python - 类型错误 : object cannot be converted to an IntegerDtype

Question

我想用 df 中的 A 替换 B 中的 nan 值:

df:

    A       B
0   Bb00    100080
1   Aa00    <NA>
2   Cc10    450089

df 数据类型:

A    object
B     Int64
dtype: object

我试过:

df['new_col'] = df['B'].fillna(df['A'])

它发现错误:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-120-1d24cd9977ed> in <module>
      2 print(df.dtypes)
      3 
----> 4 df['new_col'] = df['B'].fillna(df['A'])

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\series.py in fillna(self, value, method, axis, inplace, limit, downcast)
   4515         downcast=None,
   4516     ) -> Optional["Series"]:
-> 4517         return super().fillna(
   4518             value=value,
   4519             method=method,

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\generic.py in fillna(self, value, method, axis, inplace, limit, downcast)
   6046                     )
   6047 
-> 6048                 new_data = self._mgr.fillna(
   6049                     value=value, limit=limit, inplace=inplace, downcast=downcast
   6050                 )

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\internals\managers.py in fillna(self, value, limit, inplace, downcast)
    555 
    556     def fillna(self, value, limit, inplace: bool, downcast) -> "BlockManager":
--> 557         return self.apply(
    558             "fillna", value=value, limit=limit, inplace=inplace, downcast=downcast
    559         )

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\internals\managers.py in apply(self, f, align_keys, **kwargs)
    394                 applied = b.apply(f, **kwargs)
    395             else:
--> 396                 applied = getattr(b, f)(**kwargs)
    397             result_blocks = _extend_blocks(applied, result_blocks)
    398 

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\internals\blocks.py in fillna(self, value, limit, inplace, downcast)
   1773     def fillna(self, value, limit=None, inplace=False, downcast=None):
   1774         values = self.values if inplace else self.values.copy()
-> 1775         values = values.fillna(value=value, limit=limit)
   1776         return [
   1777             self.make_block_same_class(

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\arrays\base.py in fillna(self, value, method, limit)
    615                 # fill with value
    616                 new_values = self.copy()
--> 617                 new_values[mask] = value
    618         else:
    619             new_values = self.copy()

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\arrays\masked.py in __setitem__(self, key, value)
    103         if _is_scalar:
    104             value = [value]
--> 105         value, mask = self._coerce_to_array(value)
    106 
    107         if _is_scalar:

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\arrays\integer.py in _coerce_to_array(self, value)
    423 
    424     def _coerce_to_array(self, value) -> Tuple[np.ndarray, np.ndarray]:
--> 425         return coerce_to_array(value, dtype=self.dtype)
    426 
    427     def astype(self, dtype, copy: bool = True) -> ArrayLike:

~\AppData\Roaming\Python\Python38\site-packages\pandas\core\arrays\integer.py in coerce_to_array(values, dtype, mask, copy)
    241             "mixed-integer-float",
    242         ]:
--> 243             raise TypeError(f"{values.dtype} cannot be converted to an IntegerDtype")
    244 
    245     elif is_bool_dtype(values) and is_integer_dtype(dtype):

TypeError: object cannot be converted to an IntegerDtype

Answer 1

使用numpy.where为了避免在输出列中出现 float:

df['new_col'] = np.where(df['B'].isna(), df.A, df.B)
print (df)
      A       B new_col
0  Bb00  100080  100080
1  Aa00    <NA>    Aa00
2  Cc10  450089  450089

---

print (df['new_col'].apply(type))
0    <class 'int'>
1    <class 'str'>
2    <class 'int'>
Name: new_col, dtype: object

如果输出中需要字符串:

df['new_col'] = np.where(df['B'].isna(), df.A, df.B).astype(str)

print (df)
      A       B new_col
0  Bb00  100080  100080
1  Aa00    <NA>    Aa00
2  Cc10  450089  450089

print (df['new_col'].apply(type))
0    <class 'str'>
1    <class 'str'>
2    <class 'str'>
Name: new_col, dtype: object