问题重现

在学习数据预处理课程时，使用沐神课上代码

inputs, outputs = data.iloc[:, 0:2], data.iloc[:, 2]
inputs = inputs.fillna(inputs.mean())
print(inputs)
type(inputs)
inputs

报错

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[7], line 2
      1 inputs, outputs = data.iloc[:, 0:2], data.iloc[:, 2]
----> 2 inputs = inputs.fillna(inputs.mean())
      3 # inputs = inputs.fillna(inputs.mean(numeric_only=True))
      4 print(inputs)

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\generic.py:11556, in NDFrame._add_numeric_operations.<locals>.mean(self, axis, skipna, numeric_only, **kwargs)
  11539 @doc(
  11540     _num_doc,
  11541     desc="Return the mean of the values over the requested axis.",
   (...)
  11554     **kwargs,
  11555 ):
> 11556     return NDFrame.mean(self, axis, skipna, numeric_only, **kwargs)

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\generic.py:11201, in NDFrame.mean(self, axis, skipna, numeric_only, **kwargs)
  11194 def mean(
  11195     self,
  11196     axis: Axis | None = 0,
   (...)
  11199     **kwargs,
  11200 ) -> Series | float:
> 11201     return self._stat_function(
  11202         "mean", nanops.nanmean, axis, skipna, numeric_only, **kwargs
  11203     )

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\generic.py:11158, in NDFrame._stat_function(self, name, func, axis, skipna, numeric_only, **kwargs)
  11154     nv.validate_stat_func((), kwargs, fname=name)
  11156 validate_bool_kwarg(skipna, "skipna", none_allowed=False)
> 11158 return self._reduce(
  11159     func, name=name, axis=axis, skipna=skipna, numeric_only=numeric_only
  11160 )

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\frame.py:10519, in DataFrame._reduce(self, op, name, axis, skipna, numeric_only, filter_type, **kwds)
  10515     df = df.T
  10517 # After possibly _get_data and transposing, we are now in the
  10518 #  simple case where we can use BlockManager.reduce
> 10519 res = df._mgr.reduce(blk_func)
  10520 out = df._constructor(res).iloc[0]
  10521 if out_dtype is not None:

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\internals\managers.py:1534, in BlockManager.reduce(self, func)
   1532 res_blocks: list[Block] = []
   1533 for blk in self.blocks:
-> 1534     nbs = blk.reduce(func)
   1535     res_blocks.extend(nbs)
   1537 index = Index([None])  # placeholder

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\internals\blocks.py:339, in Block.reduce(self, func)
    333 @final
    334 def reduce(self, func) -> list[Block]:
    335     # We will apply the function and reshape the result into a single-row
    336     #  Block with the same mgr_locs; squeezing will be done at a higher level
    337     assert self.ndim == 2
--> 339     result = func(self.values)
    341     if self.values.ndim == 1:
    342         # TODO(EA2D): special case not needed with 2D EAs
    343         res_values = np.array([[result]])

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\frame.py:10482, in DataFrame._reduce.<locals>.blk_func(values, axis)
  10480     return values._reduce(name, skipna=skipna, **kwds)
  10481 else:
> 10482     return op(values, axis=axis, skipna=skipna, **kwds)

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\nanops.py:96, in disallow.__call__.<locals>._f(*args, **kwargs)
     94 try:
     95     with np.errstate(invalid="ignore"):
---> 96         return f(*args, **kwargs)
     97 except ValueError as e:
     98     # we want to transform an object array
     99     # ValueError message to the more typical TypeError
    100     # e.g. this is normally a disallowed function on
    101     # object arrays that contain strings
    102     if is_object_dtype(args[0]):

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\nanops.py:158, in bottleneck_switch.__call__.<locals>.f(values, axis, skipna, **kwds)
    156         result = alt(values, axis=axis, skipna=skipna, **kwds)
    157 else:
--> 158     result = alt(values, axis=axis, skipna=skipna, **kwds)
    160 return result

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\nanops.py:421, in _datetimelike_compat.<locals>.new_func(values, axis, skipna, mask, **kwargs)
    418 if datetimelike and mask is None:
    419     mask = isna(values)
--> 421 result = func(values, axis=axis, skipna=skipna, mask=mask, **kwargs)
    423 if datetimelike:
    424     result = _wrap_results(result, orig_values.dtype, fill_value=iNaT)

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\pandas\core\nanops.py:727, in nanmean(values, axis, skipna, mask)
    724     dtype_count = dtype
    726 count = _get_counts(values.shape, mask, axis, dtype=dtype_count)
--> 727 the_sum = _ensure_numeric(values.sum(axis, dtype=dtype_sum))
    729 if axis is not None and getattr(the_sum, "ndim", False):
    730     count = cast(np.ndarray, count)

File D:\04code\anaconda3\envs\d2l-zh\lib\site-packages\numpy\core_methods.py:49, in _sum(a, axis, dtype, out, keepdims, initial, where)
     47 def _sum(a, axis=None, dtype=None, out=None, keepdims=False,
     48          initial=_NoValue, where=True):
---> 49     return umr_sum(a, axis, dtype, out, keepdims, initial, where)

TypeError: can only concatenate str (not "int") to str

总结下来就是数据类型不匹配，这里限制一下就好:numeric_only=True

inputs, outputs = data.iloc[:, 0:2], data.iloc[:, 2]
# inputs = inputs.fillna(inputs.mean())会有警告
inputs = inputs.fillna(inputs.mean(numeric_only=True))
print(inputs)
type(inputs)
inputs