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
|
import os.path as osp
from typing import Callable, List, Optional
import numpy as np
import torch
from torch_geometric.data import Data, InMemoryDataset, download_url
from torch_geometric.utils import coalesce
class WebKB(InMemoryDataset):
r"""The WebKB datasets used in the
`"Geom-GCN: Geometric Graph Convolutional Networks"
<https://openreview.net/forum?id=S1e2agrFvS>`_ paper.
Nodes represent web pages and edges represent hyperlinks between them.
Node features are the bag-of-words representation of web pages.
The task is to classify the nodes into one of the five categories, student,
project, course, staff, and faculty.
Args:
root (str): Root directory where the dataset should be saved.
name (str): The name of the dataset (:obj:`"Cornell"`, :obj:`"Texas"`,
:obj:`"Wisconsin"`).
transform (callable, optional): A function/transform that takes in an
:obj:`torch_geometric.data.Data` object and returns a transformed
version. The data object will be transformed before every access.
(default: :obj:`None`)
pre_transform (callable, optional): A function/transform that takes in
an :obj:`torch_geometric.data.Data` object and returns a
transformed version. The data object will be transformed before
being saved to disk. (default: :obj:`None`)
force_reload (bool, optional): Whether to re-process the dataset.
(default: :obj:`False`)
**STATS:**
.. list-table::
:widths: 10 10 10 10 10
:header-rows: 1
* - Name
- #nodes
- #edges
- #features
- #classes
* - Cornell
- 183
- 298
- 1,703
- 5
* - Texas
- 183
- 325
- 1,703
- 5
* - Wisconsin
- 251
- 515
- 1,703
- 5
"""
url = 'https://raw.githubusercontent.com/graphdml-uiuc-jlu/geom-gcn/master'
def __init__(
self,
root: str,
name: str,
transform: Optional[Callable] = None,
pre_transform: Optional[Callable] = None,
force_reload: bool = False,
) -> None:
self.name = name.lower()
assert self.name in ['cornell', 'texas', 'wisconsin']
super().__init__(root, transform, pre_transform,
force_reload=force_reload)
self.load(self.processed_paths[0])
@property
def raw_dir(self) -> str:
return osp.join(self.root, self.name, 'raw')
@property
def processed_dir(self) -> str:
return osp.join(self.root, self.name, 'processed')
@property
def raw_file_names(self) -> List[str]:
out = ['out1_node_feature_label.txt', 'out1_graph_edges.txt']
out += [f'{self.name}_split_0.6_0.2_{i}.npz' for i in range(10)]
return out
@property
def processed_file_names(self) -> str:
return 'data.pt'
def download(self) -> None:
for f in self.raw_file_names[:2]:
download_url(f'{self.url}/new_data/{self.name}/{f}', self.raw_dir)
for f in self.raw_file_names[2:]:
download_url(f'{self.url}/splits/{f}', self.raw_dir)
def process(self) -> None:
with open(self.raw_paths[0]) as f:
lines = f.read().split('\n')[1:-1]
xs = [[float(value) for value in line.split('\t')[1].split(',')]
for line in lines]
x = torch.tensor(xs, dtype=torch.float)
ys = [int(line.split('\t')[2]) for line in lines]
y = torch.tensor(ys, dtype=torch.long)
with open(self.raw_paths[1]) as f:
lines = f.read().split('\n')[1:-1]
edge_indices = [[int(value) for value in line.split('\t')]
for line in lines]
edge_index = torch.tensor(edge_indices).t().contiguous()
edge_index = coalesce(edge_index, num_nodes=x.size(0))
train_masks, val_masks, test_masks = [], [], []
for path in self.raw_paths[2:]:
tmp = np.load(path)
train_masks += [torch.from_numpy(tmp['train_mask']).to(torch.bool)]
val_masks += [torch.from_numpy(tmp['val_mask']).to(torch.bool)]
test_masks += [torch.from_numpy(tmp['test_mask']).to(torch.bool)]
train_mask = torch.stack(train_masks, dim=1)
val_mask = torch.stack(val_masks, dim=1)
test_mask = torch.stack(test_masks, dim=1)
data = Data(x=x, edge_index=edge_index, y=y, train_mask=train_mask,
val_mask=val_mask, test_mask=test_mask)
data = data if self.pre_transform is None else self.pre_transform(data)
self.save([data], self.processed_paths[0])
def __repr__(self) -> str:
return f'{self.name}()'
|
