【python】利用jieba中文分词进行词频统计及生成词云

以下代码对鲁迅的《祝福》进行了词频统计:

 1 import io
 2 import jieba
 3 txt = io.open("zhufu.txt", "r", encoding='utf-8').read()
 4 words  = jieba.lcut(txt)
 5 counts = {}
 6 for word in words:
 7     if len(word) == 1:
 8         continue
 9     else:
10         counts[word] = counts.get(word,0) + 1
11 items = list(counts.items())
12 items.sort(key=lambda x:x[1], reverse=True) 
13 for i in range(15):
14     word, count = items[i]
15     print (u"{0:<10}{1:>5}".format(word, count))

结果如下：

并把它生成词云

 1 from wordcloud import WordCloud
 2 import PIL.Image as image
 3 import numpy as np
 4 import jieba
 5  
 6 # 分词
 7 def trans_CN(text):
 8     # 接收分词的字符串
 9     word_list = jieba.cut(text)
10     # 分词后在单独个体之间加上空格
11     result = " ".join(word_list)
12     return result
13  
14 with open("zhufu.txt") as fp:
15     text = fp.read()
16     # print(text)
17     # 将读取的中文文档进行分词
18     text = trans_CN(text)
19     mask = np.array(image.open("xinxing.jpg"))
20     wordcloud = WordCloud(
21         # 添加遮罩层
22         mask=mask,
23         font_path = "msyh.ttc"
24     ).generate(text)
25     image_produce = wordcloud.to_image()
26     image_produce.show()