#词云2 用jieba进行分词并产生词云

1、读取文件

import jieba
with open('china145.txt','r',encoding='utf-8') as f:
    renmin=f.read()

2、分词

jieba.load_userdict('china145.txt')
#分词
word_list=jieba.cut(renmin,cut_all=False)
#创建分词字典
wd={}
for word in word_list:
    if word in wd:
        wd[word]+=1
    else:
        wd[word]=1
ci=list(wd.keys())
#删除无用词
with open('stopword.txt','r') as ft:
    stopword=ft.read()
    
for word in ci:
    if wd[word]<5 or len(word)<2 or word in stopword or "一" in word:
        wd.pop(word)
#打印新的词典
print(wd)
#数个数
ci, num, data = list(wd.keys()), list(wd.values()),[]
#
for i in range(len(wd)):#字典长度
    data.append((num[i],ci[i])) #逐个将键值对存入data中
data.sort()#升序排列
data.reverse()#逆序，得到所需的降序排列

wd_sorted={}
print(len(data),data[0],data[0][0],data[0][1])

for i in range(len(data)):  
    wd_sorted[data[i][1]]=data[i][0]

print(wd_sorted)

3、词云

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image
mask=np.array(Image.open('heart.png'))

font=r'c:\windows\fonts\simfang.ttf'
wc=WordCloud(background_color="white",mask=mask,font_path=font).generate_from_frequencies(wd)
plt.imshow(wc)
plt.axis("off")
plt.show()

【其他方法】
分词：利用jieba的方式有所不同

import jieba

f=open("file.txt","r+",encoding="utf-8").read()
word=jieba.lcut(f)

for i in word:
    txt=[].append(word)
print (txt)
pin={}
for i in txt:
    pin[i]=0
print(pin)
for i in txt:
    pin[i]=pin[i]+1

print(pin)