代码
代码先使用stopwords过滤无效词，正则表去除多余的空格，jieba分词，再用wordcloud制作词云。详细代码如下：
# -- coding: utf-8 --#\"\"\"@author:Galen@file: world.py@time: 2019/02/13@description: 知否词云\"\"\"import reimport PIL.Image as imageimport jiebaimport jieba.analyseimport numpy as npfrom wordcloud import WordCloudstopwords_path = \"resources/stopwords.txt\"jieba.analyse.set_stop_words(stopwords_path)def clean_space(content): \"\"\"多个空格转一个\"\"\" return re.sub(' +', ' ', content)# 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 resultwith open(\"zhi_fou.txt\", 'r', errors='ignore', ) as fp: text = fp.read() # 将读取的中文文档进行分词 text = trans_CN(clean_space(text)) mask = np.array(image.open(\"zhi_fou.jpeg\")) wordcloud = WordCloud( # 添加遮罩层 mask=mask, # 生成中文字的字体,必须要加,不然看不到中文 font_path=\"/System/Library/Fonts/方正吕建德行楷.ttf\" ).generate(text) image_produce = wordcloud.to_image() # image_produce.show() image_produce.save('zhifou.png')
