Graph

class Graph

Bases: object

numpy backed graph class with support for memmapped edge_index

abstract __init__(edge_index, edge_attr=None, x=None, y=None, num_nodes=None, adj_index=None, ensure_sorted=False, undir=None, nodes=None)

Initialise graph

Parameters:

• edge_index – edge index such that edge_index[0] lists the source and edge_index[1] the target node for each edge

• edge_attr – optionally provide edge weights

• num_nodes – specify number of nodes (default: max(edge_index)+1)

• ensure_sorted – if False, assume that the edge_index input is already sorted

• undir – boolean indicating if graph is directed. If not provided, the edge_index is checked to determine this value.

Methods

__init__	Initialise graph
adj	list neighbours of node
adj_weighted	list neighbours of node and corresponding edge weight :param node: source node
bfs_order	return nodes in breadth-first-search order
connected_component_ids	return connected component ids where ids are sorted in decreasing order by component size
edges	iterator over edges
edges_weighted	iterator over weighted edges where each edge is a tuple (source, target, weight)
from_networkx
from_tg
has_node_labels
is_edge
lcc
neighbourhood	find the neighbourhood of a set of source nodes
nodes_in_lcc	Iterator over nodes in the largest connected component
partition_graph
sample_negative_edges
sample_positive_edges
subgraph	find induced subgraph for a set of nodes
to
to_networkx	convert graph to NetworkX format

Attributes

device
nodes
num_edges
num_features
weighted	boolean indicating if graph is weighted
weights
degree

classmethod from_tg(data)

classmethod from_networkx(nx_graph: Graph, weight=None)

has_node_labels()

adj(node: int)

list neighbours of node

Parameters:

node – source node

Returns:

neighbours

adj_weighted(node: int)

list neighbours of node and corresponding edge weight :param node: source node

Returns:

neighbours, weights

abstract edges()

iterator over edges

abstract edges_weighted()

iterator over weighted edges where each edge is a tuple (source, target, weight)

abstract is_edge(source, target)

abstract neighbourhood(nodes, hops: int = 1)

find the neighbourhood of a set of source nodes

note that the neighbourhood includes the source nodes themselves

Parameters:

• nodes – indices of source nodes

• hops – number of hops for neighbourhood

Returns:

neighbourhood

abstract subgraph(nodes: Iterable, relabel=False, keep_x=True, keep_y=True)

find induced subgraph for a set of nodes

Parameters:

nodes – node indeces

Returns:

subgraph

abstract connected_component_ids()

return connected component ids where ids are sorted in decreasing order by component size

Returns:

Sequence of node indeces

nodes_in_lcc()

Iterator over nodes in the largest connected component

lcc(relabel=False)

to_networkx()

convert graph to NetworkX format

to(graph_cls)

abstract bfs_order(start=0)

return nodes in breadth-first-search order

Parameters:

start – index of starting node (default: 0)

Returns:

Sequence of node indeces

abstract partition_graph(partition, self_loops=True)

abstract sample_negative_edges(num_samples)

sample_positive_edges(num_samples)