import os.path as osp
from typing import Callable, Optional
import numpy as np
import torch
from torch_geometric.data import Data, InMemoryDataset, download_url
[docs]class GemsecDeezer(InMemoryDataset):
r"""The Deezer User Network datasets introduced in the
`"GEMSEC: Graph Embedding with Self Clustering"
<https://arxiv.org/abs/1802.03997>`_ paper.
Nodes represent Deezer user and edges are mutual friendships.
The task is multi-label multi-class node classification about
the genres liked by the users.
Args:
root (str): Root directory where the dataset should be saved.
name (str): The name of the dataset (:obj:`"HU"`, :obj:`"HR"`,
:obj:`"RO"`).
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/gemsec'
def __init__(
self,
root: str,
name: str,
transform: Optional[Callable] = None,
pre_transform: Optional[Callable] = None,
force_reload: bool = False,
) -> None:
self.name = name
assert self.name in ['HU', 'HR', 'RO']
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) -> str:
return f'{self.name}.npz'
@property
def processed_file_names(self) -> str:
return 'data.pt'
def download(self) -> None:
download_url(osp.join(self.url, self.name + '.npz'), self.raw_dir)
def process(self) -> None:
data = np.load(self.raw_paths[0], 'r', allow_pickle=True)
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(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])