Question

我正在尝试比较两个Excel文件并输出一个文件，让某人看到这两个文件之间的差异。我收到了一个关键错误，我不确定如何修复它？目前我的完整代码是：

import pandas as pd
import numpy as np


def report_diff(x):
    return x[0] if x[0] == x[1] else '{} ---> {}'.format(*x)


old = pd.read_excel('Y:\Client Files\Client\ClientBill\March 2017\SPT List Retro Bill Mar 17.xlsx', 'List Bill', na_values=['NA'])
new = pd.read_excel('Y:\Client Files\Client\Client Bill\March 2017\Updated SPT Mar 17.xlsx', 'List Bill', na_values=['NA'])
old['version'] = "old"
new['version'] = "new"


full_set = pd.concat([old,new],ignore_index=True)



changes = full_set.drop_duplicates(subset=[u'Employee ID', u'Benefit Plan Type',u'Sum of Premium'],keep='first')


dupe_accts = changes.set_index(u'Employee ID', u'Benefit Plan Type', u'Sum of Premium').index.get_duplicates()


dupes = changes[changes['Employee ID', 'Benefit Plan Type', 'Sum of Premium'].isin(dupe_accts)]


change_new = dupes[(dupes["version"] == "new")]
change_old = dupes[(dupes["version"] == "old")]


change_new = change_new.drop(['version'], axis=1)
change_old = change_old.drop(['version'], axis=1)

change_new.set_index(u'Employee ID', u'Benefit Plan Type',  u'Sum of Premium',inplace=True)
change_old.set_index(u'Employee ID', u'Benefit Plan Type',  u'Sum of Premium',inplace=True)


diff_panel = pd.Panel(dict(df1=change_old,df2=change_new))
diff_output = diff_panel.apply(report_diff, axis=0)



changes['duplicate']=changes[u'Employee ID', u'Benefit Plan Type', u'Sum of Premium'].isin(dupe_accts)

removed_accounts = changes[(changes["duplicate"] == False) & (changes["version"] == "old")]


new_account_set = full_set.drop_duplicates(subset=[u'Employee ID',u'Benefit Plan Type',u'Sum of Premium'],take_last=False)


 new_account_set['duplicate']=new_account_set[u'Employee ID', u'Benefit Plan Type', u'Sum of Premium'].isin(dupe_accts)


added_accounts = new_account_set[(new_account_set["duplicate"] == False) & (new_account_set["version"] == "new")]


writer = pd.ExcelWriter("my-diff-2.xlsx")
diff_output.to_excel(writer,"changed")
removed_accounts.to_excel(writer,"removed",index=False,columns=[u'Employee ID',u'Benefit Plan Type',u'Sum of Premium'])
added_accounts.to_excel(writer,"added",index=False,columns=[u'Employee ID',u'Benefit Plan Type',u'Sum of Premium',])
writer.save()

我得到的错误与dupes变量有关。

 Traceback (most recent call last):
 File "C:\Python27\Scripts\ClientBill2.py", line 24, in <module>
dupes = changes[changes['Employee ID', 'Benefit Plan Type', 'Sum of 
Premium'].isin(dupe_accts)]
  File "C:\Python27\lib\site-packages\pandas\core\frame.py", line 2059, in 
__get
item__
return self._getitem_column(key)
  File "C:\Python27\lib\site-packages\pandas\core\frame.py", line 2066, in 
_geti
tem_column
return self._get_item_cache(key)
  File "C:\Python27\lib\site-packages\pandas\core\generic.py", line 1386, in 
_ge
t_item_cache
values = self._data.get(item)
  File "C:\Python27\lib\site-packages\pandas\core\internals.py", line 3543, 
in g
et
loc = self.items.get_loc(item)
File "C:\Python27\lib\site-packages\pandas\indexes\base.py", line 2136, in 
get
_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
  File "pandas\index.pyx", line 132, in pandas.index.IndexEngine.get_loc (pandas
\index.c:4433)
  File "pandas\index.pyx", line 154, in pandas.index.IndexEngine.get_loc (pandas
\index.c:4279)
  File "pandas\src\hashtable_class_helper.pxi", line 732, in pandas.hashtable.Py
ObjectHashTable.get_item (pandas\hashtable.c:13742)
  File "pandas\src\hashtable_class_helper.pxi", line 740, in pandas.hashtable.Py
ObjectHashTable.get_item (pandas\hashtable.c:13696)
KeyError: ('Employee ID', 'Benefit Plan Type', 'Sum of Premium')

Answer 1

看起来你不小心输入了＃34;更改＆＃34;两次。

尝试修改

dupes = changes[changes['Employee ID', 'Benefit Plan Type', 'Sum of Premium'].isin(dupe_accts)]

到

dupes = changes[['Employee ID', 'Benefit Plan Type', 'Sum of Premium']].isin(dupe_accts)

Python Pandas密钥错误

1 个答案: