-
Notifications
You must be signed in to change notification settings - Fork 78
/
utils.py
189 lines (157 loc) · 6.83 KB
/
utils.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
import pickle as pkl
import networkx as nx
import numpy as np
import scipy.sparse as sp
import torch
from sklearn.metrics import roc_auc_score, average_precision_score
def load_data(dataset):
# load the data: x, tx, allx, graph
names = ['x', 'tx', 'allx', 'graph']
objects = []
for i in range(len(names)):
'''
fix Pickle incompatibility of numpy arrays between Python 2 and 3
https://stackoverflow.com/questions/11305790/pickle-incompatibility-of-numpy-arrays-between-python-2-and-3
'''
with open("data/ind.{}.{}".format(dataset, names[i]), 'rb') as rf:
u = pkl._Unpickler(rf)
u.encoding = 'latin1'
cur_data = u.load()
objects.append(cur_data)
# objects.append(
# pkl.load(open("data/ind.{}.{}".format(dataset, names[i]), 'rb')))
x, tx, allx, graph = tuple(objects)
test_idx_reorder = parse_index_file(
"data/ind.{}.test.index".format(dataset))
test_idx_range = np.sort(test_idx_reorder)
if dataset == 'citeseer':
# Fix citeseer dataset (there are some isolated nodes in the graph)
# Find isolated nodes, add them as zero-vecs into the right position
test_idx_range_full = range(
min(test_idx_reorder), max(test_idx_reorder) + 1)
tx_extended = sp.lil_matrix((len(test_idx_range_full), x.shape[1]))
tx_extended[test_idx_range - min(test_idx_range), :] = tx
tx = tx_extended
features = sp.vstack((allx, tx)).tolil()
features[test_idx_reorder, :] = features[test_idx_range, :]
features = torch.FloatTensor(np.array(features.todense()))
adj = nx.adjacency_matrix(nx.from_dict_of_lists(graph))
return adj, features
def parse_index_file(filename):
index = []
for line in open(filename):
index.append(int(line.strip()))
return index
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 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.any(rows_close)
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
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 sparse_to_tuple(adj_normalized)
return sparse_mx_to_torch_sparse_tensor(adj_normalized)
def sparse_mx_to_torch_sparse_tensor(sparse_mx):
"""Convert a scipy sparse matrix to a torch sparse tensor."""
sparse_mx = sparse_mx.tocoo().astype(np.float32)
indices = torch.from_numpy(
np.vstack((sparse_mx.row, sparse_mx.col)).astype(np.int64))
values = torch.from_numpy(sparse_mx.data)
shape = torch.Size(sparse_mx.shape)
return torch.sparse.FloatTensor(indices, values, shape)
def get_roc_score(emb, adj_orig, edges_pos, edges_neg):
def sigmoid(x):
return 1 / (1 + np.exp(-x))
# Predict on test set of edges
adj_rec = np.dot(emb, emb.T)
preds = []
pos = []
for e in edges_pos:
preds.append(sigmoid(adj_rec[e[0], e[1]]))
pos.append(adj_orig[e[0], e[1]])
preds_neg = []
neg = []
for e in edges_neg:
preds_neg.append(sigmoid(adj_rec[e[0], e[1]]))
neg.append(adj_orig[e[0], e[1]])
preds_all = np.hstack([preds, preds_neg])
labels_all = np.hstack([np.ones(len(preds)), np.zeros(len(preds_neg))])
roc_score = roc_auc_score(labels_all, preds_all)
ap_score = average_precision_score(labels_all, preds_all)
return roc_score, ap_score