V[ @sdZddlZddlZddlZddlZddlmZddlmZddlmZddlm Z ddlm Z ddlm Z dd lm Z dd lm Z dd lmZddlZd d lmZGdddeZdddZdddZdddddddddZddZddZdddZdd Zd!d"Zd#d$Zd%d&Zd'd(Zd)d*Z dS)+z Base IO code for all datasets N)environ)dirname)join)exists) expanduser)isdir)splitext)listdir)makedirs)check_random_statec@sFeZdZdZddZddZddZdd Zd S) BunchzContainer object for datasets Dictionary-like object that exposes its keys as attributes. >>> b = Bunch(a=1, b=2) >>> b['b'] 2 >>> b.b 2 >>> b.a = 3 >>> b['a'] 3 >>> b.c = 6 >>> b['c'] 6 cKstj||dS)N)dict__init__)selfkwargsrP/s/python-3.5.2/amd64_ubu14/lib/python3.5/site-packages/sklearn/datasets/base.pyr0szBunch.__init__cCs|||`. Parameters ---------- container_path : string or unicode Path to the main folder holding one subfolder per category description: string or unicode, optional (default=None) A paragraph describing the characteristic of the dataset: its source, reference, etc. categories : A collection of strings or None, optional (default=None) If None (default), load all the categories. If not None, list of category names to load (other categories ignored). load_content : boolean, optional (default=True) Whether to load or not the content of the different files. If true a 'data' attribute containing the text information is present in the data structure returned. If not, a filenames attribute gives the path to the files. encoding : string or None (default is None) If None, do not try to decode the content of the files (e.g. for images or other non-text content). If not None, encoding to use to decode text files to Unicode if load_content is True. decode_error: {'strict', 'ignore', 'replace'}, optional Instruction on what to do if a byte sequence is given to analyze that contains characters not of the given `encoding`. Passed as keyword argument 'errors' to bytes.decode. shuffle : bool, optional (default=True) Whether or not to shuffle the data: might be important for models that make the assumption that the samples are independent and identically distributed (i.i.d.), such as stochastic gradient descent. random_state : int, RandomState instance or None, optional (default=0) 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`. Returns ------- data : Bunch Dictionary-like object, the interesting attributes are: either data, the raw text data to learn, or 'filenames', the files holding it, 'target', the classification labels (integer index), 'target_names', the meaning of the labels, and 'DESCR', the full description of the dataset. cs+g|]!}tt|r|qSr)rr).0f)container_pathrr s zload_files..Ncs"g|]}|kr|qSrr)r(r)) categoriesrrr+s csg|]}t|qSr)r)r(d) folder_pathrrr+s rrbcs"g|]}|jqSr)decode)r(r-) decode_errorencodingrrr+s data filenames target_namestargetDESCR)sortedr enumerateappendrextendlennparrayr arangeshapeshuffleopenreadr )r* descriptionr,Z load_contentrAr2r1Z random_stater6r5r4ZfolderslabelZfolderZ documentsindicesr3filenamer)r)r,r*r1r2r.r load_filesfsJ\%          rHc Csttt}tt|dd}tj|}t|}t|d}t|d}tj |dd}tj ||f}tj |fdtj}x`t |D]R\} } tj | dddtj || `. Returns ------- data : Bunch Dictionary-like object, the interesting attributes are: 'data', the data to learn, 'target', the classification labels, 'target_names', the meaning of the labels, 'feature_names', the meaning of the features, and 'DESCR', the full description of the dataset. Examples -------- Let's say you are interested in the samples 10, 25, and 50, and want to know their class name. >>> from sklearn.datasets import load_iris >>> data = load_iris() >>> data.target[[10, 25, 50]] array([0, 0, 1]) >>> list(data.target_names) ['setosa', 'versicolor', 'virginica'] r3ziris.csvrr Ndtypedescrziris.rstr6r5r7 feature_nameszsepal length (cm)zsepal width (cm)zpetal length (cm)zpetal width (cm)rM)r__file__rBrcsvreadernextintr=r>emptyr9asarrayfloatrCr ) module_pathcsv_file data_filetemp n_samples n_featuresr5r3r6iZirrst_filefdescrrrr load_iriss&%  &+r_c-Cstt}tt|dd}tj|}t|}t|d}t|d}tj |dd}tj ||f}tj |fdtj}x`t |D]R\} } tj | dd-dtj || >> from sklearn.datasets import load_breast_cancer >>> data = load_breast_cancer() >>> data.target[[10, 50, 85]] array([0, 1, 0]) >>> list(data.target_names) ['malignant', 'benign'] r3zbreast_cancer.csvrrIr rJNrKzbreast_cancer.rstz mean radiusz mean texturezmean perimeterz mean areazmean smoothnesszmean compactnesszmean concavityzmean concave pointsz mean symmetryzmean fractal dimensionz radius errorz texture errorzperimeter errorz area errorzsmoothness errorzcompactness errorzconcavity errorzconcave points errorzsymmetry errorzfractal dimension errorz worst radiusz worst texturezworst perimeterz worst areazworst smoothnesszworst compactnesszworst concavityzworst concave pointszworst symmetryzworst fractal dimensionr6r5r7rLrMrM)rrNrBrrOrPrQrRr=r>rSr9rTrUrCr )rVrWrX first_linerZr[r5r3r6countrr]r^rLrrrload_breast_cancer/sB'  &+ rc c Cstt}tjt|dddd}tt|dd}|j}WdQRX|dddf}|ddddf}|j}d|_|d kr||k}||||}}||}t d|d |j tj d tj d d |d|S)a/Load and return the digits dataset (classification). Each datapoint is a 8x8 image of a digit. ================= ============== Classes 10 Samples per class ~180 Samples total 1797 Dimensionality 64 Features integers 0-16 ================= ============== Read more in the :ref:`User Guide `. Parameters ---------- n_class : integer, between 0 and 10, optional (default=10) The number of classes to return. Returns ------- data : Bunch Dictionary-like object, the interesting attributes are: 'data', the data to learn, 'images', the images corresponding to each sample, 'target', the classification labels for each sample, 'target_names', the meaning of the labels, and 'DESCR', the full description of the dataset. Examples -------- To load the data and visualize the images:: >>> from sklearn.datasets import load_digits >>> digits = load_digits() >>> print(digits.data.shape) (1797, 64) >>> import pylab as pl #doctest: +SKIP >>> pl.gray() #doctest: +SKIP >>> pl.matshow(digits.images[0]) #doctest: +SKIP >>> pl.show() #doctest: +SKIP r3z digits.csv.gz delimiter,rKz digits.rstNrIrdr6r5imagesr7rMrMrM)rMrgrg) rrNr=loadtxtrrBrCviewr@r astyperRr?) Zn_classrVr3r)rKr6Z flat_datarhidxrrr load_digits}s$*        rmcCsXtttd}tjt|d}tjt|d}td|d|S)aLoad and return the diabetes dataset (regression). ============== ================== Samples total 442 Dimensionality 10 Features real, -.2 < x < .2 Targets integer 25 - 346 ============== ================== Read more in the :ref:`User Guide `. Returns ------- data : Bunch Dictionary-like object, the interesting attributes are: 'data', the data to learn and 'target', the regression target for each sample. r3zdiabetes_data.csv.gzzdiabetes_target.csv.gzr6)rrrNr=rir )base_dirr3r6rrr load_diabetessroc Cstttd}tj|ddd}tj|ddd}t|d}|jj}WdQRXt|d}|jj}WdQRXtttd}|j}WdQRXt d|d |d |d |d |S) aLoad and return the linnerud dataset (multivariate regression). Samples total: 20 Dimensionality: 3 for both data and targets Features: integer Targets: integer Returns ------- data : Bunch Dictionary-like object, the interesting attributes are: 'data' and 'targets', the two multivariate datasets, with 'data' corresponding to the exercise and 'targets' corresponding to the physiological measurements, as well as 'feature_names' and 'target_names'. zdata/zlinnerud_exercise.csvskiprowsrIzlinnerud_physiological.csvNz/descr/linnerud.rstr3rLr6r5r7) rrrNr=rirBreadlinesplitrCr )rnZ data_exerciseZdata_physiologicalr)Zheader_exerciseZheader_physiologicalrKrrr load_linneruds rscCsqtt}t|dd}t|}|j}WdQRXt|dd}t|}tj|}t|}t|d}t|d}t j ||f} t j |f} t|}t j |} x`t |D]R\} } t j | dd dt j| | >> from sklearn.datasets import load_boston >>> boston = load_boston() >>> print(boston.data.shape) (506, 13) rKzboston_house_prices.rstNr3zboston_house_prices.csvrrIrJr6rLr7rMrMrM)rrNrrBrCrOrPrQrRr=rSr>r9rTrUr )rVZ fdescr_namer)Z descr_textZdata_file_namerXrYrZr[r3r6rLr\r-rrr load_bostons*   &+ rtcsy=yddlmWn"tk r;ddlmYnXWntk r]tdYnXtttdttd}|j}WdQRXfddt j D}fd d|D}t d|d |d |S) a-Load sample images for image manipulation. Loads both, ``china`` and ``flower``. Returns ------- data : Bunch Dictionary-like object with the following attributes : 'images', the two sample images, 'filenames', the file names for the images, and 'DESCR' the full description of the dataset. Examples -------- To load the data and visualize the images: >>> from sklearn.datasets import load_sample_images >>> dataset = load_sample_images() #doctest: +SKIP >>> len(dataset.images) #doctest: +SKIP 2 >>> first_img_data = dataset.images[0] #doctest: +SKIP >>> first_img_data.shape #doctest: +SKIP (427, 640, 3) >>> first_img_data.dtype #doctest: +SKIP dtype('uint8') r)imreadzIThe Python Imaging Library (PIL) is required to load data from jpeg filesrhz README.txtNcs.g|]$}|jdrt|qS)z.jpg)endswithr)r(rG)rVrrr+Ts z&load_sample_images..csg|]}|qSrr)r(rG)rurrr+Xs r4r7) Z scipy.miscru ImportErrorZscipy.misc.pilutilrrrNrBrCosr r )r)rKr4rhr)rurVrload_sample_images-s    rycCslt}d}x3t|jD]"\}}|j|r|}PqW|dkratd||j|S)a:Load the numpy array of a single sample image Parameters ----------- image_name: {`china.jpg`, `flower.jpg`} The name of the sample image loaded Returns ------- img: 3D array The image as a numpy array: height x width x color Examples --------- >>> from sklearn.datasets import load_sample_image >>> china = load_sample_image('china.jpg') # doctest: +SKIP >>> china.dtype # doctest: +SKIP dtype('uint8') >>> china.shape # doctest: +SKIP (427, 640, 3) >>> flower = load_sample_image('flower.jpg') # doctest: +SKIP >>> flower.dtype # doctest: +SKIP dtype('uint8') >>> flower.shape # doctest: +SKIP (427, 640, 3) NzCannot find sample image: %s)ryr9r4rvrrh)Z image_namerhindexr\rGrrrload_sample_image_s  r{cOsj|jdd}t|d\}}tjddkrE||7}|dd||f}t|S) aEnsure different filenames for Python 2 and Python 3 pickles An object pickled under Python 3 cannot be loaded under Python 2. An object pickled under Python 2 can sometimes not be loaded loaded correctly under Python 3 because some Python 2 strings are decoded as Python 3 strings which can be problematic for objects that use Python 2 strings as byte buffers for numerical data instead of "real" strings. Therefore, dataset loaders in scikit-learn use different files for pickles manages by Python 2 and Python 3 in the same SCIKIT_LEARN_DATA folder so as to avoid conflicts. args[-1] is expected to be the ".pkl" filename. Under Python 3, a suffix is inserted before the extension to s _pkl_filepath('/path/to/folder', 'filename.pkl') returns: - /path/to/folder/filename.pkl under Python 2 - /path/to/folder/filename_py3.pkl under Python 3+ py3_suffixZ_py3rIrNrMrM)r!rsys version_infor)argsrr|basenameextZnew_argsrrr _pkl_filepaths  r)!rrxrOr~r$ros.pathrrrrrrr r numpyr=utilsr rr r#r&rHr_rcrmrorsrtryr{rrrrrs<     +  = N@  # 4 2 '