我是一个编程或机器学习的初学者，我的代码很难处理。我想从一个有时也包含整数或浮点数的列（这是一个电子邮件交换的列）中删除随机单词，然后要求BERT添加匹配的单词，以进行数据扩充，但我的代码有问题。

import pandas as pd
import nltk
from nltk.tokenize import word_tokenize

# lire les données de la colonne Excel en utilisant pandas
df = pd.read_excel("Output_Summarization/OUTPUT_ocr_OPENAIGOOD.xlsx", usecols="Open_AI_Text")

# itérer sur chaque ligne de la colonne
for index, row in df.iterrows():
  # tokeniser le texte de la ligne en mots individuels
  words = word_tokenize(row["Open_AI_Text"])

  # choisir un mot au hasard à enlever
  word_to_remove = random.choice(words)

  # enlever le mot du texte
  new_text = row["Open_AI_Text"].replace(word_to_remove, "")

  # mettre à jour la ligne dans le DataFrame
  df.at[index, "Open_AI_Text"] = new_text

# enregistrer le DataFrame mis à jour dans un nouveau fichier Excel
df.to_excel("Texte_Trou.xlsx", index=False)

我100%确定它是我的列名，因为如果我写df['Open_AI_Text']，我可以使用它。

ValueError                                Traceback (most recent call last)
<ipython-input-44-e9ccdb1ab0b2> in <module>
      4 
      5 # lire les données de la colonne Excel en utilisant pandas
----> 6 df = pd.read_excel("Output_Summarization/OUTPUT_ocr_OPENAIGOOD.xlsx", usecols="Open_AI_Text")
      7 
      8 # itérer sur chaque ligne de la colonne

/usr/local/lib64/python3.6/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
    294                 )
    295                 warnings.warn(msg, FutureWarning, stacklevel=stacklevel)
--> 296             return func(*args, **kwargs)
    297 
    298         return wrapper

/usr/local/lib64/python3.6/site-packages/pandas/io/excel/_base.py in read_excel(io, sheet_name, header, names, index_col, usecols, squeeze, dtype, engine, converters, true_values, false_values, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols)
    332         skipfooter=skipfooter,
    333         convert_float=convert_float,
--> 334         mangle_dupe_cols=mangle_dupe_cols,
    335     )
    336 

/usr/local/lib64/python3.6/site-packages/pandas/io/excel/_base.py in parse(self, sheet_name, header, names, index_col, usecols, squeeze, converters, true_values, false_values, skiprows, nrows, na_values, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols, **kwds)
    924             convert_float=convert_float,
    925             mangle_dupe_cols=mangle_dupe_cols,
--> 926             **kwds,
    927         )
    928 

/usr/local/lib64/python3.6/site-packages/pandas/io/excel/_base.py in parse(self, sheet_name, header, names, index_col, usecols, squeeze, dtype, true_values, false_values, skiprows, nrows, na_values, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols, **kwds)
    442 
    443             data = self.get_sheet_data(sheet, convert_float)
--> 444             usecols = _maybe_convert_usecols(usecols)
    445 
    446             if not data:

/usr/local/lib64/python3.6/site-packages/pandas/io/excel/_util.py in _maybe_convert_usecols(usecols)
    146 
    147     if isinstance(usecols, str):
--> 148         return _range2cols(usecols)
    149 
    150     return usecols

/usr/local/lib64/python3.6/site-packages/pandas/io/excel/_util.py in _range2cols(areas)
    117             cols.extend(range(_excel2num(rng[0]), _excel2num(rng[1]) + 1))
    118         else:
--> 119             cols.append(_excel2num(rng))
    120 
    121     return cols

/usr/local/lib64/python3.6/site-packages/pandas/io/excel/_util.py in _excel2num(x)
     82 
     83         if cp < ord("A") or cp > ord("Z"):
---> 84             raise ValueError(f"Invalid column name: {x}")
     85 
     86         index = index * 26 + cp - ord("A") + 1

ValueError: Invalid column name: Open_AI_Text

我试着只使用df[Open_AI_Text]作为df，但是出现了这个问题：

AttributeError                            Traceback (most recent call last)
<ipython-input-48-17e13b68c999> in <module>
      9 
     10 # itérer sur chaque ligne de la colonne
---> 11 for index, row in df.iterrows():
     12   # tokeniser le texte de la ligne en mots individuels
     13   words = word_tokenize(row["Open_AI_Text"])

/usr/local/lib64/python3.6/site-packages/pandas/core/generic.py in __getattr__(self, name)
   5137             if self._info_axis._can_hold_identifiers_and_holds_name(name):
   5138                 return self[name]
-> 5139             return object.__getattribute__(self, name)
   5140 
   5141     def __setattr__(self, name: str, value) -> None:

AttributeError: 'Series' object has no attribute 'iterrows'

再次抱歉，我是个实习生