/usr/share/pyshared/sklearn/svm/classes.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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 | from .base import BaseLibLinear, BaseSVC, BaseLibSVM
from ..base import RegressorMixin
from ..linear_model.base import LinearClassifierMixin, SparseCoefMixin
from ..feature_selection.from_model import _LearntSelectorMixin
class LinearSVC(BaseLibLinear, LinearClassifierMixin, _LearntSelectorMixin,
SparseCoefMixin):
"""Linear Support Vector Classification.
Similar to SVC with parameter kernel='linear', but implemented in terms of
liblinear rather than libsvm, so it has more flexibility in the choice of
penalties and loss functions and should scale better (to large numbers of
samples).
This class supports both dense and sparse input and the multiclass support
is handled according to a one-vs-the-rest scheme.
Parameters
----------
C : float, optional (default=1.0)
Penalty parameter C of the error term.
loss : string, 'l1' or 'l2' (default='l2')
Specifies the loss function. 'l1' is the hinge loss (standard SVM)
while 'l2' is the squared hinge loss.
penalty : string, 'l1' or 'l2' (default='l2')
Specifies the norm used in the penalization. The 'l2'
penalty is the standard used in SVC. The 'l1' leads to `coef_`
vectors that are sparse.
dual : bool, (default=True)
Select the algorithm to either solve the dual or primal
optimization problem. Prefer dual=False when n_samples > n_features.
tol : float, optional (default=1e-4)
Tolerance for stopping criteria
multi_class: string, 'ovr' or 'crammer_singer' (default='ovr')
Determines the multi-class strategy if `y` contains more than
two classes.
`ovr` trains n_classes one-vs-rest classifiers, while `crammer_singer`
optimizes a joint objective over all classes.
While `crammer_singer` is interesting from an theoretical perspective
as it is consistent it is seldom used in practice and rarely leads to
better accuracy and is more expensive to compute.
If `crammer_singer` is chosen, the options loss, penalty and dual will
be ignored.
fit_intercept : boolean, optional (default=True)
Whether to calculate the intercept for this model. If set
to false, no intercept will be used in calculations
(e.g. data is expected to be already centered).
intercept_scaling : float, optional (default=1)
when self.fit_intercept is True, instance vector x becomes
[x, self.intercept_scaling],
i.e. a "synthetic" feature with constant value equals to
intercept_scaling is appended to the instance vector.
The intercept becomes intercept_scaling * synthetic feature weight
Note! the synthetic feature weight is subject to l1/l2 regularization
as all other features.
To lessen the effect of regularization on synthetic feature weight
(and therefore on the intercept) intercept_scaling has to be increased
class_weight : {dict, 'auto'}, optional
Set the parameter C of class i to class_weight[i]*C for
SVC. If not given, all classes are supposed to have
weight one. The 'auto' mode uses the values of y to
automatically adjust weights inversely proportional to
class frequencies.
verbose : int, default: 0
Enable verbose output. Note that this setting takes advantage of a
per-process runtime setting in liblinear that, if enabled, may not work
properly in a multithreaded context.
random_state : int seed, RandomState instance, or None (default)
The seed of the pseudo random number generator to use when
shuffling the data.
Attributes
----------
`coef_` : array, shape = [n_features] if n_classes == 2 \
else [n_classes, n_features]
Weights asigned to the features (coefficients in the primal
problem). This is only available in the case of linear kernel.
`coef_` is readonly property derived from `raw_coef_` that \
follows the internal memory layout of liblinear.
`intercept_` : array, shape = [1] if n_classes == 2 else [n_classes]
Constants in decision function.
Notes
-----
The underlying C implementation uses a random number generator to
select features when fitting the model. It is thus not uncommon,
to have slightly different results for the same input data. If
that happens, try with a smaller tol parameter.
The underlying implementation (liblinear) uses a sparse internal
representation for the data that will incur a memory copy.
**References:**
`LIBLINEAR: A Library for Large Linear Classification
<http://www.csie.ntu.edu.tw/~cjlin/liblinear/>`__
See also
--------
SVC
Implementation of Support Vector Machine classifier using libsvm:
the kernel can be non-linear but its SMO algorithm does not
scale to large number of samples as LinearSVC does.
Furthermore SVC multi-class mode is implemented using one
vs one scheme while LinearSVC uses one vs the rest. It is
possible to implement one vs the rest with SVC by using the
:class:`sklearn.multiclass.OneVsRestClassifier` wrapper.
Finally SVC can fit dense data without memory copy if the input
is C-contiguous. Sparse data will still incur memory copy though.
sklearn.linear_model.SGDClassifier
SGDClassifier can optimize the same cost function as LinearSVC
by adjusting the penalty and loss parameters. Furthermore
SGDClassifier is scalable to large number of samples as it uses
a Stochastic Gradient Descent optimizer.
Finally SGDClassifier can fit both dense and sparse data without
memory copy if the input is C-contiguous or CSR.
"""
def __init__(self, penalty='l2', loss='l2', dual=True, tol=1e-4, C=1.0,
multi_class='ovr', fit_intercept=True, intercept_scaling=1,
class_weight=None, verbose=0, random_state=None):
super(LinearSVC, self).__init__(
penalty=penalty, loss=loss, dual=dual, tol=tol, C=C,
multi_class=multi_class, fit_intercept=fit_intercept,
intercept_scaling=intercept_scaling,
class_weight=class_weight, verbose=verbose,
random_state=random_state)
class SVC(BaseSVC):
"""C-Support Vector Classification.
The implementations is a based on libsvm. The fit time complexity
is more than quadratic with the number of samples which makes it hard
to scale to dataset with more than a couple of 10000 samples.
The multiclass support is handled according to a one-vs-one scheme.
For details on the precise mathematical formulation of the provided
kernel functions and how `gamma`, `coef0` and `degree` affect each,
see the corresponding section in the narrative documentation:
:ref:`svm_kernels`.
.. The narrative documentation is available at http://scikit-learn.org/
Parameters
----------
C : float, optional (default=1.0)
Penalty parameter C of the error term.
kernel : string, optional (default='rbf')
Specifies the kernel type to be used in the algorithm.
It must be one of 'linear', 'poly', 'rbf', 'sigmoid', 'precomputed' or
a callable.
If none is given, 'rbf' will be used. If a callable is given it is
used to precompute the kernel matrix.
degree : int, optional (default=3)
Degree of the polynomial kernel function ('poly').
Ignored by all other kernels.
gamma : float, optional (default=0.0)
Kernel coefficient for 'rbf', 'poly' and 'sigm'.
If gamma is 0.0 then 1/n_features will be used instead.
coef0 : float, optional (default=0.0)
Independent term in kernel function.
It is only significant in 'poly' and 'sigmoid'.
probability: boolean, optional (default=False)
Whether to enable probability estimates. This must be enabled prior
to calling `fit`, and will slow down that method.
shrinking: boolean, optional (default=True)
Whether to use the shrinking heuristic.
tol : float, optional (default=1e-3)
Tolerance for stopping criterion.
cache_size : float, optional
Specify the size of the kernel cache (in MB)
class_weight : {dict, 'auto'}, optional
Set the parameter C of class i to class_weight[i]*C for
SVC. If not given, all classes are supposed to have
weight one. The 'auto' mode uses the values of y to
automatically adjust weights inversely proportional to
class frequencies.
verbose : bool, default: False
Enable verbose output. Note that this setting takes advantage of a
per-process runtime setting in libsvm that, if enabled, may not work
properly in a multithreaded context.
max_iter : int, optional (default=-1)
Hard limit on iterations within solver, or -1 for no limit.
random_state : int seed, RandomState instance, or None (default)
The seed of the pseudo random number generator to use when
shuffling the data for probability estimation.
Attributes
----------
`support_` : array-like, shape = [n_SV]
Index of support vectors.
`support_vectors_` : array-like, shape = [n_SV, n_features]
Support vectors.
`n_support_` : array-like, dtype=int32, shape = [n_class]
number of support vector for each class.
`dual_coef_` : array, shape = [n_class-1, n_SV]
Coefficients of the support vector in the decision function. \
For multiclass, coefficient for all 1-vs-1 classifiers. \
The layout of the coefficients in the multiclass case is somewhat \
non-trivial. See the section about multi-class classification in the \
SVM section of the User Guide for details.
`coef_` : array, shape = [n_class-1, n_features]
Weights asigned to the features (coefficients in the primal
problem). This is only available in the case of linear kernel.
`coef_` is readonly property derived from `dual_coef_` and
`support_vectors_`
`intercept_` : array, shape = [n_class * (n_class-1) / 2]
Constants in decision function.
Examples
--------
>>> import numpy as np
>>> X = np.array([[-1, -1], [-2, -1], [1, 1], [2, 1]])
>>> y = np.array([1, 1, 2, 2])
>>> from sklearn.svm import SVC
>>> clf = SVC()
>>> clf.fit(X, y) #doctest: +NORMALIZE_WHITESPACE
SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0, degree=3,
gamma=0.0, kernel='rbf', max_iter=-1, probability=False,
random_state=None, shrinking=True, tol=0.001, verbose=False)
>>> print(clf.predict([[-0.8, -1]]))
[1]
See also
--------
SVR
Support Vector Machine for Regression implemented using libsvm.
LinearSVC
Scalable Linear Support Vector Machine for classification
implemented using liblinear. Check the See also section of
LinearSVC for more comparison element.
"""
def __init__(self, C=1.0, kernel='rbf', degree=3, gamma=0.0,
coef0=0.0, shrinking=True, probability=False,
tol=1e-3, cache_size=200, class_weight=None,
verbose=False, max_iter=-1, random_state=None):
super(SVC, self).__init__(
'c_svc', kernel, degree, gamma, coef0, tol, C, 0., 0., shrinking,
probability, cache_size, class_weight, verbose, max_iter,
random_state)
class NuSVC(BaseSVC):
"""Nu-Support Vector Classification.
Similar to SVC but uses a parameter to control the number of support
vectors.
The implementation is based on libsvm.
Parameters
----------
nu : float, optional (default=0.5)
An upper bound on the fraction of training errors and a lower
bound of the fraction of support vectors. Should be in the
interval (0, 1].
kernel : string, optional (default='rbf')
Specifies the kernel type to be used in the algorithm.
It must be one of 'linear', 'poly', 'rbf', 'sigmoid', 'precomputed' or
a callable.
If none is given, 'rbf' will be used. If a callable is given it is
used to precompute the kernel matrix.
degree : int, optional (default=3)
degree of kernel function
is significant only in poly, rbf, sigmoid
gamma : float, optional (default=0.0)
kernel coefficient for rbf and poly, if gamma is 0.0 then 1/n_features
will be taken.
coef0 : float, optional (default=0.0)
independent term in kernel function. It is only significant
in poly/sigmoid.
probability: boolean, optional (default=False)
Whether to enable probability estimates. This must be enabled prior
to calling `fit`, and will slow down that method.
shrinking: boolean, optional (default=True)
Whether to use the shrinking heuristic.
tol : float, optional (default=1e-3)
Tolerance for stopping criterion.
cache_size : float, optional
Specify the size of the kernel cache (in MB)
verbose : bool, default: False
Enable verbose output. Note that this setting takes advantage of a
per-process runtime setting in libsvm that, if enabled, may not work
properly in a multithreaded context.
max_iter : int, optional (default=-1)
Hard limit on iterations within solver, or -1 for no limit.
random_state : int seed, RandomState instance, or None (default)
The seed of the pseudo random number generator to use when
shuffling the data for probability estimation.
Attributes
----------
`support_` : array-like, shape = [n_SV]
Index of support vectors.
`support_vectors_` : array-like, shape = [n_SV, n_features]
Support vectors.
`n_support_` : array-like, dtype=int32, shape = [n_class]
number of support vector for each class.
`dual_coef_` : array, shape = [n_class-1, n_SV]
Coefficients of the support vector in the decision function. \
For multiclass, coefficient for all 1-vs-1 classifiers. \
The layout of the coefficients in the multiclass case is somewhat \
non-trivial. See the section about multi-class classification in \
the SVM section of the User Guide for details.
`coef_` : array, shape = [n_class-1, n_features]
Weights asigned to the features (coefficients in the primal
problem). This is only available in the case of linear kernel.
`coef_` is readonly property derived from `dual_coef_` and
`support_vectors_`
`intercept_` : array, shape = [n_class * (n_class-1) / 2]
Constants in decision function.
Examples
--------
>>> import numpy as np
>>> X = np.array([[-1, -1], [-2, -1], [1, 1], [2, 1]])
>>> y = np.array([1, 1, 2, 2])
>>> from sklearn.svm import NuSVC
>>> clf = NuSVC()
>>> clf.fit(X, y) #doctest: +NORMALIZE_WHITESPACE
NuSVC(cache_size=200, coef0=0.0, degree=3, gamma=0.0, kernel='rbf',
max_iter=-1, nu=0.5, probability=False, random_state=None,
shrinking=True, tol=0.001, verbose=False)
>>> print(clf.predict([[-0.8, -1]]))
[1]
See also
--------
SVC
Support Vector Machine for classification using libsvm.
LinearSVC
Scalable linear Support Vector Machine for classification using
liblinear.
"""
def __init__(self, nu=0.5, kernel='rbf', degree=3, gamma=0.0,
coef0=0.0, shrinking=True, probability=False,
tol=1e-3, cache_size=200, verbose=False, max_iter=-1,
random_state=None):
super(NuSVC, self).__init__(
'nu_svc', kernel, degree, gamma, coef0, tol, 0., nu, 0., shrinking,
probability, cache_size, None, verbose, max_iter, random_state)
class SVR(BaseLibSVM, RegressorMixin):
"""epsilon-Support Vector Regression.
The free parameters in the model are C and epsilon.
The implementations is a based on libsvm.
Parameters
----------
C : float, optional (default=1.0)
penalty parameter C of the error term.
epsilon : float, optional (default=0.1)
epsilon in the epsilon-SVR model. It specifies the epsilon-tube
within which no penalty is associated in the training loss function
with points predicted within a distance epsilon from the actual
value.
kernel : string, optional (default='rbf')
Specifies the kernel type to be used in the algorithm.
It must be one of 'linear', 'poly', 'rbf', 'sigmoid', 'precomputed' or
a callable.
If none is given, 'rbf' will be used. If a callable is given it is
used to precompute the kernel matrix.
degree : int, optional (default=3)
degree of kernel function
is significant only in poly, rbf, sigmoid
gamma : float, optional (default=0.0)
kernel coefficient for rbf and poly, if gamma is 0.0 then 1/n_features
will be taken.
coef0 : float, optional (default=0.0)
independent term in kernel function. It is only significant
in poly/sigmoid.
probability: boolean, optional (default=False)
Whether to enable probability estimates. This must be enabled prior
to calling `fit`, and will slow down that method.
shrinking: boolean, optional (default=True)
Whether to use the shrinking heuristic.
tol : float, optional (default=1e-3)
Tolerance for stopping criterion.
cache_size : float, optional
Specify the size of the kernel cache (in MB)
verbose : bool, default: False
Enable verbose output. Note that this setting takes advantage of a
per-process runtime setting in libsvm that, if enabled, may not work
properly in a multithreaded context.
max_iter : int, optional (default=-1)
Hard limit on iterations within solver, or -1 for no limit.
random_state : int seed, RandomState instance, or None (default)
The seed of the pseudo random number generator to use when
shuffling the data for probability estimaton.
Attributes
----------
`support_` : array-like, shape = [n_SV]
Index of support vectors.
`support_vectors_` : array-like, shape = [nSV, n_features]
Support vectors.
`dual_coef_` : array, shape = [n_classes-1, n_SV]
Coefficients of the support vector in the decision function.
`coef_` : array, shape = [n_classes-1, n_features]
Weights asigned to the features (coefficients in the primal
problem). This is only available in the case of linear kernel.
`coef_` is readonly property derived from `dual_coef_` and
`support_vectors_`
`intercept_` : array, shape = [n_class * (n_class-1) / 2]
Constants in decision function.
Examples
--------
>>> from sklearn.svm import SVR
>>> import numpy as np
>>> n_samples, n_features = 10, 5
>>> np.random.seed(0)
>>> y = np.random.randn(n_samples)
>>> X = np.random.randn(n_samples, n_features)
>>> clf = SVR(C=1.0, epsilon=0.2)
>>> clf.fit(X, y) #doctest: +NORMALIZE_WHITESPACE
SVR(C=1.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.2, gamma=0.0,
kernel='rbf', max_iter=-1, probability=False, random_state=None,
shrinking=True, tol=0.001, verbose=False)
See also
--------
NuSVR
Support Vector Machine for regression implemented using libsvm
using a parameter to control the number of support vectors.
"""
def __init__(self, kernel='rbf', degree=3, gamma=0.0, coef0=0.0, tol=1e-3,
C=1.0, epsilon=0.1, shrinking=True, probability=False,
cache_size=200, verbose=False, max_iter=-1,
random_state=None):
super(SVR, self).__init__(
'epsilon_svr', kernel, degree, gamma, coef0, tol, C, 0., epsilon,
shrinking, probability, cache_size, None, verbose,
max_iter, random_state)
class NuSVR(BaseLibSVM, RegressorMixin):
"""Nu Support Vector Regression.
Similar to NuSVC, for regression, uses a parameter nu to control
the number of support vectors. However, unlike NuSVC, where nu
replaces C, here nu replaces with the parameter epsilon of SVR.
The implementations is a based on libsvm.
Parameters
----------
C : float, optional (default=1.0)
penalty parameter C of the error term.
nu : float, optional
An upper bound on the fraction of training errors and a lower bound of
the fraction of support vectors. Should be in the interval (0, 1]. By
default 0.5 will be taken. Only available if impl='nu_svc'.
kernel : string, optional (default='rbf')
Specifies the kernel type to be used in the algorithm.
It must be one of 'linear', 'poly', 'rbf', 'sigmoid', 'precomputed' or
a callable.
If none is given, 'rbf' will be used. If a callable is given it is
used to precompute the kernel matrix.
degree : int, optional (default=3)
degree of kernel function
is significant only in poly, rbf, sigmoid
gamma : float, optional (default=0.0)
kernel coefficient for rbf and poly, if gamma is 0.0 then 1/n_features
will be taken.
coef0 : float, optional (default=0.0)
independent term in kernel function. It is only significant
in poly/sigmoid.
probability: boolean, optional (default=False)
Whether to enable probability estimates. This must be enabled prior
to calling `fit`, and will slow down that method.
shrinking: boolean, optional (default=True)
Whether to use the shrinking heuristic.
tol : float, optional (default=1e-3)
Tolerance for stopping criterion.
cache_size : float, optional
Specify the size of the kernel cache (in MB)
verbose : bool, default: False
Enable verbose output. Note that this setting takes advantage of a
per-process runtime setting in libsvm that, if enabled, may not work
properly in a multithreaded context.
max_iter : int, optional (default=-1)
Hard limit on iterations within solver, or -1 for no limit.
random_state : int seed, RandomState instance, or None (default)
The seed of the pseudo random number generator to use when
shuffling the data for probability estimation.
Attributes
----------
`support_` : array-like, shape = [n_SV]
Index of support vectors.
`support_vectors_` : array-like, shape = [nSV, n_features]
Support vectors.
`dual_coef_` : array, shape = [n_classes-1, n_SV]
Coefficients of the support vector in the decision function.
`coef_` : array, shape = [n_classes-1, n_features]
Weights asigned to the features (coefficients in the primal
problem). This is only available in the case of linear kernel.
`coef_` is readonly property derived from `dual_coef_` and
`support_vectors_`
`intercept_` : array, shape = [n_class * (n_class-1) / 2]
Constants in decision function.
Examples
--------
>>> from sklearn.svm import NuSVR
>>> import numpy as np
>>> n_samples, n_features = 10, 5
>>> np.random.seed(0)
>>> y = np.random.randn(n_samples)
>>> X = np.random.randn(n_samples, n_features)
>>> clf = NuSVR(C=1.0, nu=0.1)
>>> clf.fit(X, y) #doctest: +NORMALIZE_WHITESPACE
NuSVR(C=1.0, cache_size=200, coef0=0.0, degree=3, gamma=0.0, kernel='rbf',
max_iter=-1, nu=0.1, probability=False, random_state=None,
shrinking=True, tol=0.001, verbose=False)
See also
--------
NuSVC
Support Vector Machine for classification implemented with libsvm
with a parameter to control the number of support vectors.
SVR
epsilon Support Vector Machine for regression implemented with libsvm.
"""
def __init__(self, nu=0.5, C=1.0, kernel='rbf', degree=3,
gamma=0.0, coef0=0.0, shrinking=True,
probability=False, tol=1e-3, cache_size=200,
verbose=False, max_iter=-1, random_state=None):
super(NuSVR, self).__init__(
'nu_svr', kernel, degree, gamma, coef0, tol, C, nu, 0., shrinking,
probability, cache_size, None, verbose, max_iter, random_state)
class OneClassSVM(BaseLibSVM):
"""Unsupervised Outliers Detection.
Estimate the support of a high-dimensional distribution.
The implementation is based on libsvm.
Parameters
----------
kernel : string, optional (default='rbf')
Specifies the kernel type to be used in the algorithm.
It must be one of 'linear', 'poly', 'rbf', 'sigmoid', 'precomputed' or
a callable.
If none is given, 'rbf' will be used. If a callable is given it is
used to precompute the kernel matrix.
nu : float, optional
An upper bound on the fraction of training
errors and a lower bound of the fraction of support
vectors. Should be in the interval (0, 1]. By default 0.5
will be taken.
degree : int, optional
Degree of kernel function. Significant only in poly, rbf, sigmoid.
gamma : float, optional (default=0.0)
kernel coefficient for rbf and poly, if gamma is 0.0 then 1/n_features
will be taken.
coef0 : float, optional
Independent term in kernel function. It is only significant in
poly/sigmoid.
tol : float, optional
Tolerance for stopping criterion.
shrinking: boolean, optional
Whether to use the shrinking heuristic.
cache_size : float, optional
Specify the size of the kernel cache (in MB)
verbose : bool, default: False
Enable verbose output. Note that this setting takes advantage of a
per-process runtime setting in libsvm that, if enabled, may not work
properly in a multithreaded context.
max_iter : int, optional (default=-1)
Hard limit on iterations within solver, or -1 for no limit.
random_state : int seed, RandomState instance, or None (default)
The seed of the pseudo random number generator to use when
shuffling the data for probability estimation.
Attributes
----------
`support_` : array-like, shape = [n_SV]
Index of support vectors.
`support_vectors_` : array-like, shape = [nSV, n_features]
Support vectors.
`dual_coef_` : array, shape = [n_classes-1, n_SV]
Coefficient of the support vector in the decision function.
`coef_` : array, shape = [n_classes-1, n_features]
Weights asigned to the features (coefficients in the primal
problem). This is only available in the case of linear kernel.
`coef_` is readonly property derived from `dual_coef_` and
`support_vectors_`
`intercept_` : array, shape = [n_classes-1]
Constants in decision function.
"""
def __init__(self, kernel='rbf', degree=3, gamma=0.0, coef0=0.0, tol=1e-3,
nu=0.5, shrinking=True, cache_size=200, verbose=False,
max_iter=-1, random_state=None):
super(OneClassSVM, self).__init__(
'one_class', kernel, degree, gamma, coef0, tol, 0., nu, 0.,
shrinking, False, cache_size, None, verbose, max_iter,
random_state)
def fit(self, X, sample_weight=None, **params):
"""
Detects the soft boundary of the set of samples X.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
Set of samples, where n_samples is the number of samples and
n_features is the number of features.
sample_weight : array-like, shape (n_samples,)
Per-sample weights. Rescale C per sample. Higher weights
force the classifier to put more emphasis on these points.
Returns
-------
self : object
Returns self.
Notes
-----
If X is not a C-ordered contiguous array it is copied.
"""
super(OneClassSVM, self).fit(X, [], sample_weight=sample_weight,
**params)
return self
|