�
���g� � � � d dl Zd� Zdd�ZdS )� Nc �: � || z | � � � z }t j |� � }t ||� � � z
� � }|dk r�||z
}t j t j |� � � � ddd� }|D ]n}t j ||k � � \ } t t | � � |� � }
|� | |
d�� � } || xx dz
cc< ||
z }|dk r n�o|�
t j � � S )a� Computes approximate mode of multivariate hypergeometric.
This is an approximation to the mode of the multivariate
hypergeometric given by class_counts and n_draws.
It shouldn't be off by more than one.
It is the mostly likely outcome of drawing n_draws many
samples from the population given by class_counts.
Args
----------
class_counts : ndarray of int
Population per class.
n_draws : int
Number of draws (samples to draw) from the overall population.
rng : random state
Used to break ties.
Returns
-------
sampled_classes : ndarray of int
Number of samples drawn from each class.
np.sum(sampled_classes) == n_draws
r N�����F)�size�replace� ) �sum�np�floor�int�sort�unique�where�min�len�choice�astype�int64) � class_counts�n_draws�rng�
continuous�floored� need_to_add� remainder�values�value�inds�add_nows �g/home/asafur/pinokio/api/open-webui.git/app/env/lib/python3.11/site-packages/datasets/utils/stratify.py�approximate_moder s � �0 �<�'�,�*:�*:�*<�*<�<�J��h�z�"�"�G� �g�� � �
�
�-�.�.�K��Q��� ��(� �����9�-�-�.�.�t�t��t�4�� � � �E��h�y�E� 1�2�2�G�T�
�#�d�)�)�[�1�1�G��:�:�d��%�:�@�@�D� �D�M�M�M�Q� �M�M�M� �7� "�K��a� � ��� � �>�>�"�(� #� #�#� �
c # �� K � t j | d�� � \ }}|j d }t j |� � }t j |� � dk rt d� � �||k rt d||fz � � �||k rt d||fz � � �t j t j |d� � � t j |� � d
d � � � } t |� � D ]�}
t |||� � } || z
} t | ||� � }
g }g }t |� � D ]�}|� || � � }| | � |d �
� � }|�
|d
| | � � � |�
|| | | | |
| z � � � ��|� |� � }|� |� � }||fV � ��d
S )a�
Provides train/test indices to split data in train/test sets.
It's reference is taken from StratifiedShuffleSplit implementation
of scikit-learn library.
Args
----------
n_train : int,
represents the absolute number of train samples.
n_test : int,
represents the absolute number of test samples.
random_state : int or RandomState instance, default=None
Controls the randomness of the training and testing indices produced.
Pass an int for reproducible output across multiple function calls.
n_splits : int, default=10
Number of re-shuffling & splitting iterations.
T)�return_inverser � zMinimum class count errorzLThe train_size = %d should be greater or equal to the number of classes = %dzKThe test_size = %d should be greater or equal to the number of classes = %d� mergesort)�kindNr �clip)�mode)r r
�shape�bincountr �
ValueError�split�argsort�cumsum�ranger � permutation�take�extend)�y�n_train�n_testr �n_splits�classes� y_indices� n_classesr �
class_indices�_�n_i�class_counts_remaining�t_i�train�test�ir1 �perm_indices_class_is r �)stratified_shuffle_split_generate_indicesrD 6 s � � � �. ��1�T�:�:�:��G�Y��
�a� �I��;�y�)�)�L� �v�l���a� � ��4�5�5�5������ Z�^e�gp�]q� q�
�
�
� � ���� Y�]c�en�\o� o�
�
�
� �H�R�Z� � � D� D� D�b�i�P\�F]�F]�^a�_a�^a�Fb�c�c�M�
�8�_�_� � �� �|�W�c�:�:��!-��!3� � � 5�v�s�C�C�������y�!�!� H� H�A� �/�/�,�q�/�:�:�K�#0��#3�#8�#8��6�#8�#R�#R� � �L�L�-�h��A��h�7� 8� 8� 8� �K�K�,�S��V�c�!�f�s�1�v�o�-E�F� G� G� G� G�����&�&�����t�$�$���T�k�����!� r! )r" )�numpyr r rD � r! r �<module>rG s? �� � � � �/$� /$� /$�d5� 5� 5� 5� 5� 5r!