ó
    ¨ñ:i«2  ã            	       ó>  • S r SSKrSSKJr  SSKJr  SSKJr  SSKJ	r	J
r
  SSKJr  SSKrSSKJr  SS	KJrJr  S
SKJr  SrSrSr/ SQr\" 5       r\" 5       r\" \5       H  u  rr\S-   \\'   \\\S-   '   M     \" S\/S\ /S/S/S/S/S.SS9SSSSSSS.S j5       r!g)aD	  Collection of imbalanced datasets.

This collection of datasets has been proposed in [1]_. The
characteristics of the available datasets are presented in the table
below.

 ID    Name           Repository & Target           Ratio  #S       #F
 1     ecoli          UCI, target: imU              8.6:1  336      7
 2     optical_digits UCI, target: 8                9.1:1  5,620    64
 3     satimage       UCI, target: 4                9.3:1  6,435    36
 4     pen_digits     UCI, target: 5                9.4:1  10,992   16
 5     abalone        UCI, target: 7                9.7:1  4,177    10
 6     sick_euthyroid UCI, target: sick euthyroid   9.8:1  3,163    42
 7     spectrometer   UCI, target: >=44             11:1   531      93
 8     car_eval_34    UCI, target: good, v good     12:1   1,728    21
 9     isolet         UCI, target: A, B             12:1   7,797    617
 10    us_crime       UCI, target: >0.65            12:1   1,994    100
 11    yeast_ml8      LIBSVM, target: 8             13:1   2,417    103
 12    scene          LIBSVM, target: >one label    13:1   2,407    294
 13    libras_move    UCI, target: 1                14:1   360      90
 14    thyroid_sick   UCI, target: sick             15:1   3,772    52
 15    coil_2000      KDD, CoIL, target: minority   16:1   9,822    85
 16    arrhythmia     UCI, target: 06               17:1   452      278
 17    solar_flare_m0 UCI, target: M->0             19:1   1,389    32
 18    oil            UCI, target: minority         22:1   937      49
 19    car_eval_4     UCI, target: vgood            26:1   1,728    21
 20    wine_quality   UCI, wine, target: <=4        26:1   4,898    11
 21    letter_img     UCI, target: Z                26:1   20,000   16
 22    yeast_me2      UCI, target: ME2              28:1   1,484    8
 23    webpage        LIBSVM, w7a, target: minority 33:1   34,780   300
 24    ozone_level    UCI, ozone, data              34:1   2,536    72
 25    mammography    UCI, target: minority         42:1   11,183   6
 26    protein_homo   KDD CUP 2004, minority        111:1  145,751  74
 27    abalone_19     UCI, target: 19               130:1  4,177    10

References
----------
.. [1] Ding, Zejin, "Diversified Ensemble Classifiers for Highly
   Imbalanced Data Learning and their Application in Bioinformatics."
   Dissertation, Georgia State University, (2011).
é    N)ÚOrderedDict)ÚBytesIO)Úmakedirs)ÚisfileÚjoin)Úurlopen)Úget_data_home)ÚBunchÚcheck_random_stateé   )Úvalidate_paramszGhttps://zenodo.org/record/61452/files/benchmark-imbalanced-learn.tar.gzÚxzdata.npz)ÚecoliÚoptical_digitsÚsatimageÚ
pen_digitsÚabaloneÚsick_euthyroidÚspectrometerÚcar_eval_34ÚisoletÚus_crimeÚ	yeast_ml8ÚsceneÚlibras_moveÚthyroid_sickÚ	coil_2000Ú
arrhythmiaÚsolar_flare_m0ÚoilÚ
car_eval_4Úwine_qualityÚ
letter_imgÚ	yeast_me2ÚwebpageÚozone_levelÚmammographyÚprotein_homoÚ
abalone_19é   ÚbooleanÚrandom_state)Ú	data_homeÚfilter_dataÚdownload_if_missingr,   ÚshuffleÚverboseT)Úprefer_skip_nested_validationFc           
      ó¨  • [        U S9n [        U S5      n[        5       nUc  [        R	                  5       nOÈ[        R	                  5       n	/ nU H¬  n
[        U
[        5      (       a(  X©;  a  [        U
 SU	 35      eUR                  U
5        M@  [        U
[        5      (       aA  U
S:  d  U
S:”  a  [        SU
 S[        SS5       35      eUR                  [        U
   5        M–  [        S	[        U
5       S
35      e   U GHK  n
[        [        [        U
   5      -   [        -   n[        Xk5      n[        U5      nU(       at  U(       dm  [!        USS9  U(       a  [#        S[$        -  5        ['        [)        [$        5      R+                  5       5      n[,        R.                  " US9nUR1                  US9  OU(       d  U(       d  [3        S5      e[4        R6                  " U5      nUS   US   nnU(       aI  [4        R8                  " UR:                  S   5      n[=        U5      nUR?                  U5        UU   nUU   n[A        UUU
S9Xz'   GMN     U$ )a9  Load the benchmark datasets from Zenodo, downloading it if necessary.

.. versionadded:: 0.3

Parameters
----------
data_home : str, default=None
    Specify another download and cache folder for the datasets. By default
    all scikit-learn data is stored in '~/scikit_learn_data' subfolders.

filter_data : tuple of str/int, default=None
    A tuple containing the ID or the name of the datasets to be returned.
    Refer to the above table to get the ID and name of the datasets.

download_if_missing : bool, default=True
    If False, raise a IOError if the data is not locally available
    instead of trying to download the data from the source site.

random_state : int, RandomState instance or None, default=None
    Random state for shuffling the dataset.
    If int, random_state is the seed used by the random number generator;
    If RandomState instance, random_state is the random number generator;
    If None, the random number generator is the RandomState instance used
    by `np.random`.

shuffle : bool, default=False
    Whether to shuffle dataset.

verbose : bool, default=False
    Show information regarding the fetching.

Returns
-------
datasets : OrderedDict of Bunch object,
    The ordered is defined by ``filter_data``. Each Bunch object ---
    referred as dataset --- have the following attributes:

    dataset.data : ndarray of shape (n_samples, n_features)

    dataset.target : ndarray of shape (n_samples,)

    dataset.DESCR : str
        Description of the each dataset.

Notes
-----
This collection of datasets have been proposed in [1]_. The
characteristics of the available datasets are presented in the table
below.

+--+--------------+-------------------------------+-------+---------+-----+
|ID|Name          | Repository & Target           | Ratio | #S      | #F  |
+==+==============+===============================+=======+=========+=====+
|1 |ecoli         | UCI, target: imU              | 8.6:1 | 336     | 7   |
+--+--------------+-------------------------------+-------+---------+-----+
|2 |optical_digits| UCI, target: 8                | 9.1:1 | 5,620   | 64  |
+--+--------------+-------------------------------+-------+---------+-----+
|3 |satimage      | UCI, target: 4                | 9.3:1 | 6,435   | 36  |
+--+--------------+-------------------------------+-------+---------+-----+
|4 |pen_digits    | UCI, target: 5                | 9.4:1 | 10,992  | 16  |
+--+--------------+-------------------------------+-------+---------+-----+
|5 |abalone       | UCI, target: 7                | 9.7:1 | 4,177   | 10  |
+--+--------------+-------------------------------+-------+---------+-----+
|6 |sick_euthyroid| UCI, target: sick euthyroid   | 9.8:1 | 3,163   | 42  |
+--+--------------+-------------------------------+-------+---------+-----+
|7 |spectrometer  | UCI, target: >=44             | 11:1  | 531     | 93  |
+--+--------------+-------------------------------+-------+---------+-----+
|8 |car_eval_34   | UCI, target: good, v good     | 12:1  | 1,728   | 21  |
+--+--------------+-------------------------------+-------+---------+-----+
|9 |isolet        | UCI, target: A, B             | 12:1  | 7,797   | 617 |
+--+--------------+-------------------------------+-------+---------+-----+
|10|us_crime      | UCI, target: >0.65            | 12:1  | 1,994   | 100 |
+--+--------------+-------------------------------+-------+---------+-----+
|11|yeast_ml8     | LIBSVM, target: 8             | 13:1  | 2,417   | 103 |
+--+--------------+-------------------------------+-------+---------+-----+
|12|scene         | LIBSVM, target: >one label    | 13:1  | 2,407   | 294 |
+--+--------------+-------------------------------+-------+---------+-----+
|13|libras_move   | UCI, target: 1                | 14:1  | 360     | 90  |
+--+--------------+-------------------------------+-------+---------+-----+
|14|thyroid_sick  | UCI, target: sick             | 15:1  | 3,772   | 52  |
+--+--------------+-------------------------------+-------+---------+-----+
|15|coil_2000     | KDD, CoIL, target: minority   | 16:1  | 9,822   | 85  |
+--+--------------+-------------------------------+-------+---------+-----+
|16|arrhythmia    | UCI, target: 06               | 17:1  | 452     | 278 |
+--+--------------+-------------------------------+-------+---------+-----+
|17|solar_flare_m0| UCI, target: M->0             | 19:1  | 1,389   | 32  |
+--+--------------+-------------------------------+-------+---------+-----+
|18|oil           | UCI, target: minority         | 22:1  | 937     | 49  |
+--+--------------+-------------------------------+-------+---------+-----+
|19|car_eval_4    | UCI, target: vgood            | 26:1  | 1,728   | 21  |
+--+--------------+-------------------------------+-------+---------+-----+
|20|wine_quality  | UCI, wine, target: <=4        | 26:1  | 4,898   | 11  |
+--+--------------+-------------------------------+-------+---------+-----+
|21|letter_img    | UCI, target: Z                | 26:1  | 20,000  | 16  |
+--+--------------+-------------------------------+-------+---------+-----+
|22|yeast_me2     | UCI, target: ME2              | 28:1  | 1,484   | 8   |
+--+--------------+-------------------------------+-------+---------+-----+
|23|webpage       | LIBSVM, w7a, target: minority | 33:1  | 34,780  | 300 |
+--+--------------+-------------------------------+-------+---------+-----+
|24|ozone_level   | UCI, ozone, data              | 34:1  | 2,536   | 72  |
+--+--------------+-------------------------------+-------+---------+-----+
|25|mammography   | UCI, target: minority         | 42:1  | 11,183  | 6   |
+--+--------------+-------------------------------+-------+---------+-----+
|26|protein_homo  | KDD CUP 2004, minority        | 111:1 | 145,751 | 74  |
+--+--------------+-------------------------------+-------+---------+-----+
|27|abalone_19    | UCI, target: 19               | 130:1 | 4,177   | 10  |
+--+--------------+-------------------------------+-------+---------+-----+

References
----------
.. [1] Ding, Zejin, "Diversified Ensemble Classifiers for Highly
   Imbalanced Data Learning and their Application in Bioinformatics."
   Dissertation, Georgia State University, (2011).
)r-   Úzenodoz8 is not a dataset available. The available datasets are r*   é   zThe dataset with the ID=z* is not an available dataset. The IDs are é   z1The value in the tuple should be str or int. Got z	 instead.T)Úexist_okzDownloading %s)Úfileobj)Úpathz1Data not found and `download_if_missing` is FalseÚdataÚlabelr   )r:   ÚtargetÚDESCR)!r	   r   r   ÚMAP_NAME_IDÚkeysÚ
isinstanceÚstrÚ
ValueErrorÚappendÚintÚrangeÚMAP_ID_NAMEÚtypeÚPRE_FILENAMEÚPOST_FILENAMEr   r   ÚprintÚURLr   r   ÚreadÚtarfileÚopenÚ
extractallÚIOErrorÚnpÚloadÚarangeÚshaper   r0   r
   )r-   r.   r/   r,   r0   r1   Ú
zenodo_dirÚdatasetsÚfilter_data_Ú	list_dataÚitÚfilenameÚ	availableÚfÚtarr:   ÚXÚyÚindÚrngs                       Ú\/srv/projetos/modelo_ml_acdoc/venv/lib/python3.13/site-packages/imblearn/datasets/_zenodo.pyÚfetch_datasetsrc   d   s$  € ôN ¨	Ñ2€IÜ�i Ó*€JÜ‹}€HàÑÜ"×'Ñ'Ó)‰ä×$Ñ$Ó&ˆ	ØˆÛˆBÜ˜"œc×"Ñ"ØÓ&Ü$Ø˜$ð 6Ø6?°[ðBóð ð
 !×'Ñ'¨Ö+Ü˜B¤×$Ñ$Ø˜“6˜R "›WÜ$Ø2°2°$ð 7:ä   B›<˜.ð*óð ð !×'Ñ'¬°B©Ö8ä ðÜ  ›H˜: Yð0óð ñ+ ô6 ˆÜ¤#¤k°"¡oÓ"6Ñ6¼ÑFˆÜ˜
Ó-ˆÜ˜8Ó$ˆ	æ¦yÜ�Z¨$Ò/ÞÜÐ&¬Ñ,Ô-Üœ¤›×)Ñ)Ó+Ó,ˆAÜ—,’, qÑ)ˆCØ�N‰N 
ˆNÒ+Þ$®YÜÐMÓNÐNä�wŠw�xÓ ˆØ�F‰|˜T '™]ˆ1ˆæÜ—)’)˜AŸG™G A™JÓ'ˆCÜ$ \Ó2ˆCØ�K‰K˜ÔØ�#‘ˆAØ�#‘ˆAä !¨A°RÑ8ˆŒñ3 ð6 €Oó    )"Ú__doc__rM   Úcollectionsr   Úior   Úosr   Úos.pathr   r   Úurllib.requestr   ÚnumpyrQ   Úsklearn.datasetsr	   Úsklearn.utilsr
   r   Úutils._param_validationr   rK   rH   rI   ÚMAP_NAME_ID_KEYSr>   rF   Ú	enumerateÚvÚkrA   Útuplerc   © rd   rb   Ú<module>ru      sÝ   ðñ(óZ Ý #Ý Ý ß  Ý "ã Ý *ß 3å 5àO€Ø€Ø€òÐ ñ< ‹m€Ù‹m€ÙÐ&Ö'�D€A€qØ˜‘U€K��NØ€K��A‘Óñ (ñ
 à˜C�[Ø˜e�}Ø )˜{Ø'Ð(Ø�;Ø�;ñð #'ñ
ð ØØØØØô{ó
ñ{rd   