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
|
import json
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_google_url
class AmazonProducts(InMemoryDataset):
r"""The Amazon dataset from the `"GraphSAINT: Graph Sampling Based
Inductive Learning Method" <https://arxiv.org/abs/1907.04931>`_ paper,
containing products and its categories.
Args:
root (str): Root directory where the dataset should be saved.
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
:header-rows: 1
* - #nodes
- #edges
- #features
- #classes
* - 1,569,960
- 264,339,468
- 200
- 107
"""
adj_full_id = '17qhNA8H1IpbkkR-T2BmPQm8QNW5do-aa'
feats_id = '10SW8lCvAj-kb6ckkfTOC5y0l8XXdtMxj'
class_map_id = '1LIl4kimLfftj4-7NmValuWyCQE8AaE7P'
role_id = '1npK9xlmbnjNkV80hK2Q68wTEVOFjnt4K'
def __init__(
self,
root: str,
transform: Optional[Callable] = None,
pre_transform: Optional[Callable] = None,
force_reload: bool = False,
) -> None:
super().__init__(root, transform, pre_transform,
force_reload=force_reload)
self.load(self.processed_paths[0])
@property
def raw_file_names(self) -> List[str]:
return ['adj_full.npz', 'feats.npy', 'class_map.json', 'role.json']
@property
def processed_file_names(self) -> str:
return 'data.pt'
def download(self) -> None:
download_google_url(self.adj_full_id, self.raw_dir, 'adj_full.npz')
download_google_url(self.feats_id, self.raw_dir, 'feats.npy')
download_google_url(self.class_map_id, self.raw_dir, 'class_map.json')
download_google_url(self.role_id, self.raw_dir, 'role.json')
def process(self) -> None:
import scipy.sparse as sp
f = np.load(osp.join(self.raw_dir, 'adj_full.npz'))
adj = sp.csr_matrix((f['data'], f['indices'], f['indptr']), f['shape'])
adj = adj.tocoo()
row = torch.from_numpy(adj.row).to(torch.long)
col = torch.from_numpy(adj.col).to(torch.long)
edge_index = torch.stack([row, col], dim=0)
x = np.load(osp.join(self.raw_dir, 'feats.npy'))
x = torch.from_numpy(x).to(torch.float)
ys = [-1] * x.size(0)
with open(osp.join(self.raw_dir, 'class_map.json')) as f:
class_map = json.load(f)
for key, item in class_map.items():
ys[int(key)] = item
y = torch.tensor(ys)
with open(osp.join(self.raw_dir, 'role.json')) as f:
role = json.load(f)
train_mask = torch.zeros(x.size(0), dtype=torch.bool)
train_mask[torch.tensor(role['tr'])] = True
val_mask = torch.zeros(x.size(0), dtype=torch.bool)
val_mask[torch.tensor(role['va'])] = True
test_mask = torch.zeros(x.size(0), dtype=torch.bool)
test_mask[torch.tensor(role['te'])] = True
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])
|
