Method adj

python/dgl/heterograph.py:3763–3836

Get the adjacency matrix of the graph. Parameters ---------- etype : str or (str, str, str), optional The type names of the edges. The allowed type name formats are: * ``(str, str, str)`` for source node type, edge type and destination no

(self, etype=None, eweight_name=None)

        return self.adj(etype)

    def adj(self, etype=None, eweight_name=None):
        """Get the adjacency matrix of the graph.

        Parameters
        ----------
        etype : str or (str, str, str), optional
            The type names of the edges. The allowed type name formats are:

            * ``(str, str, str)`` for source node type, edge type and
            destination node type.
            * or one ``str`` edge type name if the name can uniquely identify a
              triplet format in the graph.

            Can be omitted if the graph has only one type of edges.

        eweight_name : str, optional
            The name of edge feature used as the non-zero values. If not given,
            the non-zero values are all 1.

        Returns
        -------
        SparseMatrix
            The adjacency matrix.

        Examples
        --------

        The following example uses PyTorch backend.

        >>> import dgl
        >>> import torch

        >>> g = dgl.graph(([0, 1, 2], [1, 2, 3]))
        >>> g.adj()
        SparseMatrix(indices=tensor([[0, 1, 2],
                                     [1, 2, 3]]),
                     values=tensor([1., 1., 1.]),
                     shape=(4, 4), nnz=3)

        >>> g = dgl.heterograph({
        ...     ('user', 'follows', 'user'): ([0, 1], [0, 1]),
        ...     ('developer', 'develops', 'game'): ([0, 1], [0, 2])
        ... })

        >>> g.adj(etype='develops')
        SparseMatrix(indices=tensor([[0, 1],
                                     [0, 2]]),
                     values=tensor([1., 1.]),
                     shape=(2, 3), nnz=2)
        >>> g.edata['h'] = {('user', 'follows', 'user'): torch.tensor([3, 2])}
        >>> g.adj(etype='follows', eweight_name='h')
        SparseMatrix(indices=tensor([[0, 1],
                                     [0, 1]]),
                     values=tensor([3, 2]),
                     shape=(2, 2), nnz=2)
        """
        assert F.backend_name == "pytorch", "Only PyTorch backend supports adj."
        # Temporal fix to introduce a dependency on torch