数据预处理

交作业：
data.drop(columns=[data.isna().sum().idxmax()])

inputs = inputs.fillna(inputs.mean(numeric_only=True))

mean方法有个numeric_only参数用来控制是否只计算数值，布尔值等，mean方法。我猜是因为pd版本原因，当前我的版本numeric_only预设不是false，所以报错了。

https://discuss.d2l.ai/t/topic/1750/120?u=jiemicc_lu

TypeError Traceback (most recent call last)
Cell In[109], line 2
1 inputs, outputs = data.iloc[:, 0:2], data.iloc[:, 2]
----> 2 inputs = inputs.fillna(inputs.mean())
3 print(inputs)

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\generic.py:11556, in NDFrame._add_numeric_operations..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 ~\AppData\Local\Programs\Python\Python310\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 ~\AppData\Local\Programs\Python\Python310\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 ~\AppData\Local\Programs\Python\Python310\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 ~\AppData\Local\Programs\Python\Python310\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 ~\AppData\Local\Programs\Python\Python310\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 ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\frame.py:10482, in DataFrame._reduce..blk_func(values, axis)
10480 return values._reduce(name, skipna=skipna, **kwds)
10481 else:

10482 return op(values, axis=axis, skipna=skipna, **kwds)

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\nanops.py:96, in disallow.call.._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 ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\nanops.py:158, in bottleneck_switch.call..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 ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\nanops.py:421, in _datetimelike_compat..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 ~\AppData\Local\Programs\Python\Python310\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 ~\AppData\Local\Programs\Python\Python310\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

按照案例写的，报错，如何解决呢？？？

谢谢！！！！！！我找了好久终于解决了

课本问题。3列是对的，两列是错的。[0,2]是012三列。

One line coder comes

# Ex 1
data1 = data.drop(data.isna().sum().idxmax(), axis=1)
# Ex 2
data2 = torch.tensor(data1.to_numpy(dtype=float))

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

不知道什么原因，我的代码运行必须忽略带有Pave的行数据才能正常运行，不然会报如下错误

TypeError: unsupported operand type(s) for +: ‘int’ and ‘str’

我也是报这个错误，只要输入单元格里有非NA的字符串就会报这个错误。

我猜测可能是pandas新版本mean方法输入里的非NA字符会报错，只能先执行get_dummies进行字符串类列拆分转bool类再执行均值替换NA的mean方法。

谢谢啦兄弟，

pandas 可能是今年四月份刚发布的 2.0 版本，API 有一些细微的变化。调用 inputs.mean() 的时候会出现字符串和数字不能拼接的错误是因为 NaN 是数字，‘Pave’ 是字符串。

代码更改：

1. inputs.mean报错问题
   inputs, outputs = data.iloc[:, 0], data.iloc[:, 2]
   inputs[:] = inputs.fillna(inputs.mean())
   print(inputs)
   data

2. dummy编码为True和False问题
   inputs = pd.get_dummies(inputs, dummy_na=True)
   print(inputs, type(inputs))
   inputs.iloc[:, 1:] = inputs.iloc[:, 1:].astype(int)
   inputs

讨论答案：

1. 删除NaN最多的行
   data = data.drop(data.isnull().sum().idxmax(), axis=1)

Thank you so much my bro.

是的，如果想避免这个情况，把NA前面的空格删掉就可以了

泪目了 感谢好兄弟 折腾了一个多小时 终于解决了 感谢兄弟

感谢兄弟提问 我也有同样的问题 感谢汤姆猫老兄的解答！

非常感谢兄弟 dtype=int 以及dummy_na 不加** 也可 另外int换成float也行

问题一：
删除列缺值最多的列
data.drop(data.isnull().sum().idxmax(),axis=1)
删除缺值最多的行
data.drop(data.isnull().sum(axis=1).idmax(),axis=0)
问题二：
data = torch.tensor(data.to_numpy(dtype=float))