torch_geometric.datasets.GitHub

class GitHub(root: str, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, force_reload: bool = False)[source]

Bases: InMemoryDataset

The GitHub Web and ML Developers dataset introduced in the “Multi-scale Attributed Node Embedding” paper. Nodes represent developers on github:`GitHub and edges are mutual follower relationships. It contains 37,300 nodes, 578,006 edges, 128 node features and 2 classes.

Parameters:
  • root (str) – Root directory where the dataset should be saved.

  • transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before every access. (default: None)

  • pre_transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)

  • force_reload (bool, optional) – Whether to re-process the dataset. (default: False)

STATS:

#nodes

#edges

#features

#classes

37,700

578,006

0

2