python3+pycharm实现将txt文件 使用jieba分词 wordcloud制作词云 ——以《三国演义》的txt文件为例

代码以及释义如下：

import jieba
import jieba.analyse
import wordcloud

from PIL import Image, ImageSequence
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud, ImageColorGenerator
import jieba
import jieba.analyse

##============分词===============
stopwords=[lines.strip() for lines in open('chineseStopWords.txt',encoding='utf-8').readlines()]      #停用词文件的读取
stopwords.append('')
path = '《三国演义》罗贯中.txt'     #第一步爬虫结果存储的路径
file_in = open(path,'r',encoding='utf-8').read()
jieba.del_word("却说")    #删除一些不想要的词
jieba.del_word("二人")     
jieba.del_word("荆州")
words=jieba.lcut(file_in)     #分词
# cut_text=" ".join(words)

##==============词频统计=============
word_freq={}    #词频统计的字典
for word in words:           #这一步是对近义词进行统计
    if (word in stopwords) or len(word)==1 :         #禁用词和低频词不统计了
        continue
    elif word=='玄德' or word == '玄德曰':
        newword='刘备'
    elif word=='丞相':
        newword='曹操'
    elif word=='孔明' or word=='孔明曰':
        newword='诸葛亮'
    elif word=='关公' or word=='云长':
        newword='关羽'
    else:
        newword=word
    if newword in word_freq:
        word_freq[newword]+=1
    else:
        word_freq[newword]=1
        # word_freq[word]=word_freq.get(word,0)+1
# print(word_freq)
freq_word=[]
for word,freq in word_freq.items():
    fenci=freq_word.append((word,freq))
freq_word.sort(key=lambda x:x[1],reverse=True)     #词语根据词频排序
for word,freq in freq_word[:50]:
    with open('wukaiaaaaa.txt','a',encoding='utf-8')as fp:
        fp.write(word+'\n')   #将前五十词频文件保存
    print(word,freq)   #打印排名前50%的单词
    
##===========词云制作=======================
 #background_image=np.array(Image.open("music.png"))
c=[lines.strip("\n") for lines in open('wukaiaaaaa.txt',encoding='utf-8').readlines()]   #读取词频前五十的文本文件
cc=" ".join(c)   #必要，否则 expected string or bytes-like object：应为字符串或类似对象的字节
wordcloud=WordCloud(
    font_path = 'C:/Users/Windows/fonts/simkai.ttf',   #字体样式设置
    background_color="white",width=2000,height=2000,
    mask=np.array(Image.open("music.png"))  #mask=background_image   
).generate(cc)          #词云图设置
plt.imshow(wordcloud,interpolation="bilinear")
plt.axis("off")    #不展示坐标轴 否则为plt.axis("off")  ，可以试一下结果如何
plt.show()   #词云图的展示

结果如图：
词频：

词云：背景图随便选了张，有点丑，但是不难发现词频与字体大小的关系