def testRBallHyper_CenterDefaultColor(self):
dummy_hypergraph = Hypergraph(example_graphs.gt_dummy_graph)
rball_in = algorithms.r_ball_hyper(dummy_hypergraph,
"n_10",
2,
-1,
center_default_color=True)
rball_out = algorithms.r_ball_hyper(dummy_hypergraph,
"n_10",
2,
1,
center_default_color=True)
rball_all = algorithms.r_ball_hyper(dummy_hypergraph,
"n_10",
2,
0,
center_default_color=True)
d_rball_all = Hypergraph(example_graphs.gt_dummy_rball_10_r2_all)
d_rball_out = Hypergraph(example_graphs.gt_dummy_rball_10_r2_out)
d_rball_in = Hypergraph(example_graphs.gt_dummy_rball_10_r2_in)
d_rball_all.node["n_10"]["labels"] = ["0"]
d_rball_out.node["n_10"]["labels"] = ["0"]
d_rball_in.node["n_10"]["labels"] = ["0"]
all_isomorphic = algorithms.isomorphic(d_rball_all, rball_all)
out_isomorphic = algorithms.isomorphic(d_rball_out, rball_out)
in_isomorphic = algorithms.isomorphic(d_rball_in, rball_in)
self.assertTrue(all_isomorphic,
"Problem extracting r-ball with edge_dir=0.")
self.assertTrue(out_isomorphic,
"Problem extracting r-ball with edge_dir=1.")
self.assertTrue(in_isomorphic,
"Problem extracting r-ball with edge_dir=-1.")
def testFeatureExtraction(self):
wl_state_exp = {
"labels": {
"g": "wl_0.0",
"n": "wl_0.1",
"r": "wl_0.2",
"b": "wl_0.3",
"wl_0.0;in(wl_0.2),out(wl_0.2)": "wl_1.0",
"wl_0.1;in(wl_0.2),out(wl_0.2)": "wl_1.1",
"wl_0.2;in(wl_0.1)": "wl_1.2",
"wl_0.2;out(wl_0.0,wl_0.1)": "wl_1.3",
"wl_0.2;in(wl_0.0)": "wl_1.4",
"wl_0.1;in(wl_0.3),out(wl_0.2)": "wl_1.5",
"wl_0.3;out(wl_0.1)": "wl_1.6",
"wl_0.2;in(wl_0.1,wl_0.1)": "wl_1.7"
},
"next_labels": {
0: 4,
1: 8
}
}
dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph)
rballs_database = [r_ball_hyper(dummy_hypergraph, "n_2", 1, edge_dir=1),
r_ball_hyper(dummy_hypergraph, "n_2", 1, edge_dir=-1)]
features = []
wl_state = None
for rball in rballs_database:
new_features, wl_state = feature_extraction.extract_features(rball, wl_iterations=1, wl_state=wl_state)
features += new_features
self.assertEqual(wl_state_exp, wl_state, "The wrong wl_state was computed by Weisfeiler-Lehman.")
isomorphic = all([algorithms.isomorphic(features[i], example_graphs.snm_dummy_graph_features[i]) for i in range(len(features))])
self.assertTrue(isomorphic, "Wrong features extracted.")
def extract_rballs_of_node(node,
hypergraph,
r_in=0,
r_out=0,
r_all=0,
center_default_color=False):
rballs = [
r_ball_hyper(hypergraph,
node,
r_in,
edge_dir=-1,
center_default_color=center_default_color)
if r_in > 0 else None,
r_ball_hyper(hypergraph,
node,
r_out,
edge_dir=1,
center_default_color=center_default_color)
if r_out > 0 else None,
r_ball_hyper(hypergraph,
node,
r_all,
edge_dir=0,
center_default_color=center_default_color)
if r_all > 0 else None
]
return filter(lambda x: x is not None, rballs)
def testRBallHyper(self):
dummy_hypergraph = Hypergraph(example_graphs.gt_dummy_graph)
rball_in = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, -1)
rball_out = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, 1)
rball_all = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, 0)
d_rball_all = Hypergraph(example_graphs.gt_dummy_rball_10_r2_all)
d_rball_out = Hypergraph(example_graphs.gt_dummy_rball_10_r2_out)
d_rball_in = Hypergraph(example_graphs.gt_dummy_rball_10_r2_in)
all_isomorphic = algorithms.isomorphic(d_rball_all, rball_all)
out_isomorphic = algorithms.isomorphic(d_rball_out, rball_out)
in_isomorphic = algorithms.isomorphic(d_rball_in, rball_in)
self.assertTrue(all_isomorphic, "Problem extracting r-ball with edge_dir=0.")
self.assertTrue(out_isomorphic, "Problem extracting r-ball with edge_dir=1.")
self.assertTrue(in_isomorphic, "Problem extracting r-ball with edge_dir=-1.")
def testRBallHyper(self):
dummy_hypergraph = Hypergraph(example_graphs.gt_dummy_graph)
rball_in = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, -1)
rball_out = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, 1)
rball_all = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, 0)
d_rball_all = Hypergraph(example_graphs.gt_dummy_rball_10_r2_all)
d_rball_out = Hypergraph(example_graphs.gt_dummy_rball_10_r2_out)
d_rball_in = Hypergraph(example_graphs.gt_dummy_rball_10_r2_in)
all_isomorphic = algorithms.isomorphic(d_rball_all, rball_all)
out_isomorphic = algorithms.isomorphic(d_rball_out, rball_out)
in_isomorphic = algorithms.isomorphic(d_rball_in, rball_in)
self.assertTrue(all_isomorphic,
"Problem extracting r-ball with edge_dir=0.")
self.assertTrue(out_isomorphic,
"Problem extracting r-ball with edge_dir=1.")
self.assertTrue(in_isomorphic,
"Problem extracting r-ball with edge_dir=-1.")
def testRBallHyper_CenterDefaultColor(self):
dummy_hypergraph = Hypergraph(example_graphs.gt_dummy_graph)
rball_in = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, -1, center_default_color=True)
rball_out = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, 1, center_default_color=True)
rball_all = algorithms.r_ball_hyper(dummy_hypergraph, "n_10", 2, 0, center_default_color=True)
d_rball_all = Hypergraph(example_graphs.gt_dummy_rball_10_r2_all)
d_rball_out = Hypergraph(example_graphs.gt_dummy_rball_10_r2_out)
d_rball_in = Hypergraph(example_graphs.gt_dummy_rball_10_r2_in)
d_rball_all.node["n_10"]["labels"] = ["0"]
d_rball_out.node["n_10"]["labels"] = ["0"]
d_rball_in.node["n_10"]["labels"] = ["0"]
all_isomorphic = algorithms.isomorphic(d_rball_all, rball_all)
out_isomorphic = algorithms.isomorphic(d_rball_out, rball_out)
in_isomorphic = algorithms.isomorphic(d_rball_in, rball_in)
self.assertTrue(all_isomorphic, "Problem extracting r-ball with edge_dir=0.")
self.assertTrue(out_isomorphic, "Problem extracting r-ball with edge_dir=1.")
self.assertTrue(in_isomorphic, "Problem extracting r-ball with edge_dir=-1.")
def testFeatureExtraction(self):
wl_state_exp = {
"labels": {
"g": "wl_0.0",
"n": "wl_0.1",
"r": "wl_0.2",
"b": "wl_0.3",
"wl_0.0;in(wl_0.2),out(wl_0.2)": "wl_1.0",
"wl_0.1;in(wl_0.2),out(wl_0.2)": "wl_1.1",
"wl_0.2;in(wl_0.1)": "wl_1.2",
"wl_0.2;out(wl_0.0,wl_0.1)": "wl_1.3",
"wl_0.2;in(wl_0.0)": "wl_1.4",
"wl_0.1;in(wl_0.3),out(wl_0.2)": "wl_1.5",
"wl_0.3;out(wl_0.1)": "wl_1.6",
"wl_0.2;in(wl_0.1,wl_0.1)": "wl_1.7"
},
"next_labels": {
0: 4,
1: 8
}
}
dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph)
rballs_database = [
r_ball_hyper(dummy_hypergraph, "n_2", 1, edge_dir=1),
r_ball_hyper(dummy_hypergraph, "n_2", 1, edge_dir=-1)
]
features = []
wl_state = None
for rball in rballs_database:
new_features, wl_state = feature_extraction.extract_features(
rball, wl_iterations=1, wl_state=wl_state)
features += new_features
self.assertEqual(
wl_state_exp, wl_state,
"The wrong wl_state was computed by Weisfeiler-Lehman.")
isomorphic = all([
algorithms.isomorphic(features[i],
example_graphs.snm_dummy_graph_features[i])
for i in range(len(features))
])
self.assertTrue(isomorphic, "Wrong features extracted.")
def extract_rballs_of_node(node, hypergraph, r_in=0, r_out=0, r_all=0, center_default_color=False):
rballs = [r_ball_hyper(hypergraph, node, r_in, edge_dir=-1, center_default_color=center_default_color) if r_in > 0 else None,
r_ball_hyper(hypergraph, node, r_out, edge_dir=1, center_default_color=center_default_color) if r_out > 0 else None,
r_ball_hyper(hypergraph, node, r_all, edge_dir=0, center_default_color=center_default_color) if r_all > 0 else None]
return filter(lambda x: x is not None, rballs)
def chem_database_generator(full_graph, uri_node_map, type_color_map, compounds_and_targets):
literal_colors = set()
for rdf_type in type_color_map:
# TODO: this condition is unsafe because it may remove not only literal colors
if rdf_type.startswith(u"http://www.w3.org/2001/XMLSchema#"):
literal_colors.add(type_color_map[rdf_type])
bool_colors = filter(lambda x: x.startswith(u"http://www.w3.org/2001/XMLSchema#boolean"), type_color_map)
bool_colors = set(map(lambda x: type_color_map[x], bool_colors))
literal_colors -= bool_colors
for node in full_graph.nodes():
node_labels_set = set(full_graph.node[node]["labels"])
# remove all literals (except booleans)
if literal_colors & node_labels_set:
full_graph.remove_node(node)
# remove the color of named individual type from all nodes where it occurs
named_indiv_uri = u"http://www.w3.org/2002/07/owl#NamedIndividual"
if named_indiv_uri in type_color_map:
named_indiv_color = type_color_map[named_indiv_uri]
for node in full_graph.nodes_iter():
if named_indiv_color in full_graph.node[node]["labels"]:
full_graph.node[node]["labels"].remove(named_indiv_color)
full_hypergraph = Hypergraph(full_graph)
# ################
# # INFO: use this to remove the isMutagenic property when predicting mutagenicity
# is_mutag_color = type_color_map[u"http://dl-learner.org/carcinogenesis#isMutagenic"]
# edges_to_remove = []
# for edge in full_hypergraph.edges_iter():
# if is_mutag_color in full_hypergraph.edge(edge)['labels']:
# edges_to_remove.append(edge)
# for edge in edges_to_remove:
# full_hypergraph.safe_remove_edge(edge)
# ################
if not compounds_and_targets:
compounds_and_targets = read_compounds_and_targets()
def remove_other_neighbors_of_bool_literals(hypergraph, center_node):
center_neighbors = hypergraph.neighbors(center_node)
bool_literals = filter(lambda n: set(hypergraph.node[n]['labels']) & bool_colors, center_neighbors)
for bool_literal in bool_literals:
bool_literal_neigbors = set(hypergraph.neighbors(bool_literal))
# exclude the center node from the removable nodes
bool_literal_neigbors.remove(center_node)
for neigh in bool_literal_neigbors:
hypergraph.safe_remove_node(neigh)
for comp_id, target_label in compounds_and_targets:
node_id = u"n_{0}".format(uri_node_map[uri_prefix + comp_id])
comp_neighborhood_hypergraph = algorithms.r_ball_hyper(full_hypergraph, node_id, 2, 0)
remove_other_neighbors_of_bool_literals(comp_neighborhood_hypergraph, node_id)
ch_db_record = (comp_id, [comp_neighborhood_hypergraph], target_label)
if process_compound_function:
process_compound_function(ch_db_record)
# ############
# def get_key(value, dictionary):
# for key in dictionary:
# if dictionary[key] == value:
# return key
# return None
# g = ch_db_record[1][0].copy()
# for n in g.node:
# n_new_labels = []
# for n_color in g.node[n]['labels']:
# n_rdf_type = get_key(n_color, type_color_map)
# n_rdf_type = n_rdf_type[n_rdf_type.find(u"#") + 1:]
# n_new_labels.append(n_rdf_type)
# g.node[n]['labels'] = n_new_labels
# g.visualize()
# ############
yield ch_db_record