torch_geometric.datasets.BitcoinOTC

class BitcoinOTC(root: str, edge_window_size: int = 10, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None)[source]

Bases: InMemoryDataset

The Bitcoin-OTC dataset from the “EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs” paper, consisting of 138 who-trusts-whom networks of sequential time steps.

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

  • edge_window_size (int, optional) – The window size for the existence of an edge in the graph sequence since its initial creation. (default: 10)

  • 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)