红楼梦人物分词及可视化

本文首先使用jieba分词提取出红楼梦人物及出现次数，然后使用pyecharts进行可视化。文本分词并非重点关注，主要是做pyecharts的可视化练习。

import pandas as pd
import jieba
import re
from pyecharts.globals import CurrentConfig, OnlineHostType
CurrentConfig.ONLINE_HOST = OnlineHostType.NOTEBOOK_HOST

分章节

def split_chapters(content, path):
    # 每章之间有五个空行分割
    episodes = content.split('\n\n\n\n\n\n')
    # 回目标题存储
    chapter_titles = []
    for i in range(len(episodes)):
        # 去除多余字符
        e = episodes[i].replace('\n\u3000\u3000','')
        # 提取回目标题，标题中间用空格隔开，最后一个替换是在某一回标题中单独出现的
        title = re.search(r'回(.*?)\n', e).group().replace('回', '').replace('\u3000', ' ').replace('\n','').replace('\ue7a3',' ').strip()
        chapter_titles.append(title)
        # 提取内容，去除空白字符，标题与内容之间有一个空行分割
        chapter_content = re.sub('[\s]', '', e.split('\n\n')[1])
        # 保存
        with open(path+str(i)+'.txt', 'w', encoding='utf-8') as f:
            f.write(title+'\n')
            f.write(chapter_content)
            f.close()
    return chapter_titles

​

分词，返回分词列表

def content_cut(content):
    # 分词，生成器变为列表
    segments = jieba.cut(content, cut_all=False)
    segments = [s for s in segments]
    return segments

停止词

def get_stop_words(num, path):
    # 找到每一章节都出现的字作为停用字
    stop_words = set()
    for i in range(num):
        # 读取内容
        with open(path+str(i)+'.txt', 'r', encoding='utf-8') as f:
            words = content_cut(f.readlines()[1]) 
            f.close()  
        # 取交集
        if i == 0:
            stop_words = set(words)
        else:
            stop_words &= set(words)
    stop_words = list(stop_words)
   
    # 添加停止词和自定义的红楼梦中的停止词
    with open('stopwords.txt', 'r', encoding='gbk') as f1:
        lines = f1.readlines()
        for line in lines:
            stop_words.append(line.strip())
    with open('红楼梦stopwords.txt', 'r', encoding='utf-8') as f2:
        lines = f2.readlines()
        for line in lines:
            stop_words.append(line.strip())
    stop_words = list(set(stop_words))
    
    return stop_words

统一人物名称

有些是根据第一次分词结果添加的

maps = {
   '贾宝玉':['宝二爷','宝兄弟','怡红公子','绛洞花主','二哥哥','天魔星', '宝玉'],
        '贾母': ['史太君','老祖宗','老太太','贾母笑'],
        '林黛玉': ['颦颦','颦儿','林姑娘','林妹妹','潇湘妃子','黛玉'],
        '王熙凤': ['凤姐','琏二奶奶','凤辣子','凤哥儿' , '凤丫头','凤姐儿' ,'熙凤'],
        '薛宝钗': ['蘅芜君','宝姐姐','宝丫头' ,'宝姑娘','宝钗','宝钗笑','宝钗道'],
        '袭人': ['袭人道'],
        '史湘云': ['湘云'],
        '薛姨妈':['姨妈'],
        '贾雨村': ['雨村'],
        '小红': ['红玉','小红道','红玉道','红玉笑'],
        '紫鹃': ['鹦哥'],
        '贾元春': ['贵妃','元妃','元春'],
        '贾迎春':['二妹妹','迎春'],
        '贾探春': ['三妹妹','探春'],
        '贾惜春':['四妹妹','惜春'],
        '秦可卿': ['秦氏','可儿','可卿','秦氏笑'],
        '李纨': ['李宫裁'],
        '尤氏':['尤氏笑'],
        '贾蓉':['贾蓉笑', '贾蓉道'],
        '香菱': ['英莲'],
        '贾政':['贾政道','贾政笑'],
        '空空道人': ['那道', '道士', '道人','那道士'],'癞头和尚':['僧道', '那僧道','那僧笑'],
        '冷子兴':['子兴道','子兴','子兴笑'],'林如海':['如海','如海笑']     
       }
def clear_words(segments, stop_words):
    for i in range(len(segments)):
        for k,v in maps.items():
            if segments[i] in v:
                segments[i]=k
    # 删除停止词和一个字的
    segments = [seg for seg in segments if seg not in stop_words and len(seg)>1]
    return segments

每回出现人物及次数，生成df

character_list = ['贾宝玉','贾母','林黛玉','薛宝钗', '史湘云', '王熙凤', '巧姐', '王夫人',
                  '邢夫人', '薛姨妈', '尤氏', '贾元春', '贾迎春', '贾探春','贾惜春','秦可卿',
                  '尤二姐', '尤三姐', '李纨','妙玉','紫鹃','袭人','晴雯','麝月','茗烟','刑岫烟','平儿',
                 '鸳鸯','玉钏儿','金钏儿','赵姨娘','周瑞家的','林之孝家的','小红','坠儿','芳官','龄官','藕官','翠缕',
                 '夏金桂','宝蟾','香菱','甄士隐','甄宝玉','冷子兴','智能儿','娇杏','贾琏','贾政',
                 '贾雨村','贾珍','薛蟠','薛蟠','薛蝌','贾蓉','贾蔷','贾瑞','贾芸','贾敬&