forked from sunilkmaurya/FSGNN
-
Notifications
You must be signed in to change notification settings - Fork 0
/
process.py
171 lines (144 loc) · 6.93 KB
/
process.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
import os
import re
import networkx as nx
import numpy as np
import scipy.sparse as sp
import torch as th
from sklearn.model_selection import ShuffleSplit
from utils import sys_normalized_adjacency,sparse_mx_to_torch_sparse_tensor,sys_normalized_adjacency_i
import pickle as pkl
import sys
import networkx as nx
import numpy as np
import scipy.sparse as sp
import torch
#adapted from geom-gcn
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)
def full_load_citation(dataset_str):
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':
# 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, :]
adj = nx.adjacency_matrix(nx.from_dict_of_lists(graph))
labels = np.vstack((ally, ty))
labels[test_idx_reorder, :] = labels[test_idx_range, :]
idx_test = test_idx_range.tolist()
idx_train = range(len(y))
idx_val = range(len(y), len(y)+500)
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, :]
return adj, features, labels, train_mask, val_mask, test_mask
def preprocess_features(features):
"""Row-normalize feature matrix and convert to tuple representation"""
rowsum = np.array(features.sum(1))
rowsum = (rowsum==0)*1+rowsum
r_inv = np.power(rowsum, -1).flatten()
r_inv[np.isinf(r_inv)] = 0.
r_mat_inv = sp.diags(r_inv)
features = r_mat_inv.dot(features)
return features
def full_load_data(dataset_name, splits_file_path=None):
if dataset_name in {'cora', 'citeseer', 'pubmed'}:
adj, features, labels, _, _, _ = full_load_citation(dataset_name)
labels = np.argmax(labels, axis=-1)
features = features.todense()
G = nx.DiGraph(adj)
else:
graph_adjacency_list_file_path = os.path.join('new_data', dataset_name, 'out1_graph_edges.txt')
graph_node_features_and_labels_file_path = os.path.join('new_data', dataset_name,
'out1_node_feature_label.txt')
G = nx.DiGraph()
graph_node_features_dict = {}
graph_labels_dict = {}
if dataset_name=='film':
with open(graph_node_features_and_labels_file_path) as graph_node_features_and_labels_file:
graph_node_features_and_labels_file.readline()
for line in graph_node_features_and_labels_file:
line = line.rstrip().split('\t')
assert (len(line) == 3)
assert (int(line[0]) not in graph_node_features_dict and int(line[0]) not in graph_labels_dict)
feature_blank = np.zeros(932, dtype=np.uint8)
feature_blank[np.array(line[1].split(','), dtype=np.uint16)] = 1
graph_node_features_dict[int(line[0])] = feature_blank
graph_labels_dict[int(line[0])] = int(line[2])
else:
with open(graph_node_features_and_labels_file_path) as graph_node_features_and_labels_file:
graph_node_features_and_labels_file.readline()
for line in graph_node_features_and_labels_file:
line = line.rstrip().split('\t')
assert (len(line) == 3)
assert (int(line[0]) not in graph_node_features_dict and int(line[0]) not in graph_labels_dict)
graph_node_features_dict[int(line[0])] = np.array(line[1].split(','), dtype=np.uint8)
graph_labels_dict[int(line[0])] = int(line[2])
with open(graph_adjacency_list_file_path) as graph_adjacency_list_file:
graph_adjacency_list_file.readline()
for line in graph_adjacency_list_file:
line = line.rstrip().split('\t')
assert (len(line) == 2)
if int(line[0]) not in G:
G.add_node(int(line[0]), features=graph_node_features_dict[int(line[0])],
label=graph_labels_dict[int(line[0])])
if int(line[1]) not in G:
G.add_node(int(line[1]), features=graph_node_features_dict[int(line[1])],
label=graph_labels_dict[int(line[1])])
G.add_edge(int(line[0]), int(line[1]))
adj = nx.adjacency_matrix(G, sorted(G.nodes()))
features = np.array(
[features for _, features in sorted(G.nodes(data='features'), key=lambda x: x[0])])
labels = np.array(
[label for _, label in sorted(G.nodes(data='label'), key=lambda x: x[0])])
features = preprocess_features(features)
g = adj
with np.load(splits_file_path) as splits_file:
train_mask = splits_file['train_mask']
val_mask = splits_file['val_mask']
test_mask = splits_file['test_mask']
num_features = features.shape[1]
num_labels = len(np.unique(labels))
assert (np.array_equal(np.unique(labels), np.arange(len(np.unique(labels)))))
features = th.FloatTensor(features)
labels = th.LongTensor(labels)
train_mask = th.BoolTensor(train_mask)
val_mask = th.BoolTensor(val_mask)
test_mask = th.BoolTensor(test_mask)
adj = sys_normalized_adjacency(g)
adj_i = sys_normalized_adjacency_i(g)
adj = sparse_mx_to_torch_sparse_tensor(adj)
adj_i = sparse_mx_to_torch_sparse_tensor(adj_i)
return adj,adj_i, features, labels, train_mask, val_mask, test_mask, num_features, num_labels