def embedding(args, datadict):
if not os.path.exists(f'./embedding/{args.dataset}.edgelist'):
nx.write_edgelist(datadict['g'],
f'./embedding/{args.dataset}.edgelist',
data=[('weight', int)])
datadict['g'] = nx.read_edgelist(f'./embedding/{args.dataset}.edgelist',
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
if not os.path.exists(f'./embedding/{args.dataset}_{args.emb_method}.emb'):
model = DeepWalk(datadict['g'], walk_length=5, num_walks=50, workers=8)
model.train(window_size=10, iter=10)
dict_embeddings = model.get_embeddings()
embeddings = np.zeros(
(datadict['labels'].shape[0], dict_embeddings['0'].shape[0]))
print('Saving the embeddings......')
for key in tqdm(dict_embeddings):
embeddings[int(key)] = dict_embeddings[key]
np.savetxt(f'./embedding/{args.dataset}_{args.emb_method}.emb',
embeddings)
print(f'{embeddings.shape[1]}-dims Embeddings saved.')
else:
print('Loading the embeddings')
embeddings = np.loadtxt(
f'./embedding/{args.dataset}_{args.emb_method}.emb')
print(f'{embeddings.shape[1]}-dims Embeddings load.')
return embeddings
def get_embeddings(self, inst, th=1):
G = nx.parse_edgelist(self._compose_edge_list(inst.dist_mat, th), create_using=nx.DiGraph(), nodetype=None,
data=[('weight', float)])
if self._embedding == 'deepwalk':
model = DeepWalk(G, walk_length=10, num_walks=80, workers=1)
model.train(window_size=5, iter=3)
elif self._embedding == 'node2vec':
model = Node2Vec(G, walk_length=10, num_walks=80, p=0.25, q=4, workers=1) # init model
model.train(window_size=5, iter=3) # train model
elif self._embedding == 'line':
model = LINE(G, embedding_size=128, order='second') # init model,order can be ['first','second','all']
model.train(batch_size=1024, epochs=50, verbose=2) # train model
elif self._embedding == 'sdne':
model = SDNE(G, hidden_size=[256, 128]) # init model
model.train(batch_size=3000, epochs=40, verbose=2) # train model
elif self._embedding == 'struc2vec':
model = Struc2Vec(G, 10, 80, workers=4, verbose=40, ) # init model
model.train(window_size=5, iter=3) # train model
else:
return self._normalise(inst)
ebds = model.get_embeddings()
coords = []
for i in range(inst.n):
coords.append(ebds[str(i)])
return np.array(coords)
emb_list = []
for k in X:
emb_list.append(embeddings[k])
emb_list = np.array(emb_list)
model = TSNE(n_components=2)
node_pos = model.fit_transform(emb_list)
color_idx = {}
for i in range(len(X)):
color_idx.setdefault(Y[i][0], [])
color_idx[Y[i][0]].append(i)
for c, idx in color_idx.items():
plt.scatter(node_pos[idx, 0], node_pos[idx, 1], label=c)
plt.legend()
plt.show()
if __name__ == "__main__":
G = nx.read_edgelist('./data/wiki/Wiki_edgelist.txt',
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
model = DeepWalk(G, walk_length=10, num_walks=80, workers=1)
model.train(window_size=5, iter=3)
embeddings = model.get_embeddings()
evaluate_embeddings(embeddings)
plot_embeddings(embeddings)
model = TSNE(n_components=2) #用TSNE进行降维
node_pos = model.fit_transform(emb_list)
color_idx = {}
for i in range(len(X)):
color_idx.setdefault(Y[i][0], []) #类别
color_idx[Y[i][0]].append(i) #id
for c, idx in color_idx.items(): #不同类别不同颜色
plt.scatter(node_pos[idx, 0], node_pos[idx, 1], label=c)
plt.legend()
plt.show()
if __name__ == "__main__":
#读入边列表，文件中的每一行有两个节点，表示连接这两个节点的边。
#直接用networkx读入就行，很方便的操作。
G = nx.read_edgelist('../data/wiki/Wiki_edgelist.txt',
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
#实例化模型，“句子”长度为10，80次游走。
model = DeepWalk(G, walk_length=10, num_walks=80, workers=1)
model.train(window_size=5, iter=3) #训练模型，关于gensim w2v的参数都默认在train里面
embeddings = model.get_embeddings() #得到Embedding向量
evaluate_embeddings(embeddings) #应用节点分类来评估嵌入向量的质量
plot_embeddings(embeddings) #降成二维画在图中可视化
f'../save/graph_embedding_{name}_{graph_name}_svd{svd_dim}.csv')
if __name__ == "__main__":
G = nx.read_edgelist(graph_path,
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
model = DeepWalk(G,
walk_length=dw_walk_length,
num_walks=dw_num_walks,
workers=NUM_WORKER) # init model
model.train(window_size=dw_window_size, iter=dw_iter) # train model
embeddings = model.get_embeddings() # get embedding vectors
save_embedding(embeddings, name='dw')
save_embedding_svd(embeddings, name='dw', svd_dim=svd_dim)
model = model = Struc2Vec(G,
walk_length=s2v_walk_length,
num_walks=s2v_num_walks,
workers=NUM_WORKER,
verbose=40) # init model
model.train(window_size=s2v_window_size, iter=s2v_iter) # train model
embeddings = model.get_embeddings() # get embedding vectors
save_embedding(embeddings, name='s2v')
save_embedding_svd(embeddings, name='s2v', svd_dim=svd_dim)