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)
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
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)
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/test_small.txt',
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
model = DeepWalk(G, walk_length=4, num_walks=100, workers=30)
model.train(window_size=50, iter=12)
embeddings = model.get_embeddings()
print(embeddings)
f = open('../data/wiki/_test_vector.txt', 'w') # 若是'wb'就表示写二进制文件
j = 0
for i in embeddings:
f.write(i + " ")
for q in embeddings[i]:
f.write(str(q) + " ")
# print(str(q))
f.write('\n')
j = j + 1
f.close()
# evaluate_embeddings(embeddings)
plot_embeddings(embeddings)
if __name__ == "__main__":
# G = nx.read_edgelist('../data/wiki/Wiki_edgelist.txt',
# create_using=nx.DiGraph(), nodetype=None, data=[('weight', int)])
# nx.draw(G, node_size=10, font_size=10, font_color="blue", font_weight="bold")
# plt.show()
import pandas as pd
df = pd.DataFrame()
df['source'] = [str(i) for i in [0, 1, 2, 3, 4, 4, 6, 7, 7, 9]]
df['target'] = [str(i) for i in [1, 4, 4, 4, 6, 7, 5, 8, 9, 8]]
G = nx.from_pandas_edgelist(df, create_using=nx.Graph())
model = DeepWalk(G, walk_length=50, num_walks=180, workers=1)
model.train(window_size=10, iter=3, embed_size=2)
# model = DeepWalk(G, walk_length=10, num_walks=80, workers=1)
# model.train(window_size=5, iter=3,embed_size=128)
embeddings = model.get_embeddings()
#print(embeddings)
x, y = [], []
print(sorted(embeddings.items(), key=lambda x: x[0]))
for k, i in embeddings.items():
x.append(i[0])
y.append(i[1])
plt.scatter(x, y)
plt.show()
# evaluate_embeddings(embeddings)
# plot_embeddings(embeddings)
return G
if __name__ == '__main__':
train_df, vali_df, train_mat, vali_mat = get_network("ratings.csv")
train_df.to_csv("network.txt",sep='@',mode='w',index=None,header=None,encoding='utf-16')
appendMovie()
G = buildGraph()
#G = nx.read_edgelist("network.txt", encoding='utf-16',delimiter='@',
# create_using=nx.Graph(), nodetype=None, data=[('weight', float)])
print("G done!")
#model = DeepWalk(G, walk_length=10, num_walks=80, workers=1)
model = DeepWalk(G, walk_length=100, num_walks=80, workers=1)
print("begin to train")
#model.train(window_size=5, iter=3)
model.train(embed_size=200, window_size=30, iter=5)
embeddings = model.get_embeddings()
print("embeddings got, begin to evaluate")
for N in range(5,21,5):
print("top{}".format(N))
precision, recall, precision_list, recall_list = evaluate(embeddings, train_mat, vali_mat, 6040, 3952,n=N)
print("precision{}%".format(precision * 100))
print("recall{}%".format(recall * 100))
print("f1 score{}".format((2 * precision * recall) / (precision + recall)))
microPrecision = np.average(precision_list)
microRecall = np.average(recall_list)
microF1 = (2 * microPrecision * microRecall) / (microPrecision + microRecall)
print("microPrecision:{}%".format(microPrecision * 100))
print("mircroRecall:{}%".format(microRecall * 100))
np.savetxt("../results/precision_list_d_know_" + str(N) + ".txt", precision_list)
np.savetxt("../results/recall_list_d_know_" + str(N) + ".txt", recall_list)
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
ge_features.to_csv(
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)
"""使用deepwalk模型获得节点向量"""
import sys
sys.path.append(r'D:\pythonplaces\citation-recommendation')
from ge import DeepWalk
import networkx as nx
if __name__ == "__main__":
G = nx.read_edgelist('../data/aan/aan_normal_train.txt',
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
model = DeepWalk(G, walk_length=5, num_walks=10, workers=12)
model.train(embed_size=128,
window_size=5,
iter=3,
emb_filepath="../embs/aan_deepwalk_test.emb")
embeddings = model.get_embeddings()