首先對小說進行預處理，使用jieba分詞進行分詞

import jieba
import jieba.analyse

jieba.suggest_freq('沙瑞金', True)
jieba.suggest_freq('田國富', True)
jieba.suggest_freq('高育良', True)
jieba.suggest_freq('侯亮平', True)
jieba.suggest_freq('鍾小艾', True)
jieba.suggest_freq('陳岩石', True)
jieba.suggest_freq('歐陽菁', True)
jieba.suggest_freq(
 
'易學習', True)
jieba.suggest_freq('王大路', True)
jieba.suggest_freq('蔡成功', True)
jieba.suggest_freq('孫連城', True)
jieba.suggest_freq('季昌明', True)
jieba.suggest_freq('丁義珍', True)
jieba.suggest_freq('鄭西坡', True)
jieba.suggest_freq('趙東來', True)
jieba.suggest_freq('高小琴', True)
jieba.suggest_freq('趙瑞龍', True)
jieba.suggest_freq(
 
'林華華', True)
jieba.suggest_freq('陸亦可', True)
jieba.suggest_freq('劉新建', True)
jieba.suggest_freq('劉慶祝', True)

with open('./in_the_name_of_people.txt', encoding="utf8") as f:
    document = f.read()
    # print(document)
    # document_decode = document.decode('GBK')

    document_cut = jieba.cut(document)
    # print  
 
' '.join(jieba_cut)  //如果列印結果，則分詞效果消失，後面的result無法顯示
    result = ' '.join(document_cut)
    # result = result.encode('utf-8')
    # print(result)
    with open('./in_the_name_of_people_segment.txt', 'w', encoding="utf8") as f2:
        f2.write(result)

訓練模型：

import logging
import os
from gensim.models import word2vec

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

sentences = word2vec.LineSentence('./in_the_name_of_people_segment.txt')

model = word2vec.Word2Vec(sentences, hs=1, min_count=1, window=3)

模型的三種應用：

# 找出相近詞的集合
print(model.wv.similar_by_key("沙瑞金", topn=5))

# 檢視兩個詞的相近程度
print("沙瑞金|高育良的相似度：", model.wv.similarity("沙瑞金", "高育良"))

# 找出不同類的詞
print("沙瑞金 高育良 李達康 劉慶祝中不同類別的詞為：",model.wv.doesnt_match(u"沙瑞金 高育良 李達康 劉慶祝".split()))