torch_geometric_signed_directed.data.signed.MSGNN_real_data

Classes

MSGNN_real_data

Data loader for the data sets used in the

Module Contents

class MSGNN_real_data(name: str, root: str, transform: Callable | None = None, pre_transform: Callable | None = None, sparsify_level: float = 1)

Bases: torch_geometric.data.InMemoryDataset

Data loader for the data sets used in the MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian paper.

Parameters:

  • name (str) – Name of the data set, choices are: ‘FiLL-pvCLCL”+str(year), ‘FiLL-OPCL”+str(year) (year from 2000 to 2020).

  • 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)

  • sparsify_level (float, optional) – the density of the graph, a value between 0 and 1. Default: 1.

name
url = 'https://github.com/SherylHYX/pytorch_geometric_signed_directed/raw/main/datasets/FiLL'
sparsify_level = 1
property raw_file_names
property processed_file_names
download()
process()