gensim ——訓練word2vec詞向量的使用方法。

# -*- coding: utf-8 -*-

import os
import time
import sys

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

from gensim.models import word2vec


def main():
    # 原始語料路徑,已分詞
    input_file = ur"sogou_seg.txt"
    sentences = word2vec.Text8Corpus(input_file)
　　#訓練代碼
    model = word2vec.Word2Vec(sentences, sg=1, size=100, window=5, min_count=1, negative=3, sample=0.001, hs=1,
                              workers=40)
    #save
    model.save("./sogou_word2vec/min_count-1/sogou_word.model")
    model.wv.save_word2vec_format("./sogou_word2vec/min_count-1/sogou.wor2vec.txt")


if __name__ == "__main__":
    main()
    print "Done!"

load 的時候只需要

model = word2vec.Word2Vec.load("./sogou_word2vec/min_count-1/sogou_word.model")

或者

model=gensim.models.KeyedVectors.load_word2vec_format("./sogou_word2vec/min_count-1/sogou.wor2vec.txt")