/usr/lib/python3/dist-packages/sklearn/datasets/base.py is in python3-sklearn 0.17.0-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 | """
Base IO code for all datasets
"""
# Copyright (c) 2007 David Cournapeau <cournape@gmail.com>
# 2010 Fabian Pedregosa <fabian.pedregosa@inria.fr>
# 2010 Olivier Grisel <olivier.grisel@ensta.org>
# License: BSD 3 clause
import os
import csv
import sys
import shutil
from os import environ
from os.path import dirname
from os.path import join
from os.path import exists
from os.path import expanduser
from os.path import isdir
from os.path import splitext
from os import listdir
from os import makedirs
import numpy as np
from ..utils import check_random_state
class Bunch(dict):
"""Container 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
"""
def __init__(self, **kwargs):
dict.__init__(self, kwargs)
def __setattr__(self, key, value):
self[key] = value
def __getattr__(self, key):
try:
return self[key]
except KeyError:
raise AttributeError(key)
def __getstate__(self):
return self.__dict__
def get_data_home(data_home=None):
"""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.
"""
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."""
data_home = get_data_home(data_home)
shutil.rmtree(data_home)
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 `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 `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 <datasets>`.
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.
"""
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_iris():
"""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 <datasets>`.
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']
"""
module_path = dirname(__file__)
with open(join(module_path, 'data', 'iris.csv')) 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=np.int)
for i, ir in enumerate(data_file):
data[i] = np.asarray(ir[:-1], dtype=np.float)
target[i] = np.asarray(ir[-1], dtype=np.int)
with open(join(module_path, 'descr', 'iris.rst')) as rst_file:
fdescr = rst_file.read()
return Bunch(data=data, target=target,
target_names=target_names,
DESCR=fdescr,
feature_names=['sepal length (cm)', 'sepal width (cm)',
'petal length (cm)', 'petal width (cm)'])
def load_breast_cancer():
"""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
================= ==============
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.
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__)
with open(join(module_path, 'data', 'breast_cancer.csv')) as csv_file:
data_file = csv.reader(csv_file)
first_line = next(data_file)
n_samples = int(first_line[0])
n_features = int(first_line[1])
target_names = np.array(first_line[2:4])
data = np.empty((n_samples, n_features))
target = np.empty((n_samples,), dtype=np.int)
for count, value in enumerate(data_file):
data[count] = np.asarray(value[:-1], dtype=np.float)
target[count] = np.asarray(value[-1], dtype=np.int)
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'])
return Bunch(data=data, target=target,
target_names=target_names,
DESCR=fdescr,
feature_names=feature_names)
def load_digits(n_class=10):
"""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 <datasets>`.
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
"""
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]
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]
return Bunch(data=flat_data,
target=target.astype(np.int),
target_names=np.arange(10),
images=images,
DESCR=descr)
def load_diabetes():
"""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 <datasets>`.
Returns
-------
data : Bunch
Dictionary-like object, the interesting attributes are:
'data', the data to learn and 'target', the regression target for each
sample.
"""
base_dir = join(dirname(__file__), 'data')
data = np.loadtxt(join(base_dir, 'diabetes_data.csv.gz'))
target = np.loadtxt(join(base_dir, 'diabetes_target.csv.gz'))
return Bunch(data=data, target=target)
def load_linnerud():
"""Load 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'.
"""
base_dir = join(dirname(__file__), 'data/')
# Read data
data_exercise = np.loadtxt(base_dir + 'linnerud_exercise.csv', skiprows=1)
data_physiological = np.loadtxt(base_dir + 'linnerud_physiological.csv',
skiprows=1)
# Read header
with open(base_dir + 'linnerud_exercise.csv') as f:
header_exercise = f.readline().split()
with open(base_dir + 'linnerud_physiological.csv') as f:
header_physiological = f.readline().split()
with open(dirname(__file__) + '/descr/linnerud.rst') as f:
descr = f.read()
return Bunch(data=data_exercise, feature_names=header_exercise,
target=data_physiological,
target_names=header_physiological,
DESCR=descr)
def load_boston():
"""Load and return the boston house-prices dataset (regression).
============== ==============
Samples total 506
Dimensionality 13
Features real, positive
Targets real 5. - 50.
============== ==============
Returns
-------
data : Bunch
Dictionary-like object, the interesting attributes are:
'data', the data to learn, 'target', the regression targets,
and 'DESCR', the full description of the dataset.
Examples
--------
>>> from sklearn.datasets import load_boston
>>> boston = load_boston()
>>> print(boston.data.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.float)
target[i] = np.asarray(d[-1], dtype=np.float)
return Bunch(data=data,
target=target,
# last column is target value
feature_names=feature_names[:-1],
DESCR=descr_text)
def load_sample_images():
"""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')
"""
# Try to import imread from scipy. We do this lazily here to prevent
# this module from depending on PIL.
try:
try:
from scipy.misc import imread
except ImportError:
from scipy.misc.pilutil import imread
except ImportError:
raise ImportError("The Python Imaging Library (PIL) "
"is required to load data from jpeg files")
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 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
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):
"""Ensure 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_suffix = kwargs.get("py3_suffix", "_py3")
basename, ext = splitext(args[-1])
if sys.version_info[0] >= 3:
basename += py3_suffix
new_args = args[:-1] + (basename + ext,)
return join(*new_args)
|