def disease_gene_embeddings(training_file, output_file, p, q, gamma, use_gamma,
walk_length, num_walks, dimensions, window_size,
workers, num_steps, display_step):
"""
Generate disease gene embeddings
"""
logging.basicConfig(level=logging.INFO)
print("Reading training file %s" % training_file)
training_graph = CSFGraph(training_file)
print(training_graph)
training_graph.print_edge_type_distribution()
hetgraph = xn2v.hetnode2vec.N2vGraph(training_graph, p, q, gamma,
use_gamma)
walks = hetgraph.simulate_walks(num_walks, walk_length)
worddictionary = training_graph.get_node_to_index_map()
reverse_worddictionary = training_graph.get_index_to_node_map()
numberwalks = []
for w in walks:
nwalk = []
for node in w:
i = worddictionary[node]
nwalk.append(i)
numberwalks.append(nwalk)
model = SkipGramWord2Vec(numberwalks,
worddictionary=worddictionary,
reverse_worddictionary=reverse_worddictionary,
num_steps=num_steps)
model.train(display_step=display_step)
model.write_embeddings(output_file)
def karate_test(training_file, test_file, output_file, p, q, gamma, use_gamma,
walk_length, num_walks):
training_graph = CSFGraph(training_file)
hetgraph = xn2v.hetnode2vec.N2vGraph(training_graph, p, q, gamma,
use_gamma)
walks = hetgraph.simulate_walks(num_walks, walk_length)
worddictionary = training_graph.get_node_to_index_map()
reverse_worddictionary = training_graph.get_index_to_node_map()
numberwalks = []
for w in walks:
nwalk = []
for node in w:
i = worddictionary[node]
nwalk.append(i)
numberwalks.append(nwalk)
model = SkipGramWord2Vec(numberwalks,
worddictionary=worddictionary,
reverse_worddictionary=reverse_worddictionary,
num_steps=1000)
model.train(display_step=100)
output_filenname = 'karate.embedded'
model.write_embeddings(output_filenname)
test_graph = CSFGraph(test_file)
path_to_embedded_graph = output_filenname
parameters = {
'edge_embedding_method': "hadamard",
'portion_false_edges': 1
}
lp = LinkPrediction(
training_graph, test_graph, path_to_embedded_graph, params=parameters
) #TODO:modify this part to work with new link prediction
lp.predict_links()
lp.output_Logistic_Reg_results()
def test_embedding(self):
training_file = os.path.join(os.path.dirname(__file__), 'data',
'karate.train')
output_file = os.path.join(os.path.dirname(__file__), 'data',
'disease.embedded')
training_graph = CSFGraph(training_file)
training_graph.print_edge_type_distribution()
p = 1
q = 1
gamma = 1
useGamma = False
hetgraph = xn2v.hetnode2vec.N2vGraph(training_graph, p, q, gamma,
useGamma)
walk_length = 80
num_walks = 25
walks = hetgraph.simulate_walks(num_walks, walk_length)
worddictionary = training_graph.get_node_to_index_map()
reverse_worddictionary = training_graph.get_index_to_node_map()
numberwalks = []
for w in walks:
nwalk = []
for node in w:
i = worddictionary[node]
nwalk.append(i)
numberwalks.append(nwalk)
model = SkipGramWord2Vec(numberwalks,
worddictionary=worddictionary,
reverse_worddictionary=reverse_worddictionary,
num_steps=100)
model.train(display_step=10)
model.write_embeddings(output_file)
neg_test_graph = CSFGraph(neg_test_file)
p = 1
q = 1
gamma = 1
useGamma = False
hetgraph = xn2v.hetnode2vec.N2vGraph(pos_train_graph, p, q, gamma, useGamma)
walk_length = 80
num_walks = 100
dimensions = 128
window_size = 10
workers = 8
walks = hetgraph.simulate_walks(num_walks, walk_length)
worddictionary = pos_train_graph.get_node_to_index_map()
reverse_worddictionary = pos_train_graph.get_index_to_node_map()
walks_integer_nodes = []
for w in walks:
nwalk = []
for node in w:
i = worddictionary[node]
nwalk.append(i)
walks_integer_nodes.append(nwalk)
model = SkipGramWord2Vec(walks_integer_nodes,
worddictionary=worddictionary,
reverse_worddictionary=reverse_worddictionary,
num_steps=100)
model.train(display_step=2)
g = CSFGraph(training_file)
p = 1
q = 1
gamma = 1
useGamma = False
graph = xn2v.hetnode2vec.N2vGraph(g, p, q, gamma, useGamma)
walk_length = 80
num_walks = 100
walks = graph.simulate_walks(num_walks, walk_length)
dimensions = 128
window_size = 10
workers = 8
worddictionary = g.get_node_to_index_map()
reverse_worddictionary = g.get_index_to_node_map()
walks_integer_nodes = []
for w in walks:
nwalk = []
for node in w:
i = worddictionary[node]
nwalk.append(i)
walks_integer_nodes.append(nwalk)
model = SkipGramWord2Vec(walks_integer_nodes,
worddictionary=worddictionary,
reverse_worddictionary=reverse_worddictionary,
num_steps=100)
model.train(display_step=2)