-
Notifications
You must be signed in to change notification settings - Fork 2
/
utils.py
269 lines (201 loc) · 9.2 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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
from __future__ import print_function
import scipy.sparse as sp
import numpy as np
from scipy.sparse.linalg.eigen.arpack import eigsh, ArpackNoConvergence
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(path="data/cora/", dataset="cora"):
"""Load citation network dataset (cora only for now)"""
print('Loading {} dataset...'.format(dataset))
idx_features_labels = np.genfromtxt("{}{}.content".format(path, dataset), dtype=np.dtype(str))
features = sp.csr_matrix(idx_features_labels[:, 1:-1], dtype=np.float32)
labels = encode_onehot(idx_features_labels[:, -1])
# build graph
idx = np.array(idx_features_labels[:, 0], dtype=np.int32)
idx_map = {j: i for i, j in enumerate(idx)}
edges_unordered = np.genfromtxt("{}{}.cites".format(path, dataset), 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=(labels.shape[0], labels.shape[0]), dtype=np.float32)
# build symmetric adjacency matrix
adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj)
# features = normalize_features(features)
# adj = normalize_adj(adj + sp.eye(adj.shape[0]))
print('Dataset has {} nodes, {} edges, {} features.'.format(adj.shape[0], edges.shape[0], features.shape[1]))
return features.todense(), adj, labels
def load_data_attention(path="data/cora/", dataset="cora"):
"""Load citation network dataset (cora only for now)"""
print('Loading {} dataset...'.format(dataset))
idx_features_labels = np.genfromtxt("{}{}.content".format(path, dataset), dtype=np.dtype(str))
features = sp.csr_matrix(idx_features_labels[:, 1:-1], dtype=np.float32)
labels = encode_onehot(idx_features_labels[:, -1])
# build graph
idx = np.array(idx_features_labels[:, 0], dtype=np.int32)
idx_map = {j: i for i, j in enumerate(idx)}
edges_unordered = np.genfromtxt("{}{}.cites".format(path, dataset), 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=(labels.shape[0], labels.shape[0]), dtype=np.float32)
# build symmetric adjacency matrix
adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj)
features = normalize_features(features)
adj = normalize_adj(adj + sp.eye(adj.shape[0]))
print('Dataset has {} nodes, {} edges, {} features.'.format(adj.shape[0], edges.shape[0], features.shape[1]))
return features.todense(), adj, labels
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 normalize_adj(adj, symmetric=True):
if symmetric:
d = sp.diags(np.power(np.array(adj.sum(1)), -0.5).flatten(), 0)
a_norm = adj.dot(d).transpose().dot(d).tocsr()
else:
d = sp.diags(np.power(np.array(adj.sum(1)), -1).flatten(), 0)
a_norm = d.dot(adj).tocsr()
return a_norm
def normalize_adj_numpy(adj, symmetric=True):
if symmetric:
d = np.diag(np.power(np.array(adj.sum(1)), -0.5).flatten(), 0)
a_norm = adj.dot(d).transpose().dot(d)
else:
d = np.diag(np.power(np.array(adj.sum(1)), -1).flatten(), 0)
a_norm = d.dot(adj)
return a_norm
def preprocess_adj(adj, symmetric=True):
adj = adj + sp.eye(adj.shape[0])
adj = normalize_adj(adj, symmetric)
return adj
def preprocess_adj_numpy(adj, symmetric=True):
adj = adj + np.eye(adj.shape[0])
adj = normalize_adj_numpy(adj, symmetric)
return adj
def preprocess_adj_tensor(adj_tensor, symmetric=True):
adj_out_tensor = []
for i in range(adj_tensor.shape[0]):
adj = adj_tensor[i]
adj = adj + np.eye(adj.shape[0])
adj = normalize_adj_numpy(adj, symmetric)
adj_out_tensor.append(adj)
adj_out_tensor = np.array(adj_out_tensor)
return adj_out_tensor
def preprocess_adj_tensor_with_identity(adj_tensor, symmetric=True):
adj_out_tensor = []
for i in range(adj_tensor.shape[0]):
adj = adj_tensor[i]
adj = adj + np.eye(adj.shape[0])
adj = normalize_adj_numpy(adj, symmetric)
adj = np.concatenate([np.eye(adj.shape[0]), adj], axis=0)
adj_out_tensor.append(adj)
adj_out_tensor = np.array(adj_out_tensor)
return adj_out_tensor
def preprocess_adj_tensor_with_identity_concat(adj_tensor, symmetric=True):
adj_out_tensor = []
for i in range(adj_tensor.shape[0]):
adj = adj_tensor[i]
adj = adj + np.eye(adj.shape[0])
adj = normalize_adj_numpy(adj, symmetric)
adj = np.concatenate([np.eye(adj.shape[0]), adj], axis=0)
adj_out_tensor.append(adj)
adj_out_tensor = np.concatenate(adj_out_tensor, axis=0)
return adj_out_tensor
def preprocess_adj_tensor_concat(adj_tensor, symmetric=True):
adj_out_tensor = []
for i in range(adj_tensor.shape[0]):
adj = adj_tensor[i]
adj = adj + np.eye(adj.shape[0])
adj = normalize_adj_numpy(adj, symmetric)
adj_out_tensor.append(adj)
adj_out_tensor = np.concatenate(adj_out_tensor, axis=0)
return adj_out_tensor
def preprocess_edge_adj_tensor(edge_adj_tensor, symmetric=True):
edge_adj_out_tensor = []
num_edge_features = int(edge_adj_tensor.shape[1]/edge_adj_tensor.shape[2])
for i in range(edge_adj_tensor.shape[0]):
edge_adj = edge_adj_tensor[i]
edge_adj = np.split(edge_adj, num_edge_features, axis=0)
edge_adj = np.array(edge_adj)
edge_adj = preprocess_adj_tensor_concat(edge_adj, symmetric)
edge_adj_out_tensor.append(edge_adj)
edge_adj_out_tensor = np.array(edge_adj_out_tensor)
return edge_adj_out_tensor
def sample_mask(idx, l):
mask = np.zeros(l)
mask[idx] = 1
return np.array(mask, dtype=np.bool)
def get_splits(y):
idx_train = range(80)
idx_val = range(80, 85)
idx_test = range(85, 108)
y_train = np.zeros(y.shape, dtype=np.int32)
y_val = np.zeros(y.shape, dtype=np.int32)
y_test = np.zeros(y.shape, dtype=np.int32)
y_train[idx_train] = y[idx_train]
y_val[idx_val] = y[idx_val]
y_test[idx_test] = y[idx_test]
train_mask = sample_mask(idx_train, y.shape[0])
return y_train, y_val, y_test, idx_train, idx_val, idx_test, train_mask
def get_splits_v2(y):
idx_train = range(1708)
idx_val = range(1708, 1708 + 500)
idx_test = range(1708 + 500, 2708)
y_train = np.zeros(y.shape, dtype=np.int32)
y_val = np.zeros(y.shape, dtype=np.int32)
y_test = np.zeros(y.shape, dtype=np.int32)
y_train[idx_train] = y[idx_train]
y_val[idx_val] = y[idx_val]
y_test[idx_test] = y[idx_test]
train_mask = sample_mask(idx_train, y.shape[0])
return y_train, y_val, y_test, idx_train, idx_val, idx_test, train_mask
def categorical_crossentropy(preds, labels):
return np.mean(-np.log(np.extract(labels, preds)))
def accuracy(preds, labels):
return np.mean(np.equal(np.argmax(labels, 1), np.argmax(preds, 1)))
def evaluate_preds(preds, labels, indices):
split_loss = list()
split_acc = list()
for y_split, idx_split in zip(labels, indices):
split_loss.append(categorical_crossentropy(preds[idx_split], y_split[idx_split]))
split_acc.append(accuracy(preds[idx_split], y_split[idx_split]))
return split_loss, split_acc
def normalized_laplacian(adj, symmetric=True):
adj_normalized = normalize_adj(adj, symmetric)
laplacian = sp.eye(adj.shape[0]) - adj_normalized
return laplacian
def rescale_laplacian(laplacian):
try:
print('Calculating largest eigenvalue of normalized graph Laplacian...')
largest_eigval = eigsh(laplacian, 1, which='LM', return_eigenvectors=False)[0]
except ArpackNoConvergence:
print('Eigenvalue calculation did not converge! Using largest_eigval=2 instead.')
largest_eigval = 2
scaled_laplacian = (2. / largest_eigval) * laplacian - sp.eye(laplacian.shape[0])
return scaled_laplacian
def chebyshev_polynomial(X, k):
"""Calculate Chebyshev polynomials up to order k. Return a list of sparse matrices."""
print("Calculating Chebyshev polynomials up to order {}...".format(k))
T_k = list()
T_k.append(sp.eye(X.shape[0]).tocsr())
T_k.append(X)
def chebyshev_recurrence(T_k_minus_one, T_k_minus_two, X):
X_ = sp.csr_matrix(X, copy=True)
return 2 * X_.dot(T_k_minus_one) - T_k_minus_two
for i in range(2, k + 1):
T_k.append(chebyshev_recurrence(T_k[-1], T_k[-2], X))
return T_k
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