# bert_classification_model

**Repository Path**: hbpiaoyi/bert_classification_model

## Basic Information

- **Project Name**: bert_classification_model
- **Description**: 基于Bert预训练模型的文本分类模型
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-06-30
- **Last Updated**: 2026-07-15

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

utils使用介绍
1.全局通用日志打印
导包
from utils.log import logger
logger.debug("调试信息")
logger.info("正常业务日志")
logger.warning("警告日志")
logger.error("错误信息", exc_info=True)  # exc_info自动打印异常堆栈
try:
    1 / 0
except Exception as e:
    logger.error("程序发生异常", exc_info=True)

运行结果
2026-06-30 11:28:55 | INFO  | global | test.py:11 | 正常业务日志
2026-06-30 11:28:55 | WARNING | global | test.py:12 | 警告日志
2026-06-30 11:28:55 | ERROR | global | test.py:13 | 错误信息
NoneType: None
2026-06-30 11:28:55 | ERROR | global | test.py:18 | 程序发生异常
Traceback (most recent call last):
  File "D:\PythonCode\PythonLearn\conda3_py312\project\test.py", line 16, in <module>
    1 / 0
    ~~^~~
ZeroDivisionError: division by zero

2.不同模块独立命名日志（区分哪个模块报错来源）
导包
from utils.log import get_logger

img_log = get_logger("image_download")
img_log.info("开始拉取镜像")

file_log = get_logger("file_util")
file_log.info("读取配置文件完成")

运行结果
2026-06-30 11:32:21 | INFO  | image_download | test2.py:12 | 开始拉取镜像
2026-06-30 11:32:21 | INFO  | file_util | test2.py:16 | 读取配置文件完成

3. data_preprocess.py
load_data(path) 加载数据集, 构造数据
TextDataset(Dataset) 构建数据集对象
build_dataloader 构建数据加载器对象

4. 文件读取写入工具类
mkdir(path: str) -> None:
        """递归创建文件夹，不存在则创建"""
exists(file_path: str) -> bool:
        """判断文件/文件夹是否存在"""
is_file(file_path: str) -> bool:
        """判断是否为文件"""
is_dir(dir_path: str) -> bool:
        """判断是否为文件夹"""
get_dir(file_path: str) -> str:
        """获取文件所在目录"""
read_text(file_path: str, encoding: str = "utf-8") -> str:
        """读取完整文本文件
        :param file_path: 文件路径
        :param encoding: 编码格式
        :return: 文件全部字符串
        """
read_text_lines(file_path: str, encoding: str = "utf-8", strip: bool = True) -> List[str]:
        """按行读取文本，返回行列表"""
write_text(file_path: str, content: str, encoding: str = "utf-8", append: bool = False) -> None:
        """写入文本文件
        :param file_path: 文件路径
        :param content: 写入字符串
        :param encoding: 编码
        :param append: True追加写入，False覆盖
        """
write_text_lines(file_path: str, lines: List[str], encoding: str = "utf-8", append: bool = False) -> None:
        """批量写入多行文本"""
read_bytes(file_path: str) -> bytes:
        """读取二进制文件（图片、视频、exe等）"""
write_bytes(file_path: str, data: bytes, append: bool = False) -> None:
        """写入二进制数据"""