load_data

Load Graph Datasets

graph_datasets.load_data.load_data(dataset_name: str, directory: str = './data', verbosity: int = 0, source: str = 'pyg', return_type: str = 'dgl', rm_self_loop: bool = True, to_simple: bool = True) → Tuple[DGLGraph, Tensor, int][source]

Load graphs.

Parameters:

dataset_name (str) – Dataset name.
directory (str, optional) – Raw dir for loading or saving. Defaults to DEFAULT_DATA_DIR=os.path.abspath(“./data”).
verbosity (int, optional) – Output debug information. The greater, the more detailed. Defaults to 0.
source (str, optional) – Source for data loading. Defaults to “pyg”.
return_type (str, optional) – Return type of the graphs within [“dgl”, “pyg”]. Defaults to “dgl”.
rm_self_loop (str, optional) – Remove self loops. Defaults to True.
to_simple (str, optional) – Convert to a simple graph with no duplicate undirected edges.

Raises:

NotImplementedError – Dataset unknown.

Returns:

[graph, label, n_clusters]

Return type:

Tuple[dgl.DGLGraph, torch.Tensor, int]

Example

from graph_datasets import load_data
# dgl graph
graph, label, n_clusters = load_data(
    dataset_name='cora',
    directory="./data",
    return_type="dgl",
    source='pyg',
    verbosity=3,
    rm_self_loop=True,
    to_simple=True,
)
# pyG data
data = load_data(
    dataset_name='cora',
    directory="./data",
    return_type="pyg",
    source='pyg',
    verbosity=3,
    rm_self_loop=True,
    to_simple=True,
)