需求：
現有一個 csv文件，包含'CNUM'和'COMPANY'兩列，數據里包含空行，且有內容重復的行數據。
要求：
1）去掉空行；
2）重復行數據只保留一行有效數據；
3）修改'COMPANY'列的名稱為'Company_New‘；
4）并在其后增加六列，分別為'C_col',‘D_col',‘E_col',‘F_col',‘G_col',‘H_col'。
一，使用 Python Pandas來處理：
import pandas as pd
import numpy as np
from pandas import DataFrame,Series
def deal_with_data(filepath,newpath):
file_obj=open(filepath)
df=pd.read_csv(file_obj) # 讀取csv文件，創建 DataFrame
df=df.reindex(columns=['CNUM','COMPANY','C_col','D_col','E_col','F_col','G_col','H_col'],fill_value=None) # 重新指定列索引
df.rename(columns={'COMPANY':'Company_New'}, inplace = True) # 修改列名
df=df.dropna(axis=0,how='all') # 去除 NAN 即文件中的空行
df['CNUM'] = df['CNUM'].astype('int32') # 將 CNUM 列的數據類型指定為 int32
df = df.drop_duplicates(subset=['CNUM', 'Company_New'], keep='first') # 去除重復行
df.to_csv(newpath,index=False,encoding='GBK')
file_obj.close()
if __name__=='__main__':
file_path=r'C:\Users\12078\Desktop\python\CNUM_COMPANY.csv'
file_save_path=r'C:\Users\12078\Desktop\python\CNUM_COMPANY_OUTPUT.csv'
deal_with_data(file_path,file_save_path)
二，使用 VBA來處理：
Option Base 1
Option Explicit
Sub main()
On Error GoTo error_handling
Dim wb As Workbook
Dim wb_out As Workbook
Dim sht As Worksheet
Dim sht_out As Worksheet
Dim rng As Range
Dim usedrows As Byte
Dim usedrows_out As Byte
Dim dict_cnum_company As Object
Dim str_file_path As String
Dim str_new_file_path As String
'assign values to variables:
str_file_path = "C:\Users\12078\Desktop\Python\CNUM_COMPANY.csv"
str_new_file_path = "C:\Users\12078\Desktop\Python\CNUM_COMPANY_OUTPUT.csv"
Set wb = checkAndAttachWorkbook(str_file_path)
Set sht = wb.Worksheets("CNUM_COMPANY")
Set wb_out = Workbooks.Add
wb_out.SaveAs str_new_file_path, xlCSV 'create a csv file
Set sht_out = wb_out.Worksheets("CNUM_COMPANY_OUTPUT")
Set dict_cnum_company = CreateObject("Scripting.Dictionary")
usedrows = WorksheetFunction.Max(getLastValidRow(sht, "A"), getLastValidRow(sht, "B"))
'rename the header 'COMPANY' to 'Company_New',remove blank duplicate lines/rows.
Dim cnum_company As String
cnum_company = ""
For Each rng In sht.Range("A1", "A" usedrows)
If VBA.Trim(rng.Offset(0, 1).Value) = "COMPANY" Then
rng.Offset(0, 1).Value = "Company_New"
End If
cnum_company = rng.Value "-" rng.Offset(0, 1).Value
If VBA.Trim(cnum_company) > "-" And Not dict_cnum_company.Exists(rng.Value "-" rng.Offset(0, 1).Value) Then
dict_cnum_company.Add rng.Value "-" rng.Offset(0, 1).Value, ""
End If
Next rng
'loop the keys of dict split the keyes by '-' into cnum array and company array.
Dim index_dict As Byte
Dim arr_cnum()
Dim arr_Company()
For index_dict = 0 To UBound(dict_cnum_company.keys)
ReDim Preserve arr_cnum(1 To UBound(dict_cnum_company.keys) + 1)
ReDim Preserve arr_Company(1 To UBound(dict_cnum_company.keys) + 1)
arr_cnum(index_dict + 1) = Split(dict_cnum_company.keys()(index_dict), "-")(0)
arr_Company(index_dict + 1) = Split(dict_cnum_company.keys()(index_dict), "-")(1)
Debug.Print index_dict
Next
'assigns the value of the arrays to the celles.
sht_out.Range("A1", "A" UBound(arr_cnum)) = Application.WorksheetFunction.Transpose(arr_cnum)
sht_out.Range("B1", "B" UBound(arr_Company)) = Application.WorksheetFunction.Transpose(arr_Company)
'add 6 columns to output csv file:
Dim arr_columns() As Variant
arr_columns = Array("C_col", "D_col", "E_col", "F_col", "G_col", "H_col") '
sht_out.Range("C1:H1") = arr_columns
Call checkAndCloseWorkbook(str_file_path, False)
Call checkAndCloseWorkbook(str_new_file_path, True)
Exit Sub
error_handling:
Call checkAndCloseWorkbook(str_file_path, False)
Call checkAndCloseWorkbook(str_new_file_path, False)
End Sub
' 輔助函數：
'Get last row of Column N in a Worksheet
Function getLastValidRow(in_ws As Worksheet, in_col As String)
getLastValidRow = in_ws.Cells(in_ws.Rows.count, in_col).End(xlUp).Row
End Function
Function checkAndAttachWorkbook(in_wb_path As String) As Workbook
Dim wb As Workbook
Dim mywb As String
mywb = in_wb_path
For Each wb In Workbooks
If LCase(wb.FullName) = LCase(mywb) Then
Set checkAndAttachWorkbook = wb
Exit Function
End If
Next
Set wb = Workbooks.Open(in_wb_path, UpdateLinks:=0)
Set checkAndAttachWorkbook = wb
End Function
Function checkAndCloseWorkbook(in_wb_path As String, in_saved As Boolean)
Dim wb As Workbook
Dim mywb As String
mywb = in_wb_path
For Each wb In Workbooks
If LCase(wb.FullName) = LCase(mywb) Then
wb.Close savechanges:=in_saved
Exit Function
End If
Next
End Function
三，輸出結果：
兩種方法輸出結果相同：
四，比較總結：
Python pandas 內置了大量處理數據的方法，我們不需要重復造輪子，用起來很方便，代碼簡潔的多。
Excel VBA 處理這個需求，使用了 數組，字典等數據結構（實際需求中，數據量往往很大，所以一些地方沒有直接使用遍歷單元格的方法），以及處理字符串，數組和字典的很多方法，對文件的操作也很復雜，一旦出錯，調試起來比python也較困難，代碼已經盡量優化，但還是遠比 Python要多。
到此這篇關于VBA處理數據與Python Pandas處理數據案例比較分析的文章就介紹到這了,更多相關VBA與Python Pandas處理數據內容請搜索腳本之家以前的文章或繼續瀏覽下面的相關文章希望大家以后多多支持腳本之家！
您可能感興趣的文章:- 基于python requests selenium爬取excel vba過程解析
- VBA數組用法案例詳解
- 詳解bootstrap導航欄.nav與.navbar區別
- python兼容VBA的用法詳解
