#1.读取数据集 def read_dataset(): file_path = r\'D:\SMSSpamCollection.txt\' sms = open(file_path, encoding=\'utf-8\') sms_data = [] sms_label = [] csv_reader = csv.reader(sms, delimiter=\'\t\') for line in csv_reader: sms_label.append(line[0]) #提取出标签 sms_data.append(preprocessing(line[1])) #提取出特征 sms.close() return sms_data, sms_label