5.1 使用word2vector表示词向量

读取分词后的评论，将分词的结果放在list中，每条评论为一个list，所有的评论放入list_all中。

from gensim.models import Word2Vec
import math

stopwords = None
with open('../data/stopwords.data', 'r', encoding='utf-8') as fr:
    stopwords = fr.readlines()
list_all = []
list_temp = []
with open('../data/good_seg.txt', 'r', encoding='utf-8') as fr:
    lines = fr.readlines()
    for line in lines:
        line = line.strip()
        # print(line)
        for w in stopwords:
            # print(word)
            if w.strip() == '/':
                continue
            line = line.replace(w.strip(), '')
        list_temp = line.split("/")
        while '' in list_temp:
            list_temp.remove('')
        list_all.append(list_temp)
    print(list_all)
# 利用语料训练模型
model = Word2Vec(list_all, window=5, min_count=1)
y2 = model.most_similar("电影", topn=5)  # 20个最相关的
for item in y2:
    print(item[0], item[1])
for a in X:
     print(a)

运行结果：每个词向量为100维