o +if@sddlZddZdddZdS)Nc Cs|||}t|}t||}|dkrX||}tt|ddd}|D]+}t||k\} tt| |} |j | | dd} || d7<|| 8}|dkrWnq,| tj S)aComputes 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 rNF)sizereplace) sumnpfloorintsortuniquewhereminlenchoiceastypeint64) class_countsn_drawsrng continuousfloored need_to_add remaindervaluesvalueindsadd_nowrP/var/www/html/corbot_env/lib/python3.10/site-packages/datasets/utils/stratify.pyapproximate_modes   r c csPtj|dd\}}|jd}t|}t|dkrtd||kr+td||f||kr7td||fttj|dd t|d d } t |D]X} t |||} || } t | ||} g}g}t |D].}| ||}| |j |d d }| |d | || || || || |qg| |}| |}||fVqMd 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_inverserzMinimum 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)kindNrclip)mode)rr shapebincountr ValueErrorsplitargsortcumsumranger permutationtakeextend)yn_trainn_testrn_splitsclasses y_indices n_classesr class_indices_n_iclass_counts_remainingt_itraintestir.perm_indices_class_irrr)stratified_shuffle_split_generate_indices6s<    $    $   rA)r )numpyrrrArrrrs2