37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
|
"""读写表格。
|
|||
|
|
|
|||
|
|
只保留两个函数：`load_table` / `save_table` 按扩展名分派。
|
|||
|
|
原建议里的 `load_csv` `load_excel` `save_csv` `save_excel` 四个函数
|
|||
|
|
只是在转发 pandas，合并后调用点更短。
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
from __future__ import annotations
|
|||
|
|
|
|||
|
|
from pathlib import Path
|
|||
|
|
from typing import Any
|
|||
|
|
|
|||
|
|
__all__ = ["load_table", "save_table"]
|
|||
|
|
|
|||
|
|
|
|||
|
|
def load_table(path: str | Path, **kwargs: Any) -> Any:
|
|||
|
|
"""按扩展名自动选择读取方式，返回 DataFrame。
|
|||
|
|
|
|||
|
|
约定：
|
|||
|
|
* `.csv` 默认做编码探测（utf-8 → utf-8-sig → gbk → gb18030），
|
|||
|
|
国内赛题数据常见 GBK；
|
|||
|
|
* `.xlsx` / `.xls` 需要 `openpyxl`（`pip install "mcm-toolkit[excel]"`）；
|
|||
|
|
* `na_values` 默认包含空串、`"NA"`、`"N/A"`、`"#N/A"`、`"null"`、`"-"`。
|
|||
|
|
|
|||
|
|
Examples
|
|||
|
|
--------
|
|||
|
|
>>> df = load_table("data.csv") # doctest: +SKIP
|
|||
|
|
>>> df.shape # doctest: +SKIP
|
|||
|
|
"""
|
|||
|
|
# TODO(L0): 编码探测 + 分派；Excel 缺 openpyxl 时给出可读报错。
|
|||
|
|
raise NotImplementedError
|
|||
|
|
|
|||
|
|
|
|||
|
|
def save_table(df: Any, path: str | Path, index: bool = False, **kwargs: Any) -> Path:
|
|||
|
|
"""保存 DataFrame，返回实际写入的路径。"""
|
|||
|
|
# TODO(L0)
|
|||
|
|
raise NotImplementedError
|