Question

需要一个建议

我的代码：

import pandas as pd
import openpyxl
df = pd.read_excel('workbook.xlsx', sheet_name='Sheet1')  
df_writer = pd.ExcelWriter('workbook.xlsx', engine='openpyxl')
excel = openpyxl.load_workbook('workbook.xlsx')
df_writer.book = excel


for string in ['A','B','C','D','E','F']:
    df[df['column 1'].str.contains(string)].to_excel(df_writer,sheet_name=string)

writer.save()
writer.close()

现在，我将包含某些字符串的数据分离出来，并保存在同一工作簿的不同工作表中。

每个工作表分别命名为'A'，'B'，'C'，'D'，'E'，'F' 我需要将名为“ A”和“ B”的工作表合并在一起，以便在同一工作簿中使用不同的名称进行进一步分析，例如“合并” 工作表“ A”和“ B”具有相同数量的列和标题。

任何建议将不胜感激。

Answer 1

使用带有A|B的字符串包含方法在列中找到A或B中的一个值并将其包括在内，将其另存为新的工作表：

import pandas as pd
import openpyxl
df = pd.read_excel('workbook.xlsx', sheet_name='Sheet1')  
df_writer = pd.ExcelWriter('workbook.xlsx', engine='openpyxl')
excel = openpyxl.load_workbook('workbook.xlsx')
df_writer.book = excel


for string in ['A','B','C','D','E','F']:
    df[df['column 1'].str.contains(string)].to_excel(df_writer,sheet_name=string)

df[df['column 1'].str.contains('A|B')].to_excel(df_writer,sheet_name='Combined')
#Now your excel contains all 'A','B','C','D','E','F' and 'Combined' sheet.

writer.save()
writer.close()

Answer 2

代码适用于在所有工作表中包含相同列数的.xlsx文件。但是，可以进行修改以合并具有不同编号的工作表中的数据。列数。

注意：.xlsx文件没有相同的编号时。表格中的列数，它将替换redo_files_directory中的该文件。

import numpy as np
import os
from openpyxl import *
import shutil


directory = 'filepath'
new_folder = 'New_Files_Directory'
redo_files_directory = 'Folder_for_files_with_different_num_of_columns'



def checkEqual1(iterator):
    iterator = iter(iterator)
    try:
        first = next(iterator)
    except StopIteration:
        return True
    return all(first == rest for rest in iterator)


for root, dirs, files in os.walk(directory):
    for file in files:
        filename = file
        file = os.path.join(root, file)
        wb2 = load_workbook(file)
        list_of_all_sheets = wb2.sheetnames
        array_1 = np.array([])
        array_2 = np.array([])
        array_3 = np.array([])
        array_4 = np.array([])
        if len(list_of_all_sheets) != 0:            
            for worksheet in wb2.worksheets:
                array_1 = np.append(array_2, worksheet.max_column)
                array_2 = array_1
                array_1 = array_1.astype(int)
                array_3 = np.append(array_4, worksheet.max_row)
                array_4 = array_3
                array_3 = array_3.astype(int)
        else:
            dest = shutil.move(file, redo_files_directory, copy_function = shutil.copytree)

# array_1 is an array of max. num. of columns from all sheets
# array_2 -----------/------------ of rows --------/---------

        k = 0
        for i in range(0, len(array_3)):    
            k = k + array_3[i]; 

# k is the sum of the rows from all spreadsheets

        z = 1
        wb = Workbook()
        ws = wb.active
        ws.title = 'Sheet_1'
        if checkEqual1(array_1) == True:
            while z <= k:
                for sheet in wb2.worksheets:
                    r = 1
                    while r <= sheet.max_row:
                        c = 1   
                        while c <= sheet.max_column:
                            h_1 = sheet.cell(row = r, column = c).value
                            c_1 = ws.cell(row = z, column = c)
                            c_1.value = h_1
                            c = c + 1
                        r = r + 1
                        z = z + 1
        else:
            dest = shutil.move(file, redo_files_directory, copy_function = shutil.copytree)

        wb.save(new_folder+filename)

如何使用python在同一工作簿中组合所选工作表

2 个答案: