使用gensim word2vec训练英文预料---最简洁版

使用gensim word2vec训练英文预料—最简洁版

直接上代码：

# -*- coding: utf-8 -*-
import gensim.models.word2vec as word2vec
import gensim
import logging

# word2vec Text8 的训练
def train_save_model():
    # logging.basicConfig(format='%(asctime)s : %(levelname)s :%(message)',level=logging.INFO)
    # 加载预料
    sentences = word2vec.Text8Corpus('text8')
    model = word2vec.Word2Vec(sentences, size=200)
    model.save('text.model')
# 加载模型
def load_model():
    model = word2vec.Word2Vec.load('text.model')
    # simi = model.similar_by_vector('women', 'men')
    # print(simi)
    print(model.most_similar('man'))
    print(model['red'])

# 执行代码
load_model()

text8的下载地址：
http://cs.fit.edu/%7Emmahoney/compression/enwik8.zip