-
Notifications
You must be signed in to change notification settings - Fork 1
/
utils_citeseer_pubmed.py
129 lines (102 loc) · 4.37 KB
/
utils_citeseer_pubmed.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
import numpy as np
import scipy.sparse as sp
import torch
import sys
import pickle as pkl
import networkx as nx
def encode_onehot(labels):
classes = set(labels)
classes_dict = {c: np.identity(len(classes))[i, :] for i, c in enumerate(classes)}
labels_onehot = np.array(list(map(classes_dict.get, labels)), dtype=np.int32)
return labels_onehot
def load_data(dataset_str = 'citeseer'):
names = ['x', 'y', 'tx', 'ty', 'allx', 'ally', 'graph']
objects = []
for i in range(len(names)):
with open("./data/ind.{}.{}".format(dataset_str, names[i]), 'rb') as f:
if sys.version_info > (3, 0):
objects.append(pkl.load(f, encoding='latin1'))
else:
objects.append(pkl.load(f))
x, y, tx, ty, allx, ally, graph = tuple(objects)
test_idx_reorder = parse_index_file("./data/ind.{}.test.index".format(dataset_str))
test_idx_range = np.sort(test_idx_reorder)
if dataset_str == 'citeseer':
print('loading citeseet dataset')
# 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
ty_extended = np.zeros((len(test_idx_range_full), y.shape[1]))
ty_extended[test_idx_range-min(test_idx_range), :] = ty
ty = ty_extended
features = sp.vstack((allx, tx)).tolil()
features[test_idx_reorder, :] = features[test_idx_range, :]
#print('graph element', i, graph[i])
#adj = nx.adjacency_matrix(nx.from_dict_of_lists(graph))
labels = np.vstack((ally, ty))
labels[test_idx_reorder, :] = labels[test_idx_range, :]
# idx_train = range(len(y))
# idx_val = range(len(y), len(y)+500)
# idx_test = range(len(y) + 500, len(y) + 1500)#test_idx_range.tolist()
#print('idx train', idx_train)
#print('idx val', idx_val)
#print('idx test', idx_test)
# train_mask = sample_mask(idx_train, labels.shape[0])
# val_mask = sample_mask(idx_val, labels.shape[0])
# test_mask = sample_mask(idx_test, labels.shape[0])
# y_train = np.zeros(labels.shape)
# y_val = np.zeros(labels.shape)
# y_test = np.zeros(labels.shape)
# y_train[train_mask, :] = labels[train_mask, :]
# y_val[val_mask, :] = labels[val_mask, :]
# y_test[test_mask, :] = labels[test_mask, :]
#print('adj before', adj)
#adj = normalize_adj(adj + sp.eye(adj.shape[0]))
features = normalize_features(features)
#print('dense', np.array(adj.todense())[0])
#adj = torch.FloatTensor(np.array(adj.todense()))
features = torch.FloatTensor(np.array(features.todense()))
labels = torch.LongTensor(np.where(labels)[1])
# idx_train = torch.LongTensor(idx_train)
# idx_val = torch.LongTensor(idx_val)
# idx_test = torch.LongTensor(idx_test)
return features, labels
def normalize_adj(mx):
"""Row-normalize sparse matrix"""
rowsum = np.array(mx.sum(1))
r_inv_sqrt = np.power(rowsum, -0.5).flatten()
r_inv_sqrt[np.isinf(r_inv_sqrt)] = 0.
r_mat_inv_sqrt = sp.diags(r_inv_sqrt)
return mx.dot(r_mat_inv_sqrt).transpose().dot(r_mat_inv_sqrt)
def normalize_features(mx):
"""Row-normalize sparse matrix"""
rowsum = np.array(mx.sum(1))
r_inv = np.power(rowsum, -1).flatten()
r_inv[np.isinf(r_inv)] = 0.
r_mat_inv = sp.diags(r_inv)
mx = r_mat_inv.dot(mx)
return mx
def accuracy(output, labels):
preds = output.max(1)[1].type_as(labels)
correct = preds.eq(labels).double()
correct = correct.sum()
return correct / len(labels)
def parse_index_file(filename):
"""Parse index file."""
index = []
for line in open(filename):
index.append(int(line.strip()))
return index
def sample_mask(idx, l):
"""Create mask."""
mask = np.zeros(l)
mask[idx] = 1
return np.array(mask, dtype=np.bool)
if __name__ == "__main__":
adj, features, labels, idx_train, idx_val, idx_test = load_data('citeseer')
print('features size', features.size())
print('adj size', adj.size())
print('label size', labels.size())