def karate_test(pos_train_file, pos_valid_file, pos_test_file, neg_train_file,
neg_valid_file, neg_test_file, embed_graph, p, q, walk_length,
num_walks, num_epochs, classifier, edge_embed_method,
skipValidation, output):
pos_train_graph = CSFGraph(pos_train_file)
pos_valid_graph = CSFGraph(pos_valid_file)
pos_test_graph = CSFGraph(pos_test_file)
neg_train_graph = CSFGraph(neg_train_file)
neg_valid_graph = CSFGraph(neg_valid_file)
neg_test_graph = CSFGraph(neg_test_file)
# Graph (node) embeding using SkipGram as the word2vec model, with 2 epochs.
graph = embiggen.random_walk_generator.N2vGraph(pos_train_graph, p, q)
walks = graph.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()
model = SkipGramWord2Vec(walks,
worddictionary=worddictionary,
reverse_worddictionary=reverse_worddictionary,
num_epochs=num_epochs)
model.train()
write_embeddings(embed_graph, model.embedding, reverse_worddictionary)
# Link prediction on the pos/neg train/valid/test sets using RF classifier
lp = LinkPrediction(pos_train_graph, pos_valid_graph, pos_test_graph,
neg_train_graph, neg_valid_graph, neg_test_graph,
embed_graph, edge_embed_method, classifier,
skipValidation, output)
lp.prepare_edge_and_node_labels()
lp.predict_links()
lp.output_classifier_results()
def setUp(self):
curdir = os.path.dirname(__file__)
pos_train = os.path.join(curdir, 'data/ppismall/pos_train_edges')
pos_train = os.path.abspath(pos_train)
training_graph = CSFGraph(pos_train)
# obtain data needed to build model
worddictionary = training_graph.get_node_to_index_map()
reverse_worddictionary = training_graph.get_index_to_node_map()
# initialize n2v object
p, q = 1, 1
self.number_of_nodes_in_training = training_graph.node_count()
self.n2v_graph = N2vGraph(csf_graph=training_graph, p=p, q=q)
# generate random walks
self.walk_length = 10
self.num_walks = 5
self.walks = self.n2v_graph.simulate_walks(num_walks=self.num_walks, walk_length=self.walk_length)
# walks is now a list of lists of ints
# build cbow model
self.cbow = ContinuousBagOfWordsWord2Vec(self.walks,
worddictionary=worddictionary,
reverse_worddictionary=reverse_worddictionary,
num_epochs=2)
self.cbow.train()
def setUp(self):
# read in sample data
current_directory = os.path.dirname(__file__)
self.data_dir = os.path.join(current_directory, 'data')
pos_train = os.path.abspath(self.data_dir +
'/ppismall/pos_train_edges')
# read data into graph
training_graph = CSFGraph(pos_train)
worddictionary = training_graph.get_node_to_index_map()
self.reverse_worddictionary = training_graph.get_index_to_node_map()
# generate random walks
n2v_graph = N2vGraph(training_graph, 1, 1)
walks = n2v_graph.simulate_walks(5, 10)
# learn embeddings
self.model = ContinuousBagOfWordsWord2Vec(
walks,
worddictionary=worddictionary,
reverse_worddictionary=self.reverse_worddictionary,
num_epochs=2)
# create temporary directory to write data to
self.temp_dir_loc = os.path.abspath(self.data_dir + '/temp')
os.mkdir(self.temp_dir_loc)
return None