data_desc_process.py 文件源码

def get_word_to_cloud(self):
        for file in self.file_list:
            with codecs.open('../spider/' + file, "r",encoding='utf-8', errors='ignore') as string:
                #??????????????????
                string = string.read().upper()
                #???????????
                res = jieba.cut(string, HMM=False)
                reslist = list(res)
                wordDict = {}
                #???????????
                for i in reslist:
                    if i not in self.dic_list:
                        continue
                    if i in wordDict:
                        wordDict[i]=wordDict[i]+1
                    else:
                        wordDict[i] = 1
            #???????
            coloring = imread('test.jpeg')
            #???????????????
            wc = WordCloud(font_path='msyh.ttc',mask=coloring,
                    background_color="white", max_words=50,
                    max_font_size=40, random_state=42)

            wc.generate_from_frequencies(wordDict)
            #????
            wc.to_file("%s.png"%(file))
#???????