torch_geometric.datasets.LastFM

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

Bases: InMemoryDataset

A subset of the last.fm music website keeping track of users’ listining information from various sources, as collected in the “MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding” paper. last.fm is a heterogeneous graph containing three types of entities - users (1,892 nodes), artists (17,632 nodes), and artist tags (1,088 nodes). This dataset can be used for link prediction, and no labels or features are provided.

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

  • transform (callable, optional) – A function/transform that takes in an torch_geometric.data.HeteroData 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.HeteroData 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)