Pandas: 错误：如果使用现有索引，则MultiIndex的数据透视失败。

代码示例，可复制示例

df  = pd.DataFrame([['A', 'A1', 'label1', 1],
             ['A', 'A2', 'label2', 2],
             ['B', 'A1', 'label1', 3],
             ['B', 'A2', 'label2', 4]], columns=['index_1', 'index_2', 'label', 'value'])
df = df.set_index(['index_1', 'index_2'])

pivoted_df = df.pivot(index=None,
                     columns='label',
                     values = 'value')

问题描述

枢轴函数给出错误NotImplementedError: isna is not defined for MultiIndex 。 当index设置为None 。

---------------------------------------------------------------------------
NotImplementedError                       Traceback (most recent call last)
<ipython-input-84-54426dadf31d> in <module>()
      2 pivoted_df = df.pivot(index=None,
      3                      columns='label',
----> 4                      values = 'value')

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\frame.py in pivot(self, index, columns, values)
   5192         """
   5193         from pandas.core.reshape.reshape import pivot
-> 5194         return pivot(self, index=index, columns=columns, values=values)
   5195 
   5196     _shared_docs['pivot_table'] = """

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\reshape\reshape.py in pivot(self, index, columns, values)
    404         else:
    405             index = self[index]
--> 406         index = MultiIndex.from_arrays([index, self[columns]])
    407 
    408         if is_list_like(values) and not isinstance(values, tuple):

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\indexes\multi.py in from_arrays(cls, arrays, sortorder, names)
   1272         from pandas.core.arrays.categorical import _factorize_from_iterables
   1273 
-> 1274         labels, levels = _factorize_from_iterables(arrays)
   1275         if names is None:
   1276             names = [getattr(arr, "name", None) for arr in arrays]

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\arrays\categorical.py in _factorize_from_iterables(iterables)
   2541         # For consistency, it should return a list of 2 lists.
   2542         return [[], []]
-> 2543     return map(list, lzip(*[_factorize_from_iterable(it) for it in iterables]))

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\arrays\categorical.py in <listcomp>(.0)
   2541         # For consistency, it should return a list of 2 lists.
   2542         return [[], []]
-> 2543     return map(list, lzip(*[_factorize_from_iterable(it) for it in iterables]))

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\arrays\categorical.py in _factorize_from_iterable(values)
   2513         codes = values.codes
   2514     else:
-> 2515         cat = Categorical(values, ordered=True)
   2516         categories = cat.categories
   2517         codes = cat.codes

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\arrays\categorical.py in __init__(self, values, categories, ordered, dtype, fastpath)
    359 
    360             # we're inferring from values
--> 361             dtype = CategoricalDtype(categories, dtype.ordered)
    362 
    363         elif is_categorical_dtype(values):

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\dtypes\dtypes.py in __init__(self, categories, ordered)
    136 
    137     def __init__(self, categories=None, ordered=None):
--> 138         self._finalize(categories, ordered, fastpath=False)
    139 
    140     <strong i="12">@classmethod</strong>

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\dtypes\dtypes.py in _finalize(self, categories, ordered, fastpath)
    161         if categories is not None:
    162             categories = self.validate_categories(categories,
--> 163                                                   fastpath=fastpath)
    164 
    165         self._categories = categories

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\dtypes\dtypes.py in validate_categories(categories, fastpath)
    318         if not fastpath:
    319 
--> 320             if categories.hasnans:
    321                 raise ValueError('Categorial categories cannot be null')
    322 

pandas\_libs\properties.pyx in pandas._libs.properties.CachedProperty.__get__()

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\indexes\base.py in hasnans(self)
   2237         """ return if I have any nans; enables various perf speedups """
   2238         if self._can_hold_na:
-> 2239             return self._isnan.any()
   2240         else:
   2241             return False

pandas\_libs\properties.pyx in pandas._libs.properties.CachedProperty.__get__()

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\indexes\base.py in _isnan(self)
   2218         """ return if each value is nan"""
   2219         if self._can_hold_na:
-> 2220             return isna(self)
   2221         else:
   2222             # shouldn't reach to this condition by checking hasnans beforehand

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\dtypes\missing.py in isna(obj)
    104     Name: 1, dtype: bool
    105     """
--> 106     return _isna(obj)
    107 
    108 

~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\dtypes\missing.py in _isna_new(obj)
    115     # hack (for now) because MI registers as ndarray
    116     elif isinstance(obj, ABCMultiIndex):
--> 117         raise NotImplementedError("isna is not defined for MultiIndex")
    118     elif isinstance(obj, (ABCSeries, np.ndarray, ABCIndexClass,
    119                           ABCExtensionArray)):

NotImplementedError: isna is not defined for MultiIndex

预期产量

index_1 | index_2 | 标签1 | 标签2
-| -| -| -
A | A1 | 1.0 | N
|| A2 | NaN | 2.0
B | A1 | 3.0 | N
|| A2 | NaN | 4.0

pd.show_versions()