""" Base IO code for all datasets """ # Copyright (c) 2007 David Cournapeau # 2010 Fabian Pedregosa # 2010 Olivier Grisel # License: BSD 3 clause import csv import hashlib import os import shutil from collections import namedtuple from os import environ, listdir, makedirs from os.path import dirname, exists, expanduser, isdir, join, splitext from ..utils import Bunch from ..utils import check_random_state from ..utils import check_pandas_support from ..utils.validation import _deprecate_positional_args import numpy as np from urllib.request import urlretrieve RemoteFileMetadata = namedtuple('RemoteFileMetadata', ['filename', 'url', 'checksum']) def get_data_home(data_home=None) -> str: """Return the path of the scikit-learn data dir. This folder is used by some large dataset loaders to avoid downloading the data several times. By default the data dir is set to a folder named 'scikit_learn_data' in the user home folder. Alternatively, it can be set by the 'SCIKIT_LEARN_DATA' environment variable or programmatically by giving an explicit folder path. The '~' symbol is expanded to the user home folder. If the folder does not already exist, it is automatically created. Parameters ---------- data_home : str, default=None The path to scikit-learn data directory. If `None`, the default path is `~/sklearn_learn_data`. """ if data_home is None: data_home = environ.get('SCIKIT_LEARN_DATA', join('~', 'scikit_learn_data')) data_home = expanduser(data_home) if not exists(data_home): makedirs(data_home) return data_home def clear_data_home(data_home=None): """Delete all the content of the data home cache. Parameters ---------- data_home : str, default=None The path to scikit-learn data directory. If `None`, the default path is `~/sklearn_learn_data`. """ data_home = get_data_home(data_home) shutil.rmtree(data_home) def _convert_data_dataframe(caller_name, data, target, feature_names, target_names, sparse_data=False): pd = check_pandas_support('{} with as_frame=True'.format(caller_name)) if not sparse_data: data_df = pd.DataFrame(data, columns=feature_names) else: data_df = pd.DataFrame.sparse.from_spmatrix( data, columns=feature_names ) target_df = pd.DataFrame(target, columns=target_names) combined_df = pd.concat([data_df, target_df], axis=1) X = combined_df[feature_names] y = combined_df[target_names] if y.shape[1] == 1: y = y.iloc[:, 0] return combined_df, X, y @_deprecate_positional_args def load_files(container_path, *, description=None, categories=None, load_content=True, shuffle=True, encoding=None, decode_error='strict', random_state=0): """Load text files with categories as subfolder names. Individual samples are assumed to be files stored a two levels folder structure such as the following: container_folder/ category_1_folder/ file_1.txt file_2.txt ... file_42.txt category_2_folder/ file_43.txt file_44.txt ... The folder names are used as supervised signal label names. The individual file names are not important. This function does not try to extract features into a numpy array or scipy sparse matrix. In addition, if load_content is false it does not try to load the files in memory. To use text files in a scikit-learn classification or clustering algorithm, you will need to use the :mod`~sklearn.feature_extraction.text` module to build a feature extraction transformer that suits your problem. If you set load_content=True, you should also specify the encoding of the text using the 'encoding' parameter. For many modern text files, 'utf-8' will be the correct encoding. If you leave encoding equal to None, then the content will be made of bytes instead of Unicode, and you will not be able to use most functions in :mod:`~sklearn.feature_extraction.text`. Similar feature extractors should be built for other kind of unstructured data input such as images, audio, video, ... Read more in the :ref:`User Guide `. Parameters ---------- container_path : str or unicode Path to the main folder holding one subfolder per category description : str or unicode, default=None A paragraph describing the characteristic of the dataset: its source, reference, etc. categories : list of str, default=None If None (default), load all the categories. If not None, list of category names to load (other categories ignored). load_content : bool, 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. shuffle : bool, 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. encoding : str, default=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'}, default='strict' 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. random_state : int, RandomState instance or None, default=0 Determines random number generation for dataset shuffling. Pass an int for reproducible output across multiple function calls. See :term:`Glossary `. Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : list of str Only present when `load_content=True`. The raw text data to learn. target : ndarray The target labels (integer index). target_names : list The names of target classes. DESCR : str The full description of the dataset. filenames: ndarray The filenames holding the dataset. """ target = [] target_names = [] filenames = [] folders = [f for f in sorted(listdir(container_path)) if isdir(join(container_path, f))] if categories is not None: folders = [f for f in folders if f in categories] for label, folder in enumerate(folders): target_names.append(folder) folder_path = join(container_path, folder) documents = [join(folder_path, d) for d in sorted(listdir(folder_path))] target.extend(len(documents) * [label]) filenames.extend(documents) # convert to array for fancy indexing filenames = np.array(filenames) target = np.array(target) if shuffle: random_state = check_random_state(random_state) indices = np.arange(filenames.shape[0]) random_state.shuffle(indices) filenames = filenames[indices] target = target[indices] if load_content: data = [] for filename in filenames: with open(filename, 'rb') as f: data.append(f.read()) if encoding is not None: data = [d.decode(encoding, decode_error) for d in data] return Bunch(data=data, filenames=filenames, target_names=target_names, target=target, DESCR=description) return Bunch(filenames=filenames, target_names=target_names, target=target, DESCR=description) def load_data(module_path, data_file_name): """Loads data from module_path/data/data_file_name. Parameters ---------- module_path : string The module path. data_file_name : string Name of csv file to be loaded from module_path/data/data_file_name. For example 'wine_data.csv'. Returns ------- data : Numpy array A 2D array with each row representing one sample and each column representing the features of a given sample. target : Numpy array A 1D array holding target variables for all the samples in `data. For example target[0] is the target varible for data[0]. target_names : Numpy array A 1D array containing the names of the classifications. For example target_names[0] is the name of the target[0] class. """ with open(join(module_path, 'data', data_file_name)) as csv_file: data_file = csv.reader(csv_file) temp = next(data_file) n_samples = int(temp[0]) n_features = int(temp[1]) target_names = np.array(temp[2:]) data = np.empty((n_samples, n_features)) target = np.empty((n_samples,), dtype=int) for i, ir in enumerate(data_file): data[i] = np.asarray(ir[:-1], dtype=np.float64) target[i] = np.asarray(ir[-1], dtype=int) return data, target, target_names @_deprecate_positional_args def load_wine(*, return_X_y=False, as_frame=False): """Load and return the wine dataset (classification). .. versionadded:: 0.18 The wine dataset is a classic and very easy multi-class classification dataset. ================= ============== Classes 3 Samples per class [59,71,48] Samples total 178 Dimensionality 13 Features real, positive ================= ============== Read more in the :ref:`User Guide `. Parameters ---------- return_X_y : bool, default=False If True, returns ``(data, target)`` instead of a Bunch object. See below for more information about the `data` and `target` object. as_frame : bool, default=False If True, the data is a pandas DataFrame including columns with appropriate dtypes (numeric). The target is a pandas DataFrame or Series depending on the number of target columns. If `return_X_y` is True, then (`data`, `target`) will be pandas DataFrames or Series as described below. .. versionadded:: 0.23 Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : {ndarray, dataframe} of shape (178, 13) The data matrix. If `as_frame=True`, `data` will be a pandas DataFrame. target: {ndarray, Series} of shape (178,) The classification target. If `as_frame=True`, `target` will be a pandas Series. feature_names: list The names of the dataset columns. target_names: list The names of target classes. frame: DataFrame of shape (178, 14) Only present when `as_frame=True`. DataFrame with `data` and `target`. .. versionadded:: 0.23 DESCR: str The full description of the dataset. (data, target) : tuple if ``return_X_y`` is True The copy of UCI ML Wine Data Set dataset is downloaded and modified to fit standard format from: https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data Examples -------- Let's say you are interested in the samples 10, 80, and 140, and want to know their class name. >>> from sklearn.datasets import load_wine >>> data = load_wine() >>> data.target[[10, 80, 140]] array([0, 1, 2]) >>> list(data.target_names) ['class_0', 'class_1', 'class_2'] """ module_path = dirname(__file__) data, target, target_names = load_data(module_path, 'wine_data.csv') with open(join(module_path, 'descr', 'wine_data.rst')) as rst_file: fdescr = rst_file.read() feature_names = ['alcohol', 'malic_acid', 'ash', 'alcalinity_of_ash', 'magnesium', 'total_phenols', 'flavanoids', 'nonflavanoid_phenols', 'proanthocyanins', 'color_intensity', 'hue', 'od280/od315_of_diluted_wines', 'proline'] frame = None target_columns = ['target', ] if as_frame: frame, data, target = _convert_data_dataframe("load_wine", data, target, feature_names, target_columns) if return_X_y: return data, target return Bunch(data=data, target=target, frame=frame, target_names=target_names, DESCR=fdescr, feature_names=feature_names) @_deprecate_positional_args def load_iris(*, return_X_y=False, as_frame=False): """Load and return the iris dataset (classification). The iris dataset is a classic and very easy multi-class classification dataset. ================= ============== Classes 3 Samples per class 50 Samples total 150 Dimensionality 4 Features real, positive ================= ============== Read more in the :ref:`User Guide `. Parameters ---------- return_X_y : bool, default=False If True, returns ``(data, target)`` instead of a Bunch object. See below for more information about the `data` and `target` object. .. versionadded:: 0.18 as_frame : bool, default=False If True, the data is a pandas DataFrame including columns with appropriate dtypes (numeric). The target is a pandas DataFrame or Series depending on the number of target columns. If `return_X_y` is True, then (`data`, `target`) will be pandas DataFrames or Series as described below. .. versionadded:: 0.23 Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : {ndarray, dataframe} of shape (150, 4) The data matrix. If `as_frame=True`, `data` will be a pandas DataFrame. target: {ndarray, Series} of shape (150,) The classification target. If `as_frame=True`, `target` will be a pandas Series. feature_names: list The names of the dataset columns. target_names: list The names of target classes. frame: DataFrame of shape (150, 5) Only present when `as_frame=True`. DataFrame with `data` and `target`. .. versionadded:: 0.23 DESCR: str The full description of the dataset. filename: str The path to the location of the data. .. versionadded:: 0.20 (data, target) : tuple if ``return_X_y`` is True .. versionadded:: 0.18 Notes ----- .. versionchanged:: 0.20 Fixed two wrong data points according to Fisher's paper. The new version is the same as in R, but not as in the UCI Machine Learning Repository. 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'] """ module_path = dirname(__file__) data, target, target_names = load_data(module_path, 'iris.csv') iris_csv_filename = join(module_path, 'data', 'iris.csv') with open(join(module_path, 'descr', 'iris.rst')) as rst_file: fdescr = rst_file.read() feature_names = ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)'] frame = None target_columns = ['target', ] if as_frame: frame, data, target = _convert_data_dataframe("load_iris", data, target, feature_names, target_columns) if return_X_y: return data, target return Bunch(data=data, target=target, frame=frame, target_names=target_names, DESCR=fdescr, feature_names=feature_names, filename=iris_csv_filename) @_deprecate_positional_args def load_breast_cancer(*, return_X_y=False, as_frame=False): """Load and return the breast cancer wisconsin dataset (classification). The breast cancer dataset is a classic and very easy binary classification dataset. ================= ============== Classes 2 Samples per class 212(M),357(B) Samples total 569 Dimensionality 30 Features real, positive ================= ============== Read more in the :ref:`User Guide `. Parameters ---------- return_X_y : bool, default=False If True, returns ``(data, target)`` instead of a Bunch object. See below for more information about the `data` and `target` object. .. versionadded:: 0.18 as_frame : bool, default=False If True, the data is a pandas DataFrame including columns with appropriate dtypes (numeric). The target is a pandas DataFrame or Series depending on the number of target columns. If `return_X_y` is True, then (`data`, `target`) will be pandas DataFrames or Series as described below. .. versionadded:: 0.23 Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : {ndarray, dataframe} of shape (569, 30) The data matrix. If `as_frame=True`, `data` will be a pandas DataFrame. target: {ndarray, Series} of shape (569,) The classification target. If `as_frame=True`, `target` will be a pandas Series. feature_names: list The names of the dataset columns. target_names: list The names of target classes. frame: DataFrame of shape (569, 31) Only present when `as_frame=True`. DataFrame with `data` and `target`. .. versionadded:: 0.23 DESCR: str The full description of the dataset. filename: str The path to the location of the data. .. versionadded:: 0.20 (data, target) : tuple if ``return_X_y`` is True .. versionadded:: 0.18 The copy of UCI ML Breast Cancer Wisconsin (Diagnostic) dataset is downloaded from: https://goo.gl/U2Uwz2 Examples -------- Let's say you are interested in the samples 10, 50, and 85, and want to know their class name. >>> 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'] """ module_path = dirname(__file__) data, target, target_names = load_data(module_path, 'breast_cancer.csv') csv_filename = join(module_path, 'data', 'breast_cancer.csv') with open(join(module_path, 'descr', 'breast_cancer.rst')) as rst_file: fdescr = rst_file.read() feature_names = np.array(['mean radius', 'mean texture', 'mean perimeter', 'mean area', 'mean smoothness', 'mean compactness', 'mean concavity', 'mean concave points', 'mean symmetry', 'mean fractal dimension', 'radius error', 'texture error', 'perimeter error', 'area error', 'smoothness error', 'compactness error', 'concavity error', 'concave points error', 'symmetry error', 'fractal dimension error', 'worst radius', 'worst texture', 'worst perimeter', 'worst area', 'worst smoothness', 'worst compactness', 'worst concavity', 'worst concave points', 'worst symmetry', 'worst fractal dimension']) frame = None target_columns = ['target', ] if as_frame: frame, data, target = _convert_data_dataframe("load_breast_cancer", data, target, feature_names, target_columns) if return_X_y: return data, target return Bunch(data=data, target=target, frame=frame, target_names=target_names, DESCR=fdescr, feature_names=feature_names, filename=csv_filename) @_deprecate_positional_args def load_digits(*, n_class=10, return_X_y=False, as_frame=False): """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 : int, default=10 The number of classes to return. Between 0 and 10. return_X_y : bool, default=False If True, returns ``(data, target)`` instead of a Bunch object. See below for more information about the `data` and `target` object. .. versionadded:: 0.18 as_frame : bool, default=False If True, the data is a pandas DataFrame including columns with appropriate dtypes (numeric). The target is a pandas DataFrame or Series depending on the number of target columns. If `return_X_y` is True, then (`data`, `target`) will be pandas DataFrames or Series as described below. .. versionadded:: 0.23 Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : {ndarray, dataframe} of shape (1797, 64) The flattened data matrix. If `as_frame=True`, `data` will be a pandas DataFrame. target: {ndarray, Series} of shape (1797,) The classification target. If `as_frame=True`, `target` will be a pandas Series. feature_names: list The names of the dataset columns. target_names: list The names of target classes. .. versionadded:: 0.20 frame: DataFrame of shape (1797, 65) Only present when `as_frame=True`. DataFrame with `data` and `target`. .. versionadded:: 0.23 images: {ndarray} of shape (1797, 8, 8) The raw image data. DESCR: str The full description of the dataset. (data, target) : tuple if ``return_X_y`` is True .. versionadded:: 0.18 This is a copy of the test set of the UCI ML hand-written digits datasets https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits 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 matplotlib.pyplot as plt #doctest: +SKIP >>> plt.gray() #doctest: +SKIP >>> plt.matshow(digits.images[0]) #doctest: +SKIP >>> plt.show() #doctest: +SKIP """ module_path = dirname(__file__) data = np.loadtxt(join(module_path, 'data', 'digits.csv.gz'), delimiter=',') with open(join(module_path, 'descr', 'digits.rst')) as f: descr = f.read() target = data[:, -1].astype(int, copy=False) flat_data = data[:, :-1] images = flat_data.view() images.shape = (-1, 8, 8) if n_class < 10: idx = target < n_class flat_data, target = flat_data[idx], target[idx] images = images[idx] feature_names = ['pixel_{}_{}'.format(row_idx, col_idx) for row_idx in range(8) for col_idx in range(8)] frame = None target_columns = ['target', ] if as_frame: frame, flat_data, target = _convert_data_dataframe("load_digits", flat_data, target, feature_names, target_columns) if return_X_y: return flat_data, target return Bunch(data=flat_data, target=target, frame=frame, feature_names=feature_names, target_names=np.arange(10), images=images, DESCR=descr) @_deprecate_positional_args def load_diabetes(*, return_X_y=False, as_frame=False): """Load 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 `. Parameters ---------- return_X_y : bool, default=False. If True, returns ``(data, target)`` instead of a Bunch object. See below for more information about the `data` and `target` object. .. versionadded:: 0.18 as_frame : bool, default=False If True, the data is a pandas DataFrame including columns with appropriate dtypes (numeric). The target is a pandas DataFrame or Series depending on the number of target columns. If `return_X_y` is True, then (`data`, `target`) will be pandas DataFrames or Series as described below. .. versionadded:: 0.23 Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : {ndarray, dataframe} of shape (442, 10) The data matrix. If `as_frame=True`, `data` will be a pandas DataFrame. target: {ndarray, Series} of shape (442,) The regression target. If `as_frame=True`, `target` will be a pandas Series. feature_names: list The names of the dataset columns. frame: DataFrame of shape (442, 11) Only present when `as_frame=True`. DataFrame with `data` and `target`. .. versionadded:: 0.23 DESCR: str The full description of the dataset. data_filename: str The path to the location of the data. target_filename: str The path to the location of the target. (data, target) : tuple if ``return_X_y`` is True .. versionadded:: 0.18 """ module_path = dirname(__file__) base_dir = join(module_path, 'data') data_filename = join(base_dir, 'diabetes_data.csv.gz') data = np.loadtxt(data_filename) target_filename = join(base_dir, 'diabetes_target.csv.gz') target = np.loadtxt(target_filename) with open(join(module_path, 'descr', 'diabetes.rst')) as rst_file: fdescr = rst_file.read() feature_names = ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6'] frame = None target_columns = ['target', ] if as_frame: frame, data, target = _convert_data_dataframe("load_diabetes", data, target, feature_names, target_columns) if return_X_y: return data, target return Bunch(data=data, target=target, frame=frame, DESCR=fdescr, feature_names=feature_names, data_filename=data_filename, target_filename=target_filename) @_deprecate_positional_args def load_linnerud(*, return_X_y=False, as_frame=False): """Load and return the physical excercise linnerud dataset. This dataset is suitable for multi-ouput regression tasks. ============== ============================ Samples total 20 Dimensionality 3 (for both data and target) Features integer Targets integer ============== ============================ Read more in the :ref:`User Guide `. Parameters ---------- return_X_y : bool, default=False If True, returns ``(data, target)`` instead of a Bunch object. See below for more information about the `data` and `target` object. .. versionadded:: 0.18 as_frame : bool, default=False If True, the data is a pandas DataFrame including columns with appropriate dtypes (numeric, string or categorical). The target is a pandas DataFrame or Series depending on the number of target columns. If `return_X_y` is True, then (`data`, `target`) will be pandas DataFrames or Series as described below. .. versionadded:: 0.23 Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : {ndarray, dataframe} of shape (20, 3) The data matrix. If `as_frame=True`, `data` will be a pandas DataFrame. target: {ndarray, dataframe} of shape (20, 3) The regression targets. If `as_frame=True`, `target` will be a pandas DataFrame. feature_names: list The names of the dataset columns. target_names: list The names of the target columns. frame: DataFrame of shape (20, 6) Only present when `as_frame=True`. DataFrame with `data` and `target`. .. versionadded:: 0.23 DESCR: str The full description of the dataset. data_filename: str The path to the location of the data. target_filename: str The path to the location of the target. .. versionadded:: 0.20 (data, target) : tuple if ``return_X_y`` is True .. versionadded:: 0.18 """ base_dir = join(dirname(__file__), 'data/') data_filename = join(base_dir, 'linnerud_exercise.csv') target_filename = join(base_dir, 'linnerud_physiological.csv') # Read data data_exercise = np.loadtxt(data_filename, skiprows=1) data_physiological = np.loadtxt(target_filename, skiprows=1) # Read header with open(data_filename) as f: header_exercise = f.readline().split() with open(target_filename) as f: header_physiological = f.readline().split() with open(dirname(__file__) + '/descr/linnerud.rst') as f: descr = f.read() frame = None if as_frame: (frame, data_exercise, data_physiological) = _convert_data_dataframe("load_linnerud", data_exercise, data_physiological, header_exercise, header_physiological) if return_X_y: return data_exercise, data_physiological return Bunch(data=data_exercise, feature_names=header_exercise, target=data_physiological, target_names=header_physiological, frame=frame, DESCR=descr, data_filename=data_filename, target_filename=target_filename) @_deprecate_positional_args def load_boston(*, return_X_y=False): """Load and return the boston house-prices dataset (regression). ============== ============== Samples total 506 Dimensionality 13 Features real, positive Targets real 5. - 50. ============== ============== Read more in the :ref:`User Guide `. Parameters ---------- return_X_y : bool, default=False If True, returns ``(data, target)`` instead of a Bunch object. See below for more information about the `data` and `target` object. .. versionadded:: 0.18 Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : ndarray of shape (506, 13) The data matrix. target : ndarray of shape (506, ) The regression target. filename : str The physical location of boston csv dataset. .. versionadded:: 0.20 DESCR : str The full description of the dataset. feature_names : ndarray The names of features (data, target) : tuple if ``return_X_y`` is True .. versionadded:: 0.18 Notes ----- .. versionchanged:: 0.20 Fixed a wrong data point at [445, 0]. Examples -------- >>> from sklearn.datasets import load_boston >>> X, y = load_boston(return_X_y=True) >>> print(X.shape) (506, 13) """ module_path = dirname(__file__) fdescr_name = join(module_path, 'descr', 'boston_house_prices.rst') with open(fdescr_name) as f: descr_text = f.read() data_file_name = join(module_path, 'data', 'boston_house_prices.csv') with open(data_file_name) as f: data_file = csv.reader(f) temp = next(data_file) n_samples = int(temp[0]) n_features = int(temp[1]) data = np.empty((n_samples, n_features)) target = np.empty((n_samples,)) temp = next(data_file) # names of features feature_names = np.array(temp) for i, d in enumerate(data_file): data[i] = np.asarray(d[:-1], dtype=np.float64) target[i] = np.asarray(d[-1], dtype=np.float64) if return_X_y: return data, target return Bunch(data=data, target=target, # last column is target value feature_names=feature_names[:-1], DESCR=descr_text, filename=data_file_name) def load_sample_images(): """Load sample images for image manipulation. Loads both, ``china`` and ``flower``. Read more in the :ref:`User Guide `. Returns ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. images : list of ndarray of shape (427, 640, 3) The two sample image. filenames : list The filenames for the images. DESCR : str 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') """ # import PIL only when needed from ..externals._pilutil import imread module_path = join(dirname(__file__), "images") with open(join(module_path, 'README.txt')) as f: descr = f.read() filenames = [join(module_path, filename) for filename in sorted(os.listdir(module_path)) if filename.endswith(".jpg")] # Load image data for each image in the source folder. images = [imread(filename) for filename in filenames] return Bunch(images=images, filenames=filenames, DESCR=descr) def load_sample_image(image_name): """Load the numpy array of a single sample image Read more in the :ref:`User Guide `. 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) """ images = load_sample_images() index = None for i, filename in enumerate(images.filenames): if filename.endswith(image_name): index = i break if index is None: raise AttributeError("Cannot find sample image: %s" % image_name) return images.images[index] def _pkl_filepath(*args, **kwargs): """Return filename for Python 3 pickles args[-1] is expected to be the ".pkl" filename. For compatibility with older scikit-learn versions, a suffix is inserted before the extension. _pkl_filepath('/path/to/folder', 'filename.pkl') returns '/path/to/folder/filename_py3.pkl' """ py3_suffix = kwargs.get("py3_suffix", "_py3") basename, ext = splitext(args[-1]) basename += py3_suffix new_args = args[:-1] + (basename + ext,) return join(*new_args) def _sha256(path): """Calculate the sha256 hash of the file at path.""" sha256hash = hashlib.sha256() chunk_size = 8192 with open(path, "rb") as f: while True: buffer = f.read(chunk_size) if not buffer: break sha256hash.update(buffer) return sha256hash.hexdigest() def _fetch_remote(remote, dirname=None): """Helper function to download a remote dataset into path Fetch a dataset pointed by remote's url, save into path using remote's filename and ensure its integrity based on the SHA256 Checksum of the downloaded file. Parameters ---------- remote : RemoteFileMetadata Named tuple containing remote dataset meta information: url, filename and checksum dirname : string Directory to save the file to. Returns ------- file_path: string Full path of the created file. """ file_path = (remote.filename if dirname is None else join(dirname, remote.filename)) urlretrieve(remote.url, file_path) checksum = _sha256(file_path) if remote.checksum != checksum: raise IOError("{} has an SHA256 checksum ({}) " "differing from expected ({}), " "file may be corrupted.".format(file_path, checksum, remote.checksum)) return file_path