python - Pandas 数据框错误 'StringArray requires a sequence of strings or pandas.NA'

Question

在过去的一个月里，我一直在阅读Excel工作表，而使用Pandas则没有任何问题。

尽管最近我更改了日期格式(现在已改回其原始格式mm/dd/yyyy)。

现在，当我尝试读取.xlsm时，所有突然的Pandas都会引发错误

下面是完整的错误

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-5-655581a0eaab> in <module>
----> 1 inv = p.read(r'C:\Users\Jake\OneDrive\Documents\Eastern\Inventory\Inventory_Log.xlsm')

~\Anaconda3\lib\site-packages\pyinv\__init__.py in read(filepath)
     36     'Cert_Expire':'string',
     37     'Rating':'string',
---> 38     'Notes':'string'
     39     })
     40     amount = inv.Item.count()

~\Anaconda3\lib\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, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols, **kwds)
    332         convert_float=convert_float,
    333         mangle_dupe_cols=mangle_dupe_cols,
--> 334         **kwds,
    335     )
    336 

~\Anaconda3\lib\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)
    883             convert_float=convert_float,
    884             mangle_dupe_cols=mangle_dupe_cols,
--> 885             **kwds,
    886         )
    887 

~\Anaconda3\lib\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)
    510                 )
    511 
--> 512                 output[asheetname] = parser.read(nrows=nrows)
    513 
    514                 if not squeeze or isinstance(output[asheetname], DataFrame):

~\Anaconda3\lib\site-packages\pandas\io\parsers.py in read(self, nrows)
   1131     def read(self, nrows=None):
   1132         nrows = _validate_integer("nrows", nrows)
-> 1133         ret = self._engine.read(nrows)
   1134 
   1135         # May alter columns / col_dict

~\Anaconda3\lib\site-packages\pandas\io\parsers.py in read(self, rows)
   2462         columns, data = self._do_date_conversions(columns, data)
   2463 
-> 2464         data = self._convert_data(data)
   2465         index, columns = self._make_index(data, alldata, columns, indexnamerow)
   2466 

~\Anaconda3\lib\site-packages\pandas\io\parsers.py in _convert_data(self, data)
   2532             self.verbose,
   2533             clean_conv,
-> 2534             clean_dtypes,
   2535         )
   2536 

~\Anaconda3\lib\site-packages\pandas\io\parsers.py in _convert_to_ndarrays(self, dct, na_values, na_fvalues, verbose, converters, dtypes)
   1725                         # invalid input to is_bool_dtype
   1726                         pass
-> 1727                     cvals = self._cast_types(cvals, cast_type, c)
   1728 
   1729             result[c] = cvals

~\Anaconda3\lib\site-packages\pandas\io\parsers.py in _cast_types(self, values, cast_type, column)
   1823             array_type = cast_type.construct_array_type()
   1824             try:
-> 1825                 return array_type._from_sequence_of_strings(values, dtype=cast_type)
   1826             except NotImplementedError:
   1827                 raise NotImplementedError(

~\Anaconda3\lib\site-packages\pandas\core\arrays\string_.py in _from_sequence_of_strings(cls, strings, dtype, copy)
    199     @classmethod
    200     def _from_sequence_of_strings(cls, strings, dtype=None, copy=False):
--> 201         return cls._from_sequence(strings, dtype=dtype, copy=copy)
    202 
    203     def __arrow_array__(self, type=None):

~\Anaconda3\lib\site-packages\pandas\core\arrays\string_.py in _from_sequence(cls, scalars, dtype, copy)
    195             result[na_values] = StringDtype.na_value
    196 
--> 197         return cls(result)
    198 
    199     @classmethod

~\Anaconda3\lib\site-packages\pandas\core\arrays\string_.py in __init__(self, values, copy)
    164         self._dtype = StringDtype()
    165         if not skip_validation:
--> 166             self._validate()
    167 
    168     def _validate(self):

~\Anaconda3\lib\site-packages\pandas\core\arrays\string_.py in _validate(self)
    169         """Validate that we only store NA or strings."""
    170         if len(self._ndarray) and not lib.is_string_array(self._ndarray, skipna=True):
--> 171             raise ValueError("StringArray requires a sequence of strings or pandas.NA")
    172         if self._ndarray.dtype != "object":
    173             raise ValueError(

ValueError: StringArray requires a sequence of strings or pandas.NA

发生这种情况的原因是，当 Pandas 正在读取它时，我将其将列转换为字符串dtypes。不知道为什么日期格式打破了这一点。

当前正在使用Pandas 1.0.1

任何信息都将不胜感激。

如果需要，我将提供更多详细信息。

Answer 1

根据文档Pandas doc:

新的df.astype()方法可以与str和"string"一起使用

区别在于:使用"string"它将尝试转换为不能包含任何数字的StringArray。

使用str，它将作为对象类型进行处理，该对象类型像以前一样工作。