def main(opts):
dataset = opts.dataset
embed_dim = int(opts.dimension)
# File that contains the edges. Format: source target
# Optionally, you can add weights as third column: source target weight
edge_f = 'Data/%s.edgelist' % dataset
# Specify whether the edges are directed
# isDirected = True
print "Loading Dataset"
# Load graph
G = graph_util.loadGraphFromEdgeListTxt(edge_f, directed=False)
#G = G.to_directed()
embedding = LaplacianEigenmaps(d=embed_dim)
print('Num nodes: %d, num edges: %d' %
(G.number_of_nodes(), G.number_of_edges()))
t1 = time()
# Learn embedding - accepts a networkx graph or file with edge list
print "Starting Embedding"
Y, t = embedding.learn_embedding(graph=G,
edge_f=None,
is_weighted=True,
no_python=True)
print(embedding._method_name + ':\n\tTraining time: %f' % (time() - t1))
np_save(writable("Embedding_Results", "jac_" + dataset + str(embed_dim)),
Y)
def main(data_set_name):
dimensions = 4
input_file = './graph/' + data_set_name + '.tsv'
output_file = './emb/' + data_set_name + '.emb'
# Instatiate the embedding method with hyperparameters
graph_factorization = LaplacianEigenmaps(dimensions)
# Load graph
graph = graph_util.loadGraphFromEdgeListTxt(input_file)
# Learn embedding - accepts a networkx graph or file with edge list
embeddings_array, t = graph_factorization.learn_embedding(graph, edge_f=None, is_weighted=True, no_python=True)
embeddings = pandas.DataFrame(embeddings_array)
embeddings.to_csv(output_file, sep=' ', na_rep=0.1)
G = G.to_directed()
if not os.path.exists('SAVER_SUP/'+fig_name[grp]+str(x+1)):
os.makedirs('SAVER_SUP/'+fig_name[grp]+str(x+1))
# split the graph into 60-20-20 ratio, 60% for calculating the edge features, 20% for training the classifier, 20% for evaluating the model.
train_digraph, test_digraph = train_test_split.splitDiGraphToTrainTest2(G, train_ratio = 0.6, is_undirected=True)
train_digraph1, test_digraph = evaluation_util.splitDiGraphToTrainTest(test_digraph, train_ratio=0.5, is_undirected=True)
# embeddings without relearning
print ("saving for LE")
for dim in dimensions:
embedding=LaplacianEigenmaps(d=dim)
X, _ = embedding.learn_embedding(graph=train_digraph, no_python=False)
file_name='SAVER_SUP/'+fig_name[grp]+str(x+1)+'/LE1_'+str(dim)
parameter_file=open(file_name, 'wb')
pickle.dump(X,parameter_file)
parameter_file.close()
print ("saving for DEEPWALK")
for dim in dimensions:
embedding=node2vec(d=dim, max_iter=1, walk_len=80, num_walks=10, con_size=10, ret_p=1, inout_p=1)
X, _ = embedding.learn_embedding(graph=train_digraph, no_python=False)
file_name='SAVER_SUP/'+fig_name[grp]+str(x+1)+'/DEEPWALK1_'+str(dim)
parameter_file=open(file_name, 'wb')
pickle.dump(X,parameter_file)
parameter_file.close()
print ("saving for n2vA")
print('Score without neighbours data')
create_and_evaluate_classifier(no_neighbour_train_features, train_targets,
no_neighbour_test_features, test_targets)
print('Score with neighbours data')
# we can use the same '[]_targets' because both (with neighbours and without) datasets are extracted from the same
# datasets: 'train_data' and 'test_data' and follow the same order of nodes
create_and_evaluate_classifier(neighbour_train_features, train_targets,
neighbour_test_features, test_targets)
###############################################################
if not os.path.exists(LAPLACIAN_EMB_FILE_PATH):
laplacian = LaplacianEigenmaps(d=50)
embs = laplacian.learn_embedding(g,
edge_f=None,
is_weighted=False,
no_python=True)
save_embeddings(LAPLACIAN_EMB_FILE_PATH, embs[0], list(g.nodes))
laplacian_embs = read_embeddings(LAPLACIAN_EMB_FILE_PATH)
node2vec_embs = read_embeddings(
NODE2VEC_EMB_FILE_PATH) # we already have the embeddings
sdne_embs = read_embeddings(
SDNE_EMB_FILE_PATH) # we already have the embeddings
print('LAPLACIAN')
create_and_evaluate_classifier(
*extract_data_from_embs(laplacian_embs, train_data, test_data))
print('NODE2VEC')
create_and_evaluate_classifier(
*extract_data_from_embs(node2vec_embs, train_data, test_data))