"使用 python pandas 将现有的 excel 表附加到新的数据框"

Question

我目前有这个代码。 它完美地工作。

它遍历文件夹中的 excel 文件，删除前 2 行，然后将它们保存为单独的 excel 文件，并将循环中的文件保存为附加文件。

目前，每次运行代码时，附加文件都会覆盖<\/strong>现有文件。

我需要将新数据附加到已经存在的 excel 表<\/strong>（'master_data.xlsx）的底部

dfList = []
path = 'C:\\Test\\TestRawFile' 
newpath = 'C:\\Path\\To\\New\\Folder'

for fn in os.listdir(path): 
  # Absolute file path
  file = os.path.join(path, fn)
  if os.path.isfile(file): 
    # Import the excel file and call it xlsx_file 
    xlsx_file = pd.ExcelFile(file) 
    # View the excel files sheet names 
    xlsx_file.sheet_names 
    # Load the xlsx files Data sheet as a dataframe 
    df = xlsx_file.parse('Sheet1',header= None) 
    df_NoHeader = df[2:] 
    data = df_NoHeader 
    # Save individual dataframe
    data.to_excel(os.path.join(newpath, fn))

    dfList.append(data) 

appended_data = pd.concat(dfList)
appended_data.to_excel(os.path.join(newpath, 'master_data.xlsx'))

Answer 1

---

更新 [2022-01-08]：似乎从 1.4.0 版开始，Pandas 将支持“开箱即用”附加到现有 Excel 工作表！

熊猫团队干得好！

根据pandas-dev github中的DocString，ExcelWriter将支持参数if_sheet_exists='overlay'

 if_sheet_exists : {'error', 'new', 'replace', 'overlay'}, default 'error' How to behave when trying to write to a sheet that already exists (append mode only). * error: raise a ValueError. * new: Create a new sheet, with a name determined by the engine. * replace: Delete the contents of the sheet before writing to it. * overlay: Write contents to the existing sheet without removing the old contents. .. versionadded:: 1.3.0 .. versionchanged:: 1.4.0 Added ``overlay`` option

---

对于 < 1.4.0 的 Pandas 版本，请在下方找到用于将 Pandas DataFrame 附加到现有 Excel 文件的辅助函数。

如果 Excel 文件不存在，则将创建该文件。

---

更新 [2021-09-12]：已针对 Pandas 1.3.0+ 修复

以下功能已经过测试：

• 熊猫 1.3.2
• OpenPyxl 3.0.7

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


def copy_excel_cell_range(
        src_ws: openpyxl.worksheet.worksheet.Worksheet,
        min_row: int = None,
        max_row: int = None,
        min_col: int = None,
        max_col: int = None,
        tgt_ws: openpyxl.worksheet.worksheet.Worksheet = None,
        tgt_min_row: int = 1,
        tgt_min_col: int = 1,
        with_style: bool = True
) -> openpyxl.worksheet.worksheet.Worksheet:
    """
    copies all cells from the source worksheet [src_ws] starting from [min_row] row
    and [min_col] column up to [max_row] row and [max_col] column
    to target worksheet [tgt_ws] starting from [tgt_min_row] row
    and [tgt_min_col] column.

    @param src_ws:  source worksheet
    @param min_row: smallest row index in the source worksheet (1-based index)
    @param max_row: largest row index in the source worksheet (1-based index)
    @param min_col: smallest column index in the source worksheet (1-based index)
    @param max_col: largest column index in the source worksheet (1-based index)
    @param tgt_ws:  target worksheet.
                    If None, then the copy will be done to the same (source) worksheet.
    @param tgt_min_row: target row index (1-based index)
    @param tgt_min_col: target column index (1-based index)
    @param with_style:  whether to copy cell style. Default: True

    @return: target worksheet object
    """
    if tgt_ws is None:
        tgt_ws = src_ws

    # https://stackoverflow.com/a/34838233/5741205
    for row in src_ws.iter_rows(min_row=min_row, max_row=max_row,
                                min_col=min_col, max_col=max_col):
        for cell in row:
            tgt_cell = tgt_ws.cell(
                row=cell.row + tgt_min_row - 1,
                column=cell.col_idx + tgt_min_col - 1,
                value=cell.value
            )
            if with_style and cell.has_style:
                # tgt_cell._style = copy(cell._style)
                tgt_cell.font = copy(cell.font)
                tgt_cell.border = copy(cell.border)
                tgt_cell.fill = copy(cell.fill)
                tgt_cell.number_format = copy(cell.number_format)
                tgt_cell.protection = copy(cell.protection)
                tgt_cell.alignment = copy(cell.alignment)
    return tgt_ws


def append_df_to_excel(
        filename: Union[str, Path],
        df: pd.DataFrame,
        sheet_name: str = 'Sheet1',
        startrow: Optional[int] = None,
        max_col_width: int = 30,
        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,
        storage_options: Optional[dict] = None,
        **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: 40
    @param autofilter: boolean - whether add Excel autofilter or not. Default: False
    @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 storage_options: dict, optional
        Extra options that make sense for a particular storage connection, e.g. host, port,
        username, password, etc., if using a URL that will be parsed by fsspec, e.g.,
        starting “s3://”, “gcs://”.
    @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('/tmp/test.xlsx', df, autofilter=True,
                           freeze_panes=(1,0))

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

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

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

    >>> append_df_to_excel('/tmp/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
    # calculate first column number
    # if the DF will be written using `index=True`, then `first_col = 2`, else `first_col = 1`
    first_col = int(to_excel_kwargs.get("index", True)) + 1
    # ignore [engine] parameter if it was passed
    if 'engine' in to_excel_kwargs:
        to_excel_kwargs.pop('engine')
    # save content of existing sheets
    if file_exists:
        wb = load_workbook(filename)
        sheet_names = wb.sheetnames
        sheet_exists = sheet_name in sheet_names
        sheets = {ws.title: ws for ws in wb.worksheets}

    with pd.ExcelWriter(
        filename.with_suffix(".xlsx"),
        engine="openpyxl",
        mode="a" if file_exists else "w",
        if_sheet_exists="new" if file_exists else None,
        date_format=fmt_date,
        datetime_format=fmt_datetime,
        storage_options=storage_options
    ) as writer:
        if file_exists:
            # try to open an existing workbook
            writer.book = wb
            # 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 = sheets
        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, **to_excel_kwargs)
        worksheet = writer.sheets[sheet_name]

        if autofilter:
            worksheet.auto_filter.ref = worksheet.dimensions

        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)
            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 file_exists and sheet_exists:
        # move (append) rows from new worksheet to the `sheet_name` worksheet
        wb = load_workbook(filename)
        # retrieve generated worksheet name
        new_sheet_name = set(wb.sheetnames) - set(sheet_names)
        if new_sheet_name:
            new_sheet_name = list(new_sheet_name)[0]
        # copy rows written by `df.to_excel(...)` to
        copy_excel_cell_range(
            src_ws=wb[new_sheet_name],
            tgt_ws=wb[sheet_name],
            tgt_min_row=startrow + 1,
            with_style=True
        )
        # remove new (generated by Pandas) worksheet
        del wb[new_sheet_name]
        wb.save(filename)
        wb.close()

---

旧版本（使用 Pandas 1.2.3 和 Openpyxl 3.0.5 测试）：

 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) # save the workbook writer.save()

---

使用示例：

filename = r'C:\OCC.xlsx'

append_df_to_excel(filename, df)

append_df_to_excel(filename, df, header=None, index=False)

append_df_to_excel(filename, df, sheet_name='Sheet2', index=False)

append_df_to_excel(filename, df, sheet_name='Sheet2', index=False, startrow=25)

---

c:/temp/test.xlsx:

PS如果您不想重复列名，您可能还想指定header=None ...

更新：您可能还想检查这个旧解决方案

Answer 2

如果您不是严格寻找 excel 文件，则将输出作为 csv 文件获取，然后将 csv 复制到新的 excel 文件中

df.to_csv('filepath', mode='a', index = False, header=None)

模式 = 'a'

a 表示追加

这是一种迂回的方式，但效果很好！

Answer 3

import pandas as pd
import openpyxl

workbook = openpyxl.load_workbook("test.xlsx")
writer = pd.ExcelWriter('test.xlsx', engine='openpyxl')
writer.book = workbook
writer.sheets = dict((ws.title, ws) for ws in workbook.worksheets)
data_df.to_excel(writer, 'Existing_sheetname')
writer.save()
writer.close()

Answer 4

基于 MaxU 和其他人的代码和注释，但简化为仅修复 pandas ExcelWriter 导致 to_excel 创建新工作表而不是在附加模式下附加到现有工作表的错误。

正如其他人所指出的，to_excel 使用 ExcelWriter.sheets 属性，并且在 ExcelWriter 时不会填充该属性。

Fix 是单行的，否则代码是标准的 pandas 方法，如 to_excel 中所述。

    # xl_path is destination xlsx spreadsheet
    with pd.ExcelWriter(xl_path, 'openpyxl', mode='a') as writer:
        # fix line
        writer.sheets = dict((ws.title, ws) for ws in writer.book.worksheets)
        df.to_excel(writer, sheet_name)

Answer 5

如果您每次都在工作表上使用 ExcelWriter，它将覆盖前一个工作表，那么可见的只是您附加到工作簿的最后一个数据表。 相反，您可以维护一个最初为 1 的计数器，您需要为其初始化 excel 工作表并使用现有的方法添加初始数据

writer = pd.ExcelWriter(output_file, engine='openpyxl')

df = pd.read_excel(output_file, sheet_name='TestSheet1')

Answer 6

这个问题在这里已经有一段时间了。 答案还可以，但我相信这将解决大多数人的问题。

只需使用 glob 访问特定目录中的文件，遍历它们，为每个文件创建一个数据框，将其附加到最后一个文件，然后导出到文件夹。 我还包括了注释掉的代码，以通过 csvs 运行。

import os
import pandas as pd
import glob

# put in path to folder with files you want to append
# *.xlsx or *.csv will get all files of that type
path = "C:/Users/Name/Folder/*.xlsx"
#path = "C:/Users/Name/Folder/*.csv"

# initialize a empty df
appended_data = pd.DataFrame()

#loop through each file in the path
for file in glob.glob(path):
    print(file)

    # create a df of that file path
    df = pd.read_excel(file, sheet_name = 0)
    #df = pd.read_csv(file, sep=',')

    # appened it
    appended_data = appended_data.append(df)

appended_data

# export the appeneded data to a folder of your choice
exportPath = 'C:/My/EXPORT/PATH/appended_dataExport.csv'
appended_data.to_csv(os.path.join(exportPath),index=False)

Answer 7

作为@david的补充，如果您不关心索引<\/strong>并且可以使用.csv<\/strong> ，此功能有助于将任何 df 附加到现有 csv

def append_df(self, path_file, df):
    with open(path_file, 'a+') as f:
        df.to_csv(f, header=f.tell() == 0, encoding='utf-8', index=False)

Answer 8

这对我有用

import os
import openpyxl
import pandas as pd
from openpyxl.utils.dataframe import dataframe_to_rows

file = r"myfile.xlsx"

df = pd.DataFrame({'A': 1, 'B': 2})

# create excel file
if os.path.isfile(file):  # if file already exists append to existing file
    workbook = openpyxl.load_workbook(file)  # load workbook if already exists
    sheet = workbook['my_sheet_name']  # declare the active sheet 

    # append the dataframe results to the current excel file
    for row in dataframe_to_rows(df, header = False, index = False):
        sheet.append(row)
    workbook.save(file)  # save workbook
    workbook.close()  # close workbook
else:  # create the excel file if doesn't already exist
    with pd.ExcelWriter(path = file, engine = 'openpyxl') as writer:
        df.to_excel(writer, index = False, sheet_name = 'my_sheet_name')

Answer 9

from openpyxl import load_workbook
wb = load_workbook(filepath)
ws = wb["Sheet1"]
df = dataframe.values.tolist()
for i in range(len(df)):
    ws.append(df[i])
wb.save(filepath)

Answer 10

将 DataFrame 附加到现有的 excel 文件<\/strong>

使用 ExcelWrite 将 DataFrame 附加到现有的 Excel 文件。 这是一种简单的方法，并使用现有的库功能。

with pd.ExcelWriter('existing_excel_file.xlsx',mode='a') as writer:  
    df.to_excel(writer, sheet_name='existing_sheet_name')