torchtext构建数据集，txt文件

from torchtext import data
from torchtext.vocab import Vectors
from torch.nn import init
import tqdm
from sklearn.utils import shuffle
tokenize = lambda x: x.split()
# fix_length指定每条文本的长度，截断补长
TEXT = data.Field(sequential=True, tokenize=tokenize, lower=True, fix_length=200)
LABEL = data.Field(sequential=False, use_vocab=False)
corpus_path=r"D:\torchtext-practise\1.txt"

# # 加载语料
# with open(corpus_path, "r", encoding="utf-8") as f:
#     # 将数据集全部加载到内存
#     lines = [line for line in tqdm.tqdm(f, desc="Loading Dataset")]#eval(line)处理的文本有格式时
#                                                                       #Ctrl+Alt+i缩进
#     # 打乱顺序
#     train_data = shuffle(lines)
#     # 获取数据长度(条数)
#     corpus_lines = len(lines)
def get_text_and_label(line):
        line=line.split(" ",1)
        # 获取文本和标记
        text = line[0]
       # print(text)
        label