def main(args):
t1 = time.time()
g = Graph()
singluar_node_file = "singluar_nodes.txt"
print("Reading...")
if args.graph_format == 'adjlist':
g.read_adjlist(filename=args.input)
elif args.graph_format == 'edgelist':
g.read_edgelist(filename=args.input, weighted=args.weighted, directed=args.directed)
if args.method == 'node2vec':
model = node2vec.Node2vec(graph=g, path_length=args.walk_length,
num_paths=args.number_walks, dim=args.representation_size,
workers=args.workers, p=args.p, q=args.q, window=args.window_size)
elif args.method == 'line':
if args.label_file and not args.no_auto_save:
model = line.LINE(g, epoch = args.epochs, rep_size=args.representation_size, order=args.order,
label_file=args.label_file, clf_ratio=args.clf_ratio)
else:
model = line.LINE(g, epoch = args.epochs, rep_size=args.representation_size, order=args.order)
elif args.method == 'deepWalk':
model = node2vec.Node2vec(graph=g, path_length=args.walk_length,
num_paths=args.number_walks, dim=args.representation_size,
workers=args.workers, window=args.window_size, dw=True)
elif args.method == 'tadw':
# assert args.label_file != ''
assert args.feature_file != ''
# g.read_node_label(args.label_file)
g.read_node_features(args.feature_file)
fout = open(singluar_node_file, "w+")
for node_idx in g.sgl_node_list:
fout.write("{}\n".format(node_idx))
fout.close()
model = tadw.TADW(graph=g, dim=args.representation_size, lamb=args.lamb)
# model = tadw_gpu.TADW_GPU(graph=g, dim=args.representation_size, lamb=args.lamb)
elif args.method == 'gcn':
assert args.label_file != ''
assert args.feature_file != ''
g.read_node_label(args.label_file)
g.read_node_features(args.feature_file)
model = gcnAPI.GCN(graph=g, dropout=args.dropout,
weight_decay=args.weight_decay, hidden1=args.hidden,
epochs=args.epochs, clf_ratio=args.clf_ratio)
elif args.method == 'grarep':
model = GraRep(graph=g, Kstep=args.kstep, dim=args.representation_size)
t2 = time.time()
print("time: ", t2-t1)
if args.method != 'gcn':
print("Saving embeddings...")
model.save_embeddings(args.output)
if args.label_file and args.method != 'gcn':
vectors = model.vectors
X, Y = read_node_label(args.label_file)
print("Training classifier using {:.2f}% nodes...".format(args.clf_ratio*100))
clf = Classifier(vectors=vectors, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, args.clf_ratio)
model = node2vec.Node2vec(graph=g, path_length=args.walk_length,
num_paths=args.number_walks, dim=args.representation_size,
workers=args.workers, window=args.window_size, dw=True)
elif args.method == 'tadw':
assert args.label_file != ''
assert args.feature_file != ''
g.read_node_label(args.label_file)
g.read_node_features(args.feature_file)
model = tadw.TADW(graph=g, dim=args.representation_size, lamb=args.lamb)
elif args.method == 'gcn':
assert args.label_file != ''
assert args.feature_file != ''
g.read_node_label(args.label_file)
g.read_node_features(args.feature_file)
model = gcnAPI.GCN(graph=g, dropout=args.dropout,
weight_decay=args.weight_decay, hidden1=args.hidden,
epochs=args.epochs, clf_ratio=args.clf_ratio)
elif args.method == 'grarep':
model = GraRep(graph=g, Kstep=args.kstep, dim=args.representation_size)
t2 = time.time()
print(t2-t1)
embeddings_items = model.vectors
# make full node embeddings
shape = [n_nodes, args.representation_size]
node_embeddings = np.random.uniform(-np.sqrt(6.0 / (shape[0] + shape[1])), np.sqrt(6.0 / (shape[0] + shape[1])), size=shape)
choose_nodeidx = []
for node in embeddings_items:
node_embeddings[int(node), :] = embeddings_items[node]
def main(args):
t1 = time.time()
g = Graph()
print "Reading..."
if args.graph_format == 'adjlist':
g.read_adjlist(filename=args.input)
elif args.graph_format == 'edgelist':
g.read_edgelist(filename=args.input,
weighted=args.weighted,
directed=args.directed)
if args.method == 'node2vec':
model = node2vec.Node2vec(graph=g,
path_length=args.walk_length,
num_paths=args.number_walks,
dim=args.representation_size,
workers=args.workers,
p=args.p,
q=args.q,
window=args.window_size)
elif args.method == 'line':
if args.label_file:
model = line.LINE(g,
lr=args.lr,
batch_size=args.batch_size,
epoch=args.epochs,
rep_size=args.representation_size,
order=args.order,
label_file=args.label_file,
clf_ratio=args.clf_ratio,
auto_stop=args.no - auto_stop)
else:
model = line.LINE(g,
lr=args.lr,
batch_size=args.batch_size,
epoch=args.epochs,
rep_size=args.representation_size,
order=args.order)
elif args.method == 'deepWalk':
model = node2vec.Node2vec(graph=g,
path_length=args.walk_length,
num_paths=args.number_walks,
dim=args.representation_size,
workers=args.workers,
window=args.window_size,
dw=True)
elif args.method == 'tadw':
assert args.label_file != ''
assert args.feature_file != ''
g.read_node_label(args.label_file)
g.read_node_features(args.feature_file)
model = tadw.TADW(graph=g,
dim=args.representation_size,
lamb=args.lamb)
elif args.method == 'gcn':
assert args.label_file != ''
assert args.feature_file != ''
g.read_node_label(args.label_file)
g.read_node_features(args.feature_file)
model = gcnAPI.GCN(graph=g,
dropout=args.dropout,
weight_decay=args.weight_decay,
hidden1=args.hidden,
epochs=args.epochs,
clf_ratio=args.clf_ratio)
elif args.method == 'grarep':
model = GraRep(graph=g, Kstep=args.kstep, dim=args.representation_size)
t2 = time.time()
print t2 - t1
if args.method != 'gcn':
print "Saving embeddings..."
model.save_embeddings(args.output)
if args.label_file and args.method != 'gcn':
vectors = model.vectors
X, Y = read_node_label(args.label_file)
print "Training classifier using {:.2f}% nodes...".format(
args.clf_ratio * 100)
clf = Classifier(vectors=vectors, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, args.clf_ratio)