def sdne_run():
Graph = read_graph('wiki/Wiki_edgelist.txt')
sden_model = sdne(
Graph=Graph,
dimension_size=128,
per_vertex=100,
walk_length=10,
window_size=5,
work=1,
beta=5,
alpha=1e-6,
verbose=1,
epochs=1000,
batch_size=512,
log_dir='logs/0/',
hidden_size_list=[256, 128],
l1=1e-5,
l2=1e-4
)
sden_model.train()
embeddings = sden_model.get_embeddings()
from kon.model.embedding.util.evaluate import evaluate_tools
eval_tool = evaluate_tools(embeddings, label_path='wiki/Wiki_labels.txt')
eval_tool.plot_embeddings()
def deep_walk_run(edgelist_path, is_evluate=False):
Graph = read_graph(edgelist_path)
deepwalk = DeepWalk(Graph=Graph,
per_vertex=80,
walk_length=10,
window_size=5,
dimension_size=8,
work=4)
embeddings = deepwalk.transform()
if is_evluate:
eval = evaluate_tools(embeddings=embeddings,
label_path='wiki/Wiki_labels.txt')
eval.plot_embeddings()
return embeddings
def node2vec_run():
Graph = read_graph('wiki/Wiki_edgelist.txt')
node_vec = node2vec(Graph=Graph,
per_vertex=80,
walk_length=10,
window_size=5,
dimension_size=128,
work=1,
p=0.25,
q=4)
embeddings = node_vec.transform()
eval_tool = evaluate_tools(embeddings, label_path='wiki/Wiki_labels.txt')
eval_tool.plot_embeddings()
def line_run():
from kon.model.embedding.util.util_tool import read_graph
import os
print(os.getcwd())
Graph = read_graph('wiki/Wiki_edgelist.txt')
line = Line(
Graph=Graph,
dimension_size=128,
per_vertex=100,
walk_length=10,
window_size=5,
work=1,
negative_ratio=1,
batch_size=128,
log_dir='logs/0/',
epoch=100,
)
embeddings = line.transform()
from kon.model.embedding.util.evaluate import evaluate_tools
tool = evaluate_tools(embeddings, label_path='wiki/Wiki_labels.txt')
tool.plot_embeddings()
for num in tqdm(range(self.walk_epoch), desc='walk epoch'):
random.shuffle(self.all_nodes)
for vertex in tqdm(self.all_nodes, desc='generator node walk seq'):
sentence_list.append(self.random_walk(start_vertex=vertex))
return sentence_list
def transform(self):
sentence_list = self.deepwalk()
embeddings = self.embdding_train(sentence_list)
return embeddings
if __name__ == '__main__':
Graph = read_graph('wiki/Wiki_edgelist.txt')
deepwalk = DeepWalk(Graph=Graph,
per_vertex=80,
walk_length=10,
window_size=5,
dimension_size=64,
work=4)
embeddings = deepwalk.transform()
print(embeddings.keys())
print(embeddings.values())
eval = evaluate_tools(embeddings=embeddings)
eval.plot_embeddings()
return self.model
def get_embeddings(self):
embeddings = {}
pred_embeddings = self.embedding_model.predict(
self.W, batch_size=self.batch_size)
rank = 0
for embedding in pred_embeddings:
embeddings[self.idx2node[rank]] = embedding
rank += 1
return embeddings
if __name__ == '__main__':
Graph = read_graph()
sden_model = sdne(Graph=Graph,
dimension_size=128,
per_vertex=100,
walk_length=10,
window_size=5,
work=1,
beta=5,
alpha=1e-6,
verbose=1,
epochs=1000,
batch_size=512,
log_dir='model/embedding/setence_model/logs/0/',
hidden_size_list=[256, 128],
l1=1e-5,
l2=1e-4)