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
|
from typing import Callable, Optional
import numpy as np
import torch
from torch_geometric.data import Data, InMemoryDataset, download_url
class FacebookPagePage(InMemoryDataset):
r"""The Facebook Page-Page network dataset introduced in the
`"Multi-scale Attributed Node Embedding"
<https://arxiv.org/abs/1909.13021>`_ paper.
Nodes represent verified pages on Facebook and edges are mutual likes.
It contains 22,470 nodes, 342,004 edges, 128 node features and 4 classes.
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`)
"""
url = 'https://graphmining.ai/datasets/ptg/facebook.npz'
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) -> str:
return 'facebook.npz'
@property
def processed_file_names(self) -> str:
return 'data.pt'
def download(self) -> None:
download_url(self.url, self.raw_dir)
def process(self) -> None:
data = np.load(self.raw_paths[0], 'r', allow_pickle=True)
x = torch.from_numpy(data['features']).to(torch.float)
y = torch.from_numpy(data['target']).to(torch.long)
edge_index = torch.from_numpy(data['edges']).to(torch.long)
edge_index = edge_index.t().contiguous()
data = Data(x=x, y=y, edge_index=edge_index)
if self.pre_transform is not None:
data = self.pre_transform(data)
self.save([data], self.processed_paths[0])
|
