o
    ?Hh'	                     @   sL   d Z ddlmZ ddlZddlmZ ddlm	Z	 ddl
mZmZ dd ZdS )zyTest the rcv1 loader, if the data is available,
or if specifically requested via environment variable
(e.g. for CI jobs).    )partialN)check_return_X_y)assert_almost_equalassert_array_equalc                 C   s  | dd}|j |j}}|j |j}}t|sJ t|s#J d|j jks+J d|j jks3J d|jks:J d|jksAJ d|jksHJ dt	|ksPJ |j
d	sXJ g d
}t||d d  d}d}	t|	|D ]\}
}||}|
|d d |f j jksJ qn| dd|d}|j |j}}|j}t| ddd}t|| tt|d d t| d}|D ]B}| |}| |}||d d f  }||d d f  }t|| ||d d f  }||d d f  }t|| qd S )NF)shufflei}i' )>F i  )r   g   )r   r   z.. _rcv1_dataset:)C11C12C13C14C15C151   )GMILE143CCAT)   i  i Ttrain)r   subsetrandom_state)r   r   imZ  )i  i  i6  )datatargettarget_namestolist	sample_idspissparsesizeshapelenDESCR
startswithr   zipindexr   r   npsorttoarrayr   )fetch_rcv1_fxtglobal_random_seeddata1X1Y1cat_lists1first_categoriessome_categoriesnumber_non_zero_in_catnumcatjdata2X2Y2s2
fetch_funcsome_sample_idsr   idx1idx2feature_values_1feature_values_2target_values_1target_values_2 rA   `/home/air/sanwanet/gpt-api/venv/lib/python3.10/site-packages/sklearn/datasets/tests/test_rcv1.pytest_fetch_rcv1   sL   



rC   )__doc__	functoolsr   numpyr%   scipy.sparsesparser   "sklearn.datasets.tests.test_commonr   sklearn.utils._testingr   r   rC   rA   rA   rA   rB   <module>   s    