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
|
import os
import os.path as osp
import shutil
from typing import Callable, List, Optional
import numpy as np
import torch
from torch_geometric.data import (
HeteroData,
InMemoryDataset,
download_url,
extract_zip,
)
from torch_geometric.io import fs
class OGB_MAG(InMemoryDataset):
r"""The :obj:`ogbn-mag` dataset from the `"Open Graph Benchmark: Datasets
for Machine Learning on Graphs" <https://arxiv.org/abs/2005.00687>`_ paper.
:obj:`ogbn-mag` is a heterogeneous graph composed of a subset of the
Microsoft Academic Graph (MAG).
It contains four types of entities — papers (736,389 nodes), authors
(1,134,649 nodes), institutions (8,740 nodes), and fields of study
(59,965 nodes) — as well as four types of directed relations connecting two
types of entities.
Each paper is associated with a 128-dimensional :obj:`word2vec` feature
vector, while all other node types are not associated with any input
features.
The task is to predict the venue (conference or journal) of each paper.
In total, there are 349 different venues.
Args:
root (str): Root directory where the dataset should be saved.
preprocess (str, optional): Pre-processes the original dataset by
adding structural features (:obj:`"metapath2vec"`, :obj:`"TransE"`)
to featureless nodes. (default: :obj:`None`)
transform (callable, optional): A function/transform that takes in an
:obj:`torch_geometric.data.HeteroData` 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.HeteroData` 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`)
"""
url = 'http://snap.stanford.edu/ogb/data/nodeproppred/mag.zip'
urls = {
'metapath2vec': ('https://data.pyg.org/datasets/'
'mag_metapath2vec_emb.zip'),
'transe': ('https://data.pyg.org/datasets/'
'mag_transe_emb.zip'),
}
def __init__(
self,
root: str,
preprocess: Optional[str] = None,
transform: Optional[Callable] = None,
pre_transform: Optional[Callable] = None,
force_reload: bool = False,
) -> None:
preprocess = None if preprocess is None else preprocess.lower()
self.preprocess = preprocess
assert self.preprocess in [None, 'metapath2vec', 'transe']
super().__init__(root, transform, pre_transform,
force_reload=force_reload)
self.load(self.processed_paths[0], data_cls=HeteroData)
@property
def num_classes(self) -> int:
assert isinstance(self._data, HeteroData)
return int(self._data['paper'].y.max()) + 1
@property
def raw_dir(self) -> str:
return osp.join(self.root, 'mag', 'raw')
@property
def processed_dir(self) -> str:
return osp.join(self.root, 'mag', 'processed')
@property
def raw_file_names(self) -> List[str]:
file_names = [
'node-feat', 'node-label', 'relations', 'split',
'num-node-dict.csv.gz'
]
if self.preprocess is not None:
file_names += [f'mag_{self.preprocess}_emb.pt']
return file_names
@property
def processed_file_names(self) -> str:
if self.preprocess is not None:
return f'data_{self.preprocess}.pt'
else:
return 'data.pt'
def download(self) -> None:
if not all([osp.exists(f) for f in self.raw_paths[:5]]):
path = download_url(self.url, self.raw_dir)
extract_zip(path, self.raw_dir)
for file_name in ['node-feat', 'node-label', 'relations']:
path = osp.join(self.raw_dir, 'mag', 'raw', file_name)
shutil.move(path, self.raw_dir)
path = osp.join(self.raw_dir, 'mag', 'split')
shutil.move(path, self.raw_dir)
path = osp.join(self.raw_dir, 'mag', 'raw', 'num-node-dict.csv.gz')
shutil.move(path, self.raw_dir)
fs.rm(osp.join(self.raw_dir, 'mag'))
os.remove(osp.join(self.raw_dir, 'mag.zip'))
if self.preprocess is not None:
path = download_url(self.urls[self.preprocess], self.raw_dir)
extract_zip(path, self.raw_dir)
os.remove(path)
def process(self) -> None:
import pandas as pd
data = HeteroData()
path = osp.join(self.raw_dir, 'node-feat', 'paper', 'node-feat.csv.gz')
x_paper = pd.read_csv(path, compression='gzip', header=None,
dtype=np.float32).values
data['paper'].x = torch.from_numpy(x_paper)
path = osp.join(self.raw_dir, 'node-feat', 'paper', 'node_year.csv.gz')
year_paper = pd.read_csv(path, compression='gzip', header=None,
dtype=np.int64).values
data['paper'].year = torch.from_numpy(year_paper).view(-1)
path = osp.join(self.raw_dir, 'node-label', 'paper',
'node-label.csv.gz')
y_paper = pd.read_csv(path, compression='gzip', header=None,
dtype=np.int64).values.flatten()
data['paper'].y = torch.from_numpy(y_paper)
if self.preprocess is None:
path = osp.join(self.raw_dir, 'num-node-dict.csv.gz')
num_nodes_df = pd.read_csv(path, compression='gzip')
for node_type in ['author', 'institution', 'field_of_study']:
data[node_type].num_nodes = num_nodes_df[node_type].tolist()[0]
else:
emb_dict = fs.torch_load(self.raw_paths[-1])
for key, value in emb_dict.items():
if key != 'paper':
data[key].x = value
for edge_type in [('author', 'affiliated_with', 'institution'),
('author', 'writes', 'paper'),
('paper', 'cites', 'paper'),
('paper', 'has_topic', 'field_of_study')]:
f = '___'.join(edge_type)
path = osp.join(self.raw_dir, 'relations', f, 'edge.csv.gz')
edge_index = pd.read_csv(path, compression='gzip', header=None,
dtype=np.int64).values
edge_index = torch.from_numpy(edge_index).t().contiguous()
data[edge_type].edge_index = edge_index
for f, v in [('train', 'train'), ('valid', 'val'), ('test', 'test')]:
path = osp.join(self.raw_dir, 'split', 'time', 'paper',
f'{f}.csv.gz')
idx = pd.read_csv(path, compression='gzip', header=None,
dtype=np.int64).values.flatten()
idx = torch.from_numpy(idx)
mask = torch.zeros(data['paper'].num_nodes, dtype=torch.bool)
mask[idx] = True
data['paper'][f'{v}_mask'] = mask
if self.pre_transform is not None:
data = self.pre_transform(data)
self.save([data], self.processed_paths[0])
def __repr__(self) -> str:
return 'ogbn-mag()'
|
