word2vct算法实现

本篇文章主要是实现python 自然语言处理包 gensim 中用于词向量建模的 word2vec算法。

示例代码如下：

# encoding=utf-8

import logging
import sys

from gensim.models import Word2Vec

if __name__ == '__main__':
    logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)

    if len(sys.argv) < 3:
        sys.exit(1)

    outputFile1, outputFile2 = sys.argv[1:3]

    sentences = [
        "I think that most of us know by now that water is essential to our survival We’ve probably also all heard doctors say that drinking roughly eight glasses a day is ideal",
        "yoyoyo you go home now to sleep"]

    vocab = [s.encode('utf-8').decode().split() for s in sentences]
    #建立模型
    model = Word2Vec(sentences, size=100, window=5, min_count=5, workers=4)
    #保存模型
    model.save(outputFile1)
    model.save_word2vec_format(outputFile2, binary=False)

#测试模型
# encoding='utf-8'

import logging
import sys

from gensim.models import Word2Vec

if __name__ == '__main__':
    logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)

    if len(sys.argv) < 3:
        sys.exit(1)

    file, word = sys.argv[1:3]
    #从磁盘文件 file 加载模型
    model = Word2Vec.load_word2vec_format(file, binary=False)
    print(model.most_similar(word))

更多内容可以查看官方文档