
\c           @   sr  d  Z  d d l Z d d l m Z m Z d d l Z d d l Z y4 d d l m Z d d l m	 Z	 d d l m
 Z
 WnA e k
 r d d l m Z d d l m	 Z	 d d l m
 Z
 n Xd d l Z d d l Z d d l m Z d d l m Z d	 d
 l m Z d d l m Z d d l m Z d Z e d  d    Z e d  d d e d d   Z d   Z  d   Z! d S(   s'   Automatically download MLdata datasets.iN(   t   joint   exists(   t	   HTTPError(   t   quote(   t   urlopen(   t   io(   t   copyfileobji   (   t   get_data_homei   (   t   Bunch(   t
   deprecateds4   http://mldata.org/repository/data/download/matlab/%ssR   mldata_filename was deprecated in version 0.20 and will be removed in version 0.22c         C   s+   |  j    j d d  }  t j d d |   S(   s  Convert a raw name for a data set in a mldata.org filename.

    .. deprecated:: 0.20
        Will be removed in version 0.22

    Parameters
    ----------
    dataname : str
        Name of dataset

    Returns
    -------
    fname : str
        The converted dataname.
    t    t   -s   [().]t    (   t   lowert   replacet   ret   sub(   t   dataname(    (    s6   lib/python2.7/site-packages/sklearn/datasets/mldata.pyt   mldata_filename!   s    sO   fetch_mldata was deprecated in version 0.20 and will be removed in version 0.22t   labelt   datac      	   C   s  t  |   }  t d |  } t | d  } t |  sF t j |  n  |  d } t | |  } t |  st t |   } y t |  } Wn5 t	 k
 r }	 |	 j
 d k r d |  |	 _ n    n Xy) t | d   }
 t | |
  Wd QXWn t j |    n X| j   n  t | d   }
 t j |
 d	 t } Wd QXg  | d
 d D] } t | d  ^ qO} t | t j  r| | } n  t | t j  r| | } n  i d |  d 6| d 6} t |  d k r| d } | | | d <n x | D] } | | | | <qW| | k r1| | =| | | d <n | | d =| | d | d <| | k rr| | =| | | d <n | | d =| | d | d <| r| d j | d <n  d | k rt j j | d  s| d j   | d <qn  t |   S(   s  Fetch an mldata.org data set

    mldata.org is no longer operational.

    If the file does not exist yet, it is downloaded from mldata.org .

    mldata.org does not have an enforced convention for storing data or
    naming the columns in a data set. The default behavior of this function
    works well with the most common cases:

      1) data values are stored in the column 'data', and target values in the
         column 'label'
      2) alternatively, the first column stores target values, and the second
         data values
      3) the data array is stored as `n_features x n_samples` , and thus needs
         to be transposed to match the `sklearn` standard

    Keyword arguments allow to adapt these defaults to specific data sets
    (see parameters `target_name`, `data_name`, `transpose_data`, and
    the examples below).

    mldata.org data sets may have multiple columns, which are stored in the
    Bunch object with their original name.

    .. deprecated:: 0.20
        Will be removed in version 0.22

    Parameters
    ----------

    dataname : str
        Name of the data set on mldata.org,
        e.g.: "leukemia", "Whistler Daily Snowfall", etc.
        The raw name is automatically converted to a mldata.org URL .

    target_name : optional, default: 'label'
        Name or index of the column containing the target values.

    data_name : optional, default: 'data'
        Name or index of the column containing the data.

    transpose_data : optional, default: True
        If True, transpose the downloaded data array.

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

    Returns
    -------

    data : Bunch
        Dictionary-like object, the interesting attributes are:
        'data', the data to learn, 'target', the classification labels,
        'DESCR', the full description of the dataset, and
        'COL_NAMES', the original names of the dataset columns.
    t	   data_homet   mldatas   .mati  s%   Dataset '%s' not found on mldata.org.s   w+bNt   rbt   struct_as_recordt   mldata_descr_orderingi    s   mldata.org dataset: %st   DESCRt	   COL_NAMESi   R   t   target(   R   R   R    R   t   ost   makedirst   MLDATA_BASE_URLR   R   R   t   codet   msgt   openR   t   removet   closeR   t   loadmatt   Truet   strt
   isinstancet   numberst   Integralt   lent   Tt   spt   sparset   issparset   squeezeR   (   R   t   target_namet	   data_namet   transpose_dataR   t   matlab_namet   filenamet   urlnamet
   mldata_urlt   et   matlab_filet   matlab_dictt   descrt	   col_namest   datasett   name(    (    s6   lib/python2.7/site-packages/sklearn/datasets/mldata.pyt   fetch_mldata7   sj    ?
(

c         C   s   d d l  m } | i i t j d  d 6t j d  d 6d 6i t j d  d 6t j d  d	 6d
 6i t j d  d 6d 6 d  S(   Ni(   t   install_mldata_mocki   i   R   R   t   irist   double0t   classs   datasets-uci-irisiH   i  t   leukemia(   i   i   (   i   i   (   i   (   iH   i  (   t   sklearn.utils.testingR@   t   npt   empty(   t   moduleR@   (    (    s6   lib/python2.7/site-packages/sklearn/datasets/mldata.pyt   setup_module   s    c         C   s   d d l  m } |   d  S(   Ni(   t   uninstall_mldata_mock(   RE   RJ   (   RH   RJ   (    (    s6   lib/python2.7/site-packages/sklearn/datasets/mldata.pyt   teardown_module   s    ("   t   __doc__R   t   os.pathR    R   R   R)   t   urllib2R   R   R   t   ImportErrort   urllib.errort   urllib.parset   urllib.requestt   numpyRF   t   scipyR-   R   t   shutilR   t   baseR   t   utilsR   R	   R   R   R&   t   NoneR?   RI   RK   (    (    (    s6   lib/python2.7/site-packages/sklearn/datasets/mldata.pyt   <module>   s4   		