GOOD.data.good_datasets.good_cbas

The GOOD-CBAS dataset modified from BA-Shapes.

Classes

`DataInfo`(idx, y, x)	The class for data point storage.
`GOODCBAS`(root, domain[, shift, transform, ...])	The GOOD-CBAS dataset.

class GOOD.data.good_datasets.good_cbas.DataInfo(idx, y, x)[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_cbas.GOODCBAS(root: str, domain: str, shift: str = 'no_shift', transform=None, pre_transform=None, generate: bool = False)[source]

Bases: InMemoryDataset

The GOOD-CBAS dataset. Modified from BA-Shapes.

Parameters

root (str) – The dataset saving root.
domain (str) – The domain selection. Allowed: ‘color’.
shift (str) – The distributional shift we pick. Allowed: ‘no_shift’, ‘covariate’, and ‘concept’.
generate (bool) – The flag for regenerating dataset. True: regenerate. False: download.

download()[source]: Downloads the dataset to the self.raw_dir folder.

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

dataset_root (str) – The dataset saving root.
domain (str) – The domain selection. Allowed: ‘degree’ and ‘time’.
shift (str) – The distributional shift we pick. Allowed: ‘no_shift’, ‘covariate’, and ‘concept’.
generate (bool) – The flag for regenerating dataset. True: regenerate. False: download.

Returns

dataset or dataset splits. dataset meta info.

process()[source]: Processes the dataset to the self.processed_dir folder.

property processed_file_names: The name of the files in the self.processed_dir folder that must be present in order to skip processing.