Pandas: Bug: Pivot gagal untuk MultiIndex Jika indeks yang ada digunakan.

Dibuat pada 27 Nov 2018  ·  5Komentar  ·  Sumber: pandas-dev/pandas

Contoh Kode, contoh copy-paste

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')

Deskripsi masalah

Fungsi pivot memberikan kesalahan NotImplementedError: isna is not defined for MultiIndex . Saat indeks disetel ke 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

Output yang Diharapkan

index_1 | index_2 | label1 | label2
- | - | - | -
A | A1 | 1.0 | NaN
|| A2 | NaN | 2.0
B | A1 | 3.0 | NaN
|| A2 | NaN | 4.0

Keluaran pd.show_versions()

VERSI TERPASANG

commit: Tidak ada
python: 3.6.5.final.0
python-bits: 64
OS: Windows
Rilis OS: 10
mesin: AMD64
prosesor: Intel64 Family 6 Model 85 Stepping 4, GenuineIntel
byteorder: sedikit
LC_ALL: Tidak ada
LANG: Tidak ada
LOCALE: Tidak ada. Tidak ada

panda: 0.23.4
pytest: 3.5.1
pip: 10.0.1
setuptools: 39.1.0
Cython: 0.28.2
numpy: 1.15.4
scipy: 1.1.0
pyarrow: Tidak ada
xarray: Tidak ada
IPython: 6.4.0
sphinx: 1.7.4
patsy: 0.5.0
dateutil: 2.7.3
pytz: 2018.4
blosc: Tidak ada
kemacetan: 1.2.1
tabel: 3.4.3
numexpr: 2.6.5
bulu: Tidak ada
matplotlib: 2.2.2
openpyxl: 2.5.3
xlrd: 1.1.0
xlwt: 1.3.0
xlsxwriter: 1.0.4
lxml: 4.2.1
bs4: 4.6.0
html5lib: 1.0.1
sqlalchemy: 1.2.7
pymysql: Tidak ada
psycopg2: Tidak ada
jinja2: 2.10
s3fs: Tidak ada
fastparquet: Tidak ada
pandas_gbq: Tidak ada
pandas_datareader: Tidak ada

Bug Reshaping
Sumber
picture srajanpaliwal
👍22 👀2

Komentar yang paling membantu

Terima kasih atas solusinya https://github.com/pandas-dev/pandas/issues/23955#issuecomment -480804068. Jika itu menyelamatkan seseorang dari masalah, berikut adalah generalisasi

def multiindex_pivot(df, columns=None, values=None):
    #https://github.com/pandas-dev/pandas/issues/23955
    names = list(df.index.names)
    df = df.reset_index()
    list_index = df[names].values
    tuples_index = [tuple(i) for i in list_index] # hashable
    df = df.assign(tuples_index=tuples_index)
    df = df.pivot(index="tuples_index", columns=columns, values=values)
    tuples_index = df.index  # reduced
    index = pd.MultiIndex.from_tuples(tuples_index, names=names)
    df.index = index
    return df
picture gmoutso pada 30 Mei 2019
👍22 🎉4

Semua 5 komentar

Ada pembaruan tentang ini? Seperti yang saya pahami, saat ini metode pivot() tidak berfungsi dengan banyak pengindeks, argumen index tidak menerima daftar, dan ketika None itu benar-benar gagal karena mencoba untuk gunakan MultiIndex yang ada.

Sampai sekarang, saya menyelesaikan ini dengan cara hacky dengan menghasilkan indeks tunggal sebagai rangkaian dari beberapa level indeks asli, pivot dan kemudian merekonstruksi level MultiIndex yang berbeda dengan memisahkan Indeks tunggal yang digabungkan. Mengikuti contoh @srajanpaliwal :

(df.reset_index()
 .assign(new_index=lambda dd: dd['index_1'].str.cat(dd['index_2'], sep='_'))
 .pivot(index='new_index', columns='label', values='value')
 .assign(index_1=lambda dd: dd.index.str.split('_').str.get(0),
         index_2=lambda dd: dd.index.str.split('_').str.get(1))
 .set_index(['index_1', 'index_2']))

Keluaran:

| | label | label1 | label2 |
| --------- | --------- | -------- | -------- |
| index_1 | index_1 | | |
| A | A1 | 1.0 | NaN |
| | A2 | NaN | 2.0 | |
| B | A1 | 3.0 | NaN |
|| A2 | NaN | 4.0 | |

Apa pun alasannya, apakah ada alasan mengapa MultiIndex tidak diterima dengan operasi pivot() ?

AlFontal picture AlFontal pada 8 Apr 2019
👍8

Terima kasih atas solusinya https://github.com/pandas-dev/pandas/issues/23955#issuecomment -480804068. Jika itu menyelamatkan seseorang dari masalah, berikut adalah generalisasi

def multiindex_pivot(df, columns=None, values=None):
    #https://github.com/pandas-dev/pandas/issues/23955
    names = list(df.index.names)
    df = df.reset_index()
    list_index = df[names].values
    tuples_index = [tuple(i) for i in list_index] # hashable
    df = df.assign(tuples_index=tuples_index)
    df = df.pivot(index="tuples_index", columns=columns, values=values)
    tuples_index = df.index  # reduced
    index = pd.MultiIndex.from_tuples(tuples_index, names=names)
    df.index = index
    return df
gmoutso picture gmoutso pada 30 Mei 2019
👍22 🎉4

sedikit penyesuaian komentar @gmacario demi keseragaman dengan pivot api

def multiindex_pivot(df, index=None, columns=None, values=None):
    #https://github.com/pandas-dev/pandas/issues/23955
    if index is None:
        names = list(df.index.names)
        df = df.reset_index()
    else:
        names = index
    list_index = df[names].values
    tuples_index = [tuple(i) for i in list_index] # hashable
    df = df.assign(tuples_index=tuples_index)
    df = df.pivot(index="tuples_index", columns=columns, values=values)
    tuples_index = df.index  # reduced
    index = pd.MultiIndex.from_tuples(tuples_index, names=names)
    df.index = index
    return df

pemakaian:

df.pipe(multiindex_pivot, index=['idx_column1', 'idx_column2'], columns='foo', values='bar')
MosheVai picture MosheVai pada 22 Jan 2020
👍1

peningkatan kecil lainnya yang memungkinkan beberapa columns= juga (tidak diuji secara menyeluruh, tetapi berfungsi dalam contoh saya):

def multiindex_pivot(df, index=None, columns=None, values=None):
    # https://github.com/pandas-dev/pandas/issues/23955
    if index is None:
        names = list(df.index.names)
        df = df.reset_index()
    else:
        names = index
    df = df.assign(tuples_index=[tuple(i) for i in df[names].values])  # hashable
    df = df.assign(tuples_columns=[tuple(i) for i in df[columns].values])  # hashable
    df = df.pivot(index='tuples_index', columns='tuples_columns', values=values)
    df.index = pd.MultiIndex.from_tuples(df.index, names=names)  # reduced
    df.columns = pd.MultiIndex.from_tuples(df.columns, names=columns)  # reduced
    return df

pemakaian:

df.pipe(multiindex_pivot,
        index=['idx_column1', 'idx_column2'],
        columns=['col_column1', 'col_column2'],
        values='bar')
tmasek picture tmasek pada 12 Feb 2020
👍3

Namun versi lain yang sedikit lebih baik:

def multiIndex_pivot(df, index = None, columns = None, values = None):
    # https://github.com/pandas-dev/pandas/issues/23955
    output_df = df.copy(deep = True)
    if index is None:
        names = list(output_df.index.names)
        output_df = output_df.reset_index()
    else:
        names = index
    output_df = output_df.assign(tuples_index = [tuple(i) for i in output_df[names].values])
    if isinstance(columns, list):
        output_df = output_df.assign(tuples_columns = [tuple(i) for i in output_df[columns].values])  # hashable
        output_df = output_df.pivot(index = 'tuples_index', columns = 'tuples_columns', values = values) 
        output_df.columns = pd.MultiIndex.from_tuples(output_df.columns, names = columns)  # reduced
    else:
        output_df = output_df.pivot(index = 'tuples_index', columns = columns, values = values)    
    output_df.index = pd.MultiIndex.from_tuples(output_df.index, names = names)
    return output_df

Pemakaian:

df.pipe(multiIndex_pivot, index = ['idx_column1', 'idx_column2'], columns = ['col_column1', 'col_column2'], values = 'bar')
Pawel-Kranzberg picture Pawel-Kranzberg pada 21 Apr 2020
👍6
Apakah halaman ini membantu?
0 / 5 - 0 peringkat

Masalah terkait

jaradc picture jaradc  ·  3Komentar
Abrosimov-a-a picture Abrosimov-a-a  ·  3Komentar
amelio-vazquez-reina picture amelio-vazquez-reina  ·  3Komentar
marcelnem picture marcelnem  ·  3Komentar
tade0726 picture tade0726  ·  3Komentar