Python批量统计Excel工作簿的最大值和最小值

pip install pandas xlwings

import pandas as pd
import xlwings as xw


def clean_to_number(s: pd.Series) -> pd.Series:
    """
    将 Excel 中可能带有逗号、货币符号、空格的文本数字转换为真正的数值。
    例如：
    ￥12,345.67 -> 12345.67
    9,876.5     -> 9876.5
    空值或异常字符 -> NaN
    """
    s = s.astype(str).str.strip()
    s = s.str.replace(",", "", regex=False)
    s = s.str.replace(r"[¥￥$ ]", "", regex=True)
    s = s.str.replace(r"[^0-9\.\-]", "", regex=True)
    return pd.to_numeric(s, errors="coerce")


def batch_min_max(
    input_xlsx: str,
    value_col: str = "销售利润",
    key_col: str | None = None,
    summary_sheet: str = "极值汇总",
    write_cell: str = "J1",
    start_cell: str = "A1",
    save_as: str | None = None,
) -> None:
    """
    批量统计一个工作簿中所有工作表指定列的最大值和最小值。

    参数说明：
    input_xlsx      原始 Excel 文件路径
    value_col       需要统计最大值和最小值的字段名
    key_col         可选关键字段，例如产品名称、订单号、员工姓名
    summary_sheet   汇总结果工作表名称
    write_cell      每张原始工作表中写回统计结果的位置
    start_cell      表格起始单元格
    save_as         另存为路径；如果为 None，则覆盖保存原文件
    """
    app = xw.App(visible=False, add_book=False)
    app.display_alerts = False
    app.screen_updating = False

    try:
        wb = app.books.open(input_xlsx)
        rows = []

        for sht in wb.sheets:
            if sht.name == summary_sheet:
                continue

            rng = sht.range(start_cell).expand("table")
            if rng.value is None:
                print(f"[SKIP] {sht.name}: 空表")
                continue

            df = rng.options(pd.DataFrame).value
            if df is None or df.empty:
                print(f"[SKIP] {sht.name}: 无有效数据")
                continue

            if value_col not in df.columns:
                print(f"[SKIP] {sht.name}: 缺少列：{value_col}")
                continue

            num = clean_to_number(df[value_col])

            if num.isna().all():
                print(f"[SKIP] {sht.name}: {value_col} 全部无法转换为数值")
                continue

            max_val = float(num.max(skipna=True))
            min_val = float(num.min(skipna=True))

            max_idx = int(num.idxmax(skipna=True))
            min_idx = int(num.idxmin(skipna=True))

            max_key = df.loc[max_idx, key_col] if (key_col and key_col in df.columns) else ""
            min_key = df.loc[min_idx, key_col] if (key_col and key_col in df.columns) else ""

            stat_df = pd.DataFrame({
                "指标": [
                    "最大值",
                    "最小值",
                    "最大值所在行索引",
                    "最小值所在行索引",
                    "最大值关键字段",
                    "最小值关键字段"
                ],
                "数值": [
                    max_val,
                    min_val,
                    max_idx,
                    min_idx,
                    max_key,
                    min_key
                ],
            })

            sht.range(write_cell).options(index=False).value = stat_df
            sht.autofit()

            rows.append({
                "工作表": sht.name,
                f"{value_col}最大值": max_val,
                f"{value_col}最小值": min_val,
                "最大值行索引": max_idx,
                "最小值行索引": min_idx,
                "最大值关键字段": max_key,
                "最小值关键字段": min_key,
            })

            print(f"[OK] {sht.name}: max={max_val}, min={min_val}")

        if not rows:
            raise RuntimeError("没有得到任何极值结果，请检查字段名、表格区域或数据内容。")

        summary_df = pd.DataFrame(rows)

        global_max_row = summary_df.loc[summary_df[f"{value_col}最大值"].idxmax()]
        global_min_row = summary_df.loc[summary_df[f"{value_col}最小值"].idxmin()]

        try:
            sum_sht = wb.sheets[summary_sheet]
            sum_sht.clear()
        except Exception:
            sum_sht = wb.sheets.add(summary_sheet, before=wb.sheets[0])

        sum_sht.range("A1").value = "全局最大值"
        sum_sht.range("B1").value = float(global_max_row[f"{value_col}最大值"])
        sum_sht.range("C1").value = "来自工作表"
        sum_sht.range("D1").value = global_max_row["工作表"]

        sum_sht.range("A2").value = "全局最小值"
        sum_sht.range("B2").value = float(global_min_row[f"{value_col}最小值"])
        sum_sht.range("C2").value = "来自工作表"
        sum_sht.range("D2").value = global_min_row["工作表"]

        summary_df_sorted = summary_df.sort_values(
            by=f"{value_col}最大值",
            ascending=False
        )

        sum_sht.range("A4").options(index=False).value = summary_df_sorted

        try:
            sum_sht.range("A1:D2").api.Font.Bold = True
            sum_sht.autofit()
        except Exception:
            pass

        if save_as:
            wb.save(save_as)
            print(f"[DONE] 已另存为：{save_as}")
        else:
            wb.save()
            print(f"[DONE] 已覆盖保存：{input_xlsx}")

        wb.close()

    finally:
        app.quit()


if __name__ == "__main__":
    batch_min_max(
        input_xlsx="产品销售统计表.xlsx",
        value_col="销售利润",
        key_col="产品名称",
        summary_sheet="极值汇总",
        write_cell="J1",
        start_cell="A1",
        save_as="产品销售统计表_极值统计.xlsx"
    )

print(df.columns.tolist())