如何读取sgns.financial.bigram-char about chinese-word-vectors HOT 2 OPEN

我用的这个
def weight(self,vocab_to_index):
#将词映射为预训练词向量
size_vocab = len(vocab_to_index)#字典大小
embeddings = np.zeros((size_vocab, 300))#初始化数组 为零，300维
found=0#匹配到的词向量个数
with open(r'..\datasets\sgns.weibo.char','r',encoding='utf-8') as f:#读取预训练词向量文件
for line_idx, line in enumerate(f):#遍历索引和值，值格式为：词，词向量
line = line.strip().split()#值
if len(line) != 300 + 1:#保证每个词向量为300维
continue
word = line[0]#词
embedding = line[1:]#词向量
if word in vocab_to_index:
found=found+1#加一
word_idx = vocab_to_index[word]#找到对应索引
embeddings[word_idx] = embedding#该索引位置对应词向量
print('获取到的词向量：'+str(found)+'所有的词：'+str(size_vocab)+'匹配率：{:.2f}%'.format(found/size_vocab*100))
# 保存提取到的词向量数组
np.savez_compressed(r'..\datasets\vec.npz', embeddings=embeddings)
#return embeddings

from chinese-word-vectors.

from chinese-word-vectors.