Pandas_VBA_数据分类比较

Python与VBA的比较2

需求：

input文件中有两列数据，第一列为Name,第二列为Score,Name列里有重复的值，要求按照name的唯一值统计 score，输出到output文件按中。

1--用 Pandas解决：

from pandas import DataFrame
import pandas as pd

df=pd.read_excel(r"C:\Users\12078\Desktop\UIPATH_test\20200409\input.xlsx",sheet_name='Sheet1')
df=df.groupby('Name').sum()
df.to_excel(r"C:\Users\12078\Desktop\UIPATH_test\20200409\output.xlsx",sheet_name="Sheet1")

2--用 VBA解决：

Option Explicit
Option Base 1

Sub test_data()
   on error goto errorhandling
    Dim wb_in                      As Workbook
    Dim wb_out                     As Workbook
    Dim sht_in                     As Worksheet
    Dim sht_out                    As Worksheet
    Dim rng                        As Range
    Dim usedrows                   As Integer
    Dim usedrows_out               As Integer
    Dim input_path                 As String
    Dim output_path                As String

	Dim data_dict                  As Object
    Dim data_arr                   As Variant
    Dim data_arr_out               As Variant

   input_path = "C:\Users\12078\Desktop\UIPATH_test\20200409\input.xlsx"
   output_path = "C:\Users\12078\Desktop\UIPATH_test\20200409\output.xlsx"

   Set wb_in = checkAndAttachWorkbook(input_path)
   Set sht_in = wb_in.Worksheets("Sheet1")
   Set wb_out = Workbooks.Add
   wb_out.SaveAs output_path
   Set sht_out = wb_out.Worksheets("Sheet1")

   Set data_dict = CreateObject("Scripting.Dictionary")
   usedrows = WorksheetFunction.Max(getLastValidRow(sht_in, "A"), getLastValidRow(sht_in, "B"))
   data_arr = sht_in.Range("A2", "B" & usedrows)

   Dim i As Integer
    For i = 1 To UBound(data_arr, 1)
        If Not data_dict.Exists(data_arr(i, 1)) Then
            data_dict.Add data_arr(i, 1), data_arr(i, 2)
        Else
            data_dict(data_arr(i, 1)) = data_dict(data_arr(i, 1)) + data_arr(i, 2)
        End If
        Debug.Print data_arr(i, 1) & "--" & data_dict(data_arr(i, 1))
    Next i

    sht_out.Range("A1") = "Name"
    sht_out.Range("B1") = "Score"
    usedrows_out = data_dict.Count

   Dim index_dict As Integer
   ReDim data_arr_out(1 To UBound(data_dict.keys) + 1, 1 To 2)
   For index_dict = 0 To UBound(data_dict.keys)
        data_arr_out(index_dict + 1, 1) = data_dict.keys()(index_dict)
        data_arr_out(index_dict + 1, 2) = data_dict(data_dict.keys()(index_dict))
        Debug.Print index_dict
        Debug.Print data_arr_out(index_dict + 1, 1) & "--" & data_arr_out(index_dict + 1, 2) 'for debug
   Next
   sht_out.Range("A2").Resize(UBound(data_arr_out), 2) = data_arr_out

    Call checkAndCloseWorkbook(wb_in, False)
    Call checkAndCloseWorkbook(wb_out, True)
Exit Sub
errorhandling:
    Call checkAndCloseWorkbook(wb_in, False)
    Call checkAndCloseWorkbook(wb_out, False)
End Sub

' 辅助函数：
'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

输出结果：

比对结论：

pandas简单得多！