph_name + "_cf"
if not os.path.isfile("ccf." + output + ".plt") or not os.path.isfile(
"ccf." + output + ".tab") or not os.path.isfile("ccf." + output + ".png") or overwrite:
print("{0} Computing cf distribution".format(datetime.datetime.now()))
snap.PlotClustCf(graph, output, "Play Store Graph - clustering coefficient distribution")
# shortest path distribution
output = graph_name + "_hops"
if not os.path.isfile("hop." + output + ".plt") or not os.path.isfile(
"hop." + output + ".tab") or not os.path.isfile("hop." + output + ".png") or overwrite:
print("{0} Computing shortest path distribution".format(datetime.datetime.now()))
snap.PlotHops(graph, output, "Play Store Graph - Cumulative Shortest Paths (hops) distribution", True)
# k-core edges distribution
output = graph_name + "_kcore_edges"
if not os.path.isfile("coreEdges." + output + ".plt") or not os.path.isfile(
"coreEdges." + output + ".tab") or not os.path.isfile(
"coreEdges." + output + ".png") or overwrite:
print("{0} Computing k-core edges distribution".format(datetime.datetime.now()))
snap.PlotKCoreEdges(graph, output, "Play Store Graph - K-Core edges distribution")
# k-core nodes distribution
output = graph_name + "_kcore_nodes"
if not os.path.isfile("coreNodes." + output + ".plt") or not os.path.isfile(
"coreNodes." + output + ".tab") or not os.path.isfile(
"coreNodes." + output + ".png") or overwrite:
print("{0} Computing k-core nodes distribution".format(datetime.datetime.now()))
snap.PlotKCoreNodes(graph, output, "Play Store Graph - K-Core nodes distribution")
with open(json_path, 'w') as outfile:
json.dump(statistics, outfile, indent=2)
def plotClustCfOfAllNets(network_dictionary):
for label, net in network_dictionary.items():
snap.PlotClustCf(net, label, "{0} - Clustering coefficient".format(label))
snap.GetArtPoints(G, ArtNIdV)
print("Number of articulation points:", len(ArtNIdV))
print("Average clustering coefficient: %.4f" % snap.GetClustCf(G, -1))
print("Number of triads:", snap.GetTriads(G, -1))
Ran_n = G.GetRndNId(Rnd)
print("Clustering coefficient of random node %d: %.4f" %
(Ran_n, snap.GetNodeClustCf(G, Ran_n)))
Ran_n = G.GetRndNId(Rnd)
print("Number of triads random node %d participates: %d" %
(Ran_n, snap.GetNodeTriads(G, Ran_n)))
print("Number of edges that participate in at least one triad:",
snap.GetTriadEdges(G))
snap.PlotInDegDistr(G, "D_" + sys.argv[1], "Degree Distribution")
MoveFile(os.path.join(dirname, "inDeg.D_" + sys.argv[1] + ".png"),
os.path.join(dirname, "plots", "deg_dist_" + sys.argv[1] + ".png"))
snap.PlotShortPathDistr(G, "S_" + sys.argv[1], "Shortest path Distribution")
MoveFile(
os.path.join(dirname, "diam.S_" + sys.argv[1] + ".png"),
os.path.join(dirname, "plots", "shortest_path_" + sys.argv[1] + ".png"))
snap.PlotSccDistr(G, "C_" + sys.argv[1], "Component Size Distribution")
MoveFile(
os.path.join(dirname, "scc.C_" + sys.argv[1] + ".png"),
os.path.join(dirname, "plots", "connected_comp_" + sys.argv[1] + ".png"))
snap.PlotClustCf(G, "C_" + sys.argv[1], "Clustering Coefficient Distribution")
MoveFile(
os.path.join(dirname, "ccf.C_" + sys.argv[1] + ".png"),
os.path.join(dirname, "plots", "clustering_coeff_" + sys.argv[1] + ".png"))
import numpy as np
import snap
import matplotlib.pyplot as plt
import random
payoff_a = 2
payoff_b = 3
thersold = payoff_a / (payoff_a + payoff_b)
nodestatusList = []
nodedegreeList = []
nodeaffectList = []
nodeinitialList = []
G = snap.LoadEdgeList(snap.PUNGraph, "data/soc-Slashdot0902.txt", 0, 1, '\t')
snap.PlotClustCf(G, "project_cluster_coeff",
"Undirected graph - clustering coefficient")
DegToCCfV = snap.TFltPrV()
result = snap.GetClustCfAll(G, DegToCCfV)
for item in DegToCCfV:
print("degree: %d, clustering coefficient: %f" %
(item.GetVal1(), item.GetVal2()))
print("average clustering coefficient", result[0])
clusterfile = open("clustering_list.txt", "w")
NIdCCfH = snap.TIntFltH()
snap.GetNodeClustCf(G, NIdCCfH)
for item in NIdCCfH:
clusterfile.write("%d %d\r\n" % (item, NIdCCfH[item]))
# Calculating no of edges in particular triads
print "Number of edges that participate in at least one triad in cit-HepPh-subgraph : " + str(
snap.GetTriadEdges(cit_heph_subgraph))
if (sub_graph_name == "email-Enron-subgraph"):
# Calculating no of edges in particular triads
print "Number of edges that participate in at least one triad in email-Enron-subgraph : " + str(
snap.GetTriadEdges(email_enron_subgraph))
if (sub_graph_name == "p2p-Gnutella04-subgraph"):
# Calculating no of edges in particular triads
print "Number of edges that participate in at least one triad in p2p-Gnutella04-subgraph : " + str(
snap.GetTriadEdges(p2p_gnutella04_subgraph))
# Task 1.2.5.6
if (sub_graph_name == "soc-Epinions1-subgraph"):
#Plotting clustering coefficient
snap.PlotClustCf(soc_epinions1_subgraph, "soc-Epinions1-subgraph",
"Undirected graph - clustering coefficient")
print "Clustering coefficient distribution of soc-Epinions1-subgraph is in :" + 'ccf.soc-Epinions1-subgraph.png'
if (sub_graph_name == "cit-HepPh-subgraph"):
#Plotting clustering coefficient
snap.PlotClustCf(cit_heph_subgraph, "cit-Heph-subgraph",
"Undirected graph - clustering coefficient")
print "Clustering coefficient distribution of cit-HepPh-subgraph is in :" + 'ccf.cit-Heph-subgraph.png'
if (sub_graph_name == "email-Enron-subgraph"):
#Plotting clustering coefficient
snap.PlotClustCf(email_enron_subgraph, "email-Enron-subgraph",
"Undirected graph - clustering coefficient")
print "Clustering coefficient distribution of email-Enron-subgraph is in :" + 'ccf.email-Enron-subgraph.png'
if (sub_graph_name == "p2p-Gnutella04-subgraph"):
#Plotting clustering coefficient
snap.PlotClustCf(p2p_gnutella04_subgraph, "p2p-Gnutella04-subgraph",
"Undirected graph - clustering coefficient")
snap.PlotShortPathDistr(graph, "temp", "Undirected graph - shortest path")
os.system("mv diam.temp.png plots/shortest_path_" + subgraph_name + ".png")
os.system("rm diam.*")
print("Fraction of nodes in largest connected component:",
round(snap.GetMxSccSz(graph), 4))
print("Number of edge bridges:", get_bridges(graph).Len())
print("Number of articulation points:",
get_articulation_points(graph).Len())
snap.PlotSccDistr(graph, "temp", "Undirected graph - scc distribution")
os.system("mv scc.temp.png plots/connected_comp_" + subgraph_name + ".png")
os.system("rm scc.*")
print("Average clustering coefficient:", round(snap.GetClustCf(graph), 4))
print("Number of triads:", snap.GetTriads(graph))
random_node = graph.GetRndNId()
print("Clustering coefficient of random node", random_node, ":",
round(get_each_nodes_ClusteringCofficient(graph)[random_node], 4))
random_node = graph.GetRndNId()
print("Number of triads random node", random_node, "participates:",
snap.GetNodeTriads(graph, random_node))
print("Number of edges that participate in at least one triad:",
snap.GetTriadEdges(graph))
snap.PlotClustCf(graph, "temp",
"Undirected graph - clustering coefficient")
os.system("mv ccf.temp.png plots/clustering_coeff_" + subgraph_name +
".png")
os.system("rm ccf.*")
def Clust(): return snap.PlotClustCf(Graph, "ScaleFreeClustCf", "Undirected graph - clustering coefficient")
#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
print("Number of triads random node " + str(RnId) + " participates:",
snap.GetNodeTriads(fbsgel, RnId))
#e
print("Number of edges that participate in at least one triad:",
snap.GetTriadEdges(fbsgel, -1))
#f Plot
snap.PlotClustCf(fbsgel, "clustering_coeff_" + str(subgraph_name),
"clustering_coeff_" + str(subgraph_name))
## 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)))
## Random Clustering Coefficient
rndNode = graph.GetRndNId()
print("Clustering coefficient of random node {}: {:0.4f}".format(
rndNode, sn.GetNodeClustCf(graph, rndNode)))
## Random node triads
rndNode = graph.GetRndNId()
print("Number of triads random node {} participates: {}".format(
rndNode, sn.GetNodeTriads(graph, rndNode)))
## Edges in Triads
print("Number of edges that participate in at least one triad: {}".format(
sn.GetTriadEdges(graph)))
## Plot Clustering Coefficient
sn.PlotClustCf(graph, name, "Clustering Coefficient Distribution")
plotRemove("ccf", "clustering_coeff", name)
