Newer
Older
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
"""
Affect of Lambda
Dataset-1
"""
import numpy as np
import pandas as pd
import utils
import sbm_core
import math
from itertools import combinations
import itertools
from sklearn.metrics.cluster import adjusted_rand_score
# Initilaize
np.random.seed(107)
num_roles=2
num_vertices=25
num_segments = 2
NO_SAMPLES= 95
group_assignment= np.random.randint(num_roles, size=(num_vertices))
nodes = np.arange(num_vertices)
list_of_groups= [[] for _ in range(num_roles)]
for idx, val in enumerate(group_assignment):
list_of_groups[val].append(nodes[idx])
print(list_of_groups)
size_all_pairs = {}
for k in range(0, num_roles):
for g in range(k, num_roles):
U=list_of_groups[k]
W=list_of_groups[g]
if k == g:
size_all_pairs[k,g] = math.comb(len(U), 2)
if k != g:
size_all_pairs[k,g] = len(U)*len(W)
lamda_arr = np.ones((num_roles, num_roles,num_segments) , dtype=float)
lamda_arr = 1e-1* np.random.randint(1,9, size=(num_roles, num_roles,num_segments))
#set value for each iteration ( 0 - 8 )
_itr = 8
_itr = 0
yu = (9-_itr)*.1
lamda_arr[0,0]=[yu, 0.1]
lamda_arr[0,1]= [0.1, yu]
lamda_arr[1,0]=lamda_arr[0,1]
lamda_arr[1,1]=[yu, yu]
lamda_arr_act = np.zeros((num_roles, num_roles,num_segments) , dtype=float)
change_points_arr = np.zeros((num_roles, num_roles, num_segments+1) , dtype=int)
df_all= None
points= list(range(0, (num_segments+1)*NO_SAMPLES, NO_SAMPLES))
list1 = []
# Generate piecewise non-homogeneous poisson process
for k in range(0, num_roles):
for g in range(k, num_roles):
comb = []
if k == g:
comb = list(combinations(list_of_groups[k], 2))
# print(type(comb))
else:
# comb = []
key_data = [list_of_groups[k],list_of_groups[g],]
comb = list(itertools.product(*key_data))
# print(comb)
if len(comb) != size_all_pairs[k,g]:
print('not equal..')
change_points_arr[k,g,:] = points
lamda_arr[k,g,:] = lamda_arr[g,k,:]
tot_count = np.zeros((num_segments) , dtype=float)
for pair in comb:
for d in range(0,num_segments):
s = np.random.poisson(lamda_arr[k,g,d], NO_SAMPLES)
# print(np.count_nonzero(s))
tot_count[d] += np.count_nonzero(s)
list1=[i for i, e in enumerate(s) if e != 0]
if len(list1) == 0:
print('zero')
list1 = [x+points[d] for x in list1]
df = pd.DataFrame(data=list1)
df.columns =['timestamp']
N= df.size
list_start_stations =[pair[0]] * N
list_end_stations =[pair[1]] * N
df['source'] = list_start_stations
df['target'] = list_end_stations
df_all=pd.concat([df_all, df], ignore_index=True)
for d in range(0,num_segments):
lamda_arr_act[k,g,d] = tot_count[d]/(NO_SAMPLES*len(comb))
# print(tot_count[d])
## Other preparations
# Remove self loops
df_all = df_all[((df_all['source'] ) != (df_all['target']))]
#sort
df_all=df_all.sort_values('timestamp')
df_all = df_all[['target', 'timestamp','source']]
# Save as .csv file
# df_all.to_csv('./Data/synthetic_ground_truth_g1.csv')
df=df_all
dest_folder='./Results/synthetic/3'
t_df = df['timestamp']
nodes_arr = np.union1d(df['target'],df['source']).astype(int)
# list of nodes
nodes = nodes_arr.tolist()
num_vertices = len(nodes)
# node-group dictionary
group_dic = {}
keys = nodes
values = list(group_assignment)
group_dic = dict(zip(keys,values))
# create a new dictionary - key: node-pair , value: list of timestamps
dic=df.groupby(['source','target'])['timestamp'].apply(list).to_dict()
print('{} {} {} '.format(group_dic, lamda_arr_act,change_points_arr))
liklihood_sum = sbm_core.compute_cost(group_dic,lamda_arr_act,change_points_arr,num_roles,num_segments,dic)
print(' Initial Actual likelihood .......%f'%liklihood_sum)
def _swap (row):
if row['source'] > row['target']:
row['source'] , row['target'] =row['target'] , row['source']
return row
# Undirected graph
df=df.apply(lambda row: _swap(row), axis=1)
#scale timestamps for zeroth reference point
refValue = df['timestamp'].min()
df['timestamp'] -= refValue
# Experiment
import experiment
# User parameters
num_roles=2
num_segments=2
num_levels=2# Optional arg
algo_ver=3
dest_folder='./Results/synthetic/'
# tuning parameters
theta = 0
eta = 1
tuning_params= {'theta':theta,'eta':eta}
import time
start_time = time.time()
exp_obj = experiment.Experiment(df,num_roles,num_segments,algo_ver,dest_folder,tuning_params,num_levels,refValue)
[itr_d,likelihood_d,group_dic_d,lambda_estimates_d,change_points_arr_d] = exp_obj.execute()
print("--- %s seconds ---" % (time.time() - start_time))
t_df = sorted(t_df)
chg_points = change_points_arr_d[0,0,:]
ranges_arr = [ [chg_points[s]+1,chg_points[s+1]] for s in range(0,len(chg_points)-1)]
ranges_arr[0][0] = 0
list_time_stamps = list(t_df)
# iterate over timestamps list
dis_arr = list()
gt_arr = list()
for item in list_time_stamps:
# find the segment which the timestamp belongs
# (is dependent on which groups the two nodes belong)
d = sbm_core._findSegment(ranges_arr, len(ranges_arr) , int(item))
dis_arr.append(d)
chg_points = change_points_arr[0,0,:]
ranges_arr = [ [chg_points[s]+1,chg_points[s+1]] for s in range(0,len(chg_points)-1)]
ranges_arr[0][0] = 0
list_time_stamps = list(t_df)
# iterate over timestamps list
for item in list_time_stamps:
# find the segment which the timestamp belongs
# (is dependent on which groups the two nodes belong)
d = sbm_core._findSegment(ranges_arr, len(ranges_arr) , int(item))
gt_arr.append(d)
ind = adjusted_rand_score(gt_arr,dis_arr)
print('rand index: seg {} : {}'.format(_itr, ind))
g1= group_dic_d
g2= group_dic_d[1]
ds= list(group_dic_d.values() )
gt1 = list(g1.values())
ind_grp=adjusted_rand_score(ds,gt1)
print('rand index: group {} : {}'.format(_itr, ind_grp))
# likelihood for single group and single segment # Normlaized likelihood
# num_roles=1
# num_segments=1
# num_levels=1
# exp_obj = experiment.Experiment(df,num_roles,num_segments,algo_ver,dest_folder,tuning_params,num_levels,refValue)
# exp_obj.execute()
# 0.9757628970136779
# 0.9766007299178403
# 0.976928378298833
# 0.9768191326709813
# 0.9786828903097778
# 0.9762078453564311
# 0.9731767168042805
# 0.9753286095154328
# 0.5773249110735138
# 3
# 3
# 2
# 3
# 3
# 3
# 3
# 4
# 4