jieba

jieba库对英文单词的统计

# -*- coding: utf-8 -*-

def get_text():
txt = open("1.txt", "r", encoding='UTF-8').read()
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
txt = txt.replace(ch, " ") # 将文本中特殊字符替换为空格
return txt

file_txt = get_text()
words = file_txt.split() # 对字符串进行分割，获得单词列表
counts = {}

for word in words:
if len(word) == 1:
continue
else:
counts[word] = counts.get(word, 0) + 1

items = list(counts.items()) 
items.sort(key=lambda x: x[1], reverse=True)

for i in range(5):
word, count = items[i]
print("{0:<5}->{1:>5}".format(word, count))

词云制作

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba

def create_word_cloud(filename):
text = open("哈姆雷特.txt".format(filename)).read()

wordlist = jieba.cut(text, cut_all=True)
wl = " ".join(wordlist)

wc = WordCloud(
background_color="black",
max_words=2000,
font_path='simsun.ttf',
height=1200,
width=1600,
max_font_size=100,
random_state=100,
)

myword = wc.generate(wl)
plt.imshow(myword)
plt.axis("off")
plt.show()
wc.to_file('img_book.png')

if __name__ == '__main__':
create_word_cloud('mytext')