3
���h�, � @ s d dl mZmZmZmZmZ d dlZd dlm Z m
Z d dl m
Z
d dlmZ d dlmZ d dlmZ d dlmZmZmZmZ d d lmZmZ d d
l m Z d d l m Z m Z d d l!m"Z" d d
l#m$Z$m%Z% d dl&m'Z' er�d dl(m)Z) eddd�Z*G dd� de�Z+G dd� de$e%�Z,dS )� )�
TYPE_CHECKING�Optional�Tuple�Type�TypeVarN)�lib�missing)�Scalar)�AbstractMethodError)�doc)�ExtensionDtype)�
is_integer�is_object_dtype� is_scalar�is_string_dtype)�isna�notna)�nanops)�_factorize_array�take)�masked_reductions)�ExtensionArray�ExtensionOpsMixin)�check_array_indexer)�Series�BaseMaskedArrayT�BaseMaskedArray)Zboundc @ s@ e Zd ZdZejZeej d�dd��Z
e e d d�dd��Z
dS ) �BaseMaskedDtypez@
Base class for dtypes for BasedMaskedArray subclasses.
)�returnc C s t �d S )N)r
)�self� r �;/tmp/pip-build-5_djhm0z/pandas/pandas/core/arrays/masked.py� numpy_dtype' s zBaseMaskedDtype.numpy_dtyper c C s t �dS )zq
Return the array type associated with this dtype.
Returns
-------
type
N)�NotImplementedError)�clsr r r! �construct_array_type+ s z$BaseMaskedDtype.construct_array_typeN)�__name__�
__module__� __qualname__�__doc__�
libmissing�NA�na_value�property�np�dtyper" � classmethodr r% r r r r! r s r c @ s� e Zd ZU dZed;ejejed�dd�Z e
e d�dd��Z d d
� Z
eejejf d�d d �Zd
d�dd�Zdd� Zed�dd�Zeed�dd�Zd
dejfeeejd�dd�ZdZd<ejd�dd �Zd=d d �Ze
ed�d d ��Z ejd�d!d"�Z e
d#d$� �Z e
ed�d%d&��Z e e!e ed'�d(d)��Z"d>eee#e ed*�d+d,�Z$eed�d-d.�Z%e&e'j(�d@eeeje'f d0�d1d2��Z(dAed4d5�d6d7�Z)dBe*ed8�d9d:�Z+d
S )Cr zf
Base class for masked arrays (which use _data and _mask to store the data).
numpy based
F)�values�mask�copyc C sh t |tj�o|jtjks td��|jdks2td��|jdksDtd��|rX|j� }|j� }|| _ || _
d S )NzGmask should be boolean numpy array. Use the 'pd.array' function instead� zvalues must be a 1D arrayzmask must be a 1D array) �
isinstancer. �ndarrayr/ Zbool_� TypeError�ndim�
ValueErrorr3 �_data�_mask)r r1 r2 r3 r r r! �__init__A s
zBaseMaskedArray.__init__)r c C s t | ��d S )N)r
)r r r r! r/ T s zBaseMaskedArray.dtypec C sH t |�r$| j| r| jjS | j| S t| |�}t| �| j| | j| �S )N)r
r; r/ r, r: r �type)r �itemr r r! � __getitem__X s
zBaseMaskedArray.__getitem__c C s t | ��d S )N)r
)r r1 r r r! �_coerce_to_arrayb s z BaseMaskedArray._coerce_to_arrayNc C sV t |�}|r|g}| j|�\}}|r4|d }|d }t| |�}|| j|< || j|< d S )Nr )r r@ r r: r; )r �key�valueZ
_is_scalarr2 r r r! � __setitem__e s
zBaseMaskedArray.__setitem__c c s< x6t t| ��D ]&}| j| r(| jjV q| j| V qW d S )N)�range�lenr; r/ r, r: )r �ir r r! �__iter__s s
zBaseMaskedArray.__iter__c C s
t | j�S )N)rE r: )r r r r! �__len__z s zBaseMaskedArray.__len__)r r c C s t | �| j | j�S )N)r= r: r; )r r r r! �
__invert__} s zBaseMaskedArray.__invert__)r3 r, r c C sz |t jkrtj}|dkr t}| jrft|�p0t|� rN|tjkrNtd|� d���| j j
|�}||| j < n| j j
||d�}|S )aF
Convert to a NumPy Array.
By default converts to an object-dtype NumPy array. Specify the `dtype` and
`na_value` keywords to customize the conversion.
Parameters
----------
dtype : dtype, default object
The numpy dtype to convert to.
copy : bool, default False
Whether to ensure that the returned value is a not a view on
the 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. This is typically
only possible when no missing values are present and `dtype`
is the equivalent numpy dtype.
na_value : scalar, optional
Scalar missing value indicator to use in numpy array. Defaults
to the native missing value indicator of this array (pd.NA).
Returns
-------
numpy.ndarray
Examples
--------
An object-dtype is the default result
>>> a = pd.array([True, False, pd.NA], dtype="boolean")
>>> a.to_numpy()
array([True, False, <NA>], dtype=object)
When no missing values are present, an equivalent dtype can be used.
>>> pd.array([True, False], dtype="boolean").to_numpy(dtype="bool")
array([ True, False])
>>> pd.array([1, 2], dtype="Int64").to_numpy("int64")
array([1, 2])
However, requesting such dtype will raise a ValueError if
missing values are present and the default missing value :attr:`NA`
is used.
>>> a = pd.array([True, False, pd.NA], dtype="boolean")
>>> a
<BooleanArray>
[True, False, <NA>]
Length: 3, dtype: boolean
>>> a.to_numpy(dtype="bool")
Traceback (most recent call last):
...
ValueError: cannot convert to bool numpy array in presence of missing values
Specify a valid `na_value` instead
>>> a.to_numpy(dtype="bool", na_value=False)
array([ True, False, False])
Nzcannot convert to 'zZ'-dtype NumPy array with missing values. Specify an appropriate 'na_value' for this dtype.)r3 ) r �
no_defaultr* r+ �object�_hasnar r r9 r: �astyper; )r r/ r3 r, �datar r r! �to_numpy� s ?
zBaseMaskedArray.to_numpyi� c C s | j |d�S )z|
the array interface, return my values
We return an object array here to preserve our scalar values
)r/ )rO )r r/ r r r! � __array__� s zBaseMaskedArray.__array__c C s ddl }|j| j| j|d�S )z6
Convert myself into a pyarrow Array.
r N)r2 r= )Zpyarrow�arrayr: r; )r r= �par r r! �__arrow_array__� s z BaseMaskedArray.__arrow_array__c C s
| j j� S )N)r; �any)r r r r! rL � s zBaseMaskedArray._hasnac C s | j S )N)r; )r r r r! r � s zBaseMaskedArray.isnac C s | j jS )N)r/ r, )r r r r! � _na_value� s zBaseMaskedArray._na_valuec C s | j j| jj S )N)r: �nbytesr; )r r r r! rV � s zBaseMaskedArray.nbytes)r$ r c C s2 t jdd� |D ��}t jdd� |D ��}| ||�S )Nc S s g | ]
}|j �qS r )r: )�.0�xr r r! �
<listcomp>� s z5BaseMaskedArray._concat_same_type.<locals>.<listcomp>c S s g | ]
}|j �qS r )r; )rW rX r r r! rY � s )r. � concatenate)r$ Z to_concatrN r2 r r r! �_concat_same_type� s z!BaseMaskedArray._concat_same_type)r �
allow_fill�
fill_valuer c C sr t |�r| jn|}t| j|||d�}t| j|d|d�}|r`t|�r`tj|�dk}|||< ||A }t| �||dd�S )N)r] r\ Tr4 F)r3 ���) r �_internal_fill_valuer r: r; r r. Zasarrayr= )r Zindexerr\ r] Zdata_fill_value�resultr2 Z fill_maskr r r! r � s zBaseMaskedArray.takec C s0 | j | j }}|j� }|j� }t| �||dd�S )NF)r3 )r: r; r3 r= )r rN r2 r r r! r3 s zBaseMaskedArray.copyr4 )� na_sentinelr c C sT | j }| j}t|||d�\}}|j| jjdd�}t| �|tjt |�t
d��}||fS )N)ra r2 F)r3 )r/ ) r: r; r rM r/ r" r= r. �zerosrE �bool)r ra Zarrr2 �codesZuniquesr r r! � factorize s zBaseMaskedArray.factorizeTr )�dropnar c
C s� ddl m}m} ddlm} | j| j }||�j� }|jj j
t �}|rP|j }nVt j
t|�d dd�}||dd
�< | jj� |d < |t j|t j| jjgt d�g�t d�}t jt|�dd�} ||| �}|||d �S ) aA
Returns a Series containing counts of each unique value.
Parameters
----------
dropna : bool, default True
Don't include counts of missing values.
Returns
-------
counts : Series
See Also
--------
Series.value_counts
r )�Indexr )� IntegerArrayr4 Zint64)r/ Nrc )�indexr^ r^ )�pandasrg r Z
pandas.arraysrh r: r; � value_countsri Z_valuesrM rK r. �emptyrE �sumrZ rQ r/ r, rb )
r rf rg r rh rN rk ri �countsr2 r r r! rk ) s
z BaseMaskedArray.value_counts)�name�skipnac K s� | j }| j}|d kr4tt|�}|||fd|i|��S | jrJ| jdtjd�}ttd| �}||fd ||d
�|��}tj |�r�t
j S |S ) Nrm �prod�min�maxrp Zfloat64)r, �nanr )Zaxisrp r2 > rm rq rr rs ) r: r; �getattrr rL rO r. rt r �isnanr* r+ )r ro rp �kwargsrN r2 �opr` r r r! �_reduceX s
zBaseMaskedArray._reduce)F)N)N)FNr^ )r^ )T)T),r& r' r( r) r r_ r. r6 rc r< r- r r/ r? r r@ rC rG �intrH r rI r rJ rO Z__array_priority__rP rS rL r rU rV r0 r r[ r r r3 r r re rk �strry r r r r! r 7 s@
R
/)-Ztypingr r r r r Znumpyr. Z pandas._libsr r r* Zpandas._typingr Z
pandas.errorsr
Zpandas.util._decoratorsr Zpandas.core.dtypes.baser Zpandas.core.dtypes.commonr
r r r Zpandas.core.dtypes.missingr r Z pandas.corer Zpandas.core.algorithmsr r Zpandas.core.array_algosr Zpandas.core.arraysr r Zpandas.core.indexersr rj r r r r r r r r! �<module> s$ |