Python 将DataFrame写入Excel：如何自动调整列宽

我正在尝试将一系列数据框写入Excel工作表，以便：

工作表的现有内容不会被覆盖或删除，以及

Excel列宽会根据列条目的长度进行调整（这样我就不必在Excel中手动执行此操作）

对于1），我找到了一个极好的解决方案，它是@MaxU编写的helper函数。例如，我找到了一个看起来不错的解决方案。但是，当我尝试将这些解决方案放在一起时，列宽根本不会改变。以下是我的完整代码：

import pandas as pd
import os
from openpyxl import load_workbook

def append_df_to_excel(filename, df, sheet_name='Sheet1', startrow=None,
                       truncate_sheet=False, 
                       **to_excel_kwargs):
    """
    Append a DataFrame [df] to existing Excel file [filename]
    into [sheet_name] Sheet.
    If [filename] doesn't exist, then this function will create it.

    @param filename: File path or existing ExcelWriter
                     (Example: '/path/to/file.xlsx')
    @param df: DataFrame to save to workbook
    @param sheet_name: Name of sheet which will contain DataFrame.
                       (default: 'Sheet1')
    @param startrow: upper left cell row to dump data frame.
                     Per default (startrow=None) calculate the last row
                     in the existing DF and write to the next row...
    @param truncate_sheet: truncate (remove and recreate) [sheet_name]
                           before writing DataFrame to Excel file
    @param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
                            [can be a dictionary]
    @return: None

    Usage examples:

    >>> append_df_to_excel('d:/temp/test.xlsx', df)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, header=None, index=False)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
                           index=False)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2', 
                           index=False, startrow=25)

    (c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
    """
    # Excel file doesn't exist - saving and exiting
    if not os.path.isfile(filename):
        df.to_excel(
            filename,
            sheet_name=sheet_name, 
            startrow=startrow if startrow is not None else 0, 
            **to_excel_kwargs)
        return
    
    # ignore [engine] parameter if it was passed
    if 'engine' in to_excel_kwargs:
        to_excel_kwargs.pop('engine')

    writer = pd.ExcelWriter(filename, engine='openpyxl', mode='a')

    # try to open an existing workbook
    writer.book = load_workbook(filename)
    
    # get the last row in the existing Excel sheet
    # if it was not specified explicitly
    if startrow is None and sheet_name in writer.book.sheetnames:
        startrow = writer.book[sheet_name].max_row

    # truncate sheet
    if truncate_sheet and sheet_name in writer.book.sheetnames:
        # index of [sheet_name] sheet
        idx = writer.book.sheetnames.index(sheet_name)
        # remove [sheet_name]
        writer.book.remove(writer.book.worksheets[idx])
        # create an empty sheet [sheet_name] using old index
        writer.book.create_sheet(sheet_name, idx)
    
    # copy existing sheets
    writer.sheets = {ws.title:ws for ws in writer.book.worksheets}

    if startrow is None:
        startrow = 0

    # write out the new sheet
    df.to_excel(writer, sheet_name, startrow=startrow, **to_excel_kwargs)

   
  """
   Now attempt to adjust the column widths as necessary so that all the cell contents are visible 
   in Excel. The code below is taken from https://towardsdatascience.com/how-to-auto-adjust-the-width-of-excel-columns-with-pandas-excelwriter-60cee36e175e.
 """
    for column in df:
      column_width = max(df[column].astype(str).map(len).max(), len(column))
      col_idx = df.columns.get_loc(column)
      writer.sheets[sheet_name].set_column(col_idx, col_idx, column_width)

    writer.save()

现在我尝试测试该函数：

df = pd.DataFrame({'A_Very_Long_Column_Name': [10, 20, 30, 20, 15, 30, 45]})
append_df_to_excel("C:/Users/Leonidas/Documents/test.xlsx", df, "Sheet1")

import numpy as np
import pandas as pd
from pathlib import Path
from typing import Union, Optional, List, Tuple
from openpyxl import load_workbook
from openpyxl.utils import get_column_letter


def append_df_to_excel(
        filename: Union[str, Path],
        df: pd.DataFrame,
        sheet_name: str = 'Sheet1',
        startrow: int = None,
        max_col_width: int = 40,
        autofilter: bool = False,
        fmt_int: str = "#,##0",
        fmt_float: str = "#,##0.00",
        fmt_date: str = "yyyy-mm-dd",
        fmt_datetime: str = "yyyy-mm-dd hh:mm",
        truncate_sheet: bool = False,
        **to_excel_kwargs
) -> None:
    """
    Append a DataFrame [df] to existing Excel file [filename]
    into [sheet_name] Sheet.
    If [filename] doesn't exist, then this function will create it.

    @param filename: File path or existing ExcelWriter
                     (Example: '/path/to/file.xlsx')
    @param df: DataFrame to save to workbook
    @param sheet_name: Name of sheet which will contain DataFrame.
                       (default: 'Sheet1')
    @param startrow: upper left cell row to dump data frame.
                     Per default (startrow=None) calculate the last row
                     in the existing DF and write to the next row...
    @param max_col_width: maximum column width in Excel. Default: 30
    @param autofilter: boolean - whether add Excel autofilter or not. Default: True
    @param fmt_int: Excel format for integer numbers
    @param fmt_float: Excel format for float numbers
    @param fmt_date: Excel format for dates
    @param fmt_datetime: Excel format for datetime's
    @param truncate_sheet: truncate (remove and recreate) [sheet_name]
                           before writing DataFrame to Excel file
    @param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
                            [can be a dictionary]
    @return: None

    Usage examples:

    >>> append_df_to_excel('d:/temp/test.xlsx', df, autofilter=True,
                           freeze_panes=(1,0))

    >>> append_df_to_excel('d:/temp/test.xlsx', df, header=None, index=False)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
                           index=False)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
                           index=False, startrow=25)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, index=False,
                           fmt_datetime="dd.mm.yyyy hh:mm")

    (c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
    """
    def set_column_format(ws, column_letter, fmt):
        for cell in ws[column_letter]:
            cell.number_format = fmt
    filename = Path(filename)
    file_exists = filename.is_file()
    # process parameters
    first_col = int(to_excel_kwargs.get("index", True)) + 1
    sheet_name = to_excel_kwargs.get("sheet_name", "Sheet1")
    # ignore [engine] parameter if it was passed
    if 'engine' in to_excel_kwargs:
        to_excel_kwargs.pop('engine')

    with pd.ExcelWriter(
        filename.with_suffix(".xlsx"),
        engine="openpyxl",
        mode="a" if file_exists else "w",
        date_format=fmt_date,
        datetime_format=fmt_datetime,
        **to_excel_kwargs
    ) as writer:
        if file_exists:
            # try to open an existing workbook
            writer.book = load_workbook(filename)
            # get the last row in the existing Excel sheet
            # if it was not specified explicitly
            if startrow is None and sheet_name in writer.book.sheetnames:
                startrow = writer.book[sheet_name].max_row
            # truncate sheet
            if truncate_sheet and sheet_name in writer.book.sheetnames:
                # index of [sheet_name] sheet
                idx = writer.book.sheetnames.index(sheet_name)
                # remove [sheet_name]
                writer.book.remove(writer.book.worksheets[idx])
                # create an empty sheet [sheet_name] using old index
                writer.book.create_sheet(sheet_name, idx)

            # copy existing sheets
            writer.sheets = {ws.title:ws for ws in writer.book.worksheets}
        else:
            # file doesn't exist, we are creating a new one
            startrow = 0

        # write out the DataFrame to an ExcelWriter
        df.to_excel(writer, sheet_name=sheet_name, startrow=startrow,
                    **to_excel_kwargs)

        # automatically set columns' width
        worksheet = writer.sheets[sheet_name]
        for xl_col_no, dtyp in enumerate(df.dtypes, first_col):
            col_no = xl_col_no - first_col
            width = max(df.iloc[:, col_no].astype(str).str.len().max(),
                        len(df.columns[col_no]) + 6)
            width = min(max_col_width, width)
            # print(f"column: [{df.columns[col_no]} ({dtyp.name})]\twidth:\t[{width}]")
            column_letter = get_column_letter(xl_col_no)
            worksheet.column_dimensions[column_letter].width = width
            if np.issubdtype(dtyp, np.integer):
                set_column_format(worksheet, column_letter, fmt_int)
            if np.issubdtype(dtyp, np.floating):
                set_column_format(worksheet, column_letter, fmt_float)
        if autofilter:
            worksheet.auto_filter.ref = worksheet.dimensions

将创建名为test.xlsx的新Excel工作簿以及名为Sheet1的工作表，并将

df

的内容写入Sheet1，但列宽完全不受影响：

奇怪的是，当我第二次尝试执行函数时（不更改参数），我得到了一个错误：

runcell(2, 'C:/Users/Leonidas/Documents/write_to_excel2.py')
Traceback (most recent call last):

  File "C:\Users\Leonidas\Documents\write_to_excel2.py", line 125, in <module>
    append_df_to_excel("C:/Users/Leonidas/Documents/test.xlsx", df,

  File "C:\Users\Leonidas\Documents\write_to_excel2.py", line 100, in append_df_to_excel
    writer.sheets[sheet_name].set_column(col_idx, col_idx, column_width)

AttributeError: 'Worksheet' object has no attribute 'set_column'

runcell（2，'C:/Users/Leonidas/Documents/write_to_excel2.py'）
回溯（最近一次呼叫最后一次）：
文件“C:\Users\Leonidas\Documents\write_to_excel2.py”，第125行，在
将_df_添加到_excel（“C:/Users/Leonidas/Documents/test.xlsx”，df，
文件“C:\Users\Leonidas\Documents\write_to_excel2.py”，第100行，在附录_df_to_excel中
writer.sheets[sheet\u name].set\u列（列idx、列idx、列宽度）
AttributeError:“工作表”对象没有属性“set\u column”

---

我现在很困惑…任何关于如何修复代码的建议都将不胜感激。

尝试使用此帮助函数：

df = pd.DataFrame({'A_Very_Long_Column_Name': [10, 20, 30, 20, 15, 30, 45]})
append_df_to_excel("C:/Users/Leonidas/Documents/test.xlsx", df, "Sheet1")

import numpy as np
import pandas as pd
from pathlib import Path
from typing import Union, Optional, List, Tuple
from openpyxl import load_workbook
from openpyxl.utils import get_column_letter


def append_df_to_excel(
        filename: Union[str, Path],
        df: pd.DataFrame,
        sheet_name: str = 'Sheet1',
        startrow: int = None,
        max_col_width: int = 40,
        autofilter: bool = False,
        fmt_int: str = "#,##0",
        fmt_float: str = "#,##0.00",
        fmt_date: str = "yyyy-mm-dd",
        fmt_datetime: str = "yyyy-mm-dd hh:mm",
        truncate_sheet: bool = False,
        **to_excel_kwargs
) -> None:
    """
    Append a DataFrame [df] to existing Excel file [filename]
    into [sheet_name] Sheet.
    If [filename] doesn't exist, then this function will create it.

    @param filename: File path or existing ExcelWriter
                     (Example: '/path/to/file.xlsx')
    @param df: DataFrame to save to workbook
    @param sheet_name: Name of sheet which will contain DataFrame.
                       (default: 'Sheet1')
    @param startrow: upper left cell row to dump data frame.
                     Per default (startrow=None) calculate the last row
                     in the existing DF and write to the next row...
    @param max_col_width: maximum column width in Excel. Default: 30
    @param autofilter: boolean - whether add Excel autofilter or not. Default: True
    @param fmt_int: Excel format for integer numbers
    @param fmt_float: Excel format for float numbers
    @param fmt_date: Excel format for dates
    @param fmt_datetime: Excel format for datetime's
    @param truncate_sheet: truncate (remove and recreate) [sheet_name]
                           before writing DataFrame to Excel file
    @param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
                            [can be a dictionary]
    @return: None

    Usage examples:

    >>> append_df_to_excel('d:/temp/test.xlsx', df, autofilter=True,
                           freeze_panes=(1,0))

    >>> append_df_to_excel('d:/temp/test.xlsx', df, header=None, index=False)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
                           index=False)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
                           index=False, startrow=25)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, index=False,
                           fmt_datetime="dd.mm.yyyy hh:mm")

    (c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
    """
    def set_column_format(ws, column_letter, fmt):
        for cell in ws[column_letter]:
            cell.number_format = fmt
    filename = Path(filename)
    file_exists = filename.is_file()
    # process parameters
    first_col = int(to_excel_kwargs.get("index", True)) + 1
    sheet_name = to_excel_kwargs.get("sheet_name", "Sheet1")
    # ignore [engine] parameter if it was passed
    if 'engine' in to_excel_kwargs:
        to_excel_kwargs.pop('engine')

    with pd.ExcelWriter(
        filename.with_suffix(".xlsx"),
        engine="openpyxl",
        mode="a" if file_exists else "w",
        date_format=fmt_date,
        datetime_format=fmt_datetime,
        **to_excel_kwargs
    ) as writer:
        if file_exists:
            # try to open an existing workbook
            writer.book = load_workbook(filename)
            # get the last row in the existing Excel sheet
            # if it was not specified explicitly
            if startrow is None and sheet_name in writer.book.sheetnames:
                startrow = writer.book[sheet_name].max_row
            # truncate sheet
            if truncate_sheet and sheet_name in writer.book.sheetnames:
                # index of [sheet_name] sheet
                idx = writer.book.sheetnames.index(sheet_name)
                # remove [sheet_name]
                writer.book.remove(writer.book.worksheets[idx])
                # create an empty sheet [sheet_name] using old index
                writer.book.create_sheet(sheet_name, idx)

            # copy existing sheets
            writer.sheets = {ws.title:ws for ws in writer.book.worksheets}
        else:
            # file doesn't exist, we are creating a new one
            startrow = 0

        # write out the DataFrame to an ExcelWriter
        df.to_excel(writer, sheet_name=sheet_name, startrow=startrow,
                    **to_excel_kwargs)

        # automatically set columns' width
        worksheet = writer.sheets[sheet_name]
        for xl_col_no, dtyp in enumerate(df.dtypes, first_col):
            col_no = xl_col_no - first_col
            width = max(df.iloc[:, col_no].astype(str).str.len().max(),
                        len(df.columns[col_no]) + 6)
            width = min(max_col_width, width)
            # print(f"column: [{df.columns[col_no]} ({dtyp.name})]\twidth:\t[{width}]")
            column_letter = get_column_letter(xl_col_no)
            worksheet.column_dimensions[column_letter].width = width
            if np.issubdtype(dtyp, np.integer):
                set_column_format(worksheet, column_letter, fmt_int)
            if np.issubdtype(dtyp, np.floating):
                set_column_format(worksheet, column_letter, fmt_float)
        if autofilter:
            worksheet.auto_filter.ref = worksheet.dimensions

---

您还可以尝试使用openpyxl bestFit属性，该属性将列宽设置为双击列边框时的宽度。它应该可以做到这一点。请尝试执行以下操作：

for column in df:
    ws.column_dimensions[column].bestFit = True

---

根据导出到Excel的原因，您还可以查看许多不同的基于Python的电子表格。我是一个名为的电子表格的作者。它可以让您将pandas dataframe显示为交互式电子表格。

谢谢您的帮助！这几乎满足了我的要求：当我尝试并排写入dataframes时，列宽将调整为ent似乎对第一个df非常有效，但似乎对第二个df没有影响。我将尝试调整代码，看看是否可以修复它……根据你提到的文章，你是通过

pip安装xlsxwriter

来安装模块xlsxwriter，还是如果你使用Windows并在其中安装了Office，你可以使用

AutoFi来尝试
win32com
t

，有关详细信息，请参阅。