def simpleprocess(self): data = open(self.dataset_path, "r") for d in data.readlines(): item = d.strip().split("\t") self.dataset.append(nlpir.segWithTag(item[0]).replace("\t", " ")) self.label.append(item[1]) data.close()
def content_cut(content): #l_words = list(jieba.cut(content)) str_words = nlpir.segWithTag(str(content)) #return string #str_words = nlpir.seg(content) ## word with nature #str_words = str_words.replace('/','') #prt_debug_msg2(str_words) return str_words
def simpleprocessone(self): data = open(self.dataset_path, "r") for d in data.readlines(): item = d.strip("\n").split("#$|_$_|$#") if len(item) == 3: self.dataset.append(nlpir.segWithTag(item[2]).replace("\t", " ")) self.label.append(item[0]) data.close()
def simpleprocessone(self): data = open(self.dataset_path, "r") for d in data.readlines(): item = d.strip("\n").split("#$|_$_|$#") if len(item) == 3: self.dataset.append( nlpir.segWithTag(item[2]).replace("\t", " ")) self.label.append(item[0]) data.close()