torch_geometric.datasets.Airports

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

Bases: InMemoryDataset

The Airports dataset from the “struc2vec: Learning Node Representations from Structural Identity” paper, where nodes denote airports and labels correspond to activity levels. Features are given by one-hot encoded node identifiers, as described in the “GraLSP: Graph Neural Networks with Local Structural Patterns” paper.

Parameters:

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

  • name (str) – The name of the dataset ("USA", "Brazil", "Europe").

  • transform (Optional[Callable], default: None) – 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.

  • pre_transform (callable, optional) – A function/transform that takes in torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before being saved to disk.

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