def test_betweenness_by_hand():
graph = Graph('gr', 'gr.xml', 4)
graph.add_node(Node(0, LabelNodeLetter(0, 0)))
graph.add_node(Node(1, LabelNodeLetter(0, 0)))
graph.add_node(Node(2, LabelNodeLetter(0, 0)))
graph.add_node(Node(3, LabelNodeLetter(0, 0)))
graph.add_edge(Edge(0, 1, LabelEdge(0)))
graph.add_edge(Edge(1, 2, LabelEdge(0)))
graph.add_edge(Edge(2, 3, LabelEdge(0)))
betweenness = Betweenness()
results = betweenness.calc_centrality_score(graph)
results = np.asarray(results)
graph2 = nx.Graph()
graph2.add_node(1)
graph2.add_node(2)
graph2.add_node(3)
graph2.add_node(4)
graph2.add_edge(1, 2)
graph2.add_edge(2, 3)
graph2.add_edge(3, 4)
expected_dict = nx.betweenness_centrality(graph2, normalized=False)
expected = np.array([val for _, val in expected_dict.items()])
print(results)
assert np.linalg.norm(results - expected) < 1e-6
def test_remove_node(num_nodes, idx_to_remove, expected_adj):
my_graph = Graph(f'gr{num_nodes}', f'gr{num_nodes}.gxl', num_nodes)
nodes = []
for i in range(num_nodes):
tmp_node = Node(i, LabelNodeLetter(1+i, 1))
nodes.append(tmp_node)
my_graph.add_node(tmp_node)
for idx_start, idx_end in combinations(range(num_nodes), 2):
tmp_edge = Edge(idx_start, idx_end, LabelEdge(0))
my_graph.add_edge(tmp_edge)
my_graph.remove_node_by_idx(idx_to_remove)
# nodes.pop(0)
# expected edges
# expected_adjacency_mat = np.array([[0, 1, 1],
# [1, 0, 1],
# [1, 1, 0]])
print(f'--{nodes}')
print(my_graph.get_nodes())
# assert my_graph.get_nodes() == nodes
assert len(my_graph) == num_nodes - 1
def test_pagerank_by_hand():
graph = Graph('gr', 'gr.xml', 4)
graph.add_node(Node(0, LabelNodeLetter(0, 0)))
graph.add_node(Node(1, LabelNodeLetter(0, 0)))
graph.add_node(Node(2, LabelNodeLetter(0, 0)))
graph.add_node(Node(3, LabelNodeLetter(0, 0)))
graph.add_edge(Edge(0, 1, LabelEdge(0)))
graph.add_edge(Edge(1, 2, LabelEdge(0)))
graph.add_edge(Edge(2, 3, LabelEdge(0)))
pagerank = PageRank()
results = pagerank.calc_centrality_score(graph)
results = np.asarray(results)
graph2 = nx.Graph()
graph2.add_node(1)
graph2.add_node(2)
graph2.add_node(3)
graph2.add_node(4)
graph2.add_edge(1, 2)
graph2.add_edge(2, 3)
graph2.add_edge(3, 4)
expected = np.array([val for _, val in nx.pagerank_scipy(graph2).items()])
print(results)
assert np.linalg.norm(results - expected) < 1e-6
def test_insert_invalid_edge(num_nodes, nodes, edge, expected_error_msg):
my_graph = Graph(f'gr{num_nodes}', f'gr{num_nodes}.gxl', num_nodes)
for node in nodes:
my_graph.add_node(node)
with pytest.raises(AssertionError) as execinfo:
my_graph.add_edge(edge)
error_msg = execinfo.value.args[0]
assert error_msg == expected_error_msg
def test_out_in_degrees(num_nodes, expected_matrix):
my_graph = Graph(f'gr{num_nodes}', f'gr{num_nodes}.gxl', num_nodes)
for i in range(num_nodes):
tmp_node = Node(i, LabelNodeLetter(i, i))
my_graph.add_node(tmp_node)
for idx_start, idx_end in combinations(range(num_nodes), 2):
tmp_edge = Edge(idx_start, idx_end, LabelEdge(0))
my_graph.add_edge(tmp_edge)
assert np.array_equal(np.asarray(my_graph.out_degrees()), expected_matrix)
def test_add_clique_edge(num_nodes, expected_edges):
my_graph = Graph(f'gr{num_nodes}', f'gr{num_nodes}.gxl', num_nodes)
for i in range(num_nodes):
tmp_node = Node(i, LabelNodeLetter(i, i))
my_graph.add_node(tmp_node)
for idx_start, idx_end in combinations(range(num_nodes), 2):
tmp_edge = Edge(idx_start, idx_end, LabelEdge(0))
my_graph.add_edge(tmp_edge)
assert my_graph.get_edges() == expected_edges
assert my_graph.has_edge(0, num_nodes - 1) == True
assert my_graph.has_edge(num_nodes - 1, 0) == True
assert my_graph.has_edge(0, num_nodes + 1) == False
def test_adjacency_matrix(num_nodes, expected_matrix):
my_graph = Graph(f'gr{num_nodes}', f'gr{num_nodes}.gxl', num_nodes)
for i in range(num_nodes):
tmp_node = Node(i, LabelNodeLetter(i, i))
my_graph.add_node(tmp_node)
for idx_start, idx_end in combinations(range(num_nodes), 2):
tmp_edge = Edge(idx_start, idx_end, LabelEdge(0))
my_graph.add_edge(tmp_edge)
# transform memoryview to np.array
# my_graph.adjacency_matrix.base
# np.asarray(my_graph.adjacency_matrix)
assert np.array_equal(np.asarray(my_graph.adjacency_matrix), expected_matrix)
def test_pagerank_by_hand_big():
graph = Graph('gr', 'gr.xml', 6)
graph2 = nx.Graph()
for i in range(6):
graph.add_node(Node(i, LabelNodeLetter(0, 0)))
graph2.add_node(i)
### Add edge to graph
graph.add_edge(Edge(0, 1, LabelEdge(0)))
graph.add_edge(Edge(0, 2, LabelEdge(0)))
graph.add_edge(Edge(0, 4, LabelEdge(0)))
graph.add_edge(Edge(0, 5, LabelEdge(0)))
graph.add_edge(Edge(1, 2, LabelEdge(0)))
graph.add_edge(Edge(2, 3, LabelEdge(0)))
graph.add_edge(Edge(2, 5, LabelEdge(0)))
graph.add_edge(Edge(3, 4, LabelEdge(0)))
graph.add_edge(Edge(3, 5, LabelEdge(0)))
pagerank = PageRank()
results = pagerank.calc_centrality_score(graph)
results = np.asarray(results)
### Add edge to nx.graph
graph2.add_edge(0, 1)
graph2.add_edge(0, 2)
graph2.add_edge(0, 4)
graph2.add_edge(0, 5)
graph2.add_edge(1, 2)
graph2.add_edge(2, 3)
graph2.add_edge(2, 5)
graph2.add_edge(3, 4)
graph2.add_edge(3, 5)
expected = np.array([val for _, val in nx.pagerank_scipy(graph2).items()])
assert np.linalg.norm(results - expected) < 1e-6
def test_3_nodes_1_node(ged):
gr_src = Graph('gr1', 'gr1.gxl', 3)
gr_trgt = Graph('gr2', 'gr2.gxl', 1)
gr_src.add_node(Node(0, LabelNodeAIDS('O', 1, 1, 2., 2.)))
gr_src.add_node(Node(1, LabelNodeAIDS('C', 1, 1, 2., 2.)))
gr_src.add_node(Node(2, LabelNodeAIDS('O', 1, 1, 2., 2.)))
gr_src.add_edge(Edge(0, 1, LabelEdge(0)))
gr_src.add_edge(Edge(1, 2, LabelEdge(0)))
gr_trgt.add_node(Node(0, LabelNodeAIDS('H', 1, 1, 2., 2.)))
dist = ged.compute_edit_distance(gr_src, gr_trgt)
print(ged.C.base)
print(ged.C_star.base)
expected_dist = 4.6
assert round(dist, 2) == expected_dist
def define_graphs():
n, m = 4, 3
graph_source = Graph('gr_source', 'gr_source.gxl', n)
graph_target = Graph('gr_target', 'gr_targe.gxl', m)
# Init graph source: add nodes and edges
graph_source.add_node(Node(0, LabelNodeLetter(1, 0)))
graph_source.add_node(Node(1, LabelNodeLetter(2, 0)))
graph_source.add_node(Node(2, LabelNodeLetter(1, 0)))
graph_source.add_node(Node(3, LabelNodeLetter(3, 0)))
graph_source.add_edge(Edge(0, 1, LabelEdge(0)))
graph_source.add_edge(Edge(1, 2, LabelEdge(0)))
graph_source.add_edge(Edge(1, 3, LabelEdge(0)))
graph_source.add_edge(Edge(2, 3, LabelEdge(0)))
# Init graph target: add nodes and edges
graph_target.add_node(Node(0, LabelNodeLetter(3, 0)))
graph_target.add_node(Node(1, LabelNodeLetter(2, 0)))
graph_target.add_node(Node(2, LabelNodeLetter(2, 0)))
graph_target.add_edge(Edge(0, 1, LabelEdge(0)))
graph_target.add_edge(Edge(1, 2, LabelEdge(0)))
return graph_source, graph_target
def test_mutagenicity_with_deleted_nodes(mutagenicity_graphs, dataframe_mutagenicity, graph_name_source_target):
gr_name_src, gr_name_trgt = ['mutagen/' + name for name in graph_name_source_target]
graph_name_source, graph_name_target = graph_name_source_target
graph_source = [graph for graph in mutagenicity_graphs if graph.name == graph_name_source][0]
graph_target = [graph for graph in mutagenicity_graphs if graph.name == graph_name_target][0]
cst_cost_node = 11.0
cst_cost_edge = 1.1
ged = GED(EditCostMutagenicity(cst_cost_node, cst_cost_node,
cst_cost_edge, cst_cost_edge, 'dirac'))
# Reproduce the source graph with more nodes
new_gr_src = Graph(gr_name_src, 'gr.xls', len(graph_source)+2)
for node in graph_source.nodes:
new_gr_src.add_node(node)
for idx, edges in graph_source.get_edges().items():
for edge in edges:
if edge is None:
continue
new_gr_src.add_edge(edge)
new_gr_src.add_node(Node(len(graph_source), LabelNodeMutagenicity('C')))
new_gr_src.add_node(Node(len(graph_source)+1, LabelNodeMutagenicity('N')))
# Add random Edges
for _ in range(4):
new_gr_src.add_edge(Edge(len(graph_source),
random.randint(0, len(graph_source)-1),
LabelEdge(0)))
for _ in range(6):
new_gr_src.add_edge(Edge(len(graph_source) + 1,
random.randint(0, len(graph_source)),
LabelEdge(0)))
new_gr_src.remove_node_by_idx(len(graph_source))
new_gr_src.remove_node_by_idx(len(graph_source))
results = ged.compute_edit_distance(new_gr_src, graph_target)
expected = dataframe_mutagenicity.loc[gr_name_src, gr_name_trgt]
# import numpy as np
# np.savetxt(f'_c_{"X".join(graph_name_source_target)}.csv', np.asarray(ged.C), fmt='%10.3f', delimiter=';')
# np.savetxt(f'c_star_{"X".join(graph_name_source_target)}.csv', np.asarray(ged.C_star), fmt='%10.3f', delimiter=';')
print(f'###### diff {results - expected}')
print(f'{graph_name_source_target}: new dist {results} - old dist {expected}')
print(f'exp {expected}')
assert results == expected
def test_with_deleted_node(ged):
gr_src = Graph('gr1', 'gr1.gxl', 3)
gr_trgt = Graph('gr2', 'gr2.gxl', 3)
gr_src = Graph('gr1', 'gr1.gxl', 5)
gr_src.add_node(Node(0, LabelNodeAIDS('O', 1, 1, 2., 2.)))
gr_src.add_node(Node(1, LabelNodeAIDS('C', 1, 1, 2., 2.)))
gr_src.add_node(Node(2, LabelNodeAIDS('O', 1, 1, 2., 2.)))
# print(gr_src)
gr_src.add_node(Node(3, LabelNodeAIDS('Cl', 1, 1, 2., 2.)))
gr_src.add_node(Node(4, LabelNodeAIDS('N', 1, 1, 2.4, 2.)))
gr_src.add_edge(Edge(0, 3, LabelEdge(0)))
gr_src.add_edge(Edge(1, 3, LabelEdge(0)))
gr_src.add_edge(Edge(4, 2, LabelEdge(0)))
gr_src.add_edge(Edge(3, 4, LabelEdge(0)))
gr_src.remove_node_by_idx(4)
gr_src.remove_node_by_idx(3)
print(gr_src)
gr_trgt.add_node(Node(0, LabelNodeAIDS('H', 1, 1, 2., 2.)))
gr_trgt.add_node(Node(1, LabelNodeAIDS('Ca', 1, 1, 2., 2.)))
gr_trgt.add_node(Node(2, LabelNodeAIDS('C', 1, 1, 2., 2.)))
gr_trgt.add_edge(Edge(0, 1, LabelEdge(0)))
gr_trgt.add_edge(Edge(1, 2, LabelEdge(0)))
gr_trgt.add_edge(Edge(2, 0, LabelEdge(0)))
dist = ged.compute_edit_distance(gr_src, gr_trgt)
print(ged.C.base)
print(ged.C_star.base)
expected_dist = 4.7
print(dist)
assert round(dist, 2) == expected_dist