dgl.DGLGraph.to_networkx¶

DGLGraph.to_networkx(node_attrs=None, edge_attrs=None)[source]¶

Convert to networkx graph.

The edge id will be saved as the ‘id’ edge attribute.

Parameters:	node_attrs (iterable of str, optional) – The node attributes to be copied. edge_attrs (iterable of str, optional) – The edge attributes to be copied.
Returns:	The nx graph
Return type:	networkx.DiGraph

Examples

Note

Here we use pytorch syntax for demo. The general idea applies to other frameworks with minor syntax change (e.g. replace torch.tensor with mxnet.ndarray).

>>> import torch as th
>>> g = DGLGraph()
>>> g.add_nodes(5, {'n1': th.randn(5, 10)})
>>> g.add_edges([0,1,3,4], [2,4,0,3], {'e1': th.randn(4, 6)})
>>> nxg = g.to_networkx(node_attrs=['n1'], edge_attrs=['e1'])