【python】利用jieba中文分词进行词频统计

以下代码对鲁迅的《祝福》进行了词频统计:

 import io
 import jieba
 txt = io.open("zhufu.txt", "r", encoding='utf-8').read()
 words  = jieba.lcut(txt)
 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(15):
     word, count = items[i]
     print (u"{0:<10}{1:>5}".format(word, count))

结果如下：

并把它生成词云

 from wordcloud import WordCloud
 import PIL.Image as image
 import numpy as np
 import jieba

 # 分词
 def trans_CN(text):
     # 接收分词的字符串
     word_list = jieba.cut(text)
     # 分词后在单独个体之间加上空格
     result = " ".join(word_list)
     return result

 with open("zhufu.txt") as fp:
     text = fp.read()
     # print(text)
     # 将读取的中文文档进行分词
     text = trans_CN(text)
     mask = np.array(image.open("xinxing.jpg"))
     wordcloud = WordCloud(
         # 添加遮罩层
         mask=mask,
         font_path = "msyh.ttc"
     ).generate(text)
     image_produce = wordcloud.to_image()
     image_produce.show()

效果如下：