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
|
import os.path as osp
from typing import Callable, List, Optional
import torch
from torch_geometric.data import InMemoryDataset, download_url
from torch_geometric.data.hypergraph_data import HyperGraphData
class CornellTemporalHyperGraphDataset(InMemoryDataset):
r"""A collection of temporal higher-order network datasets from the
`"Simplicial Closure and higher-order link prediction"
<https://arxiv.org/abs/1802.06916>`_ paper.
Each of the datasets is a timestamped sequence of simplices, where a
simplex is a set of :math:`k` nodes.
See the original `datasets page
<https://www.cs.cornell.edu/~arb/data/>`_ for more details about
individual datasets.
Args:
root (str): Root directory where the dataset should be saved.
name (str): The name of the dataset.
split (str, optional): If :obj:`"train"`, loads the training dataset.
If :obj:`"val"`, loads the validation dataset.
If :obj:`"test"`, loads the test dataset.
(default: :obj:`"train"`)
setting (str, optional): If :obj:`"transductive"`, loads the dataset
for transductive training.
If :obj:`"inductive"`, loads the dataset for inductive training.
(default: :obj:`"transductive"`)
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`)
pre_filter (callable, optional): A function that takes in an
:obj:`torch_geometric.data.Data` object and returns a boolean
value, indicating whether the data object should be included in the
final dataset. (default: :obj:`None`)
force_reload (bool, optional): Whether to re-process the dataset.
(default: :obj:`False`)
"""
names = [
'email-Eu',
'email-Enron',
'NDC-classes',
'tags-math-sx',
'email-Eu-25',
'NDC-substances',
'congress-bills',
'tags-ask-ubuntu',
'email-Enron-25',
'NDC-classes-25',
'threads-ask-ubuntu',
'contact-high-school',
'NDC-substances-25',
'congress-bills-25',
'contact-primary-school',
]
url = ('https://huggingface.co/datasets/SauravMaheshkar/{}/raw/main/'
'processed/{}/{}')
def __init__(
self,
root: str,
name: str,
split: str = 'train',
setting: str = 'transductive',
transform: Optional[Callable] = None,
pre_transform: Optional[Callable] = None,
pre_filter: Optional[Callable] = None,
force_reload: bool = False,
) -> None:
assert name in self.names
assert setting in ['transductive', 'inductive']
self.name = name
self.setting = setting
super().__init__(root, transform, pre_transform, pre_filter,
force_reload)
if split == 'train':
path = self.processed_paths[0]
elif split == 'val':
path = self.processed_paths[1]
elif split == 'test':
path = self.processed_paths[2]
else:
raise ValueError(f"Split '{split}' not found")
self.load(path)
@property
def raw_dir(self) -> str:
return osp.join(self.root, self.name, self.setting, 'raw')
@property
def raw_file_names(self) -> List[str]:
return ['train_df.csv', 'val_df.csv', 'test_df.csv']
@property
def processed_dir(self) -> str:
return osp.join(self.root, self.name, self.setting, 'processed')
@property
def processed_file_names(self) -> List[str]:
return ['train_data.pt', 'val_data.pt', 'test_data.pt']
def download(self) -> None:
for filename in self.raw_file_names:
url = self.url.format(self.name, self.setting, filename)
download_url(url, self.raw_dir)
def process(self) -> None:
import pandas as pd
for raw_path, path in zip(self.raw_paths, self.processed_paths):
df = pd.read_csv(raw_path)
data_list = []
for i, row in df.iterrows():
edge_indices: List[List[int]] = [[], []]
for node in eval(row['nodes']): # str(list) -> list:
edge_indices[0].append(node)
edge_indices[1].append(i) # Use `i` as hyper-edge index.
x = torch.tensor([[row['timestamp']]], dtype=torch.float)
edge_index = torch.tensor(edge_indices)
data = HyperGraphData(x=x, edge_index=edge_index)
if self.pre_filter is not None and not self.pre_filter(data):
continue
if self.pre_transform is not None:
data = self.pre_transform(data)
data_list.append(data)
self.save(data_list, path)
|
