GOOD.data.good_datasets.good_webkb
The GOOD-WebKB dataset adapted from the Geom-GCN: Geometric Graph Convolutional Networks.
Classes
|
The class for data point storage. |
A class containing methods for data domain extraction. |
|
|
The GOOD-WebKB dataset adapted from the Geom-GCN: Geometric Graph Convolutional Networks. |
- class GOOD.data.good_datasets.good_webkb.DataInfo(idx, y)[source]
Bases:
object
The class for data point storage. This enables tackling node data point like graph data point, facilitating data splits.
- class GOOD.data.good_datasets.good_webkb.DomainGetter[source]
Bases:
object
A class containing methods for data domain extraction.
- class GOOD.data.good_datasets.good_webkb.GOODWebKB(root: str, domain: str, shift: str = 'no_shift', transform=None, pre_transform=None, generate: bool = False)[source]
Bases:
InMemoryDataset
The GOOD-WebKB dataset adapted from the Geom-GCN: Geometric Graph Convolutional Networks.
- Parameters
- static load(dataset_root: str, domain: str, shift: str = 'no_shift', generate: bool = False)[source]
A staticmethod for dataset loading. This method instantiates dataset class, constructing train, id_val, id_test, ood_val (val), and ood_test (test) splits. Besides, it collects several dataset meta information for further utilization.
- Parameters
- Returns
dataset or dataset splits. dataset meta info.
- property processed_file_names
The name of the files in the
self.processed_dir
folder that must be present in order to skip processing.