top 10 ranking

# 打印文件名称
for filename in filenames:
    print(filename)

import jieba
   
file_path= r'C:\Users\apache\Desktop\上卷.txt'
file=open(file_path,'r',encoding='utf-8')
counts=file.read()
# file.readlines()[10]
words=jieba.lcut(counts)
file.close()

count_words={}
for item in words:
    if len(item)==1:
        continue
    if item not in count_words:
        count_words[item]=1
    else:
        count_words[item]+=1

list_count=list(count_words.items())

list_count.sort(key=lambda x:x[1],reverse=True)

import pandas as pd

df=pd.DataFrame(data=count_words.items(),columns=['words','count'])
df.sort_values(by='count',ascending=False,inplace=True)

df.reset_index(inplace=True)
df.rename(columns={'index':'new'},inplace=True)
df.reset_index(inplace=True)

import matplotlib.pyplot as plt

df.plot()
df['count'].plot()

plt.rcParams['font.sans-serif'] = ['SimHei']
df['size']=df['count']/df['count'].sum()
df['count'].sum()

plt.pie(df['size'],labels=df.words)