使用 Python 比较 2 个 excel 文件

Question

我有两个

xlsx

文件如下：

value1   value2   value3
0.456   3.456    0.4325436
6.24654 0.235435 6.376546
4.26545 4.264543 7.2564523

和

value1   value2  value3
0.456   3.456    0.4325436
6.24654 0.23546  6.376546
4.26545 4.264543 7.2564523

我需要比较所有单元格，如果来自

file1 !=

的单元格来自

file2

print

的单元格。

import xlrd
rb = xlrd.open_workbook('file1.xlsx')
rb1 = xlrd.open_workbook('file2.xlsx')
sheet = rb.sheet_by_index(0)
for rownum in range(sheet.nrows):
    row = sheet.row_values(rownum)
    for c_el in row:
        print c_el

如何添加

file1

和

file2

的比较单元格？

Answer 1

使用

pandas

，你可以像这样简单地完成：

import pandas as pd

df1 = pd.read_excel('excel1.xlsx')
df2 = pd.read_excel('excel2.xlsx')

difference = df1[df1!=df2]
print difference

结果将如下所示：

Answer 2

以下方法应该可以帮助您开始：

from itertools import zip_longest
import xlrd

rb1 = xlrd.open_workbook('file1.xlsx')
rb2 = xlrd.open_workbook('file2.xlsx')

sheet1 = rb1.sheet_by_index(0)
sheet2 = rb2.sheet_by_index(0)

for rownum in range(max(sheet1.nrows, sheet2.nrows)):
    if rownum < sheet1.nrows:
        row_rb1 = sheet1.row_values(rownum)
        row_rb2 = sheet2.row_values(rownum)

        for colnum, (c1, c2) in enumerate(zip_longest(row_rb1, row_rb2)):
            if c1 != c2:
                print("Row {} Col {} - {} != {}".format(rownum+1, colnum+1, c1, c2))
    else:
        print("Row {} missing".format(rownum+1))

这将显示两个文件之间不同的任何单元格。对于给定的两个文件，将显示：

Row 3 Col 2 - 0.235435 != 0.23546

如果您更喜欢单元格名称，请使用

xlrd.formular.colname()

:

print "Cell {}{}  {} != {}".format(rownum+1, xlrd.formula.colname(colnum), c1, c2)

给你：

Cell 3B  0.235435 != 0.23546

Answer 3

我使用代码来做类似的事情。有点通用化效果很好。

import pandas as pd
import numpy as np
from xlsxwriter.utility import xl_rowcol_to_cell

template = pd.read_excel("template.xlsx",na_values=np.nan,header=None)
testSheet = pd.read_excel("test.xlsx",na_values=np.nan,header=None)

rt,ct = template.shape
rtest,ctest = testSheet.shape

df = pd.DataFrame(columns=['Cell_Location','BaseTemplate_Value','CurrentFile_Value'])

for rowNo in range(max(rt,rtest)):
  for colNo in range(max(ct,ctest)):
    # Fetching the template value at a cell
    try:
        template_val = template.iloc[rowNo,colNo]
    except:
        template_val = np.nan
    
    # Fetching the testsheet value at a cell
    try:
        testSheet_val = testSheet.iloc[rowNo,colNo]
    except:
        testSheet_val = np.nan
        
    # Comparing the values
    if (str(template_val)!=str(testSheet_val)):
        cell = xl_rowcol_to_cell(rowNo, colNo)
        dfTemp = pd.DataFrame([[cell,template_val,testSheet_val]],
                              columns=['Cell_Location','BaseTemplate_Value','CurrentFile_Value'])
        df = df.append(dfTemp)

df 是所需的数据框

2023更新

使用

df = pd.concat([df,dfTemp], ignore_index=True)

代替

df.append(dfTemp)

下面是程序的修改版本，修改为接受多个文件并将结果输出到txt文件。

import pandas as pd
import numpy as np
from xlsxwriter.utility import xl_rowcol_to_cell

wbList1 = ["tpl-excel1","tpl-excel2","tpl-excel3"]
wbList2 = ["test-excel1","test-excel2","test-excel3"]

output = open("workbook-compare-results.txt", "w")
for index in range(len(wbList1)):
    fileName1 = f'{wbList1[index]}.xlsx'
    fileName2 = f'{wbList2[index]}.xlsx'
    woorkBook1 = pd.read_excel(fileName1,na_values=np.nan,header=None)
    woorkBook2 = pd.read_excel(fileName2,na_values=np.nan,header=None)

    rt,ct = woorkBook1.shape
    rtest,ctest = woorkBook2.shape

    df = pd.DataFrame(columns=['Cell_Location','BaseTemplate_Value','CurrentFile_Value'])
    output.write(f"DIFFERENCE: {fileName1} | {fileName2}\n")
    dfOut = ""
    for rowNo in range(max(rt,rtest)):
        for colNo in range(max(ct,ctest)):
            # Fetching the woorkBook1 value at a cell
            try:
                woorkBook1_val = woorkBook1.iloc[rowNo,colNo]
            except:
                woorkBook1_val = np.nan

            # Fetching the woorkBook2 value at a cell
            try:
                woorkBook2_val = woorkBook2.iloc[rowNo,colNo]
            except:
                woorkBook2_val = np.nan

            # Comparing the values
            if (str(woorkBook1_val)!=str(woorkBook2_val)):
                cell = xl_rowcol_to_cell(rowNo, colNo)
                dfTemp = pd.DataFrame([[cell,woorkBook1_val,woorkBook2_val]],
                                    columns=['Cell_Location','BaseTemplate_Value','CurrentFile_Value'])
                df = pd.concat([df,dfTemp], ignore_index=True)
    if df.empty:
        output.write("NO DIFFERENCE IN DATA\n")
    else:
        dfOut = df.to_string(index=False)             
        output.write(f"{dfOut}\n")
    output.write("\n")
output.close()

Answer 4

使用 load_workbook 库的简单解决方案

from openpyxl import load_workbook
wb1 = load_workbook('test.xlsx')
wb2 = load_workbook('validation.xlsx')
for worksheet in wb1.sheetnames:
    sheet1 = wb1[worksheet]
    sheet2 = wb2[worksheet]

    # iterate through the rows and columns of both worksheets
    for row in range(1, sheet1.max_row + 1):
        for col in range(1, sheet1.max_column + 1):
            cell1 = sheet1.cell(row, col)
            cell2 = sheet2.cell(row, col)
            if cell1.value != cell2.value:
                print("Sheet {0} -> Row {1} Column {2} - {3} != {4}".format(worksheet ,row, col, cell1.value, cell2.value))

    

Answer 5

df_file1 = pd.read_csv("Source_data.csv")
df_file1 = df_file1.replace(np.nan, '', regex=True) #Replacing Nan with space
df_file2 = pd.read_csv("Target_data.csv")
df_file2 = df_file2.replace(np.nan, '', regex=True)

df_i = pd.concat([df_file1, df_file2], axis='columns', keys=['file1', 'file2'])

df_f = df_i.swaplevel(axis='columns')[df_s.columns[0:]]

def highlight_diff(data, color='yellow'):
    attr = 'background-color: {}'.format(color)
    other = data.xs('file1', axis='columns', level=-1)
    return pd.DataFrame(np.where(data.ne(other, level=0), attr, ''), index=data.index, columns=data.columns)

df_final = df_f.style.apply(highlight_diff, axis=None)

writer = pd.ExcelWriter('comparexcels.xlsx')
df_final.to_excel(writer)
 writer.save()

Answer 6

import pandas as pd
import numpy as np

df1=pd.read_excel('Product_Category_Jan.xlsx')
df2=pd.read_excel('Product_Category_Feb.xlsx')

df1.equals(df2)

comparison_values = df1.values == df2.values
print (comparison_values)


rows,cols=np.where(comparison_values==False)

for item in zip(rows,cols):
    df1.iloc[item[0], item[1]] = '{} --> {}'.format(df1.iloc[item[0], 
    item[1]],df2.iloc[item[0], item[1]])

Answer 7

改编 Martin Evans 上面的答案，因为 xlrd 不再支持 xlsx 和 openpyxl，这是我当前的解决方案：

from itertools import zip_longest
from openpyxl import load_workbook


def xlsx_same(fn1, fn2):
    same = True
    wb1 = load_workbook(filename = fn1, read_only=True)
    wb2 = load_workbook(filename = fn2, read_only=True)

    if len(wb1.sheetnames) != len(wb2.sheetnames):
        print(f" Difference in number of sheets {len(wb1.sheetnames)} != {len(wb2.sheetnames)}")
        same = False

    for sheet in wb1.sheetnames:
        sheet1 = wb1[sheet]
        try:
            sheet2 = wb2[sheet]
        except KeyError:
            print(f"{fn2} does not have sheet {sheet} which is in {fn1}")
            same = False
            break

        if sheet1.max_row != sheet2.max_row:
            print(f" Difference in number of rows {len(sheet1.rows)} != {len(sheet2.rows)}")
            same = False
        if sheet1.max_column != sheet2.max_column:
            print(f" Difference in number of columns {sheet1.max_column} != {sheet2.max_column}")
            same = False
        for rownum,row_wb1 in enumerate(sheet1.rows):
            if rownum < sheet2.max_row:
                row_wb2 = sheet2.rows[rownum]

                for colnum, (c1, c2) in enumerate(zip_longest(row_wb1, row_wb2)):
                    if c1 != c2:
                        same = False
                        print(
                            "Row {} Col {} - {} != {}".format(
                                rownum + 1, colnum + 1, c1, c2
                            )
                        )
            else:
                same = False
                print("Row {} missing".format(rownum + 1))
    return same