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
|
# cython: boundscheck=False, cdivision=True
import numpy as np
cimport numpy as np
from libc.math cimport log, exp
DTYPE = np.float64
ctypedef np.float_t DTYPE_t
cdef DTYPE_t weight_success(int dist, int dt, DTYPE_t alpha, DTYPE_t delta, DTYPE_t lmbda,
DTYPE_t w1, DTYPE_t w2, DTYPE_t w3):
"""weight for successful infection, exponential time model"""
cdef DTYPE_t structural, temporal, result
structural = delta ** dist
# structural = delta/(1. + 1./(w1*lmbda) + 1./(w2*lmbda) + 1./(w3*lmbda))
temporal = log(exp(alpha)-1.) - alpha*dt
# temporal = 1. / (1. + (dt - 1.)/alpha)**0.01 - 1. / (1. + dt/alpha)**0.01
result = log(structural) + temporal
return result
cdef DTYPE_t weight_failure(int dist, int dt, DTYPE_t alpha, DTYPE_t delta, DTYPE_t lmbda,
DTYPE_t w1, DTYPE_t w2, DTYPE_t w3):
"""weight for failed infection, exponential time model"""
cdef DTYPE_t structural, temporal, result
structural = delta ** dist
# structural = delta/(1. + 1./(w1*lmbda) + 1./(w2*lmbda) + 1./(w3*lmbda))
temporal = exp(-alpha * dt)
# temporal = 1. - 1. / (1. + dt/alpha)**0.01
result = log(1. - structural + structural * temporal)
return result
def ml2(dict root_victims, dict victims, dict non_victims,
DTYPE_t alpha, DTYPE_t delta, DTYPE_t lmbda):
cdef:
int n_roots, n_victims, roots, i, dist, dt, t, l
DTYPE_t ll
list parents, failures, successes
n_roots, n_victims = len(root_victims), len(victims)
cdef:
np.ndarray[DTYPE_t] probs = np.zeros(n_victims, dtype=DTYPE)
np.ndarray[DTYPE_t] probs_fail = np.zeros(n_victims, dtype=DTYPE)
np.ndarray[DTYPE_t] probs_nv = np.zeros(len(non_victims), dtype=DTYPE)
np.ndarray[DTYPE_t] parent_dists = np.zeros(n_victims, dtype=DTYPE)
np.ndarray[DTYPE_t] parent_dts = np.zeros(n_victims, dtype=DTYPE)
np.ndarray[DTYPE_t] infectors = np.zeros(n_victims, dtype=DTYPE)
# loop through victims
for i, parents in enumerate(victims.itervalues()):
# for each victim node i, compute the probability that all its parents
# fail to infect it, also computes the probability that its most
# likely parent infects it
failures = [weight_failure(dist, dt, alpha, delta, lmbda, w1, w2, w3)
for (prnt, dist, dt, w1, w2, w3) in parents]
probs_fail[i] = sum(failures)
successes = [weight_success(dist, dt, alpha, delta, lmbda, w1, w2, w3)
for (prnt, dist, dt, w1, w2, w3) in parents]
dists = [dist for (prnt, dist, dt, w1, w2, w3) in parents]
dts = [dt for (prnt, dist, dt, w1, w2, w3) in parents]
prnts = [prnt for (prnt, dist, dt, w1, w2, w3) in parents]
# find parent that maximizes log(p) - log(\tilde{p})
# probs[i] = max(s - failures[l] for l, s in enumerate(successes))
probs[i] = float("-inf")
for l, s in enumerate(successes):
prob = s - failures[l]
if prob > probs[i]:
probs[i] = prob
infectors[i] = prnts[l]
parent_dists[i] = dists[l]
parent_dts[i] = dts[l]
# loop through non-victims
for i, parents in enumerate(non_victims.itervalues()):
# for each non victim node, compute the probability that all its
# parents fail to infect it
failures = [weight_failure(dist, dt, alpha, delta, lmbda, w1, w2, w3)
for (prnt, dist, dt, w1, w2, w3) in parents]
probs_nv[i] = sum(failures)
# calculate log likelihood
ll = probs_fail.sum() # add probability that all edges to victims fail
ll += probs_nv.sum() # add probability that all edges to non_victims fail
ll += probs.sum() # add probability for realized edges and subtract probability these edges fail
roots = n_roots
# print n_nodes, n_roots, n_victims, max_i, roots
# print parent_dists[1:100]
# print parent_dts[1:100]
# print victims.keys()
# print infectors
# print np.mean(parent_dists)
# print np.mean(parent_dts)
with open('../../Results/infectors.csv', 'w') as infectors_file:
for i, infector in enumerate(infectors):
infectors_file.write("%s, %s\n" % ((victims.keys())[i], infector))
return (lmbda, roots, ll)
|
