-
Notifications
You must be signed in to change notification settings - Fork 3
/
grandom.py
396 lines (345 loc) · 11.4 KB
/
grandom.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
#-*- coding:utf-8 -*-
__author__ = 'Peng<liupeng@gxnu.edu.cn>'
from scipy import stats
from scipy import sparse
import numpy as np
import pylab as pl
import matplotlib.pyplot as plt
from gfile import *
from rsel import *
import networkx as nx
import random
import string
import math
#-------------------------------------------------------------------------------------------------------
def r_perturbS(g,p=None):
'''固定参数的随机扰动方法,p伯努利实验成功的概率'''
A=nx.to_scipy_sparse_matrix(g)
B=sparse.triu(A).toarray()
#print B
n=len(g)
e_num=len(g.edges())#图中存在的边数
q = e_num * (1 - p) / ((n * (n - 1)) / 2 - e_num)
#print q
i = 0
ts=0
while i<n:
j=i+1#略过对角线上的0
while j<n:
if(B[i,j]==1):
B[i,j] = stats.bernoulli.rvs(p)#参数p伯努利实验成功的概率
ts=ts + 1
# print "+",ts, ":", i, ",", j, ",", B[i, j]
else:
B[i,j] = stats.bernoulli.rvs(q)#参数q伯努利实验成功的概率
ts=ts + 1
# print "-",ts, ":", i, ",", j, ",", B[i, j]
j = j + 1
i=i+1
return nx.from_numpy_matrix(B,create_using=nx.Graph())#重新构建了Graph类型的返回对象
#-------------------------------------------------------------------------------------------------------
def r_perturbSa(g,p=None):
'''固定参数的随机扰动方法,p伯努利实验成功的概率'''
A=nx.to_scipy_sparse_matrix(g)
B=sparse.triu(A).toarray()
#print B
n=len(g)
e_num=len(g.edges())#图中存在的边数
q = e_num * (1 - p) / ((n * (n - 1)) / 2 - e_num)
#print q
i = 0
ts=0
listp=stats.bernoulli.rvs(p,size=e_num)
listp=listp.tolist()
listq=stats.bernoulli.rvs(q,size=(n * (n - 1)) / 2 - e_num)
listq=listq.tolist()
while i<n:
j=i+1#略过对角线上的0
while j<n:
if(B[i,j]==1):
B[i,j] = listp.pop()#参数p伯努利实验成功的概率
#ts=ts + 1
# print "+",ts, ":", i, ",", j, ",", B[i, j]
else:
B[i,j] = listq.pop()#参数q伯努利实验成功的概率
#ts=ts + 1
# print "-",ts, ":", i, ",", j, ",", B[i, j]
j = j + 1
i=i+1
return nx.from_numpy_matrix(B,create_using=nx.Graph())#重新构建了Graph类型的返回对象
#-------------------------------------------------------------------------------------------------------
def binomial_vdiS(z,v,g,p):
"""z 是节点的度,node节点的标签,g图,p边仍然存在的概率 """
n = len(g)
N=(n*(n-1))/2
e_num = len(g.edges()) # 图中存在的边数
q = e_num * (1 - p) / ((n * (n - 1)) / 2 - e_num)
di = len(g[v])
sum = 0.0
t = 0
while t <= di:
sum = sum + stats.binom.pmf(t, di, p) * stats.binom.pmf(z-t,N-di, q)
t += 1
return sum
#-------------------------------------------------------------------------------------------------------
def riskS(v,g,p):
"""v是节点,g是图,p边仍然存在的概率,输入为点v被重识别的概率
"""
di=len(g[v])
b=binomial_vdiS(di, v, g, p)
tsum=0
for each in g:
tsum=tsum+binomial_vdiS(di, each, g, p)
return b/tsum
#-------------------------------------------------------------------------------------------------------
def cal_pS(g, pr):
"""g图,pr要求的隐私保护力度"""
p=0.05
for each in g:
if riskS(each, g, p)>pr:
while 1:
p=p+0.05
print 'v=',each,'p=',p,'r=',riskS(each, g, p)
if riskS(each, g, p) < pr or p > 0.95:
break
return p
#-------------------------------------------------------------------------------------------------------
def cal_pSa(g, pr):
"""g图,pr要求的隐私保护力度"""
p=1
for each in g:
if riskS(each, g, p)>pr:
while 1:
p=p-0.05
print 'v=',each,'p=',p,'r=',riskS(each, g, p)
if riskS(each, g, p) < pr or p<0.05:
break
return p
#-------------------------------------------------------------------------------------------------------
def r_perturbR(g,R):
'''可变参数的随机扰动方法'''
A=nx.to_scipy_sparse_matrix(g)
B=sparse.triu(A).toarray()
#print B
n=len(g)
i = 0
ts=0
while i<n:
j=i+1
while j<n:
if(B[i,j]==1):
if R[i,j]<1:
B[i,j] = stats.bernoulli.rvs(R[i,j])#参数p伯努利实验成功的概率
else:
B[i, j] = stats.bernoulli.rvs(1) #其实可以去掉
ts=ts + 1
#print "+",ts, ":", i, ",", j, ",", B[i, j]
else:
if R[i,j]<1:
B[i,j] = stats.bernoulli.rvs(R[i,j])#参数q伯努利实验成功的概率
else:
B[i, j] = stats.bernoulli.rvs(0) #其实可以去掉
ts=ts + 1
#print "-",ts, ":", i, ",", j, ",", B[i, j]
j = j + 1
i=i+1
return nx.from_numpy_matrix(B,create_using=nx.Graph())#重新构建了Graph类型的返回对象
# -------------------------------------------------------------------------------------------------------
def gRa(g, w):
'''w为图中的边数,表示经过减边p扰动后仍然留在数据中的边数'''
tg = g.copy()
Rq = nx.to_scipy_sparse_matrix(g)
Rq = Rq.toarray()
bw = nx.edge_betweenness_centrality(g, normalized=False)
norm = sum(bw.values())
e_num = len(g.edges())
n = len(g)
N = (n * (n - 1)) / 2
for k, v in bw.items():
g.add_edge(*k, weight=v)
# print g.edges(data=True)
R = nx.to_scipy_sparse_matrix(g, weight='weight')
Rp = R.toarray()
Rp = w * Rp * 2.0 / Rp.sum()
q = float(e_num - w) / (N - e_num)
for i, each in enumerate(Rq):
for j, e in enumerate(each):
if e == 0:
Rp[i, j] = q # 超级绕采用特别方式在Rp中加入Rq
for i in range(n):
Rp[i,i]=0 #去除对角线上的q
return Rp
def normal_vdiR(z, v, g, Rp):
"""z 是节点的度,v节点的标签,Rp是扰动将矩阵 """
n = len(g)
di = len(g[v])
i=g.nodes().index(v)
mvar=0
for each in Rp[i]:
each=(each if each<1 else 1)
mvar=mvar+each*(1-each)
X=stats.norm(di,mvar)
sum=X.cdf(z+0.5)-X.cdf(z-0.5)
return sum
#-------------------------------------------------------------------------------------------------------
def riskR(v,g,R):
"""v是节点,R是扰动将矩阵,输出为点v被重识别的概率
"""
di=len(g[v])
b=normal_vdiR(di, v, g, R)
tsum=0
for each in g:
tsum=tsum+normal_vdiR(di, each, g, R)
return b/tsum
#-------------------------------------------------------------------------------------------------------
def cal_pR(g, pr):
"""g图,pr要求的隐私保护力度"""
w=len(g.edges())
w=math.ceil(w*0.8)
step=math.ceil(0.05*w)
R=gRa(g, w)
for each in g:
if riskR(each, g, R)>pr:
while 1:
w=w-step
R = gRa(g, w)
print 'v=',each,'w=',w,'r=',riskR(each, g, R)
if riskR(each, g, R) < pr or w<step:
break
return w
def cal_pRv(v,g,pr):
w=len(g.edges())
w=math.ceil(w*0.9)
step=math.ceil(0.05*w)
R=gRa(g, w)
if riskR(v, g, R) > pr:
while 1:
w = w - step
R = gRa(g, w)
print 'v=', v, 'w=', w, 'r=', riskR(v, g, R)
if riskR(v, g, R) < pr or w < step:
break
return w
def t_facebook_cc(path=r"d:\data\facebook1.txt"):
rstr = ''
g = nx.Graph()
g = read_file_txt(g, path)
w = [1945, 1294, 860, 643]
for each in w:
R=gRa(g,each)
pg=r_perturbR(g, R)
rstr=rstr+'{0:8},{1:10.4}'.format(each,nx.average_clustering(pg))
rstr=rstr+'\n'
try:
path=path.replace('book1','book1_cc')
f=open(path, 'w')
except:
print "int readFileTxt open error"
p = np.array(w)/4813.0
for each in p:
pg=r_perturbS(g, each)
rstr=rstr+'{0:8},{1:10.4}'.format(each,nx.average_clustering(pg))
rstr=rstr+'\n'
f.write(rstr)
f.close()
def t_GrQc_cc(path=r"d:\data\CA-GrQc.txt"):
rstr = ''
g = nx.Graph()
g = read_file_txt(g, path)
w = [14496,13454,12394,9782]
for each in w:
R=gRa(g,each)
pg=r_perturbR(g, R)
rstr=rstr+'{0:8},{1:10.4}'.format(each,nx.average_clustering(pg))
rstr=rstr+'\n'
try:
path=path.replace('GrQc','GrQc_cc')
f=open(path, 'w')
except:
print "int readFileTxt open error"
p = np.array(w)/14496.0
for each in p:
pg=r_perturbS(g, each)
rstr=rstr+'{0:8},{1:10.4}'.format(each,nx.average_clustering(pg))
rstr=rstr+'\n'
f.write(rstr)
f.close()
def t_Gnutella_cc(path=r"d:\data\p2p-Gnutella08.txt"):
rstr = ''
g = nx.Graph()
g = read_file_txt(g, path)
w = [20777,18700,17995,17023]
for each in w:
R=gRa(g,each)
pg=r_perturbR(g, R)
rstr=rstr+'{0:8},{1:10.4}'.format(each,nx.average_clustering(pg))
rstr=rstr+'\n'
try:
path=path.replace('p2p-Gnutella','GrQcp2p-Gnutella_cc')
f=open(path, 'w')
except:
print "int Create File error"
p = np.array(w)/20777.0
for each in p:
pg=r_perturbS(g, each)
rstr=rstr+'{0:8},{1:10.4}'.format(each,nx.average_clustering(pg))
rstr=rstr+'\n'
f.write(rstr)
f.close()
def t_t_cc(path=r"d:\data\9.txt"):
rstr = ''
g = nx.Graph()
g = read_file_txt(g, path)
w = [14,13,12,6]
print nx.average_clustering(g)
for each in w:
R=gRa(g,each)
pg=r_perturbR(g, R)
rstr=rstr+'{0:8},{1:10.4}'.format(each,nx.average_clustering(pg))
rstr=rstr+'\n'
try:
path=path.replace('9','9_cc')
f=open(path, 'w')
except:
print "int Create File error"
p = np.array(w)/14.0
for each in p:
pg=r_perturbS(g, each)
rstr=rstr+'{0:8},{1:10.4}'.format(each,nx.average_clustering(pg))
rstr=rstr+'\n'
f.write(rstr)
f.close()
if __name__=='__main__':
print 'in grandom'
g=nx.Graph()
# g = read_file_txt(g,r"E:\data\facebook1.txt")
#g = read_file_txt(g, r"d:\data\facebook1.txt")
#g = read_file_txt(g,r"d:\data\Cora.txt")
g = read_file_txt(g,r"d:\data\CA-GrQc.txt")
da(g)
# p=0.7
#r=RPerturbS(g,p)
# for v in g:
# print "z:",v,"=",riskS(v,g,p)
#print cal_pSa(g,0.3)
# x=gRa(g,6)
# for each in g:
# print each, riskR(each,g,x)
# for p in np.arange(0.1,0.4,0.1):
# print cal_pRv('3830',g,p)
# print len(g.nodes())
# print len(g.edges())
# print nx.average_clustering(g)
ds=nx.degree_centrality(g)
dd=sorted(ds.items(),key=lambda item: item[1], reverse=True)
print ds
print dd
# d=nx.degree(g)
# print d
# print sorted(d.items(),key=lambda item:item[1],reverse=True)
# bw = nx.edge_betweenness_centrality(g, normalized=False)
# print bw
#t_facebook_cc(path=r"d:\data\facebook1.txt")
#t_GrQc_cc(path=r"d:\data\CA-GrQc.txt")
#t_t_cc(path=r"d:\data\9.txt")
#DrawGraph(r)