| Server IP : 209.209.40.120 / Your IP : 216.73.217.112 Web Server : Microsoft-IIS/10.0 System : Windows NT NEWWWW 10.0 build 17763 (Windows Server 2019) i586 User : NEWWWW$ ( 0) PHP Version : 8.3.30 Disable Function : NONE MySQL : OFF | cURL : ON | WGET : OFF | Perl : OFF | Python : OFF | Sudo : OFF | Pkexec : OFF Directory : C:/Python312/Lib/site-packages/pandas/core/arrays/arrow/__pycache__/ |
Upload File : |
�
- �g'6 � �� � d Z ddlmZ ddlmZmZ ddlmZmZ ddl m
Z
m Z ddl m
Z
e
sddlZddlmZ ddlmZ erdd lmZ dd
lmZmZ G d � d e�
� Z G d� de� Z G d� de� Z y)z Accessors for arrow-backed data.� )� annotations)�ABCMeta�abstractmethod)�
TYPE_CHECKING�cast)�pa_version_under10p1�pa_version_under11p0)� is_list_likeN)�
ArrowDtype)�Iterator)� DataFrame�Seriesc �F � e Zd Zedd�� Zedd�� Zd� Zed� � Zy)�
ArrowAccessorc �B � || _ || _ | j |� y �N)�_data�_validation_msg� _validate)�self�data�validation_msgs �DC:\Python312\Lib\site-packages\pandas/core/arrays/arrow/accessors.py�__init__zArrowAccessor.__init__% s � ���
� -�� � ���t� � c � � y r � �r �
pyarrow_dtypes r �_is_valid_pyarrow_dtypez%ArrowAccessor._is_valid_pyarrow_dtype+ s � � r c � � |j }t |t � s%t | j j |�� � �| j
|j � s%t | j j |�� � �y )N��dtype)r# �
isinstancer �AttributeErrorr �formatr r )r r r# s r r zArrowAccessor._validate/ sm � ��
�
���%��,� ��!5�!5�!<�!<�5�!<�!I�J� J��+�+�E�,?�,?�@� ��!5�!5�!<�!<�5�!<�!I�J� J� Ar c �B � | j j j S r )r �array� _pa_array�r s r r) zArrowAccessor._pa_array9 s � ��z�z� � �)�)�)r N)r �str�return�None�r, �bool) �__name__�
__module__� __qualname__r r r r �propertyr) r r r r r $ sB � �� � � �
�
� �
�K� �*� �*r r )� metaclassc �N � � e Zd ZdZdd � fd�
Zd
d�Zd d�Zd d�Zd
d�Zd d�Z � xZ
S )� ListAccessorz�
Accessor object for list data properties of the Series values.
Parameters
----------
data : Series
Series containing Arrow list data.
c �( �� t �| � |d�� y )NzJCan only use the '.list' accessor with 'list[pyarrow]' dtype, not {dtype}.�r ��superr �r r � __class__s �r r zListAccessor.__init__H s �� �
��� � 2� �
r c �� � t j j |� xs@ t j j |� xs t j j |� S r )�pa�types�is_list�is_fixed_size_list�
is_large_listr s r r z$ListAccessor._is_valid_pyarrow_dtypeO sG � � �H�H� � �]� +�
5��x�x�*�*�=�9�
5��x�x�%�%�m�4�
r c � � ddl m} t j | j � } ||t |j � �� S )a
Return the length of each list in the Series.
Returns
-------
pandas.Series
The length of each list.
Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... [1, 2, 3],
... [3],
... ],
... dtype=pd.ArrowDtype(pa.list_(
... pa.int64()
... ))
... )
>>> s.list.len()
0 3
1 1
dtype: int32[pyarrow]
r �r r" )�pandasr �pc�list_value_lengthr) r �type)r r �
value_lengthss r �lenzListAccessor.lenV s3 � �4 "��,�,�T�^�^�<�
��m�:�m�6H�6H�+I�J�Jr c �& � ddl m} t |t � r=t j
| j |� } ||t |j � �� S t |t � r�t r t dt j � d�� �|j |j |j }}}|�d}|�d}t j" | j |||� } ||t |j � �� S t% dt |� j& � �� �)a�
Index or slice lists in the Series.
Parameters
----------
key : int | slice
Index or slice of indices to access from each list.
Returns
-------
pandas.Series
The list at requested index.
Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... [1, 2, 3],
... [3],
... ],
... dtype=pd.ArrowDtype(pa.list_(
... pa.int64()
... ))
... )
>>> s.list[0]
0 1
1 3
dtype: int64[pyarrow]
r rD r" z$List slice not supported by pyarrow �.� z!key must be an int or slice, got )rE r r$ �intrF � list_elementr) r rH �slicer �NotImplementedErrorr> � __version__�start�stop�step�
list_slice�
ValueErrorr0 )r �keyr �elementrS rT rU �sliceds r � __getitem__zListAccessor.__getitem__u s� � �> "� �c�3� �
�o�o�d�n�n�c�:�G��'��G�L�L�)A�B� B�
��U�
#�#�)�:�2�>�>�:J�!�L�� � !$� � �3�8�8�S�X�X��4�E��}� ���|����]�]�4�>�>�5�$��E�F��&�
�6�;�;�(?�@� @� � @��c��AS�AS�@T� U�V� Vr c �F � t dt | � j � d�� �)N�'z' object is not iterable)� TypeErrorrH r0 r* s r �__iter__zListAccessor.__iter__� s" � ��!�D��J� /� /�0�0H�I�J�Jr c � � ddl m} t j | j � } ||t |j � �� S )a;
Flatten list values.
Returns
-------
pandas.Series
The data from all lists in the series flattened.
Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... [1, 2, 3],
... [3],
... ],
... dtype=pd.ArrowDtype(pa.list_(
... pa.int64()
... ))
... )
>>> s.list.flatten()
0 1
1 2
2 3
3 3
dtype: int64[pyarrow]
r rD r" )rE r rF � list_flattenr) r rH )r r � flatteneds r �flattenzListAccessor.flatten� s/ � �8 "��O�O�D�N�N�3� ��i�z�)�.�.�'A�B�Br r �r, r- r. �r, r )rX z int | slicer, r )r, r ) r0 r1 r2 �__doc__r r rJ r[ r_ rc �
__classcell__�r< s @r r6 r6 > s+ �� ��
�
� K�>;W�zK� Cr r6 c �X � � e Zd ZdZdd� fd�
Zd d�Zed
d�� Z d d�Zd d�Z � xZ
S )
�StructAccessorz�
Accessor object for structured data properties of the Series values.
Parameters
----------
data : Series
Series containing Arrow struct data.
c �( �� t �| � |d�� y )NzNCan only use the '.struct' accessor with 'struct[pyarrow]' dtype, not {dtype}.r8 r9 r; s �r r zStructAccessor.__init__� s �� �
��� �&� �
r c �@ � t j j |� S r )r> r? � is_structr s r r z&StructAccessor._is_valid_pyarrow_dtype� s � ��x�x�!�!�-�0�0r c � � ddl m}m} | j j j
}|D �cg c] }t
|j � �� }}|D �cg c] }|j �� }} || ||� �� S c c}w c c}w )a�
Return the dtype object of each child field of the struct.
Returns
-------
pandas.Series
The data type of each child field.
Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... {"version": 1, "project": "pandas"},
... {"version": 2, "project": "pandas"},
... {"version": 1, "project": "numpy"},
... ],
... dtype=pd.ArrowDtype(pa.struct(
... [("version", pa.int64()), ("project", pa.string())]
... ))
... )
>>> s.struct.dtypes
version int64[pyarrow]
project string[pyarrow]
dtype: object
r )�Indexr )�index) rE ro r r r# r r rH �name)r ro r �pa_type�structr? �namess r �dtypeszStructAccessor.dtypes� sk � �8
�
�*�*�"�"�0�0��7>�?�V��F�K�K�(�?��?�+2�3�����3��3��e�5��<�0�0�� @��3s � A4�A9c � �� ddl m} d�fd� �| j j j } �||� }t j ||� } ||t |j � | j j |�� S )a�
Extract a child field of a struct as a Series.
Parameters
----------
name_or_index : str | bytes | int | expression | list
Name or index of the child field to extract.
For list-like inputs, this will index into a nested
struct.
Returns
-------
pandas.Series
The data corresponding to the selected child field.
See Also
--------
Series.struct.explode : Return all child fields as a DataFrame.
Notes
-----
The name of the resulting Series will be set using the following
rules:
- For string, bytes, or integer `name_or_index` (or a list of these, for
a nested selection), the Series name is set to the selected
field's name.
- For a :class:`pyarrow.compute.Expression`, this is set to
the string form of the expression.
- For list-like `name_or_index`, the name will be set to the
name of the final field selected.
Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... {"version": 1, "project": "pandas"},
... {"version": 2, "project": "pandas"},
... {"version": 1, "project": "numpy"},
... ],
... dtype=pd.ArrowDtype(pa.struct(
... [("version", pa.int64()), ("project", pa.string())]
... ))
... )
Extract by field name.
>>> s.struct.field("project")
0 pandas
1 pandas
2 numpy
Name: project, dtype: string[pyarrow]
Extract by field index.
>>> s.struct.field(0)
0 1
1 2
2 1
Name: version, dtype: int64[pyarrow]
Or an expression
>>> import pyarrow.compute as pc
>>> s.struct.field(pc.field("project"))
0 pandas
1 pandas
2 numpy
Name: project, dtype: string[pyarrow]
For nested struct types, you can pass a list of values to index
multiple levels:
>>> version_type = pa.struct([
... ("major", pa.int64()),
... ("minor", pa.int64()),
... ])
>>> s = pd.Series(
... [
... {"version": {"major": 1, "minor": 5}, "project": "pandas"},
... {"version": {"major": 2, "minor": 1}, "project": "pandas"},
... {"version": {"major": 1, "minor": 26}, "project": "numpy"},
... ],
... dtype=pd.ArrowDtype(pa.struct(
... [("version", version_type), ("project", pa.string())]
... ))
... )
>>> s.struct.field(["version", "minor"])
0 5
1 1
2 26
Name: minor, dtype: int64[pyarrow]
>>> s.struct.field([0, 0])
0 1
1 2
2 1
Name: major, dtype: int64[pyarrow]
r rD c �, �� t | t � r'|j j | � j }|S t | t
t f� r| }|S t | t j � r
t | � }|S t | � r�t t | � � } |}| rlt t | � } | j � } �||� }|j j |j j |� � }|j }| r�lS t d� �)NzVname_or_index must be an int, str, bytes, pyarrow.compute.Expression, or list of those)r$ rN rH �fieldrq r+ �bytesrF �
Expressionr
�list�reversedr �pop�get_field_indexrW )�level_name_or_indexr rq �selected�
name_or_index�get_names �r r� z&StructAccessor.field.<locals>.get_name� s �� � �-�s�3��y�y���':�;�@�@��0 �K�/ � /�#�u� �>�*��, �K�+ � /�� � �?��.�/��( �K�' � 1�2� '+�8�4G�+H�&I�#� ��)� +/�t�5H�*I�'�$7�$;�$;�$=�M�#�M�8�<�D� '�}�}� 2� 2�8�=�=�3P�3P�QU�3V� W�H�#�=�=�D� *� �K� !�C�� r )r# rp rq )r �Glist[str] | list[bytes] | list[int] | pc.Expression | bytes | str | intr zpa.ChunkedArray)
rE r r r( r) rF � struct_fieldr rH rp )r r� r �pa_arrrq � field_arrr� s @r rx zStructAccessor.field s� �� �\ "�# �"�# � "�# �J ���!�!�+�+���
�v�.���O�O�F�M�:� �� � �Y�^�^�,��*�*�"�"��
�
r c � � ddl m} | j j } |t |j
� D �cg c] }| j
|� �� c}d�� S c c}w )at
Extract all child fields of a struct as a DataFrame.
Returns
-------
pandas.DataFrame
The data corresponding to all child fields.
See Also
--------
Series.struct.field : Return a single child field as a Series.
Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... {"version": 1, "project": "pandas"},
... {"version": 2, "project": "pandas"},
... {"version": 1, "project": "numpy"},
... ],
... dtype=pd.ArrowDtype(pa.struct(
... [("version", pa.int64()), ("project", pa.string())]
... ))
... )
>>> s.struct.explode()
version project
0 1 pandas
1 2 pandas
2 1 numpy
r )�concat�columns)�axis)rE r� r) rH �range�
num_fieldsrx )r r� rr �is r �explodezStructAccessor.explode� sJ � �B "��.�.�%�%���$)�'�*<�*<�$=� >�q�T�Z�Z��]� >�Y�
�
�� >s �Ar rd r. re )r� r� r, r )r, r
) r0 r1 r2 rf r r r3 ru rx r� rg rh s @r rj rj � sI �� ��
�1� �#1� �#1�J^
��^
�
�^
�@&
r rj ) rf �
__future__r �abcr r �typingr r �
pandas.compatr r �pandas.core.dtypes.commonr
�pyarrowr> �pyarrow.compute�computerF �pandas.core.dtypes.dtypesr �collections.abcr rE r
r r r6 rj r r r �<module>r� sa �� &� "���
�
3��� �4��(�� *�g� *�4VC�=� VC�rB
�]� B
r