-
Notifications
You must be signed in to change notification settings - Fork 18
/
Copy pathpreprocessing.py
122 lines (103 loc) · 4.25 KB
/
preprocessing.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
import numpy as np
import scipy.sparse as sp
# ------------------------------------
# Some functions borrowed from:
# https://github.com/tkipf/pygcn and
# https://github.com/tkipf/gcn
# ------------------------------------
def sparse_to_tuple(sparse_mx):
if not sp.isspmatrix_coo(sparse_mx):
sparse_mx = sparse_mx.tocoo()
coords = np.vstack((sparse_mx.row, sparse_mx.col)).transpose()
values = sparse_mx.data
shape = sparse_mx.shape
return coords, values, shape
def preprocess_graph(adj):
adj = sp.coo_matrix(adj)
adj_ = adj + sp.eye(adj.shape[0])
rowsum = np.array(adj_.sum(1))
degree_mat_inv_sqrt = sp.diags(np.power(rowsum, -0.5).flatten())
adj_normalized = adj_.dot(degree_mat_inv_sqrt).transpose().dot(
degree_mat_inv_sqrt).tocoo()
return adj_normalized
def construct_feed_dict(adj_normalized, adj, features, placeholders):
# construct feed dictionary
feed_dict = dict()
feed_dict.update({placeholders['features']: features})
feed_dict.update({placeholders['adj']: adj_normalized})
feed_dict.update({placeholders['adj_orig']: adj})
return feed_dict
def mask_test_edges(adj):
# Function to build test set with 10% positive links
# NOTE: Splits are randomized and results might slightly deviate from reported numbers in the paper.
# TODO: Clean up.
# Remove diagonal elements
adj = adj - \
sp.dia_matrix((adj.diagonal()[np.newaxis, :], [0]), shape=adj.shape)
adj.eliminate_zeros()
# Check that diag is zero:
assert np.diag(adj.todense()).sum() == 0
adj_triu = sp.triu(adj)
adj_tuple = sparse_to_tuple(adj_triu)
edges = adj_tuple[0]
edges_all = sparse_to_tuple(adj)[0]
num_test = int(np.floor(edges.shape[0] / 10.))
num_val = int(np.floor(edges.shape[0] / 20.))
all_edge_idx = list(range(edges.shape[0]))
np.random.shuffle(all_edge_idx)
val_edge_idx = all_edge_idx[:num_val]
test_edge_idx = all_edge_idx[num_val:(num_val + num_test)]
test_edges = edges[test_edge_idx]
val_edges = edges[val_edge_idx]
train_edges = np.delete(edges, np.hstack(
[test_edge_idx, val_edge_idx]), axis=0)
def ismember(a, b, tol=5):
rows_close = np.all(np.round(a - b[:, None], tol) == 0, axis=-1)
return (np.all(np.any(rows_close, axis=-1), axis=-1) and
np.all(np.any(rows_close, axis=0), axis=0))
test_edges_false = []
while len(test_edges_false) < len(test_edges):
idx_i = np.random.randint(0, adj.shape[0])
idx_j = np.random.randint(0, adj.shape[0])
if idx_i == idx_j:
continue
if ismember([idx_i, idx_j], edges_all):
continue
if test_edges_false:
if ismember([idx_j, idx_i], np.array(test_edges_false)):
continue
if ismember([idx_i, idx_j], np.array(test_edges_false)):
continue
test_edges_false.append([idx_i, idx_j])
val_edges_false = []
while len(val_edges_false) < len(val_edges):
idx_i = np.random.randint(0, adj.shape[0])
idx_j = np.random.randint(0, adj.shape[0])
if idx_i == idx_j:
continue
if ismember([idx_i, idx_j], train_edges):
continue
if ismember([idx_j, idx_i], train_edges):
continue
if ismember([idx_i, idx_j], val_edges):
continue
if ismember([idx_j, idx_i], val_edges):
continue
if val_edges_false:
if ismember([idx_j, idx_i], np.array(val_edges_false)):
continue
if ismember([idx_i, idx_j], np.array(val_edges_false)):
continue
val_edges_false.append([idx_i, idx_j])
assert ~ismember(test_edges_false, edges_all)
assert ~ismember(val_edges_false, edges_all)
assert ~ismember(val_edges, train_edges)
assert ~ismember(test_edges, train_edges)
assert ~ismember(val_edges, test_edges)
data = np.ones(train_edges.shape[0])
# Re-build adj matrix
adj_train = sp.csr_matrix(
(data, (train_edges[:, 0], train_edges[:, 1])), shape=adj.shape)
adj_train = adj_train + adj_train.T
# NOTE: these edge lists only contain single direction of edge!
return adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false