python 调用word2vec

示例代码如下
# -*- coding: utf-8 -*-

import os
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

from gensim.models import word2vec


def main():
    #原始搜狗语料路径
    input_file=ur"/users1/ymli/wlj/dataset/corpus/sogou_seg_all_ban.txt"
    sentences = word2vec.Text8Corpus(input_file)
    model = word2vec.Word2Vec(sentences, sg=1, size=100, window=5, min_count=5, negative=3, sample=0.001, hs=1, workers=4)
    model.save("./sogou_phrase/sogou_phrase.model")


if __name__=="__main__":
    main()