使用OpenPyxl和insert_rows的MemoryError

如何解决使用OpenPyxl和insert_rows的MemoryError

我有一个脚本，可打开一个excel工作表（1.353 kB），根据值更新行，并根据索引插入新行。不幸的是，我收到了MemoryError。此外，该脚本正在消耗大量RAM。这是基于代码还是基于库？谢谢您的支持。

错误消息如下：

Traceback (most recent call last):
  File "update_worksheet.py",line 42,in <module>
    update.add_row(idx)
  File "update_worksheet.py",line 30,in add_row
    self.__ws.insert_rows(idx)
  File ".\Python\Python38-32\lib\site-packages\openpyxl\worksheet\worksheet.py",line 713,in insert_rows
    self._move_cells(min_row=idx,offset=amount,row_or_col="row")
  File ".\Python\Python38-32\lib\site-packages\openpyxl\worksheet\worksheet.py",line 706,in _move_cells
    self._move_cell(row,column,row_offset,col_offset)
  File ".\Programs\Python\Python38-32\lib\site-packages\openpyxl\worksheet\worksheet.py",line 802,in _move_cell
    self._cells[new_row,new_col] = cell
MemoryError

from openpyxl import load_workbook
import pandas as pd
import time 

class UpdateWorksheet():
    def __init__(self,path):
        self.__wb = load_workbook(path,read_only = False)
        self.__ws = self.__wb["WP_Planning"]
        self.__df = pd.DataFrame(self.__ws.values)
    
    def search_value_in_col_idx(self,search_string,col_idx=1):
        try:
            idx = self.__df[self.__df[col_idx]==search_string].index.item()
            return idx
        except ValueError:
            return None  

    def update_status(self,row_idx,col_idx,status):
        self.__ws.cell(row = row_idx,column = col_idx).value = status

    def find_last_row(self,key,status):
        idx = None
        try:
            idx = self.__df[self.__df[1]=="HMI"].index.tolist()
        except ValueError:
            idx = None
        return idx[-1]        

    def add_row(self,idx):
        self.__ws.insert_rows(idx)
    
    def save_workbook(self,path):
        self.__wb.save(path)
        print("finish")

if __name__ == "__main__":
    path = './data/TrackingSheet.xlsx'
    update = UpdateWorksheet(path)
    index = update.search_value_in_col_idx("PFIVEDAIEX-4244",4)
    update.update_status(index,7,"Mikey")
    idx = update.find_last_row("PFIVEDAIEX-4244","Fixed")
    update.add_row(idx)

编辑1：

from openpyxl import load_workbook
from openpyxl import Workbook
import pandas as pd

class UpdateWorksheet():
    def __init__(self,path):
        self.__path = path

    def load_file(self,read_only):
        wb = load_workbook(self.__path,read_only)
        return wb
   
    # Search line to be updated
    def search_value_in_col_idx(self,ws):
        df = pd.DataFrame(ws.values)
        try:
            idx = df[df[col_idx]==search_string].index.item()
            return idx
        except ValueError:
            return None  

    # Update line attributes
    def update_status(self,status,ws):
        if not row_idx is None:
            ws.cell(row = row_idx,column = col_idx).value = status

    # Find last row for new rows
    def find_last_row(self,ws):
        df = pd.DataFrame(ws.values)
        idx = None
        try:
            idx = df[df[1]=="HMI"].index.tolist()
        except ValueError:
            idx = None
        return idx[-1]        

    # Add new rows
    def add_row(self,idx,ws):
        if idx is not None:
            ws.insert_rows(idx,5)

    # Save changes made to workbook
    def save_workbook(self,wb):
        wb.save(self.__path)

if __name__ == "__main__":
    path = './data/TrackingSheet.xlsx'
    update = UpdateWorksheet(path)
    wb = update.load_file(read_only=True)
    idx = update.search_value_in_col_idx("PFIVEDAIEX-4244",4,wb["WP_Planning"])
    last_row = update.find_last_row(wb["WP_Planning"])
    wb.close()
    wb = update.load_file(read_only=False)
    update.update_status(idx,"Mikey",wb["WP_Planning"])
    update.add_row(200,wb["WP_Planning"])
    pdate.save_workbook(wb)
    wb.close()