Class Data

torch_geometric/data/data.py:472–1249

r"""A data object describing a homogeneous graph. The data object can hold node-level, link-level and graph-level attributes. In general, :class:`~torch_geometric.data.Data` tries to mimic the behavior of a regular :python:`Python` dictionary. In addition, it provides useful function

class Data(BaseData, FeatureStore, GraphStore):
    r"""A data object describing a homogeneous graph.
    The data object can hold node-level, link-level and graph-level attributes.
    In general, :class:`~torch_geometric.data.Data` tries to mimic the
    behavior of a regular :python:`Python` dictionary.
    In addition, it provides useful functionality for analyzing graph
    structures, and provides basic PyTorch tensor functionalities.
    See `here <https://pytorch-geometric.readthedocs.io/en/latest/get_started/
    introduction.html#data-handling-of-graphs>`__ for the accompanying
    tutorial.

    .. code-block:: python

        from torch_geometric.data import Data

        data = Data(x=x, edge_index=edge_index, ...)

        # Add additional arguments to `data`:
        data.train_idx = torch.tensor([...], dtype=torch.long)
        data.test_mask = torch.tensor([...], dtype=torch.bool)

        # Analyzing the graph structure:
        data.num_nodes
        >>> 23

        data.is_directed()
        >>> False

        # PyTorch tensor functionality:
        data = data.pin_memory()
        data = data.to('cuda:0', non_blocking=True)

    Args:
        x (torch.Tensor, optional): Node feature matrix with shape
            :obj:`[num_nodes, num_node_features]`. (default: :obj:`None`)
        edge_index (LongTensor, optional): Graph connectivity in COO format
            with shape :obj:`[2, num_edges]`. (default: :obj:`None`)
        edge_attr (torch.Tensor, optional): Edge feature matrix with shape
            :obj:`[num_edges, num_edge_features]`. (default: :obj:`None`)
        y (torch.Tensor, optional): Graph-level or node-level ground-truth
            labels with arbitrary shape. (default: :obj:`None`)
        pos (torch.Tensor, optional): Node position matrix with shape
            :obj:`[num_nodes, num_dimensions]`. (default: :obj:`None`)
        time (torch.Tensor, optional): The timestamps for each event with shape
            :obj:`[num_edges]` or :obj:`[num_nodes]`. (default: :obj:`None`)
        **kwargs (optional): Additional attributes.
    """
    def __init__(
        self,
        x: Optional[Tensor] = None,
        edge_index: OptTensor = None,
        edge_attr: OptTensor = None,
        y: Optional[Union[Tensor, int, float]] = None,
        pos: OptTensor = None,
        time: OptTensor = None,
        **kwargs,
    ):
        # `Data` doesn't support group_name, so we need to adjust `TensorAttr`