3
���h� � @ sX U d Z ddlZddlmZmZmZmZmZmZm Z ddl
Z ddl m
Z
ddlmZ ddlmZ ddlmZ ddlmZ dd lmZmZ dd
lmZ dd l m Z dd l m Z m Z m!Z! dd
l"m#Z# ddl$m%Z%m&Z& ddl'm(Z( ddl)m*Z* ddl+m,Z,m-Z- ddl.m/Z/m0Z0 ddl1m2Z2m3Z3 e4� Z5ee6e6f 5G dd� d�Z7G dd� d�Z8G dd� de8�Z9dS )z�
An interface for extending pandas with custom arrays.
.. warning::
This is an experimental API and subject to breaking changes
without warning.
� N)�Any�Callable�Dict�Optional�Sequence�Tuple�Union)�lib)� ArrayLike)�set_function_name)�function)�AbstractMethodError)�Appender� Substitution)�validate_fillna_kwargs)� maybe_cast_to_extension_array)�
is_array_like� is_list_like� pandas_dtype)�ExtensionDtype)�
ABCIndexClass� ABCSeries)�isna)�ops)�_factorize_array�unique)� backfill_1d�pad_1d)�
nargminmax�nargsortc @ s� e Zd ZdZdZedgdd��Zedhdd��Zed d
� �Zd d � Z e
e e j
f edd
�dd�Ze d�dd�Zdd� Zeed�dd�Zeed�dd�Zddejfee j
d�dd �Zeed�d d ��Zee e d f d�d d!��Z ee d�d"d#��Z ee d�d$d%��Z ee d�d&d'��Z did)d*�Z!ed�d+d,�Z"e j
d�d-d.�Z#djee$e j
d0�d1d2�Z%d3d4� Z&d5d6� Z'dkd7d8�Z(d9d:� Z)dle e*d d<�d=d>�Z+d?d@� Z,dmdBdC�Z-d ed�dDdE�Z.e e j
ef d�dFdG�Z/doe e e j
d f dH�dIdJ�Z0dKe1dL< e2d dM�e3e1dL �dpdNdO���Z4dqe5e eed dP�dQdR�Z6d d�dSdT�Z7dred�dUdV�Z8e$d�dWdX�Z9dsee:ege;e$ f dY�dZd[�Z<dtd d�d]d^�Z=ee5d d d_�d`da��Z>d(Z?due$edb�dcdd�Z@dedf� ZAdS )v�ExtensionArraya
Abstract base class for custom 1-D array types.
pandas will recognize instances of this class as proper arrays
with a custom type and will not attempt to coerce them to objects. They
may be stored directly inside a :class:`DataFrame` or :class:`Series`.
.. versionadded:: 0.23.0
Attributes
----------
dtype
nbytes
ndim
shape
Methods
-------
argsort
astype
copy
dropna
factorize
fillna
equals
isna
ravel
repeat
searchsorted
shift
take
unique
view
_concat_same_type
_formatter
_from_factorized
_from_sequence
_from_sequence_of_strings
_reduce
_values_for_argsort
_values_for_factorize
Notes
-----
The interface includes the following abstract methods that must be
implemented by subclasses:
* _from_sequence
* _from_factorized
* __getitem__
* __len__
* __eq__
* dtype
* nbytes
* isna
* take
* copy
* _concat_same_type
A default repr displaying the type, (truncated) data, length,
and dtype is provided. It can be customized or replaced by
by overriding:
* __repr__ : A default repr for the ExtensionArray.
* _formatter : Print scalars inside a Series or DataFrame.
Some methods require casting the ExtensionArray to an ndarray of Python
objects with ``self.astype(object)``, which may be expensive. When
performance is a concern, we highly recommend overriding the following
methods:
* fillna
* dropna
* unique
* factorize / _values_for_factorize
* argsort / _values_for_argsort
* searchsorted
The remaining methods implemented on this class should be performant,
as they only compose abstract methods. Still, a more efficient
implementation may be available, and these methods can be overridden.
One can implement methods to handle array reductions.
* _reduce
One can implement methods to handle parsing from strings that will be used
in methods such as ``pandas.io.parsers.read_csv``.
* _from_sequence_of_strings
This class does not inherit from 'abc.ABCMeta' for performance reasons.
Methods and properties required by the interface raise
``pandas.errors.AbstractMethodError`` and no ``register`` method is
provided for registering virtual subclasses.
ExtensionArrays are limited to 1 dimension.
They may be backed by none, one, or many NumPy arrays. For example,
``pandas.Categorical`` is an extension array backed by two arrays,
one for codes and one for categories. An array of IPv6 address may
be backed by a NumPy structured array with two fields, one for the
lower 64 bits and one for the upper 64 bits. Or they may be backed
by some other storage type, like Python lists. Pandas makes no
assumptions on how the data are stored, just that it can be converted
to a NumPy array.
The ExtensionArray interface does not impose any rules on how this data
is stored. However, currently, the backing data cannot be stored in
attributes called ``.values`` or ``._values`` to ensure full compatibility
with pandas internals. But other names as ``.data``, ``._data``,
``._items``, ... can be freely used.
If implementing NumPy's ``__array_ufunc__`` interface, pandas expects
that
1. You defer by returning ``NotImplemented`` when any Series are present
in `inputs`. Pandas will extract the arrays and call the ufunc again.
2. You define a ``_HANDLED_TYPES`` tuple as an attribute on the class.
Pandas inspect this to determine whether the ufunc is valid for the
types present.
See :ref:`extending.extension.ufunc` for more.
By default, ExtensionArrays are not hashable. Immutable subclasses may
override this behavior.
� extensionNFc C s t | ��dS )aN
Construct a new ExtensionArray from a sequence of scalars.
Parameters
----------
scalars : Sequence
Each element will be an instance of the scalar type for this
array, ``cls.dtype.type`` or be converted into this type in this method.
dtype : dtype, optional
Construct for this particular dtype. This should be a Dtype
compatible with the ExtensionArray.
copy : bool, default False
If True, copy the underlying data.
Returns
-------
ExtensionArray
N)r
)�clsZscalars�dtype�copy� r% �9/tmp/pip-build-5_djhm0z/pandas/pandas/core/arrays/base.py�_from_sequence� s z ExtensionArray._from_sequencec C s t | ��dS )aB
Construct a new ExtensionArray from a sequence of strings.
.. versionadded:: 0.24.0
Parameters
----------
strings : Sequence
Each element will be an instance of the scalar type for this
array, ``cls.dtype.type``.
dtype : dtype, optional
Construct for this particular dtype. This should be a Dtype
compatible with the ExtensionArray.
copy : bool, default False
If True, copy the underlying data.
Returns
-------
ExtensionArray
N)r
)r" �stringsr# r$ r% r% r& �_from_sequence_of_strings� s z(ExtensionArray._from_sequence_of_stringsc C s t | ��dS )a}
Reconstruct an ExtensionArray after factorization.
Parameters
----------
values : ndarray
An integer ndarray with the factorized values.
original : ExtensionArray
The original ExtensionArray that factorize was called on.
See Also
--------
factorize
ExtensionArray.factorize
N)r
)r" �values�originalr% r% r& �_from_factorized� s z ExtensionArray._from_factorizedc C s t | ��dS )aE
Select a subset of self.
Parameters
----------
item : int, slice, or ndarray
* int: The position in 'self' to get.
* slice: A slice object, where 'start', 'stop', and 'step' are
integers or None
* ndarray: A 1-d boolean NumPy ndarray the same length as 'self'
Returns
-------
item : scalar or ExtensionArray
Notes
-----
For scalar ``item``, return a scalar value suitable for the array's
type. This should be an instance of ``self.dtype.type``.
For slice ``key``, return an instance of ``ExtensionArray``, even
if the slice is length 0 or 1.
For a boolean mask, return an instance of ``ExtensionArray``, filtered
to the values where ``item`` is True.
N)r
)�self�itemr% r% r& � __getitem__� s zExtensionArray.__getitem__)�key�value�returnc C s t t| �� d���dS )a^
Set one or more values inplace.
This method is not required to satisfy the pandas extension array
interface.
Parameters
----------
key : int, ndarray, or slice
When called from, e.g. ``Series.__setitem__``, ``key`` will be
one of
* scalar int
* ndarray of integers.
* boolean ndarray
* slice object
value : ExtensionDtype.type, Sequence[ExtensionDtype.type], or object
value or values to be set of ``key``.
Returns
-------
None
z does not implement __setitem__.N)�NotImplementedError�type)r- r0 r1 r% r% r& � __setitem__ s +zExtensionArray.__setitem__)r2 c C s t | ��dS )z\
Length of this array
Returns
-------
length : int
N)r
)r- r% r% r& �__len__> s zExtensionArray.__len__c c s$ x t t| ��D ]}| | V qW dS )z5
Iterate over elements of the array.
N)�range�len)r- �ir% r% r& �__iter__H s zExtensionArray.__iter__)�otherr2 c C s t | ��dS )zE
Return for `self == other` (element-wise equality).
N)r
)r- r; r% r% r& �__eq__R s
zExtensionArray.__eq__c C s
| |k S )zH
Return for `self != other` (element-wise in-equality).
r% )r- r; r% r% r& �__ne__^ s zExtensionArray.__ne__)r$ r2 c C s> t j| |d�}|s |tjk r$|j� }|tjk r:||| j� < |S )aj
Convert to a NumPy ndarray.
.. versionadded:: 1.0.0
This is similar to :meth:`numpy.asarray`, but may provide additional control
over how the conversion is done.
Parameters
----------
dtype : str or numpy.dtype, optional
The dtype to pass to :meth:`numpy.asarray`.
copy : bool, default False
Whether to ensure that the returned value is a not a view on
another array. Note that ``copy=False`` does not *ensure* that
``to_numpy()`` is no-copy. Rather, ``copy=True`` ensure that
a copy is made, even if not strictly necessary.
na_value : Any, optional
The value to use for missing values. The default value depends
on `dtype` and the type of the array.
Returns
-------
numpy.ndarray
)r# )�np�asarrayr �
no_defaultr$ r )r- r# r$ �na_value�resultr% r% r& �to_numpyd s
zExtensionArray.to_numpyc C s t | ��dS )z2
An instance of 'ExtensionDtype'.
N)r
)r- r% r% r& r# � s zExtensionArray.dtype.c C s
t | �fS )z9
Return a tuple of the array dimensions.
)r8 )r- r% r% r& �shape� s zExtensionArray.shapec C s t j| j�S )z6
The number of elements in the array.
)r> �prodrD )r- r% r% r& �size� s zExtensionArray.sizec C s dS )zH
Extension Arrays are only allowed to be 1-dimensional.
� r% )r- r% r% r& �ndim� s zExtensionArray.ndimc C s t | ��dS )zL
The number of bytes needed to store this object in memory.
N)r
)r- r% r% r& �nbytes� s zExtensionArray.nbytesTc C s@ ddl m} t|�}t||�r0|j� j| dd�S tj| ||d�S )a�
Cast to a NumPy array with 'dtype'.
Parameters
----------
dtype : str or dtype
Typecode or data-type to which the array is cast.
copy : bool, default True
Whether to copy the data, even if not necessary. If False,
a copy is made only if the old dtype does not match the
new dtype.
Returns
-------
array : ndarray
NumPy ndarray with 'dtype' for its dtype.
r )� StringDtypeF)r$ )r# r$ )Zpandas.core.arrays.string_rJ r �
isinstanceZconstruct_array_typer' r> �array)r- r# r$ rJ r% r% r& �astype� s
zExtensionArray.astypec C s t | ��dS )a�
A 1-D array indicating if each value is missing.
Returns
-------
na_values : Union[np.ndarray, ExtensionArray]
In most cases, this should return a NumPy ndarray. For
exceptional cases like ``SparseArray``, where returning
an ndarray would be expensive, an ExtensionArray may be
returned.
Notes
-----
If returning an ExtensionArray, then
* ``na_values._is_boolean`` should be True
* `na_values` should implement :func:`ExtensionArray._reduce`
* ``na_values.any`` and ``na_values.all`` should be implemented
N)r
)r- r% r% r& r � s zExtensionArray.isnac C s
t j| �S )a
Return values for sorting.
Returns
-------
ndarray
The transformed values should maintain the ordering between values
within the array.
See Also
--------
ExtensionArray.argsort
)r> rL )r- r% r% r& �_values_for_argsort� s z"ExtensionArray._values_for_argsort� quicksort)� ascending�kindr2 c O s" t j|||�}t| ||dd�}|S )a�
Return the indices that would sort this array.
Parameters
----------
ascending : bool, default True
Whether the indices should result in an ascending
or descending sort.
kind : {'quicksort', 'mergesort', 'heapsort'}, optional
Sorting algorithm.
*args, **kwargs:
Passed through to :func:`numpy.argsort`.
Returns
-------
ndarray
Array of indices that sort ``self``. If NaN values are contained,
NaN values are placed at the end.
See Also
--------
numpy.argsort : Sorting implementation used internally.
�last)rQ rP Z na_position)�nvZ validate_argsort_with_ascendingr )r- rP rQ �args�kwargsrB r% r% r& �argsort� s zExtensionArray.argsortc C s
t | d�S )a&
Return the index of minimum value.
In case of multiple occurrences of the minimum value, the index
corresponding to the first occurrence is returned.
Returns
-------
int
See Also
--------
ExtensionArray.argmax
�argmin)r )r- r% r% r& rW s zExtensionArray.argminc C s
t | d�S )a&
Return the index of maximum value.
In case of multiple occurrences of the maximum value, the index
corresponding to the first occurrence is returned.
Returns
-------
int
See Also
--------
ExtensionArray.argmin
�argmax)r )r- r% r% r& rX ) s zExtensionArray.argmaxc C s� t ||�\}}| j� }t|�rRt|�t| �krJtdt|�� dt| �� ���|| }|j� r�|dk r�|dkrntnt}|| jt �||d�}| j
|| j d�}q�| j � }|||< n| j � }|S )a�
Fill NA/NaN values using the specified method.
Parameters
----------
value : scalar, array-like
If a scalar value is passed it is used to fill all missing values.
Alternatively, an array-like 'value' can be given. It's expected
that the array-like have the same length as 'self'.
method : {'backfill', 'bfill', 'pad', 'ffill', None}, default None
Method to use for filling holes in reindexed Series
pad / ffill: propagate last valid observation forward to next valid
backfill / bfill: use NEXT valid observation to fill gap.
limit : int, default None
If method is specified, this is the maximum number of consecutive
NaN values to forward/backward fill. In other words, if there is
a gap with more than this number of consecutive NaNs, it will only
be partially filled. If method is not specified, this is the
maximum number of entries along the entire axis where NaNs will be
filled.
Returns
-------
ExtensionArray
With NA/NaN filled.
z'Length of 'value' does not match. Got (z ) expected N�pad)�limit�mask)r# )
r r r r8 �
ValueError�anyr r rM �objectr' r# r$ )r- r1 �methodrZ r[ �funcZ
new_valuesr% r% r& �fillna: s
zExtensionArray.fillnac C s | | j � S )zz
Return ExtensionArray without NA values.
Returns
-------
valid : ExtensionArray
)r )r- r% r% r& �dropnan s zExtensionArray.dropnarG )�periods�
fill_valuer2 c C s� t | � s|dkr| j� S t|�r*| jj}| j|gtt|�t | �� | jd�}|dkrj|}| d| � }n| t|�d� }|}| j||g�S )a�
Shift values by desired number.
Newly introduced missing values are filled with
``self.dtype.na_value``.
.. versionadded:: 0.24.0
Parameters
----------
periods : int, default 1
The number of periods to shift. Negative values are allowed
for shifting backwards.
fill_value : object, optional
The scalar value to use for newly introduced missing values.
The default is ``self.dtype.na_value``.
.. versionadded:: 0.24.0
Returns
-------
ExtensionArray
Shifted.
Notes
-----
If ``self`` is empty or ``periods`` is 0, a copy of ``self`` is
returned.
If ``periods > len(self)``, then an array of size
len(self) is returned, with all values filled with
``self.dtype.na_value``.
r )r# N) r8 r$ r r# rA r' �min�abs�_concat_same_type)r- rc rd �empty�a�br% r% r& �shiftx s % zExtensionArray.shiftc C s t | jt��}| j|| jd�S )z�
Compute the ExtensionArray of unique values.
Returns
-------
uniques : ExtensionArray
)r# )r rM r^ r' r# )r- �uniquesr% r% r& r � s zExtensionArray.unique�leftc C s | j t�}|j|||d�S )a�
Find indices where elements should be inserted to maintain order.
.. versionadded:: 0.24.0
Find the indices into a sorted array `self` (a) such that, if the
corresponding elements in `value` were inserted before the indices,
the order of `self` would be preserved.
Assuming that `self` is sorted:
====== ================================
`side` returned index `i` satisfies
====== ================================
left ``self[i-1] < value <= self[i]``
right ``self[i-1] <= value < self[i]``
====== ================================
Parameters
----------
value : array_like
Values to insert into `self`.
side : {'left', 'right'}, optional
If 'left', the index of the first suitable location found is given.
If 'right', return the last such index. If there is no suitable
index, return either 0 or N (where N is the length of `self`).
sorter : 1-D array_like, optional
Optional array of integer indices that sort array a into ascending
order. They are typically the result of argsort.
Returns
-------
array of ints
Array of insertion points with the same shape as `value`.
See Also
--------
numpy.searchsorted : Similar method from NumPy.
)�side�sorter)rM r^ � searchsorted)r- r1 rn ro �arrr% r% r& rp � s -
zExtensionArray.searchsortedc C sx t | �t |�ksdS | j|jks$dS t| �t|�ks8dS | |k}t|t�rT|jd�}| j� |j� @ }t||B j� �S dS )a�
Return if another array is equivalent to this array.
Equivalent means that both arrays have the same shape and dtype, and
all values compare equal. Missing values in the same location are
considered equal (in contrast with normal equality).
Parameters
----------
other : ExtensionArray
Array to compare to this Array.
Returns
-------
boolean
Whether the arrays are equivalent.
FN) r4 r# r8 rK r ra r �bool�all)r- r; Z equal_valuesZequal_nar% r% r& �equals� s
zExtensionArray.equalsc C s | j t�tjfS )a
Return an array and missing value suitable for factorization.
Returns
-------
values : ndarray
An array suitable for factorization. This should maintain order
and be a supported dtype (Float64, Int64, UInt64, String, Object).
By default, the extension array is cast to object dtype.
na_value : object
The value in `values` to consider missing. This will be treated
as NA in the factorization routines, so it will be coded as
`na_sentinel` and not included in `uniques`. By default,
``np.nan`` is used.
Notes
-----
The values returned by this method are also used in
:func:`pandas.util.hash_pandas_object`.
)rM r^ r> �nan)r- r% r% r& �_values_for_factorize s z$ExtensionArray._values_for_factorize)� na_sentinelr2 c C s2 | j � \}}t|||d�\}}| j|| �}||fS )ag
Encode the extension array as an enumerated type.
Parameters
----------
na_sentinel : int, default -1
Value to use in the `codes` array to indicate missing values.
Returns
-------
codes : ndarray
An integer NumPy array that's an indexer into the original
ExtensionArray.
uniques : ExtensionArray
An ExtensionArray containing the unique values of `self`.
.. note::
uniques will *not* contain an entry for the NA value of
the ExtensionArray if there are any missing values present
in `self`.
See Also
--------
factorize : Top-level factorize method that dispatches here.
Notes
-----
:meth:`pandas.factorize` offers a `sort` keyword as well.
)rw rA )rv r r, )r- rw rq rA �codesrl r% r% r& � factorize! s
' zExtensionArray.factorizeaL
Repeat elements of a %(klass)s.
Returns a new %(klass)s where each element of the current %(klass)s
is repeated consecutively a given number of times.
Parameters
----------
repeats : int or array of ints
The number of repetitions for each element. This should be a
non-negative integer. Repeating 0 times will return an empty
%(klass)s.
axis : None
Must be ``None``. Has no effect but is accepted for compatibility
with numpy.
Returns
-------
repeated_array : %(klass)s
Newly created %(klass)s with repeated elements.
See Also
--------
Series.repeat : Equivalent function for Series.
Index.repeat : Equivalent function for Index.
numpy.repeat : Similar method for :class:`numpy.ndarray`.
ExtensionArray.take : Take arbitrary positions.
Examples
--------
>>> cat = pd.Categorical(['a', 'b', 'c'])
>>> cat
['a', 'b', 'c']
Categories (3, object): ['a', 'b', 'c']
>>> cat.repeat(2)
['a', 'a', 'b', 'b', 'c', 'c']
Categories (3, object): ['a', 'b', 'c']
>>> cat.repeat([1, 2, 3])
['a', 'b', 'b', 'c', 'c', 'c']
Categories (3, object): ['a', 'b', 'c']
�repeat)�klassc C s2 t jt� t|d�� tjt| ��j|�}| j|�S )N)�axis) rS Zvalidate_repeat�tuple�dictr> Zaranger8 rz �take)r- Zrepeatsr| �indr% r% r& rz } s zExtensionArray.repeat)�indices�
allow_fillrd r2 c C s t | ��dS )a�
Take elements from an array.
Parameters
----------
indices : sequence of int
Indices to be taken.
allow_fill : bool, default False
How to handle negative values in `indices`.
* False: negative values in `indices` indicate positional indices
from the right (the default). This is similar to
:func:`numpy.take`.
* True: negative values in `indices` indicate
missing values. These values are set to `fill_value`. Any other
other negative values raise a ``ValueError``.
fill_value : any, optional
Fill value to use for NA-indices when `allow_fill` is True.
This may be ``None``, in which case the default NA value for
the type, ``self.dtype.na_value``, is used.
For many ExtensionArrays, there will be two representations of
`fill_value`: a user-facing "boxed" scalar, and a low-level
physical NA value. `fill_value` should be the user-facing version,
and the implementation should handle translating that to the
physical version for processing the take if necessary.
Returns
-------
ExtensionArray
Raises
------
IndexError
When the indices are out of bounds for the array.
ValueError
When `indices` contains negative values other than ``-1``
and `allow_fill` is True.
See Also
--------
numpy.take
api.extensions.take
Notes
-----
ExtensionArray.take is called by ``Series.__getitem__``, ``.loc``,
``iloc``, when `indices` is a sequence of values. Additionally,
it's called by :meth:`Series.reindex`, or any other method
that causes realignment, with a `fill_value`.
Examples
--------
Here's an example implementation, which relies on casting the
extension array to object dtype. This uses the helper method
:func:`pandas.api.extensions.take`.
.. code-block:: python
def take(self, indices, allow_fill=False, fill_value=None):
from pandas.core.algorithms import take
# If the ExtensionArray is backed by an ndarray, then
# just pass that here instead of coercing to object.
data = self.astype(object)
if allow_fill and fill_value is None:
fill_value = self.dtype.na_value
# fill value should always be translated from the scalar
# type for the array, to the physical storage type for
# the data, before passing to take.
result = take(data, indices, fill_value=fill_value,
allow_fill=allow_fill)
return self._from_sequence(result, dtype=self.dtype)
N)r
)r- r� r� rd r% r% r& r � s YzExtensionArray.takec C s t | ��dS )ze
Return a copy of the array.
Returns
-------
ExtensionArray
N)r
)r- r% r% r& r$ � s zExtensionArray.copyc C s |dk rt |��| dd� S )a)
Return a view on the array.
Parameters
----------
dtype : str, np.dtype, or ExtensionDtype, optional
Default None.
Returns
-------
ExtensionArray or np.ndarray
A view on the :class:`ExtensionArray`'s data.
N)r3 )r- r# r% r% r& �view� s zExtensionArray.viewc C sT ddl m} || | j� dd�jd�}dt| �j� d�}|� |� dt| �� d | j� �S )
Nr )�format_object_summaryF)Zindent_for_namez,
�<z>
z
Length: z , dtype: )Zpandas.io.formats.printingr� �
_formatter�rstripr4 �__name__r8 r# )r- r� �data�
class_namer% r% r& �__repr__ s zExtensionArray.__repr__)�boxedr2 c C s |rt S tS )aY
Formatting function for scalar values.
This is used in the default '__repr__'. The returned formatting
function receives instances of your scalar type.
Parameters
----------
boxed : bool, default False
An indicated for whether or not your array is being printed
within a Series, DataFrame, or Index (True), or just by
itself (False). This may be useful if you want scalar values
to appear differently within a Series versus on its own (e.g.
quoted or not).
Returns
-------
Callable[[Any], str]
A callable that gets instances of the scalar type and
returns a string. By default, :func:`repr` is used
when ``boxed=False`` and :func:`str` is used when
``boxed=True``.
)�str�repr)r- r� r% r% r& r� s zExtensionArray._formatter�Cc C s | S )ax
Return a flattened view on this array.
Parameters
----------
order : {None, 'C', 'F', 'A', 'K'}, default 'C'
Returns
-------
ExtensionArray
Notes
-----
- Because ExtensionArrays are 1D-only, this is a no-op.
- The "order" argument is ignored, is for compatibility with NumPy.
r% )r- �orderr% r% r& �ravel3 s zExtensionArray.ravel)� to_concatr2 c C s t | ��dS )z�
Concatenate multiple array of this dtype.
Parameters
----------
to_concat : sequence of this type
Returns
-------
ExtensionArray
N)r
)r" r� r% r% r& rg F s z ExtensionArray._concat_same_type)�name�skipnac K s t d|� d| j� ���dS )a�
Return a scalar result of performing the reduction operation.
Parameters
----------
name : str
Name of the function, supported values are:
{ any, all, min, max, sum, mean, median, prod,
std, var, sem, kurt, skew }.
skipna : bool, default True
If True, skip NaN values.
**kwargs
Additional keyword arguments passed to the reduction function.
Currently, `ddof` is the only supported kwarg.
Returns
-------
scalar
Raises
------
TypeError : subclass does not define reductions
zcannot perform z with type N)� TypeErrorr# )r- r� r� rU r% r% r& �_reducec s zExtensionArray._reducec C s t dtt| �j�� ���d S )Nzunhashable type: )r� r� r4 r� )r- r% r% r& �__hash__} s zExtensionArray.__hash__)NF)NF)T)TrO )NNN)rG N)rm N���)r� )N)FN)N)F)r� )T)Br� �
__module__� __qualname__�__doc__Z_typ� classmethodr' r) r, r/ r �intr> Zndarrayr r5 r6 r: r
r< r= r r@ rr rC �propertyr r# r rD rF rH rI rM r rN r� rV rW rX ra rb r^ rk r rp rt rv ry � _extension_array_shared_docsr r rz r r r$ r� r� r r r� r� rg Z _can_hold_nar� r� r% r% r% r& r $ sr ~ -
%
!
4
6
0 Z
Y
r c @ s4 e Zd ZdZedd� �Zedd� �Zedd� �ZdS ) �ExtensionOpsMixinz�
A base class for linking the operators to their dunder names.
.. note::
You may want to set ``__array_priority__`` if you want your
implementation to be called when involved in binary operations
with NumPy arrays.
c C s� | j tj�| _| j tj�| _| j tj�| _| j tj �| _
| j tj �| _ | j tj
�| _| j tj�| _| j tj�| _| j tj�| _| j tj�| _| j tj�| _| j tj�| _| j tj�| _ | j tj �| _ | j t �| _ | j tj!�| _"d S )N)#�_create_arithmetic_method�operator�add�__add__r Zradd�__radd__�sub�__sub__Zrsub�__rsub__�mul�__mul__Zrmul�__rmul__�pow�__pow__Zrpow�__rpow__�mod�__mod__Zrmod�__rmod__�floordiv� __floordiv__Z rfloordiv�
__rfloordiv__�truediv� __truediv__Zrtruediv� __rtruediv__�divmod�
__divmod__�rdivmod� __rdivmod__)r" r% r% r& �_add_arithmetic_ops� s z%ExtensionOpsMixin._add_arithmetic_opsc C sX | j tj�| _| j tj�| _| j tj�| _| j tj�| _ | j tj
�| _ | j tj �| _
d S )N)�_create_comparison_methodr� �eqr< �ner= �lt�__lt__�gt�__gt__�le�__le__�ge�__ge__)r" r% r% r& �_add_comparison_ops� s z%ExtensionOpsMixin._add_comparison_opsc C sX | j tj�| _| j tj�| _| j tj�| _| j tj �| _
| j tj �| _ | j tj
�| _d S )N)Z_create_logical_methodr� �and_�__and__r Zrand_�__rand__�or_�__or__Zror_�__ror__�xor�__xor__Zrxor�__rxor__)r" r% r% r& �_add_logical_ops� s z"ExtensionOpsMixin._add_logical_opsN)r� r� r� r� r� r� r� r� r% r% r% r& r� � s r� c @ s6 e Zd ZdZed
dd��Zedd� �Zedd � �ZdS ) �ExtensionScalarOpsMixina�
A mixin for defining ops on an ExtensionArray.
It is assumed that the underlying scalar objects have the operators
already defined.
Notes
-----
If you have defined a subclass MyExtensionArray(ExtensionArray), then
use MyExtensionArray(ExtensionArray, ExtensionScalarOpsMixin) to
get the arithmetic operators. After the definition of MyExtensionArray,
insert the lines
MyExtensionArray._add_arithmetic_ops()
MyExtensionArray._add_comparison_ops()
to link the operators to your class.
.. note::
You may want to set ``__array_priority__`` if you want your
implementation to be called when involved in binary operations
with NumPy arrays.
TNc s* � ��fdd�}d�j � d�}t||| �S )a
A class method that returns a method that will correspond to an
operator for an ExtensionArray subclass, by dispatching to the
relevant operator defined on the individual elements of the
ExtensionArray.
Parameters
----------
op : function
An operator that takes arguments op(a, b)
coerce_to_dtype : bool, default True
boolean indicating whether to attempt to convert
the result to the underlying ExtensionArray dtype.
If it's not possible to create a new ExtensionArray with the
values, an ndarray is returned instead.
Returns
-------
Callable[[Any, Any], Union[ndarray, ExtensionArray]]
A method that can be bound to a class. When used, the method
receives the two arguments, one of which is the instance of
this class, and should return an ExtensionArray or an ndarray.
Returning an ndarray may be necessary when the result of the
`op` cannot be stored in the ExtensionArray. The dtype of the
ndarray uses NumPy's normal inference rules.
Examples
--------
Given an ExtensionArray subclass called MyExtensionArray, use
__add__ = cls._create_method(operator.add)
in the class definition of MyExtensionArray to create the operator
for addition, that will be based on the operator implementation
of the underlying elements of the ExtensionArray
c s� � fdd�}t |ttf�r tS � }||�}�fdd�t||�D �}��� fdd�}�jd krxt|� \}}||�||�fS ||�S )
Nc s* t | t�st| �r| }n| gt� � }|S )N)rK r r r8 )�paramZovalues)r- r% r& �convert_values� s zNExtensionScalarOpsMixin._create_method.<locals>._binop.<locals>.convert_valuesc s g | ]\}}� ||��qS r% r% )�.0ri rj )�opr% r& �
<listcomp> s zJExtensionScalarOpsMixin._create_method.<locals>._binop.<locals>.<listcomp>c s> � r,t t��| �}t|t���s:tj| �}ntj| �d�}|S )N)r# )r r4 rK r> r? )rq �res)�coerce_to_dtype� result_dtyper- r% r& �_maybe_convert s zNExtensionScalarOpsMixin._create_method.<locals>._binop.<locals>._maybe_convertr� r� > r� r� )rK r r �NotImplemented�zipr� ) r- r; r� ZlvaluesZrvaluesr� r� ri rj )r� r� r� )r- r& �_binop� s
z6ExtensionScalarOpsMixin._create_method.<locals>._binop�__)r� r )r" r� r� r� r� Zop_namer% )r� r� r� r& �_create_method� s (&z&ExtensionScalarOpsMixin._create_methodc C s
| j |�S )N)r� )r" r� r% r% r& r� s z1ExtensionScalarOpsMixin._create_arithmetic_methodc C s | j |dtd�S )NF)r� r� )r� rr )r" r� r% r% r& r� ! s z1ExtensionScalarOpsMixin._create_comparison_method)TN)r� r� r� r� r� r� r� r� r% r% r% r& r� � s
P r� ):r� r� Ztypingr r r r r r r Znumpyr> Z pandas._libsr Zpandas._typingr
Z
pandas.compatr Zpandas.compat.numpyr rS Z
pandas.errorsr
Zpandas.util._decoratorsr r Zpandas.util._validatorsr Zpandas.core.dtypes.castr Zpandas.core.dtypes.commonr r r Zpandas.core.dtypes.dtypesr Zpandas.core.dtypes.genericr r Zpandas.core.dtypes.missingr Z pandas.corer Zpandas.core.algorithmsr r Zpandas.core.missingr r Zpandas.core.sortingr r r~ r� r� r r� r� r% r% r% r& �<module> s> $ e1 |