def net_structure(dataset_dir, output_dir, net, IsDir, weight):
print(
"\n######################################################################\n"
)
if os.path.isfile(str(output_dir) + str(net) + "_connected_comp.json"):
print("Arquivo já existe: " + str(output_dir) + str(net) +
"_connected_comp.json")
else:
print("Componentes conectados - " + str(dataset_dir))
cc = [
] # Vetor com tamanho de todos os componentes conectados por modelo
cc_normal = [
] # Vetor com tamanho de todos os componentes conectados por modelo - Cada tamanho é normalizado pelo número de vértices da rede em que está o componente.
n_cc = [] # Número de componentes conectados por modelo
i = 0
for file in os.listdir(dataset_dir):
i += 1
print(
str(output_dir) + str(net) + "/" + str(file) +
" - Calculando propriedades para o ego " + str(i) + ": " +
str(file))
if IsDir is True:
G = snap.LoadEdgeList(
snap.PNGraph, dataset_dir + file, 0, 1
) # load from a text file - pode exigir um separador.: snap.LoadEdgeList(snap.PNGraph, file, 0, 1, '\t')
else:
G = snap.LoadEdgeList(
snap.PUNGraph, dataset_dir + file, 0, 1
) # load from a text file - pode exigir um separador.: snap.LoadEdgeList(snap.PNGraph, file, 0, 1, '\t')
# G.Dump()
# time.sleep(5)
#####################################################################################
n_nodes = G.GetNodes() # Número de vértices
n_edges = G.GetEdges() # Número de arestas
#####################################################################################
if n_edges == 0:
a = 0
cc.append(a)
cc_normal.append(a)
print("Nenhuma aresta encontrada para a rede-ego " + str(i) +
" - (" + str(file))
else:
Components = snap.TCnComV()
snap.GetWccs(G, Components)
n_cc.append(len(Components))
for CnCom in Components:
cc.append(CnCom.Len())
b = float(CnCom.Len()) / float(n_nodes)
cc_normal.append(b)
N_CC = calc.calcular_full(
n_cc
) # Número de componentes conectados dividido pelo número de egos, pra saber a média de componentes conectados por ego.
CC = calc.calcular_full(cc)
CC_NORMAL = calc.calcular_full(cc_normal)
overview = {}
overview['Len_ConnectedComponents'] = CC
overview['Len_ConnectedComponents_Normal'] = CC_NORMAL
overview['N_ConnectedComponents'] = N_CC
with open(str(output_dir) + str(net) + "_connected_comp.json",
'w') as f:
f.write(json.dumps(overview))
with open(str(output_dir) + str(net) + "_connected_comp.txt",
'w') as f:
f.write(
"\n######################################################################\n"
)
f.write(
"Number_Connected_Comp: Média: %5.3f -- Var:%5.3f -- Des. Padrão: %5.3f \n"
% (N_CC['media'], CC['variancia'], N_CC['desvio_padrao']))
f.write(
"Length_Connected_Comp: Média: %5.3f -- Var:%5.3f -- Des. Padrão: %5.3f \n"
% (CC['media'], CC['variancia'], CC['desvio_padrao']))
f.write(
"Length_Connected_Comp_Normalized: Média: %5.3f -- Var:%5.3f -- Des. Padrão: %5.3f \n"
% (CC_NORMAL['media'], CC_NORMAL['variancia'],
CC_NORMAL['desvio_padrao']))
f.write(
"\n######################################################################\n"
)
print(
"\n######################################################################\n"
)
print(
"Number_Connected_Comp: Média: %5.3f -- Var:%5.3f -- Des. Padrão: %5.3f \n"
% (N_CC['media'], CC['variancia'], N_CC['desvio_padrao']))
print(
"Length_Connected_Comp: Média: %5.3f -- Var:%5.3f -- Des. Padrão: %5.3f \n"
% (CC['media'], CC['variancia'], CC['desvio_padrao']))
print(
"Length_Connected_Comp_Normalized: Média: %5.3f -- Var:%5.3f -- Des. Padrão: %5.3f \n"
% (CC_NORMAL['media'], CC_NORMAL['variancia'],
CC_NORMAL['desvio_padrao']))
print(
"\n######################################################################\n"
)
# pickle_out.close()
# pickle_out = open(USERID_SET_PICKLE_PATH,"wb")
# pickle.dump(userid_set, pickle_out)
# pickle_out.close()
# pickle_out = open(POSTID_SET_PICKLE_PATH,"wb")
# pickle.dump(postid_set, pickle_out)
# pickle_out.close()
# # ### Fold Bipartite Graphs to create User-id and Post-id Graphs
# # In[40]:
# # Load the graphs in SNAP.
userid_ngram_bipartite_graph = snap.LoadEdgeList(snap.PUNGraph,
USERID_NGRAM_TSV_PATH, 0, 1)
postid_ngram_bipartite_graph = snap.LoadEdgeList(snap.PUNGraph,
POSTID_NGRAM_TSV_PATH, 0, 1)
# # In[44]:
# # Load pickled datastructures.
ngramid_dict = pickle.load(open(NGRAMID_DICT_PICKLE_PATH, "rb"))
userid_set = pickle.load(open(USERID_SET_PICKLE_PATH, "rb"))
postid_set = pickle.load(open(POSTID_SET_PICKLE_PATH, "rb"))
# # In[42]:
# # Basic userid ngram bipartite graph statistics.
# print "Nodes", userid_ngram_bipartite_graph.GetNodes()
# print "Edges", userid_ngram_bipartite_graph.GetEdges()
import snap
import matplotlib.pyplot as plt
# Global Variable
betweeness = 0
ModularityList = []
CommunityList = []
CheckModularity = 0
# Load File Data
Graphkarateclub = snap.LoadEdgeList(snap.PUNGraph, "karateclub.txt", 0, 1)
GraphkarateclubMaintainForDeleteEdges = snap.LoadEdgeList(
snap.PUNGraph, "karateclub.txt", 0, 1)
# Display Nodes and Edges of Graph
TotalNumberOfNodes = Graphkarateclub.GetNodes()
TotalBumberOfEdges = Graphkarateclub.GetEdges()
print("Total # of Nodes in Graph %d", TotalNumberOfNodes)
print("Total # of Edges in Graph %d", TotalBumberOfEdges)
# Iterate No. Of Edges time
while GraphkarateclubMaintainForDeleteEdges.GetEdges() != 0:
betweennessList = []
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
''' Compute the edge betweeness of all the edges in the graph '''
snap.GetBetweennessCentr(GraphkarateclubMaintainForDeleteEdges, Nodes,
Edges, 1.0)
# Prepare BetweenessList Of List
for edge in Edges:
betweennessSubList = [edge.GetVal1(), edge.GetVal2(), Edges[edge]]
list_prank = []
for item in PRankH:
list_prank.append([item, PRankH[item]])
list_prank = sorted(list_prank, key=lambda x: x[1]) # Sort by page rank
remove_node = list_prank[: num_remove]
for node in remove_node:
graph.DelNode(node[0])
snap.SaveEdgeList(graph, edges_extracted_file)
# prepare_data("bigdata/friends_list.yaml", "bigdata/dict_bigdata.csv", "bigdata/edges_bigdata.csv")
edges_file = "edges_1000.csv"
num_nodes = 1000
graph_name = "graph-1000nodes.png"
extract_top_nodes("bigdata/edges_bigdata.csv", edges_file, num_nodes)
graph = snap.LoadEdgeList(snap.PUNGraph, edges_file, 0, 1, '\t')
# graph.Dump() #show graph information
list_comunity , modularity = comunityDetect(graph)
print ("list comunity: ", list_comunity)
print ("len list comunity: ", len(list_comunity))
print ("Modularity of the network: %f" % modularity)
# # visualize_graph(edges_file, graph_name, list_comunity)
from __future__ import division
import snap
import math
G = snap.LoadEdgeList(snap.PUNGraph, 'predict_delete.txt', 0, 1)
d_common = {}
d_jaccard = {}
d_adamic = {}
for N1 in G.Nodes():
#print node_list
for N2 in G.Nodes():
if ((int(N1.GetId()) < int(N2.GetId()))
and not ((N1.GetId() == N2.GetId()) or
(N1.IsNbrNId(N2.GetId())))):
node_list_all = set([])
value_adamic = 0
for Id in N1.GetOutEdges():
#save the neighbors
node_list_all.add(Id)
#sage the same neighbors of n1 and n2
node_list_same = set([])
for Id in N2.GetOutEdges():
#save the all neighbors of n1 and n2
if (Id in node_list_all):
node_list_same.add(Id)
node_list_n = set([])
for N_n in G.GetNI(Id).GetOutEdges():
def load(self):
graph = snap.LoadEdgeList(snap.PUNGraph, self.root, 0, 1,
self.separator)
return graph
p = r / r.sum()
# r = [random.uniform(0,1) for i in range(out_d)]
# sum_ = sum(r)
# p = [i/sum_ for i in r]
v = node_v.GetId()
for idx in range(node_v.GetInDeg()):
u = node_v.GetInNId(idx)
probs[(u, v)] = p[idx]
return probs
if __name__ == '__main__':
# load config
conf = Config()
sina_network = snap.LoadEdgeList(snap.PNEANet, conf.network_file)
with open(conf.edge_result, 'rb') as f:
edge_dist = pickle.load(f)
with open(conf.node_result, 'rb') as f:
node_dist = pickle.load(f)
print('Sampling probabilities...')
# Can use empty dict for sigma here, if choose deterministic
NodeStat.sample_probability(sina_network, 0, node_dist['mu'],
node_dist['sigma'])
EdgeStat.sample_probability(sina_network, 1, edge_dist['mu'],
edge_dist['sigma'])
# Rakshith Singh Assignment 1
import snap
#Helper function
def graph_info(graph):
for node in graph.Nodes():
print("node id", node.GetId(), " out degree ", node.GetOutDeg(),
" in degree ", node.GetInDeg())
wiki_graph = snap.LoadEdgeList(snap.PNGraph, "wiki-Vote.txt")
#graph_info(wiki_graph)
#Question 1 - The number of nodes in the network
number_nodes = wiki_graph.GetNodes()
print("Question 1 - Number of Nodes in the graph is ", number_nodes)
#Question 2 - The number of nodes with a self-edge (self-loop)
self_edge_nodes = 0
for edge in wiki_graph.Edges():
if edge.GetSrcNId() == edge.GetDstNId():
self_edge_nodes += 1
print("Question 2 - Number of Nodes with a self loop is ", self_edge_nodes)
#Question 3 - The number of directed edges in the network
directed_edges = wiki_graph.GetEdges()
print("Question 3 - Number of directed edges is ", directed_edges)
#Question 4 - The number of undirected edges in the network
import snap
import json
from sys import argv
script, directory, item = argv
graphList = ['Items','Users']
for graph in graphList:
G = snap.LoadEdgeList(snap.PUNGraph, directory + 'Edge_List_' + graph + '_' + item +'.txt', 0, 1, '\t')
dict1 = {}
PRankH = snap.TIntFltH()
snap.GetPageRank(G, PRankH)
for i in PRankH:
dict1[i] = PRankH[i]
with open(directory + 'Pagerank_' + graph + '_' + item +'.txt', 'w') as outfile1:
json.dump(dict1, outfile1)
dict2 = {}
NIdEigenH = snap.TIntFltH()
snap.GetEigenVectorCentr(G, NIdEigenH)
for i in NIdEigenH:
dict2[i] = NIdEigenH[i]
with open(directory + 'Eigen_Value_' + graph + '_' + item +'.txt', 'w') as outfile2:
json.dump(dict2, outfile2)
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
if __name__ == '__main__':
# parameters
# filepath = '../input/Test/toy_graph'
filepath = "/home/carlons/workspace_python/network_data_analysis/knowledge_graph/output/YAGO3/facts-id-pair"
label = "facts-id-pair"
outpath = './output/' + label + '/'
# check whether the output directory exists
if not os.path.exists(outpath):
os.mkdir(outpath)
net = snap.LoadEdgeList(snap.PNGraph, filepath, 0, 1)
paras = {'net': net, 'label': label, 'outpath': outpath}
get_pagerank(**paras)
get_hits(**paras)
net = snap.LoadEdgeList(snap.PUNGraph, filepath, 0, 1)
paras = {'net': net, 'label': label, 'outpath': outpath}
get_eigen_vector_centr(**paras)
# Main training loop
with tf.GradientTape() as tape:
for epoch in range(num_epochs):
print("Epoch {}".format(epoch))
optimizer.minimize(likelihood, var_list=kernels)
return kernels
if __name__ == '__main__':
# Run the main script
target_graph = 'ENZYMES_g123'
G = snap.LoadEdgeList(snap.PUNGraph,
target_graph + "/" + target_graph + ".txt", 0, 1,
' ')
print("Loaded {} with {} nodes".format(target_graph, G.GetNodes()))
kernel_sizes = [2, 3, 3, 5]
print('Finding the optimal kernels')
optimized_kernels = optimize(G, kernel_sizes)
final_graph = construct_graph(optimized_kernels)
generated = snap.TUNGraph.New()
for i in range(len(final_graph)):
generated.AddNode(i)
for i in range(len(final_graph)):
for j in range(i, len(final_graph)):
import snap
fw = open('results.txt', 'w')
# load the edge list using snap library
Graph = snap.LoadEdgeList(snap.PUNGraph, "data/edges.txt", 0, 1)
for NI in Graph.Nodes():
# calculate the closeness centrality value
closeness_value = snap.GetClosenessCentr(Graph, NI.GetId())
# write the results into a txt file
fw.write("Node:{0}, Value: {1} \n".format(NI.GetId(), closeness_value))
fw.flush()
fw.close()
def getDirAttribute(filename, node_num, weighted=None, param=1.0):
Graph = snap.LoadEdgeList(snap.PNGraph, filename, 0, 1)
attributeNames = [
'Graph', 'Id', 'Degree', 'InDegree', 'OutDegree',
'NodeBetweennessCentrality', 'PageRank', 'EgonetDegree',
'EgonetInDegree', 'EgonetOutDegree', 'AvgNeighborDeg',
'AvgNeighborInDeg', 'AvgNeighborOutDeg', 'EgonetConnectivity'
]
if weighted:
attributeNames += [
'WeightedDegree', 'WeightedInDegree', 'WeightedOutDegree',
'EgoWeightedDegree', 'AvgWeightedNeighborDeg',
'EgonetWeightedConnectivity', 'EgoWeightedInDegree',
'EgoWeightedOutDegree', 'AvgWeightedNeighborInDeg',
'AvgWeightedNeighborOutDeg'
]
attributes = pd.DataFrame(np.zeros((node_num, len(attributeNames))),
columns=attributeNames)
attributes['Graph'] = [filename.split('/')[-1].split('.')[0]] * node_num
attributes['Id'] = range(0, node_num)
# Degree
degree = np.zeros((node_num, ))
InDegV = snap.TIntPrV()
snap.GetNodeInDegV(Graph, InDegV)
for item in InDegV:
degree[item.GetVal1()] = item.GetVal2()
attributes['Degree'] += degree
attributes['InDegree'] = degree
degree = np.zeros((node_num, ))
OutDegV = snap.TIntPrV()
snap.GetNodeOutDegV(Graph, OutDegV)
for item in OutDegV:
degree[item.GetVal1()] = item.GetVal2()
attributes['Degree'] += degree
attributes['OutDegree'] = degree
getEgoAttr(Graph, node_num, attributes)
if weighted:
df = getWeightedDegree(filename, node_num, attributes, directed=True)
getWeightedEgoAttr(Graph, node_num, attributes, df, directed=True)
# Betweenness Centrality
betCentr = np.zeros((node_num, ))
Nodes = snap.TIntFltH()
Edges = snap.TIntPrFltH()
snap.GetBetweennessCentr(Graph, Nodes, Edges, param, True)
for node in Nodes:
betCentr[node] = Nodes[node]
attributes['NodeBetweennessCentrality'] = betCentr
# PageRank
pgRank = np.zeros((node_num, ))
PRankH = snap.TIntFltH()
snap.GetPageRank(Graph, PRankH)
for item in PRankH:
pgRank[item] = PRankH[item]
attributes['PageRank'] = pgRank
return attributes
#!/usr/bin/env python
from __future__ import division
import sys
import os
import snap
import math
file = sys.argv[1]
filename = file[:-9] + "er" + file[-10:]
inGraph = snap.LoadEdgeList(snap.PUNGraph, file, 0, 1)
nodes = inGraph.GetNodes()
edges = 0
with open(file, "r") as f:
for x in f:
edges += 1
print "nodes: %d, edges: %d" % (nodes, edges)
path = os.path.join(r"p3_data", filename[3:])
print "starting ER graph\n"
edgeList = []
UGraph = snap.GenRndGnm(snap.PUNGraph, nodes, edges)
for EI in UGraph.Edges():
edgeList.append([EI.GetSrcNId(), EI.GetDstNId()])
with open(path, "w") as f:
for x in edgeList:
f.write('{0:4d} {1:9d}\n'.format(x[0], x[1]))
print "finished ER graph\n"
