B
    0dI              	   @   sN  d Z ddlmZmZmZ ddlmZmZmZ ddl	Z	ddl
ZddlZddlmZ ddlmZmZmZmZ dd	lmZ dd
lmZ e	eZeddddZeddddZeddddeddddeddddfZd1ddZdd Zd2d!d"Zddd#dd e d$d%e d&d'fdd d(d)d*Z!d3d+d,Z"d-ddd#d e d$d%e d&d'fdd.d/d0Z#dS )4zLabeled Faces in the Wild (LFW) dataset

This dataset is a collection of JPEG pictures of famous people collected
over the internet, all details are available on the official website:

    http://vis-www.cs.umass.edu/lfw/
    )listdirmakedirsremove)joinexistsisdirN)Memory   )get_data_home_fetch_remoteRemoteFileMetadata
load_descr   )Bunch)parse_versionzlfw.tgzz.https://ndownloader.figshare.com/files/5976018Z@055f7d9c632d7370e6fb4afc7468d40f970c34a80d4c6f50ffec63f5a8d536c0)filenameurlZchecksumzlfw-funneled.tgzz.https://ndownloader.figshare.com/files/5976015Z@b47c8422c8cded889dc5a13418c4bc2abbda121092b3533a83306f90d900100azpairsDevTrain.txtz.https://ndownloader.figshare.com/files/5976012Z@1d454dada7dfeca0e7eab6f65dc4e97a6312d44cf142207be28d688be92aabfazpairsDevTest.txtz.https://ndownloader.figshare.com/files/5976009Z@7cb06600ea8b2814ac26e946201cdb304296262aad67d046a16a7ec85d0ff87cz	pairs.txtz.https://ndownloader.figshare.com/files/5976006Z@ea42330c62c92989f9d7c03237ed5d591365e89b3e649747777b70e692dc1592Tc       
      C   s  t | d} t| d}t|s$t| xLtD ]D}t||j}t|s*|rbtd|j t	||d q*t
d| q*W |rt|d}t}nt|d}t}t|st||j}t|s|rtd|j t	||d nt
d| d	d
l}	td| |	|dj|d t| ||fS )z0Helper function to download any missing LFW data)	data_homelfw_homezDownloading LFW metadata: %s)dirnamez%s is missingZlfw_funneledZlfwz!Downloading LFW data (~200MB): %sr   Nz$Decompressing the data archive to %szr:gz)path)r
   r   r   r   TARGETSr   loggerinfor   r   IOErrorFUNNELED_ARCHIVEARCHIVEtarfiledebugopen
extractallr   )
r   funneleddownload_if_missingr   targetZtarget_filepathdata_folder_patharchivearchive_pathr    r'   G/var/www/html/venv/lib/python3.7/site-packages/sklearn/datasets/_lfw.py_check_fetch_lfwL   s8    





r)   c             C   s  ddl m}m} tddtddf}|dkr2|}ntdd t||D }|\}}|j|j |jpdd }	|j|j |jpzd }
|dk	rt	|}t
||	 }	t
||
 }
t| }|stj||	|
ftjd	}ntj||	|
d
ftjd	}xt| D ]\}}|d dkrtd|d | ||}|jdkr4td| tj|| tjd	}|d }|dk	rd|||}|sv|jdd}|||df< qW |S )zInternally used to load imagesr   )imreadimresizer      Nc             s   s   | ]\}}|p|V  qd S )Nr'   ).0sZdsr'   r'   r(   	<genexpr>   s    z_load_imgs.<locals>.<genexpr>r	   )dtype   i  zLoading face #%05d / %05dzLFailed to read the image file %s, Please make sure that libjpeg is installedg     o@)Zaxis.)Zexternals._pilutilr*   r+   slicetuplezipstopstartstepfloatintlennpzerosZfloat32	enumerater   r   ndimRuntimeErrorZasarrayZmean)
file_pathsslice_colorresizer*   r+   Zdefault_sliceZh_sliceZw_slicehwn_facesfacesi	file_pathZimgZfacer'   r'   r(   
_load_imgsw   s@    

rJ   Fc                s   g g  }}xxt t| D ]h}t| | t s0q fddt t D }t|}	|	|kr|dd}||g|	  || qW t|}
|
dkrtd| t	|}t
||}t||||}t|
}tjd| || ||  }}|||fS )z~Perform the actual data loading for the lfw people dataset

    This operation is meant to be cached by a joblib wrapper.
    c                s   g | ]}t  |qS r'   )r   )r-   f)folder_pathr'   r(   
<listcomp>   s    z%_fetch_lfw_people.<locals>.<listcomp>_ r   z*min_faces_per_person=%d is too restrictive*   )sortedr   r   r   r:   replaceextend
ValueErrorr;   uniqueZsearchsortedrJ   ZarangerandomZRandomStateshuffle)r$   rA   rB   rC   min_faces_per_personZperson_namesr@   Zperson_namepathsZ
n_picturesrF   target_namesr#   rG   indicesr'   )rL   r(   _fetch_lfw_people   s,    	




r\   g      ?F      N      )r   r!   rC   rX   rB   rA   r"   
return_X_yc             C   s   t | ||d\}}	td| ttjtdk r@t|ddd}
nt|ddd}
|
t}||	||||d\}}}|	t
|d	}td
}|r||fS t|||||dS )a  Load the Labeled Faces in the Wild (LFW) people dataset (classification).

    Download it if necessary.

    =================   =======================
    Classes                                5749
    Samples total                         13233
    Dimensionality                         5828
    Features            real, between 0 and 255
    =================   =======================

    Read more in the :ref:`User Guide <labeled_faces_in_the_wild_dataset>`.

    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.

    funneled : bool, default=True
        Download and use the funneled variant of the dataset.

    resize : float, default=0.5
        Ratio used to resize the each face picture.

    min_faces_per_person : int, default=None
        The extracted dataset will only retain pictures of people that have at
        least `min_faces_per_person` different pictures.

    color : bool, default=False
        Keep the 3 RGB channels instead of averaging them to a single
        gray level channel. If color is True the shape of the data has
        one more dimension than the shape with color = False.

    slice_ : tuple of slice, default=(slice(70, 195), slice(78, 172))
        Provide a custom 2D slice (height, width) to extract the
        'interesting' part of the jpeg files and avoid use statistical
        correlation from the background

    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.

    return_X_y : bool, default=False
        If True, returns ``(dataset.data, dataset.target)`` instead of a Bunch
        object. See below for more information about the `dataset.data` and
        `dataset.target` object.

        .. versionadded:: 0.20

    Returns
    -------
    dataset : :class:`~sklearn.utils.Bunch`
        Dictionary-like object, with the following attributes.

        data : numpy array of shape (13233, 2914)
            Each row corresponds to a ravelled face image
            of original size 62 x 47 pixels.
            Changing the ``slice_`` or resize parameters will change the
            shape of the output.
        images : numpy array of shape (13233, 62, 47)
            Each row is a face image corresponding to one of the 5749 people in
            the dataset. Changing the ``slice_``
            or resize parameters will change the shape of the output.
        target : numpy array of shape (13233,)
            Labels associated to each face image.
            Those labels range from 0-5748 and correspond to the person IDs.
        DESCR : str
            Description of the Labeled Faces in the Wild (LFW) dataset.

    (data, target) : tuple if ``return_X_y`` is True

        .. versionadded:: 0.20

    )r   r!   r"   z Loading LFW people faces from %sz0.12   r   )cachedircompressverbose)locationrd   re   )rC   rX   rB   rA   zlfw.rst)dataZimagesr#   rZ   DESCR)r)   r   r   r   joblib__version__r   cacher\   reshaper:   r   r   )r   r!   rC   rX   rB   rA   r"   ra   r   r$   m	load_funcrG   r#   rZ   Xfdescrr'   r'   r(   fetch_lfw_people   s&    W
rr   c          
   C   s  t | d}dd |D }W dQ R X dd |D }t|}tj|td}	t }
x0t|D ]"\}}t|dkrd|	|< |d	 t|d d f|d	 t|d
 d ff}nZt|dkrd	|	|< |d	 t|d d f|d
 t|d d ff}ntd|d |f xxt|D ]l\}\}}yt||}W n& t	k
rN   t|t
|d}Y nX ttt|}t||| }|
| qW qZW t|
|||}t|j}|d	}|d	d
 |d	|d
  ||_||	tddgfS )z}Perform the actual data loading for the LFW pairs dataset

    This operation is meant to be cached by a joblib wrapper.
    rbc             S   s   g | ]}|   d qS )	)decodestripsplit)r-   lnr'   r'   r(   rM   k  s    z$_fetch_lfw_pairs.<locals>.<listcomp>Nc             S   s   g | ]}t |d kr|qS )r   )r:   )r-   slr'   r'   r(   rM   l  s    )r0   r1   r	   r   r      zinvalid line %d: %rzUTF-8zDifferent personszSame person)r   r:   r;   r<   r9   listr=   rT   r   	TypeErrorstrrQ   r   appendrJ   shapepopinsertarray)index_file_pathr$   rA   rB   rC   Z
index_filesplit_linesZ
pair_specsZn_pairsr#   r@   rH   
componentspairjnameidxZperson_folder	filenamesrI   pairsr   rF   r'   r'   r(   _fetch_lfw_pairsa  s>    	

r   train)subsetr   r!   rC   rB   rA   r"   c             C   s   t |||d\}}td| | ttjtdk rBt|ddd}	nt|ddd}	|	t}
dd	d
d}| |krt	d| t
t| f t|||  }|
|||||d\}}}td}t|t|d||||dS )a  Load the Labeled Faces in the Wild (LFW) pairs dataset (classification).

    Download it if necessary.

    =================   =======================
    Classes                                   2
    Samples total                         13233
    Dimensionality                         5828
    Features            real, between 0 and 255
    =================   =======================

    In the official `README.txt`_ this task is described as the
    "Restricted" task.  As I am not sure as to implement the
    "Unrestricted" variant correctly, I left it as unsupported for now.

      .. _`README.txt`: http://vis-www.cs.umass.edu/lfw/README.txt

    The original images are 250 x 250 pixels, but the default slice and resize
    arguments reduce them to 62 x 47.

    Read more in the :ref:`User Guide <labeled_faces_in_the_wild_dataset>`.

    Parameters
    ----------
    subset : {'train', 'test', '10_folds'}, default='train'
        Select the dataset to load: 'train' for the development training
        set, 'test' for the development test set, and '10_folds' for the
        official evaluation set that is meant to be used with a 10-folds
        cross validation.

    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.

    funneled : bool, default=True
        Download and use the funneled variant of the dataset.

    resize : float, default=0.5
        Ratio used to resize the each face picture.

    color : bool, default=False
        Keep the 3 RGB channels instead of averaging them to a single
        gray level channel. If color is True the shape of the data has
        one more dimension than the shape with color = False.

    slice_ : tuple of slice, default=(slice(70, 195), slice(78, 172))
        Provide a custom 2D slice (height, width) to extract the
        'interesting' part of the jpeg files and avoid use statistical
        correlation from the background

    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.

    Returns
    -------
    data : :class:`~sklearn.utils.Bunch`
        Dictionary-like object, with the following attributes.

        data : ndarray of shape (2200, 5828). Shape depends on ``subset``.
            Each row corresponds to 2 ravel'd face images
            of original size 62 x 47 pixels.
            Changing the ``slice_``, ``resize`` or ``subset`` parameters
            will change the shape of the output.
        pairs : ndarray of shape (2200, 2, 62, 47). Shape depends on ``subset``
            Each row has 2 face images corresponding
            to same or different person from the dataset
            containing 5749 people. Changing the ``slice_``,
            ``resize`` or ``subset`` parameters will change the shape of the
            output.
        target : numpy array of shape (2200,). Shape depends on ``subset``.
            Labels associated to each pair of images.
            The two label values being different persons or the same person.
        DESCR : str
            Description of the Labeled Faces in the Wild (LFW) dataset.

    )r   r!   r"   zLoading %s LFW pairs from %sz0.12rb   r   )rc   rd   re   )rf   rd   re   zpairsDevTrain.txtzpairsDevTest.txtz	pairs.txt)r   testZ10_foldsz+subset='%s' is invalid: should be one of %r)rC   rB   rA   zlfw.rstrg   )rh   r   r#   rZ   ri   )r)   r   r   r   rj   rk   r   rl   r   rT   r{   rQ   keysr   r   r   rm   r:   )r   r   r!   rC   rB   rA   r"   r   r$   rn   ro   Zlabel_filenamesr   r   r#   rZ   rq   r'   r'   r(   fetch_lfw_pairs  s0    X
r   )NTT)NFNr   )NFN)$__doc__osr   r   r   os.pathr   r   r   loggingnumpyr;   rj   r   _baser
   r   r   r   utilsr   Zutils.fixesr   	getLogger__name__r   r   r   r   r)   rJ   r\   r2   rr   r   r   r'   r'   r'   r(   <module>   sb   


+@
,x
5