a jZ@sXdZddlZddlmZmZddlmZmZmZm Z ddl m Z m Z m Z ddlZddlmZddlmZdd lmZmZmZmZdd lmZd d lmZmZmZmZe e!Z"ed dddZ#eddddZ$eddddeddddeddddfZ%dd5d6Z-eehd7ge)edgd'geeddd(d)dgd'ge*edgd'geed dd*d)geed+dd(d)gd8 dd-d9ddd.d$e+d/d0e+d1d2fdddd8 d:d;Z.dS)?zLabeled 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/ N)IntegralReal)PathLikelistdirmakedirsremove)existsisdirjoin)Memory)Bunch)HiddenInterval StrOptionsvalidate_params)tarfile_extractall)RemoteFileMetadata _fetch_remote get_data_home load_descrzlfw.tgzz.https://ndownloader.figshare.com/files/5976018Z@055f7d9c632d7370e6fb4afc7468d40f970c34a80d4c6f50ffec63f5a8d536c0)filenameurlZchecksumzlfw-funneled.tgzz.https://ndownloader.figshare.com/files/5976015Z@b47c8422c8cded889dc5a13418c4bc2abbda121092b3533a83306f90d900100apairsDevTrain.txtz.https://ndownloader.figshare.com/files/5976012Z@1d454dada7dfeca0e7eab6f65dc4e97a6312d44cf142207be28d688be92aabfapairsDevTest.txtz.https://ndownloader.figshare.com/files/5976009Z@7cb06600ea8b2814ac26e946201cdb304296262aad67d046a16a7ec85d0ff87c pairs.txtz.https://ndownloader.figshare.com/files/5976006Z@ea42330c62c92989f9d7c03237ed5d591365e89b3e649747777b70e692dc1592T?c Cs@t|d}t|d}t|s$t|tD]H}t||j}t|s(|rdtd|jt ||||dq(t d|q(|rt|d}t } nt|d}t } t|s8t|| j} t| s|rtd| jt | |||dn t d| d d l } td || | d } t| |d Wd n1s&0Yt| ||fS)z0Helper function to download any missing LFW data) data_homelfw_homezDownloading LFW metadata: %s)dirname n_retriesdelayz %s is missingZ lfw_funneledZlfwz!Downloading LFW data (~200MB): %srNz$Decompressing the data archive to %szr:gz)path)rr rrTARGETSrloggerinforrOSErrorFUNNELED_ARCHIVEARCHIVEtarfiledebugopenrr) rfunneleddownload_if_missingr"r#r targetZtarget_filepathdata_folder_patharchive archive_pathr+fpr5;E:\soccer\ml_env\Lib\site-packages\sklearn/datasets/_lfw.py_check_fetch_lfwMsB         ,r7cCszddlm}Wnty*tdYn0tddtddf}|durN|}ntddt||D}|\}}|j|j|jpd}|j|j|jpd} |durt |}t ||}t || } t |} |st j | || ft jd } nt j | || d ft jd } t|D]\} } | d dkr.td | d| || }||j|j|j|jf}|durj|| |f}t j|t jd }|jdkrtd | |d}|s|jdd}|| | df<q| S)zInternally used to load imagesr)ImagezThe Python Imaging Library (PIL) is required to load data from jpeg files. Please refer to https://pillow.readthedocs.io/en/stable/installation.html for installing PIL.Ncss|]\}}|p|VqdS)Nr5).0sZdsr5r5r6 z_load_imgs..rZdtyperizLoading face #%05d / %05dzLFailed to read the image file %s, Please make sure that libjpeg is installedgo@r )Zaxis.)ZPILr8 ImportErrorslicetuplezipstopstartstepfloatintlennpzerosZfloat32 enumerater&r,r-cropresizeZasarrayndim RuntimeErrormean) file_pathsslice_colorrMr8Z default_sliceZh_sliceZw_slicehwn_facesfacesi file_pathZpil_imgZfacer5r5r6 _load_imgssT        rZFcsgg}}tt|D]h}t||ts.qfddttD}t|} | |kr|dd}||g| ||qt|} | dkrtd|t |} t | |} t ||||} t | }tj d|| || |} } | | | fS)z~Perform the actual data loading for the lfw people dataset This operation is meant to be cached by a joblib wrapper. csg|]}t|qSr5)r )r:fZ folder_pathr5r6 r=z%_fetch_lfw_people.._ rz*min_faces_per_person=%d is too restrictive*)sortedrr r rHreplaceextend ValueErrorrIuniqueZ searchsortedrZZarangerandomZ RandomStateshuffle)r1rRrSrMmin_faces_per_personZ person_namesrQZ person_namepathsZ n_picturesrV target_namesr0rWindicesr5r\r6_fetch_lfw_peoples.       rlbooleanZneither)closedleftg) rr.rMrhrSrRr/ return_X_yr"r#)Zprefer_skip_nested_validationg?FNc Cst||||| d\} } td| t| ddd} | t} | | ||||d\}}}|t|d}td}|rv||fSt |||||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 ================= ======================= For a usage example of this dataset, see :ref:`sphx_glr_auto_examples_applications_plot_face_recognition.py`. Read more in the :ref:`User Guide `. Parameters ---------- data_home : str or path-like, 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 or None, default=0.5 Ratio used to resize the each face picture. If `None`, no resizing is performed. 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 an OSError 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 n_retries : int, default=3 Number of retries when HTTP errors are encountered. .. versionadded:: 1.5 delay : float, default=1.0 Number of seconds between retries. .. versionadded:: 1.5 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. target_names : numpy array of shape (5749,) Names of all persons in the dataset. Position in array corresponds to the person ID in the target array. DESCR : str Description of the Labeled Faces in the Wild (LFW) dataset. (data, target) : tuple if ``return_X_y`` is True A tuple of two ndarray. The first containing a 2D array of shape (n_samples, n_features) with each row representing one sample and each column representing the features. The second ndarray of shape (n_samples,) containing the target samples. .. versionadded:: 0.20 Examples -------- >>> from sklearn.datasets import fetch_lfw_people >>> lfw_people = fetch_lfw_people() >>> lfw_people.data.shape (13233, 2914) >>> lfw_people.target.shape (13233,) >>> for name in lfw_people.target_names[:5]: ... print(name) AJ Cook AJ Lamas Aaron Eckhart Aaron Guiel Aaron Patterson rr.r/r"r#z Loading LFW people faces from %srlocationcompressverbose)rMrhrSrRlfw.rst)dataZimagesr0rjDESCR) r7r&r,r cacherlreshaperHrr )rr.rMrhrSrRr/rpr"r#r r1m load_funcrWr0rjXfdescrr5r5r6fetch_lfw_peoples2      rc Cst|d}dd|D}Wdn1s.0Ydd|D}t|}tj|td} t} t|D]\} } t| dkrd| | <| d t| ddf| d t| d dff} n\t| d krd | | <| d t| ddf| d t| ddff} ntd | d| ft| D]j\}\}}zt||}Wn$t y\t|t |d }Yn0tt t |}t|||}| |qqjt| |||}t|j}|d }|d d |d |d ||_|| tddgfS)z}Perform the actual data loading for the LFW pairs dataset This operation is meant to be cached by a joblib wrapper. rbcSsg|]}|dqS) )decodestripsplit)r:lnr5r5r6r]r=z$_fetch_lfw_pairs..NcSsg|]}t|dkr|qS)r )rH)r:slr5r5r6r]r=r>rrrr zinvalid line %d: %rzUTF-8zDifferent personsz Same person)r-rHrIrJrGlistrKrdr TypeErrorstrrarappendrZshapepopinsertarray)index_file_pathr1rRrSrMZ index_file split_linesZ pair_specsZn_pairsr0rQrX componentspairjnameidxZ person_folder filenamesrYpairsrrVr5r5r6_fetch_lfw_pairssB ,    r>train10_foldstest) subsetrr.rMrSrRr/r"r#rc Cst|||||d\} } td|| t| ddd} | t} dddd } || vrltd |tt| ft | | |}| || |||d \}}}t d }t | t|d ||||dS)a8Load 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 `. 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 or path-like, 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 an OSError if the data is not locally available instead of trying to download the data from the source site. n_retries : int, default=3 Number of retries when HTTP errors are encountered. .. versionadded:: 1.5 delay : float, default=1.0 Number of seconds between retries. .. versionadded:: 1.5 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. target_names : numpy array of shape (2,) Explains the target values of the target array. 0 corresponds to "Different person", 1 corresponds to "same person". DESCR : str Description of the Labeled Faces in the Wild (LFW) dataset. Examples -------- >>> from sklearn.datasets import fetch_lfw_pairs >>> lfw_pairs_train = fetch_lfw_pairs(subset='train') >>> list(lfw_pairs_train.target_names) [np.str_('Different persons'), np.str_('Same person')] >>> lfw_pairs_train.pairs.shape (2200, 2, 62, 47) >>> lfw_pairs_train.data.shape (2200, 5828) >>> lfw_pairs_train.target.shape (2200,) ruzLoading %s LFW pairs from %srvrrwrrr)rrrz+subset='%s' is invalid: should be one of %r)rMrSrRr|r{)r}rr0rjr~)r7r&r,r rrrdrrakeysr rr rrH)rrr.rMrSrRr/r"r#r r1rrZlabel_filenamesrrr0rjrr5r5r6fetch_lfw_pairssB   r)NTTrr)NFNr)NFN)/__doc__loggingnumbersrrosrrrros.pathrr r numpyrIZjoblibr utilsr Zutils._param_validationrrrrZ utils.fixesrZ_baserrrr getLogger__name__r&r*r)r%r7rZrlrrAr@rrrr5r5r5r6s       2K +  ( 4