-
Notifications
You must be signed in to change notification settings - Fork 19
/
node2vec.py
executable file
·150 lines (127 loc) · 4.47 KB
/
node2vec.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
# Leverage Node2vec for random walks
from __future__ import print_function
import numpy as np
import networkx as nx
import random
class Graph():
def __init__(self, nx_G, is_directed, p, q):
self.G = nx_G
self.is_directed = is_directed
self.p = p
self.q = q
def node2vec_walk(self, walk_length, start_node):
G = self.G
alias_nodes = self.alias_nodes
alias_edges = self.alias_edges
walk = [start_node]
while len(walk) < walk_length:
cur = walk[-1]
cur_nbrs = sorted(G.neighbors(cur))
if len(cur_nbrs) > 0:
if len(walk) == 1:
walk.append(
cur_nbrs[alias_draw(alias_nodes[cur][0], alias_nodes[cur][1])])
else:
prev = walk[-2]
next = cur_nbrs[alias_draw(alias_edges[(prev, cur)][0],
alias_edges[(prev, cur)][1])]
walk.append(next)
else:
break
return walk
def simulate_walks(self, num_walks, walk_length):
'''
Repeatedly simulate random walks from each node.
'''
G = self.G
walks = []
nodes = list(G.nodes())
print('simulating random walk...')
for walk_iter in range(num_walks):
print(str(walk_iter + 1), '/', str(num_walks))
random.shuffle(nodes)
for node in nodes:
walks.append(self.node2vec_walk(
walk_length=walk_length, start_node=node))
return walks
def get_alias_edge(self, src, dst):
'''
Get the alias edge setup lists for a given edge.
'''
G = self.G
p = self.p
q = self.q
unnormalized_probs = []
for dst_nbr in sorted(G.neighbors(dst)):
if dst_nbr == src:
unnormalized_probs.append(G[dst][dst_nbr]['weight'] / p)
elif G.has_edge(dst_nbr, src):
unnormalized_probs.append(G[dst][dst_nbr]['weight'])
else:
unnormalized_probs.append(G[dst][dst_nbr]['weight'] / q)
norm_const = sum(unnormalized_probs)
normalized_probs = [
float(u_prob) / norm_const for u_prob in unnormalized_probs]
return alias_setup(normalized_probs)
def preprocess_transition_probs(self):
'''
Preprocessing of transition probabilities for guiding the random walks.
'''
G = self.G
is_directed = self.is_directed
alias_nodes = {}
for node in G.nodes():
unnormalized_probs = [G[node][nbr]['weight']
for nbr in sorted(G.neighbors(node))]
norm_const = sum(unnormalized_probs)
normalized_probs = [
float(u_prob) / norm_const for u_prob in unnormalized_probs]
alias_nodes[node] = alias_setup(normalized_probs)
alias_edges = {}
if is_directed:
for edge in G.edges():
alias_edges[edge] = self.get_alias_edge(edge[0], edge[1])
else:
for edge in G.edges():
alias_edges[edge] = self.get_alias_edge(edge[0], edge[1])
alias_edges[(edge[1], edge[0])] = self.get_alias_edge(
edge[1], edge[0])
self.alias_nodes = alias_nodes
self.alias_edges = alias_edges
def alias_setup(probs):
'''
Compute utility lists for non-uniform sampling from discrete distributions.
Refer to https://hips.seas.harvard.edu/blog/2013/03/03/the-alias-method-efficient-sampling-with-many-discrete-outcomes/
for details
'''
K = len(probs)
q = np.zeros(K)
J = np.zeros(K, dtype=np.int)
smaller = []
larger = []
for kk, prob in enumerate(probs):
q[kk] = K * prob
if q[kk] < 1.0:
smaller.append(kk)
else:
larger.append(kk)
while len(smaller) > 0 and len(larger) > 0:
small = smaller.pop()
large = larger.pop()
J[small] = large
q[large] = q[large] + q[small] - 1.0
if q[large] < 1.0:
smaller.append(large)
else:
larger.append(large)
return J, q
def alias_draw(J, q):
'''
Draw sample from a non-uniform discrete distribution using alias sampling.
'''
K = len(J)
kk = int(np.floor(np.random.rand() * K))
if np.random.rand() < q[kk]:
return kk
else:
return J[kk]