def get_context_pairs(graphs, num_time_steps):
""" Load/generate context pairs for each snapshot through random walk sampling."""
load_path = "data/{}/train_pairs_n2v_{}.pkl".format(FLAGS.dataset, str(num_time_steps - 2))
try:
context_pairs_train = dill.load(open(load_path, 'rb'))
print("Loaded context pairs from pkl file directly")
except (IOError, EOFError):
print("Computing training pairs ...")
context_pairs_train = []
for i in range(0, num_time_steps):
context_pairs_train.append(run_random_walks_n2v(graphs[i], graphs[i].nodes()))
dill.dump(context_pairs_train, open(load_path, 'wb'))
print ("Saved pairs")
return context_pairs_train
def get_context_pairs(graphs, num_time_steps):
""" Load/generate context pairs for each snapshot through random walk sampling."""
load_path = "data/{}/train_pairs_n2v_{}.pkl".format(
FLAGS.dataset, str(num_time_steps - 2))
try:
# dill 可以用于保存对象等大多数Python的数据格式
context_pairs_train = dill.load(open(load_path, 'rb'))
print("Loaded context pairs from pkl file directly")
except (IOError, EOFError):
print("Computing training pairs ...")
context_pairs_train = []
#num_time_steps表示训练的静态快照图，
#所以这里的context_pairs_train列表包含num_time_steps个数的字典。
for i in range(0, num_time_steps):
#run_random_walks_n2v()返回的是一个字典。
context_pairs_train.append(
run_random_walks_n2v(graphs[i], graphs[i].nodes()))
#保存不同时刻图的随机游走的固定窗口的节点对。
dill.dump(context_pairs_train, open(load_path, 'wb'))
print("Saved pairs")
return context_pairs_train
def get_context_pairs_incremental(graph):
return run_random_walks_n2v(graph, graph.nodes())