U mdL @s:dZddlmZmZmZddlmZmZmZddl Z ddl Z ddl m Z ddlmZmZmZmZdd lmZe eZed d d d Zedddd Zedddd edddd edddd fZd0ddZddZd1d d!Zddd"dded#d$ed%d&fddd'd(d)Zd2d*d+Z d,ddd"ded#d$ed%d&fdd-d.d/Z!dS)3zLabeled 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/ )listdirmakedirsremove)joinexistsisdirN)Memory) get_data_home _fetch_remoteRemoteFileMetadata load_descr)Bunchzlfw.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@ea42330c62c92989f9d7c03237ed5d591365e89b3e649747777b70e692dc1592Tc Cst|d}t|d}t|s$t|tD]D}t||j}t|s(|r`td|jt ||dq(t d|q(|rt|d}t }nt|d}t }t|s t||j}t|s|rtd|jt ||dn t d|d d l } td || |d j|d t|||fS)z0Helper function to download any missing LFW data) data_homelfw_homezDownloading LFW metadata: %s)dirnamez %s is missingZ lfw_funneledZlfwz!Downloading LFW data (~200MB): %srNz$Decompressing the data archive to %szr:gz)path)r rrrTARGETSrloggerinforr IOErrorFUNNELED_ARCHIVEARCHIVEtarfiledebugopen extractallr) rfunneleddownload_if_missingrtargetZtarget_filepathdata_folder_patharchive archive_pathrr)N/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/sklearn/datasets/_lfw.py_check_fetch_lfwJs8         r+cCszddlm}Wntk r,tdYnXtddtddf}|dkrP|}ntddt||D}|\}}|j|j|jpd}|j|j|jpd} |dk rt |}t ||}t || } t |} |st j | || ft jd } nt j | || d ft jd } t|D]\} } | d dkr0td | d| || }||j|j|j|jf}|dk rl|| |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)Nr)).0sZdsr)r)r* sz_load_imgs..r ZdtypeizLoading face #%05d / %05dzLFailed to read the image file %s, Please make sure that libjpeg is installedgo@r)Zaxis.)ZPILr, ImportErrorslicetuplezipstopstartstepfloatintlennpzerosZfloat32 enumeraterr r!cropresizeZasarrayndim RuntimeErrorZmean) file_pathsslice_colorrAr,Z default_sliceZh_sliceZw_slicehwn_facesfacesi file_pathZpil_imgZfacer)r)r* _load_imgsusT       rMFcsgg}}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|qSr))r)r.fZ folder_pathr)r* sz%_fetch_lfw_people.._ rz*min_faces_per_person=%d is too restrictive*)sortedrrrr<replaceextend ValueErrorr=uniqueZ searchsortedrMZarangerandomZ RandomStateshuffle)r&rErFrAmin_faces_per_personZ person_namesrDZ person_namepathsZ n_picturesrI target_namesr%rJindicesr)rOr*_fetch_lfw_peoples.       r_g?FN)rr#rAr[rFrEr$ return_X_ycCst|||d\}} td|t|ddd} | t} | | ||||d\} } }| t| d}td}|rr|| 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 ================= ======================= Read more in the :ref:`User Guide `. 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 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 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. 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 rr#r$z Loading LFW people faces from %srlocationcompressverbose)rAr[rFrElfw.rst)dataZimagesr%r]DESCR) r+rr rcacher_reshaper<r r)rr#rAr[rFrEr$rdrr&m load_funcrJr%r]Xfdescrr)r)r*fetch_lfw_peoples4^    ruc Cst|d}dd|D}W5QRXdd|D}t|}tj|td} t} t|D]\} } t| dkrd| | <| dt| ddf| dt| d dff} nZt| d krd| | <| dt| ddf| d t| ddff} ntd | d| ft| D]l\}\}}zt||}Wn&t k rHt|t |d }YnXtt t |}t|||}| |qqVt| |||}t|j}|d}|dd |d|d ||_|| td dgfS)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.lnr)r)r*rPwsz$_fetch_lfw_pairs..cSsg|]}t|dkr|qS)r)r<)r.slr)r)r*rPxs r1r2r rrzinvalid line %d: %rzUTF-8zDifferent personsz Same person)r!r<r=r>r;listr?rWr TypeErrorstrrTrappendrMshapepopinsertarray)index_file_pathr&rErFrAZ index_file split_linesZ pair_specsZn_pairsr%rDrK componentspairjnameidxZ person_folder filenamesrLpairsrrIr)r)r*_fetch_lfw_pairsmsB      rtrain)subsetrr#rArFrEr$cCst|||d\}}td||t|ddd} | t} dddd } || krhtd |tt| ft || |} | | ||||d \} }}t d }t | t| d | |||dS)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 `. 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. 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. rezLoading %s LFW pairs from %srfrrgrrr)rtestZ10_foldsz+subset='%s' is invalid: should be one of %r)rArFrErlrk)rmrr%r]rn)r+rr rrorrWr~rTkeysrr rrpr<)rrr#rArFrEr$rr&rqrrZlabel_filenamesrrr%r]rtr)r)r*fetch_lfw_pairssDZ   r)NTT)NFNr)NFN)"__doc__osrrros.pathrrrloggingnumpyr=Zjoblibr_baser r r r utilsr getLogger__name__rrrrr+rMr_r4rurrr)r)r)r*s~      +K -  6