使用自己的语料训练word2vec模型

# -*- coding: utf-8 -*-
import jieba
import io
# 加载自己的自己的金融词库
jieba.load_userdict("financialWords.txt")

def main():
    with io.open('news201708.txt','r',encoding='utf-8') as content:
        for line in content:
            seg_list = jieba.cut(line)
#           print '/'.join(seg_list)
            with io.open('seg201708.txt', 'a', encoding='utf-8') as output:
                output.write(' '.join(seg_list))

if __name__ == '__main__':
    main()

from gensim.models import word2vec

def main():

    num_features = 300    # Word vector dimensionality
    min_word_count = 10   # Minimum word count
    num_workers = 16       # Number of threads to run in parallel
    context = 10          # Context window size
    downsampling = 1e-3   # Downsample setting for frequent words
    sentences = word2vec.Text8Corpus("seg201708.txt")

    model = word2vec.Word2Vec(sentences, workers=num_workers, \
            size=num_features, min_count = min_word_count, \
            window = context, sg = 1, sample = downsampling)
    model.init_sims(replace=True)
    # 保存模型，供日後使用
    model.save("model201708")

    # 可以在加载模型之后使用另外的句子来进一步训练模型
    # model = gensim.models.Word2Vec.load('/tmp/mymodel')
    # model.train(more_sentences)

if __name__ == "__main__":
    main()

model = Word2Vec.load('model201708')      #模型讀取方式
model.most_similar(positive=['woman', 'king'], negative=['man']) #根据给定的条件推断相似词
model.doesnt_match("breakfast cereal dinner lunch".split()) #寻找离群词
model.similarity('woman', 'man') #计算两个单词的相似度
model['computer'] #获取单词的词向量