def computeClusteringCoeff(G, NodeAttributes):
NIdCCfH = snap.TIntFltH()
snap.GetNodeClustCf(G, NIdCCfH)
ClusterCoeffList = list()
for nodeId in NIdCCfH:
NodeAttributes[nodeId]['ClusterCoeff'] = NIdCCfH[nodeId]
ClusterCoeffList.append((nodeId, NIdCCfH[nodeId]))
ClusterCoeffList.sort(key=lambda x: x[1], reverse=True)
minClusterCoeff = min(ClusterCoeffList, key=lambda x: x[1])[1]
maxClusterCoeff = max(ClusterCoeffList, key=lambda x: x[1])[1]
#
# Sanity Check
#
print ClusterCoeffList[1], maxClusterCoeff, ClusterCoeffList[
-1], minClusterCoeff
NIdCCfH = snap.TIntFltH()
snap.GetNodeClustCf(G, NIdCCfH)
ClusterCoeffList = list()
for nodeId in NIdCCfH:
clusterCoeff = NIdCCfH[nodeId]
normClusterCoeff = (clusterCoeff - minClusterCoeff) / (
maxClusterCoeff - minClusterCoeff)
NodeAttributes[nodeId]['NormClusterCoeff'] = normClusterCoeff
#print NodeAttributes[2012]
return NodeAttributes
def get_hits_venues():
mapping = snap.TStrIntSH()
t0 = time()
file_output_1 = open("paper_venues_hits_hub.txt", 'w')
file_output_2 = open("paper_venues_hits_auth.txt", 'w')
G0 = snap.LoadEdgeListStr(snap.PNGraph, "paperid_venueid_ref.txt", 0, 1,
mapping)
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(G0, NIdHubH, NIdAuthH, 1000)
print("HITS time:", round(time() - t0, 3), "s")
for item in NIdHubH:
file_output_1.write(
str(mapping.GetKey(item)) + "," + str(NIdHubH[item]) + '\n')
for item in NIdAuthH:
file_output_2.write(
str(mapping.GetKey(item)) + "," + str(NIdAuthH[item]) + '\n')
# convert input string to node id
# NodeId = mapping.GetKeyId("814DF491")
# convert node id to input string
# NodeName = mapping.GetKey(NodeId)
# print "name", NodeName
# print "id ", NodeId
print("finish hits!")
file_output_1.close()
file_output_2.close()
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 getNodeAttributes(self,UGraph):
attriList=[]
for index in range(UGraph.GetNodes()):
nodelist=[]
attriList.append(nodelist)
#page rank
PRankH = snap.TIntFltH()
snap.GetPageRank(UGraph, PRankH)
counter=0
for item in PRankH:
attriList[counter].append(PRankH[item])
counter+=1
#HIN
counter=0
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(UGraph, NIdHubH, NIdAuthH)
for item in NIdHubH:
attriList[counter].append(NIdHubH[item])
attriList[counter].append(NIdAuthH[item])
counter+=1
# Betweenness Centrality
counter=0
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
snap.GetBetweennessCentr(UGraph, Nodes, Edges, 1.0)
for node in Nodes:
attriList[counter].append(Nodes[node])
counter+=1
# closeness centrality
counter=0
for NI in UGraph.Nodes():
CloseCentr = snap.GetClosenessCentr(UGraph, NI.GetId())
attriList[counter].append(CloseCentr)
counter+=1
# farness centrality
counter=0
for NI in UGraph.Nodes():
FarCentr = snap.GetFarnessCentr(UGraph, NI.GetId())
attriList[counter].append(FarCentr)
counter+=1
# node eccentricity
counter=0
for NI in UGraph.Nodes():
attriList[counter].append(snap.GetNodeEcc(UGraph, NI.GetId(), True))
counter+=1
atrriMarix=np.array(attriList)
return atrriMarix
def hits(graph_filename):
# create graph
name_id_map = snap.TStrIntSH()
graph = snap.LoadEdgeListStr(snap.PNGraph, graph_filename, 0, 1,
name_id_map)
# run HITS algo
id_hub_map = snap.TIntFltH()
id_auth_map = snap.TIntFltH()
snap.GetHits(graph, id_hub_map, id_auth_map, 1000) # iterate 1000 times
return name_id_map, id_hub_map, id_auth_map
def getUndirAttribute(filename, node_num, weighted=None, param=1.0):
UGraph = snap.LoadEdgeList(snap.PUNGraph, filename, 0, 1)
attributeNames = [
'Graph', 'Id', 'Degree', 'NodeBetweennessCentrality', 'PageRank',
'EgonetDegree', 'AvgNeighborDeg', 'EgonetConnectivity'
]
if weighted:
attributeNames += [
'WeightedDegree', 'EgoWeightedDegree', 'AvgWeightedNeighborDeg',
'EgonetWeightedConnectivity'
]
attributes = pd.DataFrame(np.zeros((node_num, len(attributeNames))),
columns=attributeNames)
attributes['Graph'] = [filename.split('/')[-1].split('.')[0]
] * node_num #node_num
# Degree
attributes['Id'] = range(0, node_num)
degree = np.zeros((node_num, ))
OutDegV = snap.TIntPrV()
snap.GetNodeOutDegV(UGraph, OutDegV)
for item in OutDegV:
degree[item.GetVal1()] = item.GetVal2()
attributes['Degree'] = degree
getEgoAttr(UGraph, node_num, attributes, directed=False)
if weighted:
df = getWeightedDegree(filename, node_num, attributes, directed=False)
getWeightedEgoAttr(UGraph, node_num, attributes, df, directed=False)
# Betweenness Centrality
betCentr = np.zeros((node_num, ))
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
snap.GetBetweennessCentr(UGraph, Nodes, Edges, param)
for node in Nodes:
betCentr[node] = Nodes[node]
attributes['NodeBetweennessCentrality'] = betCentr
# PageRank
pgRank = np.zeros((node_num, ))
PRankH = snap.TIntFltH()
snap.GetPageRank(UGraph, PRankH)
for item in PRankH:
pgRank[item] = PRankH[item]
attributes['PageRank'] = pgRank
return attributes
def compute_hub_authority_score(self, graph):
# A hash table of int keys and float values (output).
# The keys are the node ids and the values are the hub scores as outputed by the HITS algorithm.
# Type: snap.TIntFltH
hub_scores = snap.TIntFltH()
# A hash table of int keys and float values (output)
# The keys are the node ids and the values are the authority scores as outputed by the HITS algorithm.
# Type: snap.TIntFltH
authority_scores = snap.TIntFltH()
snap.GetHits(graph, hub_scores, authority_scores)
return hub_scores, authority_scores
def GetOverlap(filePathName, Graph, t):
# l is here the final ranking of the nodes
# Intially, we just put all the nodes in this
# and afterwards we sort it
l = [i for i in range(Graph.GetNodes())]
# The reference vector whose information is used to sort l
ref_vect = [0 for i in range(Graph.GetNodes())]
# if Type 1, then fill ref_vect with closeness centrality measure
if (t == 1):
for NI in Graph.Nodes():
ref_vect[NI.GetId()] = snap.GetClosenessCentr(Graph, NI.GetId())
# if Type 2, then fill ref_vect with betweenness centrality measure
if (t == 2):
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
# Setting NodeFrac parameter as 0.8 as instructed
snap.GetBetweennessCentr(Graph, Nodes, Edges, 0.8)
for node in Nodes:
ref_vect[node] = Nodes[node]
# if Type 3, then fill ref_vect with PageRank scores
if (t == 3):
PRankH = snap.TIntFltH()
# Taking the limit as 1e-6 as used in gen_centrality.py
snap.GetPageRank(Graph, PRankH, 0.8, 1e-6, 100)
for item in PRankH:
ref_vect[item] = PRankH[item]
# Now we sort l using the ref_vect
l.sort(
key=cmp_to_key(lambda item1, item2: ref_vect[item2] - ref_vect[item1]))
# make a set containing top 100 nodes of l
S1 = set(l[:100])
# make another set containing top 100 nodes from the text files
S2 = set()
f = open(filePathName, 'r')
for _ in range(100):
s = f.readline()
a, b = s.split()
S2.add(int(a))
# return the number of overlaps in S1 and S2
return len(S1.intersection(S2))
def calc_HubAndAuthorityScores(Graph, node_to_g):
## calculate Hub and Authority scores for nodes in the graph.
prot_to_hub = {}
prot_to_authority = {}
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(Graph, NIdHubH, NIdAuthH)
for node in NIdHubH:
my_prot = node_to_g[node]
prot_to_hub[my_prot] = NIdHubH[node]
for node in NIdAuthH:
my_prot = node_to_g[node]
prot_to_authority[my_prot] = NIdAuthH[node]
return (prot_to_hub, prot_to_authority)
def HITS(G):
NIdHubH = snap.TIntFltH()
NIdAuthH = snap.TIntFltH()
snap.GetHits(G, NIdHubH, NIdAuthH)
max = 0.0
for item in NIdHubH:
if NIdHubH[item] > max:
max = NIdHubH[item]
print item, NIdHubH[item]
max = 0.0
for item in NIdAuthH:
if NIdAuthH[item] > max:
max = NIdAuthH[item]
print item, NIdAuthH[item]
def pageRank(rankCommands, Graph, conn, cur):
PRankH = snap.TIntFltH()
before_time = time.time()
snap.GetPageRank(Graph, PRankH)
print "Total handling time is: ", (time.time() - before_time)
slist = sorted(PRankH, key=lambda key: PRankH[key], reverse=True)
createTable(rankCommands, slist, PRankH, conn, cur)
def get_ev_centr_sum(G, n1, n2, reset=False):
global NIdEigenH
if reset or NIdEigenH is None:
print 'Initializing EV Centrality...'
NIdEigenH = snap.TIntFltH()
snap.GetEigenVectorCentr(G, NIdEigenH, 1e-2, 50)
return NIdEigenH[n1] + NIdEigenH[n2]
def generate_scores(self):
scores = {}
common_neighbor_scores = {}
for e in self.g.Edges():
# common_neighbor_scores[(e.GetSrcNId(), e.GetDstNId())] = snap.GetCmnNbrs(self.g, e.GetSrcNId(), e.GetDstNId())
n1 = snap.TIntV()
n2 = snap.TIntV()
snap.GetNodesAtHop(self.g, e.GetSrcNId(), 1, n1, True)
snap.GetNodesAtHop(self.g, e.GetDstNId(), 1, n2, True)
common_neighbor_scores[(e.GetSrcNId(), e.GetDstNId())] = len(set(n1) & set(n2))
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
snap.GetBetweennessCentr(self.g, Nodes, Edges, self.node_frac, True)
edge_betweenness_scores = {}
for e in Edges:
edge_betweenness_scores[(e.GetVal1(), e.GetVal2())] = Edges[e]
max_cn = max(common_neighbor_scores.values())
max_eb = max(edge_betweenness_scores.values())
print(common_neighbor_scores)
print(edge_betweenness_scores)
for e in self.g.Edges():
src = e.GetSrcNId()
dst = e.GetDstNId()
scores[(src, dst)] = self.l * common_neighbor_scores[(src,dst)] / max_cn + (1-self.l) * edge_betweenness_scores[(src,dst)] / max_eb
return scores
def computeBetweenessCentrality(G, NodeAttributes):
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
BetweenessNodeList = list()
BetweenessEdgeList = list()
snap.GetBetweennessCentr(G, Nodes, Edges, 1.0)
for node in Nodes:
NodeAttributes[node]['Betweeness'] = Nodes[node]
BetweenessNodeList.append((node, Nodes[node]))
for edge in Edges:
#print "edge: (%d, %d) centrality: %f" % (edge.GetVal1(), edge.GetVal2(), Edges[edge])
BetweenessEdgeList.append(
(edge.GetVal1(), edge.GetVal2(), Edges[edge]))
BetweenessNodeList.sort(key=lambda x: x[1], reverse=True)
BetweenessEdgeList.sort(key=lambda x: x[2], reverse=True)
#print BetweenessNodeList[0], BetweenessNodeList[-1]
minBetweeness = BetweenessNodeList[-1][1]
maxBetweeness = BetweenessNodeList[0][1]
for (node, betweeness) in BetweenessNodeList:
normBetweeness = (betweeness - minBetweeness) / (maxBetweeness -
minBetweeness)
NodeAttributes[node]['normBetweeness'] = normBetweeness
#print NodeAttributes[1669]
#print NodeAttributes[884]
return NodeAttributes
def get_page_rank_sum(G, n1, n2, reset=False):
global PRankH
if reset or PRankH is None:
print 'Initializing Page Rank'
PRankH = snap.TIntFltH()
snap.GetPageRank(G, PRankH, 1e-2, 50)
return PRankH[n1] + PRankH[n2]
def nodes_centrality_page_rank():
PRankH = snap.TIntFltH()
snap.GetPageRank(G, PRankH)
sorted_PRankH = sorted(PRankH, key=lambda key: PRankH[key], reverse=True)
# print top n nodes with highest PageRank
for item in sorted_PRankH[0:5]: #top 5
print(item, PRankH[item])
def CalculateClusteringCoefficient(graph):
#output={}
NIdCCfH = snap.TIntFltH()
snap.GetNodeClustCf(graph, NIdCCfH)
print "CLUSTERRING COEFFICIENT"
for item in NIdCCfH:
print "Node %d th have coefficient %f" % (item, NIdCCfH[item])
def RW_iteration(graph, PRankH, C=0.85):
# Performs one Random Walk
PRankH_temp = snap.TIntFltH()
# Step 1: calculate new page ranks from in-nodes
# This new page rank is 'dampened' by a factor C, usually about 0.85
for i in PRankH:
node_id = i.GetKey()
PR = get_in_node_PR_weight(graph, node_id, PRankH)
PRankH_temp.AddDat(node_id, PR * C)
# Step 2: The total rank lost to leakage is calculated (sum)
# The leaked value is then apportioned to all nodes by adding leakage/|N| to each node
sum = diff = NewVal = 0.00
for i in PRankH_temp:
sum += i.GetDat()
leaked = (1 - sum)/float(graph.GetNodes())
for i in PRankH:
NewVal = PRankH_temp(i.GetKey()) + leaked
diff += abs(PRankH(i.GetKey()) - NewVal)
PRankH.AddDat(i.GetKey(), NewVal)
print diff
# Return value is the 'difference' in value between the new PRs and the old ones.
# After this value goes below some threshold, we will want to stop iterating random walks
return diff
def PageRank(d, e):
f = open(d)
s = f.read()
s1 = re.split('\n', s)
G1 = snap.PNGraph.New()
PRankH = snap.TIntFltH()
a = re.split(' ', s1[0])
for i in range(0, int(a[0])):
G1.AddNode(i)
for i in range(1, int(a[1]) + 1):
b = re.split(' ', s1[i])
b0 = re.sub("\D", "", b[0])
b1 = re.sub("\D", "", b[1])
G1.AddEdge(int(b0), int(b1))
snap.GetPageRank(G1, PRankH)
EdgePara = dict()
for i in range(1, int(a[1]) + 1):
c = re.split(' ', s1[i])
if PRankH[int(c[0])] == 0 and PRankH[int(c[1])] == 0:
EdgePara[(int(c[0]), int(c[1]))] == 0
EdgePara[(int(c[1]), int(c[0]))] == 0
else:
EdgePara[(int(c[0]), int(c[1]))] = e * PRankH[int(
c[0])] / (PRankH[int(c[0])] + PRankH[int(c[1])])
EdgePara[(int(c[1]), int(c[0]))] = e * PRankH[int(
c[1])] / (PRankH[int(c[0])] + PRankH[int(c[1])])
return EdgePara
def get_betweenness_centr(net, label, outpath):
"""
get betweenness centrality.
:param net:
:param label:
:param outpath:
:return:
"""
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
snap.GetBetweennessCentr(net, Nodes, Edges, 1.0)
node_betweenness_centr_file = open(outpath + label + '-node_btweennesss_centr', 'w')
node_betweenness_centr_top_file = open(outpath + label + '-node_betweenness_centr-top100', 'w')
node_betweenness_centr = {}
for item in Nodes:
node_betweenness_centr[item] = Nodes[item]
node_betweenness_centr = sorted(node_betweenness_centr.items(), key=operator.itemgetter(1), reverse=True)
id, value = zip(*node_betweenness_centr)
for i in range(len(id)):
node_betweenness_centr_file.write(str(id[i]) + '\t' + str(value[i]) + '\n')
for i in range(100):
node_betweenness_centr_top_file.write(str(id[i]) + '\t' + str(value[i]) + '\n')
node_betweenness_centr_file.close()
node_betweenness_centr_top_file.close()
return id, value
def CalculatePageRank(graph, alpha, number_iteration):
PRankH = snap.TIntFltH()
snap.GetPageRank(graph, PRankH, alpha, 1e-4, number_iteration)
output = {}
for item in PRankH:
output[item] = PRankH[item]
return output
def compute_betwenness_centrality(self, graph):
nodes_betweenness_centrality = snap.TIntFltH()
edges_betweenness_centrality = snap.TIntPrFltH()
snap.GetBetweennessCentr(graph, nodes_betweenness_centrality,
edges_betweenness_centrality, 1.0)
return nodes_betweenness_centrality, edges_betweenness_centrality
def getCentr(self, centrMethod):
nodesKeysCentrVals = snap.TIntFltH()
for node in self.G.Nodes():
centrValue = centrMethod(self.G, node.GetId())
nodesKeysCentrVals[node.GetId()] = centrValue
return nodesKeysCentrVals
def rank_eigvec(self):
""" Return dictionary of node ID and its eigenvector
centrality score, in score order """
NIdEigenH = snap.TIntFltH()
snap.GetEigenVectorCentr(self._graph, NIdEigenH)
assert len(NIdEigenH) == self._num_nodes, 'Number of nodes in centrality result must match number of nodes in graph'
return snap_hash_to_dict(NIdEigenH)
def compute_page_rank(graph):
logging.info("compute pagerank")
PRankH = snap.TIntFltH()
snap.GetPageRank(graph, PRankH)
for item in PRankH:
print item, PRankH[item]
return PRankH
def rank_pagerank(self , C=0.85, Eps=1e-4, MaxIter=100):
""" Return dictionary of node ID and its pagerank
centrality score, in score order """
PRankH = snap.TIntFltH()
snap.GetPageRank(self._graph, PRankH, C, Eps, MaxIter)
assert len(PRankH) == self._num_nodes, 'Number of nodes in centrality result must match number of nodes in graph'
return snap_hash_to_dict(PRankH)
def getBetweennessCentr(self):
nodesKeyCentrVals = snap.TIntFltH()
edgesKeyCentrVals = snap.TIntPrFltH()
snap.GetBetweennessCentr(self.G, nodesKeyCentrVals, edgesKeyCentrVals,
1.0)
return nodesKeyCentrVals
def betweenness_test(name):
if os.path.isfile(DATA_PATH + name + ".between"):
print "Skipping", name
return
start = time.time()
G, coords = osmParser.simpleLoadFromFile(name)
print "Calculating betweenness", name
nodeToBetweenness = snap.TIntFltH()
edgeToBetweenness = snap.TIntPrFltH()
snap.GetBetweennessCentr(G, nodeToBetweenness, edgeToBetweenness, 0.25)
betweenness = {}
for node in nodeToBetweenness:
betweenness[node] = nodeToBetweenness[node]
betweenOut = open(DATA_PATH + name + ".between", 'w')
pickle.dump(betweenness, betweenOut, 1)
plotTopK(name, betweenness, coords, "GnBu")
end = time.time()
print "took", end - start, "seconds"
def pageRank_components(g):
print 'executing pagerank components ---- getting components for page rank'
Components = snap.TCnComV()
snap.GetWccs(g, Components)
f = open('component_pr.txt', 'w')
cgraphs = []
for com in Components:
v = snap.TIntV()
for ni in com:
v.Add(ni)
cgraphs.append(snap.GetSubGraph_PNGraph(g, v))
print 'components retrived for pagerank'
f.write('Total components:' + str(len(cgraphs)) + '\n')
for graph in cgraphs:
if graph.GetNodes() == 2:
continue
sprank = snap.TIntFltH()
snap.GetPageRank_PNGraph(graph, sprank)
sprank.SortByDat(False)
f.write(
str(graph.GetNodes()) + ' ' + str(sprank[sprank.BegI().GetKey()]) +
'\n')
f.close()
print 'finished writing pagerank components values'
def get_top_packages(graph_path, n):
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))
# snap.py doesn't suport absolute paths for some operations. Let's cd to the directory
os.chdir(directory)
# print("{0} Computing top {0} nodes with highest pagerank".format(n, datetime.datetime.now()))
data_file = graph_name + "_pageranks"
prank_hashtable = snap.TIntFltH()
if not os.path.isfile(data_file):
# 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, n)
top_n.sort(key=itemgetter(1))
top_packages = []
for pair in top_n:
top_packages.append(id_pkg_dict[pair[0]])
return top_packages