stgraph.dataset.static package

Submodules

stgraph.dataset.static.cora_dataloader module

Citation network consisting of scientific publications.

class stgraph.dataset.static.cora_dataloader.CoraDataLoader(verbose: bool = False, redownload: bool = False)

Bases: STGraphStaticDataset

Citation network consisting of scientific publications.

The Cora dataset consists of 2708 scientific publications classified into one of seven classes. The citation network consists of 5429 links. Each publication in the dataset is described by a 0/1-valued word vector indicating the absence/presence of the corresponding word from the dictionary. The dictionary consists of 1433 unique words.

This class provides functionality for loading, processing, and accessing the Cora dataset for use in deep learning tasks such as graph-based node classification.

gdata

num_nodes	num_edges	num_feats	num_classes
2708	10556	1433	7

Example

from stgraph.dataset import CoraDataLoader

cora = CoraDataLoader()
num_nodes = cora.gdata["num_nodes"]
edge_list = cora.get_edges()

Parameters:

• verbose (bool, optional) – Flag to control whether to display verbose info (default is False)

• redownload (bool, optional (default is False)) – Redownload the dataset online and save to cache

name

The name of the dataset.

Type:

str

gdata

Graph meta data.

Type:

dict

get_all_features() → ndarray

Get all features.

get_all_targets() → ndarray

Get all targets.

get_edges() → list

Get the edge list.

stgraph.dataset.static.stgraph_static_dataset module

Base class for all STGraph static graph datasets.

class stgraph.dataset.static.stgraph_static_dataset.STGraphStaticDataset

Bases: STGraphDataset

Base class for static graph datasets.

Module contents

Collection of dataset loaders for Static real-world datasets.