词频统计、词云小案例

词频统计小案例

import jieba
file = open(r'C:\Users\Administrator\Desktop\day01\琵琶行','r',encoding='utf8')
data = file.read()
data_jieba = jieba.lcut(data)
count_dict = {}
for word in data_jieba:
    if len(word) == 1:
        continue
    if word in count_dict:
        count_dict[word] += 1
    else:
        count_dict[word] = 1
def func(i):
    return i[1]
data_list=list(count_dict.items())
data_list.sort(key=func)
data_list.reverse()
for i in data_list[0:4]:
    print(f'{i[0]:^8}{i[1]:^5}')

词云小案例

import wordcloud
from imageio import imread
mask = imread(r'C:\Users\Administrator\Desktop\day01\无标题.png')
file_write = open(r'C:\Users\Administrator\Desktop\day01\琵琶行','r',encoding='utf8')
data = file_write.read()
word = wordcloud.WordCloud(font_path=r'C:\Windows\Fonts\simfang',mask=mask,width=500,height=500,background_color="white")
word.generate(data)
word.to_file('myimage.png')