Word2vector 中文词向量训练
代码1:
# -*- coding: utf-8 -*-
from gensim.models import Word2Vec
from gensim.models.word2vec import LineSentence
txtpath = "corpus.txt"# 输入语料文件
with open(txtpath,'r',encoding='utf8') as f:
model = Word2Vec(LineSentence(f), sg=0, size=100, window=5, min_count=1,workers=9)
model.save("new_vecoter.word2vec")
model=gensim.models.Word2Vec.load("new_vecoter")#加载词向量
代码2 :
# -*- coding: utf-8 -*-
from gensim.models import Word2Vec
from gensim.test.utils import common_texts, get_tmpfile
path = get_tmpfile("word2vec.model") #创建临时文件
txtpath = "corpus.txt"
with open(txtpath,'r',encoding='utf8') as f:
sentences = [line.split(' ') for line in f.readlines()]
# print(sentences[:5])
model = Word2Vec(sentences, size=100, window=5, min_count=1)
model.save("word2vec.model")