词云-wordcloud

 

import jieba
book = "2015.txt"
txt = open(book).read()
ex = {'不是','就是','的话','1.1','docin','www'}
ls = []
words = jieba.lcut(txt)
print(words)
counts = {}
for word in words:
    ls.append(word)
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word, 0) + 1
print(ls)

for word in ex:
    del (counts[word])
print(counts)
items = list(counts.items())
print(items)
items.sort(key=lambda x: x[1], reverse=True)
for i in range(5):
    word, count = items[i]
    print("{:<20}{:>8}".format(word, count))

wz = open('ms.txt', 'w+')
wz.write(str(ls))

import matplotlib.pyplot as plt
from wordcloud import WordCloud
font = r'/simhei.ttf'
wzhz = WordCloud(collocations=False, font_path=font, width=1400, height=1400).generate(txt)
plt.imshow(wzhz)
plt.show()

 

项目 55
励志 46
远洋渔船 42
命运 33
生命 25

 关于jieba库：https://www.cnblogs.com/wkfvawl/p/9487165.html

转载于:https://www.cnblogs.com/zx3707/p/10629046.html