-
Notifications
You must be signed in to change notification settings - Fork 72
/
utils.py
68 lines (51 loc) · 2.09 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
import numpy as np
import scipy.sparse as sp
import h5py
import torch
from torch.utils.data import Dataset
def load_graph(dataset, k):
if k:
path = 'graph/{}{}_graph.txt'.format(dataset, k)
else:
path = 'graph/{}_graph.txt'.format(dataset)
data = np.loadtxt('data/{}.txt'.format(dataset))
n, _ = data.shape
idx = np.array([i for i in range(n)], dtype=np.int32)
idx_map = {j: i for i, j in enumerate(idx)}
edges_unordered = np.genfromtxt(path, dtype=np.int32)
edges = np.array(list(map(idx_map.get, edges_unordered.flatten())),
dtype=np.int32).reshape(edges_unordered.shape)
adj = sp.coo_matrix((np.ones(edges.shape[0]), (edges[:, 0], edges[:, 1])),
shape=(n, n), dtype=np.float32)
# build symmetric adjacency matrix
adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj)
adj = adj + sp.eye(adj.shape[0])
adj = normalize(adj)
adj = sparse_mx_to_torch_sparse_tensor(adj)
return adj
def normalize(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 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)
class load_data(Dataset):
def __init__(self, dataset):
self.x = np.loadtxt('data/{}.txt'.format(dataset), dtype=float)
self.y = np.loadtxt('data/{}_label.txt'.format(dataset), dtype=int)
def __len__(self):
return self.x.shape[0]
def __getitem__(self, idx):
return torch.from_numpy(np.array(self.x[idx])),\
torch.from_numpy(np.array(self.y[idx])),\
torch.from_numpy(np.array(idx))