/usr/share/pyshared/sklearn/preprocessing/label.py is in python-sklearn 0.14.1-2.
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 | # Authors: Alexandre Gramfort <alexandre.gramfort@inria.fr>
# Mathieu Blondel <mathieu@mblondel.org>
# Olivier Grisel <olivier.grisel@ensta.org>
# Andreas Mueller <amueller@ais.uni-bonn.de>
# License: BSD 3 clause
import numpy as np
from ..base import BaseEstimator, TransformerMixin
from ..utils.fixes import unique
from ..utils import deprecated, column_or_1d
from ..utils.multiclass import unique_labels
from ..utils.multiclass import type_of_target
from ..externals import six
zip = six.moves.zip
map = six.moves.map
__all__ = [
'label_binarize',
'LabelBinarizer',
'LabelEncoder',
]
class LabelEncoder(BaseEstimator, TransformerMixin):
"""Encode labels with value between 0 and n_classes-1.
Attributes
----------
`classes_` : array of shape (n_class,)
Holds the label for each class.
Examples
--------
`LabelEncoder` can be used to normalize labels.
>>> from sklearn import preprocessing
>>> le = preprocessing.LabelEncoder()
>>> le.fit([1, 2, 2, 6])
LabelEncoder()
>>> le.classes_
array([1, 2, 6])
>>> le.transform([1, 1, 2, 6]) #doctest: +ELLIPSIS
array([0, 0, 1, 2]...)
>>> le.inverse_transform([0, 0, 1, 2])
array([1, 1, 2, 6])
It can also be used to transform non-numerical labels (as long as they are
hashable and comparable) to numerical labels.
>>> le = preprocessing.LabelEncoder()
>>> le.fit(["paris", "paris", "tokyo", "amsterdam"])
LabelEncoder()
>>> list(le.classes_)
['amsterdam', 'paris', 'tokyo']
>>> le.transform(["tokyo", "tokyo", "paris"]) #doctest: +ELLIPSIS
array([2, 2, 1]...)
>>> list(le.inverse_transform([2, 2, 1]))
['tokyo', 'tokyo', 'paris']
"""
def _check_fitted(self):
if not hasattr(self, "classes_"):
raise ValueError("LabelEncoder was not fitted yet.")
def fit(self, y):
"""Fit label encoder
Parameters
----------
y : array-like of shape (n_samples,)
Target values.
Returns
-------
self : returns an instance of self.
"""
y = column_or_1d(y, warn=True)
self.classes_ = np.unique(y)
return self
def fit_transform(self, y):
"""Fit label encoder and return encoded labels
Parameters
----------
y : array-like of shape [n_samples]
Target values.
Returns
-------
y : array-like of shape [n_samples]
"""
y = column_or_1d(y, warn=True)
self.classes_, y = unique(y, return_inverse=True)
return y
def transform(self, y):
"""Transform labels to normalized encoding.
Parameters
----------
y : array-like of shape [n_samples]
Target values.
Returns
-------
y : array-like of shape [n_samples]
"""
self._check_fitted()
classes = np.unique(y)
if len(np.intersect1d(classes, self.classes_)) < len(classes):
diff = np.setdiff1d(classes, self.classes_)
raise ValueError("y contains new labels: %s" % str(diff))
return np.searchsorted(self.classes_, y)
def inverse_transform(self, y):
"""Transform labels back to original encoding.
Parameters
----------
y : numpy array of shape [n_samples]
Target values.
Returns
-------
y : numpy array of shape [n_samples]
"""
self._check_fitted()
y = np.asarray(y)
return self.classes_[y]
class LabelBinarizer(BaseEstimator, TransformerMixin):
"""Binarize labels in a one-vs-all fashion
Several regression and binary classification algorithms are
available in the scikit. A simple way to extend these algorithms
to the multi-class classification case is to use the so-called
one-vs-all scheme.
At learning time, this simply consists in learning one regressor
or binary classifier per class. In doing so, one needs to convert
multi-class labels to binary labels (belong or does not belong
to the class). LabelBinarizer makes this process easy with the
transform method.
At prediction time, one assigns the class for which the corresponding
model gave the greatest confidence. LabelBinarizer makes this easy
with the inverse_transform method.
Parameters
----------
neg_label : int (default: 0)
Value with which negative labels must be encoded.
pos_label : int (default: 1)
Value with which positive labels must be encoded.
Attributes
----------
`classes_` : array of shape [n_class]
Holds the label for each class.
`multilabel_` : boolean
True if the transformer was fitted on a multilabel rather than a
multiclass set of labels.
Examples
--------
>>> from sklearn import preprocessing
>>> lb = preprocessing.LabelBinarizer()
>>> lb.fit([1, 2, 6, 4, 2])
LabelBinarizer(neg_label=0, pos_label=1)
>>> lb.classes_
array([1, 2, 4, 6])
>>> lb.multilabel_
False
>>> lb.transform([1, 6])
array([[1, 0, 0, 0],
[0, 0, 0, 1]])
>>> lb.fit_transform([(1, 2), (3,)])
array([[1, 1, 0],
[0, 0, 1]])
>>> lb.classes_
array([1, 2, 3])
>>> lb.multilabel_
True
See also
--------
label_binarize : function to perform the transform operation of
LabelBinarizer with fixed classes.
"""
def __init__(self, neg_label=0, pos_label=1):
if neg_label >= pos_label:
raise ValueError("neg_label must be strictly less than pos_label.")
self.neg_label = neg_label
self.pos_label = pos_label
@property
@deprecated("Attribute `multilabel` was renamed to `multilabel_` in "
"0.14 and will be removed in 0.16")
def multilabel(self):
return self.multilabel_
def _check_fitted(self):
if not hasattr(self, "classes_"):
raise ValueError("LabelBinarizer was not fitted yet.")
def fit(self, y):
"""Fit label binarizer
Parameters
----------
y : numpy array of shape (n_samples,) or sequence of sequences
Target values. In the multilabel case the nested sequences can
have variable lengths.
Returns
-------
self : returns an instance of self.
"""
y_type = type_of_target(y)
self.multilabel_ = y_type.startswith('multilabel')
if self.multilabel_:
self.indicator_matrix_ = y_type == 'multilabel-indicator'
self.classes_ = unique_labels(y)
return self
def transform(self, y):
"""Transform multi-class labels to binary labels
The output of transform is sometimes referred to by some authors as the
1-of-K coding scheme.
Parameters
----------
y : numpy array of shape [n_samples] or sequence of sequences
Target values. In the multilabel case the nested sequences can
have variable lengths.
Returns
-------
Y : numpy array of shape [n_samples, n_classes]
"""
self._check_fitted()
y_is_multilabel = type_of_target(y).startswith('multilabel')
if y_is_multilabel and not self.multilabel_:
raise ValueError("The object was not fitted with multilabel"
" input.")
return label_binarize(y, self.classes_,
multilabel=self.multilabel_,
pos_label=self.pos_label,
neg_label=self.neg_label)
def inverse_transform(self, Y, threshold=None):
"""Transform binary labels back to multi-class labels
Parameters
----------
Y : numpy array of shape [n_samples, n_classes]
Target values.
threshold : float or None
Threshold used in the binary and multi-label cases.
Use 0 when:
- Y contains the output of decision_function (classifier)
Use 0.5 when:
- Y contains the output of predict_proba
If None, the threshold is assumed to be half way between
neg_label and pos_label.
Returns
-------
y : numpy array of shape [n_samples] or sequence of sequences
Target values. In the multilabel case the nested sequences can
have variable lengths.
Notes
-----
In the case when the binary labels are fractional
(probabilistic), inverse_transform chooses the class with the
greatest value. Typically, this allows to use the output of a
linear model's decision_function method directly as the input
of inverse_transform.
"""
self._check_fitted()
if threshold is None:
half = (self.pos_label - self.neg_label) / 2.0
threshold = self.neg_label + half
if self.multilabel_:
Y = np.array(Y > threshold, dtype=int)
# Return the predictions in the same format as in fit
if self.indicator_matrix_:
# Label indicator matrix format
return Y
else:
# Lists of tuples format
return [tuple(self.classes_[np.flatnonzero(Y[i])])
for i in range(Y.shape[0])]
if len(Y.shape) == 1 or Y.shape[1] == 1:
y = np.array(Y.ravel() > threshold, dtype=int)
else:
y = Y.argmax(axis=1)
return self.classes_[y]
def label_binarize(y, classes, multilabel=False, neg_label=0, pos_label=1):
"""Binarize labels in a one-vs-all fashion
Several regression and binary classification algorithms are
available in the scikit. A simple way to extend these algorithms
to the multi-class classification case is to use the so-called
one-vs-all scheme.
This function makes it possible to compute this transformation for a
fixed set of class labels known ahead of time.
Parameters
----------
y : array-like
Sequence of integer labels to encode.
classes : array of shape [n_classes]
Uniquely holds the label for each class.
multilabel : boolean
Set to true if y is encoding a multilabel tasks (with a variable
number of label assignements per sample) rather than a multiclass task
where one sample has one and only one label assigned.
neg_label: int (default: 0)
Value with which negative labels must be encoded.
pos_label: int (default: 1)
Value with which positive labels must be encoded.
Examples
--------
>>> from sklearn.preprocessing import label_binarize
>>> label_binarize([1, 6], classes=[1, 2, 4, 6])
array([[1, 0, 0, 0],
[0, 0, 0, 1]])
The class ordering is preserved:
>>> label_binarize([1, 6], classes=[1, 6, 4, 2])
array([[1, 0, 0, 0],
[0, 1, 0, 0]])
>>> label_binarize([(1, 2), (6,), ()], multilabel=True,
... classes=[1, 6, 4, 2])
array([[1, 0, 0, 1],
[0, 1, 0, 0],
[0, 0, 0, 0]])
See also
--------
label_binarize : function to perform the transform operation of
LabelBinarizer with fixed classes.
"""
y_type = type_of_target(y)
if multilabel or len(classes) > 2:
if y_type == 'multilabel-indicator':
# nothing to do as y is already a label indicator matrix
return y
Y = np.zeros((len(y), len(classes)), dtype=np.int)
else:
Y = np.zeros((len(y), 1), dtype=np.int)
Y += neg_label
y_is_multilabel = y_type.startswith('multilabel')
if multilabel:
if not y_is_multilabel:
raise ValueError("y should be a list of label lists/tuples,"
"got %r" % (y,))
# inverse map: label => column index
imap = dict((v, k) for k, v in enumerate(classes))
for i, label_tuple in enumerate(y):
for label in label_tuple:
Y[i, imap[label]] = pos_label
return Y
else:
y = column_or_1d(y)
if len(classes) == 2:
Y[y == classes[1], 0] = pos_label
return Y
elif len(classes) >= 2:
for i, k in enumerate(classes):
Y[y == k, i] = pos_label
return Y
else:
# Only one class, returns a matrix with all negative labels.
return Y
|