def create_simple_graph():
"""
Creates a simple directed graph for testing. The node ids are integers.
Returns:
A small, directed graph with 3 nodes and 2 edges in StellarDiGraph format.
"""
nodes = pd.DataFrame([-1, -2, -3], index=[1, 2, 3])
edges = pd.DataFrame([(1, 2), (2, 3)], columns=["source", "target"])
return StellarDiGraph(nodes, edges)
def create_simple_graph():
"""
Creates a simple directed graph for testing. The node ids are integers.
Returns:
A small, directed graph with 3 nodes and 2 edges in StellarDiGraph format.
"""
g = nx.DiGraph()
edges = [(1, 2), (2, 3)]
g.add_edges_from(edges)
nodes = list(g.nodes())
features = [(node, -1.0 * node) for node in nodes]
df = pd.DataFrame(features, columns=["id", "f0"]).set_index("id")
return StellarDiGraph(g, node_features=df)
def create_simple_graph():
"""
Creates a simple directed graph for testing. The node ids are string or integers.
:return: A small, directed graph with 4 nodes and 6 edges in StellarDiGraph format.
"""
g = nx.DiGraph()
edges = [
("root", 2),
("root", 1),
("root", "0"),
(2, "c2.1"),
(2, "c2.2"),
(1, "c1.1"),
]
g.add_edges_from(edges)
return StellarDiGraph(g)
def create_test_graph():
"""
Creates a simple graph for testing. The node ids are string or integers.
:return: A simple graph with 13 nodes and 24 edges (including self loops for all but two of the nodes) in
StellarDiGraph format.
"""
g = nx.DiGraph()
edges = [
("0", 1),
("0", 2),
(1, 3),
(1, 4),
(3, 6),
(4, 7),
(4, 8),
(2, 5),
(5, 9),
(5, 10),
("0", "0"),
(1, 1),
(3, 3),
(6, 6),
(4, 4),
(7, 7),
(8, 8),
(2, 2),
(5, 5),
(9, 9),
(
"self loner",
"self loner",
), # node that is not connected with any other nodes but has self loop
]
g.add_edges_from(edges)
g.add_node(
"loner"
) # node that is not connected to any other nodes and not having a self loop
return StellarDiGraph(g)
def test_weighted_all_zero(self):
edges = pd.DataFrame({
"source": [0, 0],
"target": [1, 2],
"weight": [0.0, 0]
})
g = StellarDiGraph(edges=edges)
bfw = DirectedBreadthFirstNeighbours(g)
walks = bfw.run(nodes=[0],
n=10,
in_size=[20, 20],
out_size=[20, 20],
weighted=True)
assert len(walks) == 10
for walk in walks:
assert len(walk) == 7
assert walk[0] == [0]
for hop in walk:
np.testing.assert_array_equal(hop[1:], -1)
def test_directed_walk_generation_single_root_node(self):
g = nx.DiGraph()
edges = [
("root", 2),
("root", 1),
("root", "0"),
(2, "c2.1"),
(2, "c2.2"),
(1, "c1.1"),
]
g.add_edges_from(edges)
g = StellarDiGraph(g)
def _check_directed_walk(walk, n_size):
if len(n_size) > 1 and n_size[0] > 0 and n_size[1] > 0:
for child_pos in range(n_size[0]):
child = walk[child_pos + 1]
grandchildren_start = 1 + n_size[0] + child_pos * n_size[1]
grandchildren_end = grandchildren_start + n_size[1]
grandchildren = walk[grandchildren_start:grandchildren_end]
if child == "root": # node with three children
for grandchild in grandchildren:
assert grandchild in [0, 1, 2]
elif child == "0": # node without children
for grandchild in grandchildren:
assert grandchild == "root"
elif child == 1: # node with single child
for grandchild in grandchildren:
assert grandchild in ["c1.1", "root"]
elif child == 2: # node with two children
for grandchild in grandchildren:
assert grandchild in ["c2.1", "c2.2", "root"]
else:
assert 1 == 0
bfw = SampledBreadthFirstWalk(g)
nodes = ["root"]
n = 1
n_size = [0]
subgraphs = bfw.run(nodes=nodes, n=n, n_size=n_size)
assert len(subgraphs) == n
assert len(subgraphs[0]) == 1 # all elements should be the same node
assert subgraphs[0][0] == "root"
n_size = [1]
subgraphs = bfw.run(nodes=nodes, n=n, n_size=n_size)
assert len(subgraphs) == n
assert len(subgraphs[0]) == expected_bfw_size(
n_size) # "root" plus child
assert subgraphs[0][0] == "root"
n_size = [2, 2]
subgraphs = bfw.run(nodes=nodes, n=n, n_size=n_size)
assert len(subgraphs) == n
# "root" plus 2 * child + 2 * 2 * grandchild or None
assert len(subgraphs[0]) == expected_bfw_size(n_size)
assert subgraphs[0][0] == "root"
assert subgraphs[0][1] is not None
assert subgraphs[0][2] is not None
_check_directed_walk(subgraphs[0], n_size)
n_size = [3, 2]
subgraphs = bfw.run(nodes=nodes, n=n, n_size=n_size)
assert len(subgraphs) == n
# "root" plus 3 * child + 3 * 2 * grandchild or None
assert len(subgraphs[0]) == expected_bfw_size(n_size)
assert subgraphs[0][0] == "root"
_check_directed_walk(subgraphs[0], n_size)
n = 3
n_size = [0]
subgraphs = bfw.run(nodes=nodes, n=n, n_size=n_size)
assert len(subgraphs) == n
for subgraph in subgraphs:
assert len(subgraph) == 1 # root node only
assert subgraph[0] == "root"
n_size = [1]
subgraphs = bfw.run(nodes=nodes, n=n, n_size=n_size)
assert len(subgraphs) == n
for subgraph in subgraphs:
# "root" plus child
assert len(subgraph) == expected_bfw_size(n_size)
assert subgraph[0] == "root"
n = 99
n_size = [2, 2]
subgraphs = bfw.run(nodes=nodes, n=n, n_size=n_size)
assert len(subgraphs) == n
for subgraph in subgraphs:
# "root" plus 2 * child + 2 * 2 * grandchild or None
assert len(subgraph) == expected_bfw_size(n_size)
assert subgraph[0] == "root"
_check_directed_walk(subgraph, n_size)
n = 17
n_size = [3, 2]
subgraphs = bfw.run(nodes=nodes, n=n, n_size=n_size)
assert len(subgraphs) == n
for subgraph in subgraphs:
# "root" plus 3 * child + 3 * 2 * grandchild or None
assert len(subgraph) == expected_bfw_size(n_size)
assert subgraph[0] == "root"