torch_geometric.datasets.AmazonBook

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

Bases: InMemoryDataset

A subset of the AmazonBook rating dataset from the “LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation” paper. This is a heterogeneous dataset consisting of 52,643 users and 91,599 books with approximately 2.9 million ratings between them. 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)