《红楼梦》中文分词以及绘制词云图

代码:

import jieba
from wordcloud import WordCloud

excludes = {"什么","一个"}
excludes = {"qut"}
f = open("红楼梦.txt", "r", encoding='utf-8')
txt = f.read()
f.close()
words  = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:  #排除单个字符的分词结果
        continue
    else:
        counts[word] = counts.get(word,0) + 1
for word in excludes:
    del(counts[word])
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(30):
    word, count = items[i]
    print ("{0:{2}<10}出场次数:{1:{2}<5}".format(word, count,(chr(12288))))

##############
newtxt = "".join(words)
wordcloud = WordCloud(background_color="white",\
                width=800,
                height=600,
                font_path="msyh.ttf",
                max_words=200,
                max_font_size=80,
                stopwords=excludes,
            ).generate(newtxt)
wordcloud.to_file("红楼梦词云.png")


from PIL import Image
img = Image.open('红楼梦词云.png')
img.show()

运行结果1:

运行结果2: