from typing import Callable, Optional
import numpy as np
import torch
from torch_geometric.data import Data, InMemoryDataset, download_url
[docs]class LastFMAsia(InMemoryDataset):
r"""The LastFM Asia Network dataset introduced in the `"Characteristic
Functions on Graphs: Birds of a Feather, from Statistical Descriptors to
Parametric Models" <https://arxiv.org/abs/2005.07959>`_ paper.
Nodes represent LastFM users from Asia and edges are friendships.
It contains 7,624 nodes, 55,612 edges, 128 node features and 18 classes.
Args:
root (string): 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`)
"""
url = 'https://graphmining.ai/datasets/ptg/lastfm_asia.npz'
def __init__(self, root: str, transform: Optional[Callable] = None,
pre_transform: Optional[Callable] = None):
super().__init__(root, transform, pre_transform)
self.data, self.slices = torch.load(self.processed_paths[0])
@property
def raw_file_names(self) -> str:
return 'lastfm_asia.npz'
@property
def processed_file_names(self) -> str:
return 'data.pt'
def download(self):
download_url(self.url, self.raw_dir)
def process(self):
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)
torch.save(self.collate([data]), self.processed_paths[0])