/usr/share/pyshared/sklearn/tree/tree.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 | """
This module gathers tree-based methods, including decision, regression and
randomized trees. Single and multi-output problems are both handled.
"""
# Authors: Gilles Louppe <g.louppe@gmail.com>
# Peter Prettenhofer <peter.prettenhofer@gmail.com>
# Brian Holt <bdholt1@gmail.com>
# Noel Dawe <noel@dawe.me>
# Satrajit Gosh <satrajit.ghosh@gmail.com>
# Licence: BSD 3 clause
from __future__ import division
import numbers
import numpy as np
from abc import ABCMeta, abstractmethod
from warnings import warn
from ..base import BaseEstimator, ClassifierMixin, RegressorMixin
from ..externals import six
from ..externals.six.moves import xrange
from ..feature_selection.from_model import _LearntSelectorMixin
from ..utils import array2d, check_random_state
from ..utils.fixes import unique
from ..utils.validation import check_arrays
from ._tree import Criterion, Splitter, Tree
from . import _tree
__all__ = ["DecisionTreeClassifier",
"DecisionTreeRegressor",
"ExtraTreeClassifier",
"ExtraTreeRegressor"]
# =============================================================================
# Types and constants
# =============================================================================
DTYPE = _tree.DTYPE
DOUBLE = _tree.DOUBLE
CRITERIA_CLF = {"gini": _tree.Gini, "entropy": _tree.Entropy}
CRITERIA_REG = {"mse": _tree.MSE}
SPLITTERS = {"best": _tree.BestSplitter, "random": _tree.RandomSplitter}
# =============================================================================
# Base decision tree
# =============================================================================
class BaseDecisionTree(six.with_metaclass(ABCMeta, BaseEstimator,
_LearntSelectorMixin)):
"""Base class for decision trees.
Warning: This class should not be used directly.
Use derived classes instead.
"""
@abstractmethod
def __init__(self,
criterion,
splitter,
max_depth,
min_samples_split,
min_samples_leaf,
max_features,
random_state):
self.criterion = criterion
self.splitter = splitter
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.max_features = max_features
self.random_state = random_state
self.n_features_ = None
self.n_outputs_ = None
self.classes_ = None
self.n_classes_ = None
self.splitter_ = None
self.tree_ = None
def fit(self, X, y, sample_mask=None, X_argsorted=None, check_input=True,
sample_weight=None):
"""Build a decision tree from the training set (X, y).
Parameters
----------
X : array-like, shape = [n_samples, n_features]
The training input samples. Use ``dtype=np.float32`` for maximum
efficiency.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (integers that correspond to classes in
classification, real numbers in regression).
Use ``dtype=np.float64`` and ``order='C'`` for maximum
efficiency.
sample_weight : array-like, shape = [n_samples] or None
Sample weights. If None, then samples are equally weighted. Splits
that would create child nodes with net zero or negative weight are
ignored while searching for a split in each node. In the case of
classification, splits are also ignored if they would result in any
single class carrying a negative weight in either child node.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Returns
-------
self : object
Returns self.
"""
random_state = check_random_state(self.random_state)
# Deprecations
if sample_mask is not None:
warn("The sample_mask parameter is deprecated as of version 0.14 "
"and will be removed in 0.16.", DeprecationWarning)
if X_argsorted is not None:
warn("The X_argsorted parameter is deprecated as of version 0.14 "
"and will be removed in 0.16.", DeprecationWarning)
# Convert data
if check_input:
X, = check_arrays(X, dtype=DTYPE, sparse_format="dense",
check_ccontiguous=True)
# Determine output settings
n_samples, self.n_features_ = X.shape
is_classification = isinstance(self, ClassifierMixin)
y = np.atleast_1d(y)
if y.ndim == 1:
# reshape is necessary to preserve the data contiguity against vs
# [:, np.newaxis] that does not.
y = np.reshape(y, (-1, 1))
self.n_outputs_ = y.shape[1]
if is_classification:
y = np.copy(y)
self.classes_ = []
self.n_classes_ = []
for k in xrange(self.n_outputs_):
classes_k, y[:, k] = unique(y[:, k], return_inverse=True)
self.classes_.append(classes_k)
self.n_classes_.append(classes_k.shape[0])
else:
self.classes_ = [None] * self.n_outputs_
self.n_classes_ = [1] * self.n_outputs_
self.n_classes_ = np.array(self.n_classes_, dtype=np.intp)
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
y = np.ascontiguousarray(y, dtype=DOUBLE)
# Check parameters
max_depth = (2 ** 31) - 1 if self.max_depth is None else self.max_depth
if isinstance(self.max_features, six.string_types):
if self.max_features == "auto":
if is_classification:
max_features = max(1, int(np.sqrt(self.n_features_)))
else:
max_features = self.n_features_
elif self.max_features == "sqrt":
max_features = max(1, int(np.sqrt(self.n_features_)))
elif self.max_features == "log2":
max_features = max(1, int(np.log2(self.n_features_)))
else:
raise ValueError(
'Invalid value for max_features. Allowed string '
'values are "auto", "sqrt" or "log2".')
elif self.max_features is None:
max_features = self.n_features_
elif isinstance(self.max_features, (numbers.Integral, np.integer)):
max_features = self.max_features
else: # float
max_features = int(self.max_features * self.n_features_)
if len(y) != n_samples:
raise ValueError("Number of labels=%d does not match "
"number of samples=%d" % (len(y), n_samples))
if self.min_samples_split <= 0:
raise ValueError("min_samples_split must be greater than zero.")
if self.min_samples_leaf <= 0:
raise ValueError("min_samples_leaf must be greater than zero.")
if max_depth <= 0:
raise ValueError("max_depth must be greater than zero. ")
if not (0 < max_features <= self.n_features_):
raise ValueError("max_features must be in (0, n_features]")
if sample_weight is not None:
if (getattr(sample_weight, "dtype", None) != DOUBLE or
not sample_weight.flags.contiguous):
sample_weight = np.ascontiguousarray(
sample_weight, dtype=DOUBLE)
if len(sample_weight.shape) > 1:
raise ValueError("Sample weights array has more "
"than one dimension: %d" %
len(sample_weight.shape))
if len(sample_weight) != n_samples:
raise ValueError("Number of weights=%d does not match "
"number of samples=%d" %
(len(sample_weight), n_samples))
# Set min_samples_split sensibly
min_samples_split = max(self.min_samples_split,
2 * self.min_samples_leaf)
# Build tree
criterion = self.criterion
if not isinstance(criterion, Criterion):
if is_classification:
criterion = CRITERIA_CLF[self.criterion](self.n_outputs_,
self.n_classes_)
else:
criterion = CRITERIA_REG[self.criterion](self.n_outputs_)
splitter = self.splitter
if not isinstance(self.splitter, Splitter):
splitter = SPLITTERS[self.splitter](criterion,
max_features,
self.min_samples_leaf,
random_state)
self.criterion_ = criterion
self.splitter_ = splitter
self.tree_ = Tree(self.n_features_, self.n_classes_,
self.n_outputs_, splitter, max_depth,
min_samples_split, self.min_samples_leaf,
random_state)
self.tree_.build(X, y, sample_weight=sample_weight)
if self.n_outputs_ == 1:
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
return self
def predict(self, X):
"""Predict class or regression value for X.
For a classification model, the predicted class for each sample in X is
returned. For a regression model, the predicted value based on X is
returned.
Parameters
----------
X : array-like of shape = [n_samples, n_features]
The input samples.
Returns
-------
y : array of shape = [n_samples] or [n_samples, n_outputs]
The predicted classes, or the predict values.
"""
if getattr(X, "dtype", None) != DTYPE or X.ndim != 2:
X = array2d(X, dtype=DTYPE)
n_samples, n_features = X.shape
if self.tree_ is None:
raise Exception("Tree not initialized. Perform a fit first")
if self.n_features_ != n_features:
raise ValueError("Number of features of the model must "
" match the input. Model n_features is %s and "
" input n_features is %s "
% (self.n_features_, n_features))
proba = self.tree_.predict(X)
# Classification
if isinstance(self, ClassifierMixin):
if self.n_outputs_ == 1:
return self.classes_.take(np.argmax(proba, axis=1), axis=0)
else:
predictions = np.zeros((n_samples, self.n_outputs_))
for k in xrange(self.n_outputs_):
predictions[:, k] = self.classes_[k].take(
np.argmax(proba[:, k], axis=1),
axis=0)
return predictions
# Regression
else:
if self.n_outputs_ == 1:
return proba[:, 0]
else:
return proba[:, :, 0]
@property
def feature_importances_(self):
"""Return the feature importances.
The importance of a feature is computed as the (normalized) total
reduction of the criterion brought by that feature.
It is also known as the Gini importance.
Returns
-------
feature_importances_ : array, shape = [n_features]
"""
if self.tree_ is None:
raise ValueError("Estimator not fitted, "
"call `fit` before `feature_importances_`.")
return self.tree_.compute_feature_importances()
# =============================================================================
# Public estimators
# =============================================================================
class DecisionTreeClassifier(BaseDecisionTree, ClassifierMixin):
"""A decision tree classifier.
Parameters
----------
criterion : string, optional (default="gini")
The function to measure the quality of a split. Supported criteria are
"gini" for the Gini impurity and "entropy" for the information gain.
max_features : int, float, string or None, optional (default=None)
The number of features to consider when looking for the best split:
- If int, then consider `max_features` features at each split.
- If float, then `max_features` is a percentage and
`int(max_features * n_features)` features are considered at each
split.
- If "auto", then `max_features=sqrt(n_features)`.
- If "sqrt", then `max_features=sqrt(n_features)`.
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.
max_depth : integer or None, optional (default=None)
The maximum depth of the tree. If None, then nodes are expanded until
all leaves are pure or until all leaves contain less than
min_samples_split samples.
min_samples_split : integer, optional (default=2)
The minimum number of samples required to split an internal node.
min_samples_leaf : integer, optional (default=1)
The minimum number of samples required to be at a leaf node.
random_state : int, RandomState instance or None, optional (default=None)
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`.
Attributes
----------
`tree_` : Tree object
The underlying Tree object.
`classes_` : array of shape = [n_classes] or a list of such arrays
The classes labels (single output problem),
or a list of arrays of class labels (multi-output problem).
`n_classes_` : int or list
The number of classes (for single output problems),
or a list containing the number of classes for each
output (for multi-output problems).
`feature_importances_` : array of shape = [n_features]
The feature importances. The higher, the more important the
feature. The importance of a feature is computed as the (normalized)
total reduction of the criterion brought by that feature. It is also
known as the Gini importance [4]_.
See also
--------
DecisionTreeRegressor
References
----------
.. [1] http://en.wikipedia.org/wiki/Decision_tree_learning
.. [2] L. Breiman, J. Friedman, R. Olshen, and C. Stone, "Classification
and Regression Trees", Wadsworth, Belmont, CA, 1984.
.. [3] T. Hastie, R. Tibshirani and J. Friedman. "Elements of Statistical
Learning", Springer, 2009.
.. [4] L. Breiman, and A. Cutler, "Random Forests",
http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
Examples
--------
>>> from sklearn.datasets import load_iris
>>> from sklearn.cross_validation import cross_val_score
>>> from sklearn.tree import DecisionTreeClassifier
>>> clf = DecisionTreeClassifier(random_state=0)
>>> iris = load_iris()
>>> cross_val_score(clf, iris.data, iris.target, cv=10)
... # doctest: +SKIP
...
array([ 1. , 0.93..., 0.86..., 0.93..., 0.93...,
0.93..., 0.93..., 1. , 0.93..., 1. ])
"""
def __init__(self,
criterion="gini",
splitter="best",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
max_features=None,
random_state=None,
min_density=None,
compute_importances=None):
super(DecisionTreeClassifier, self).__init__(criterion,
splitter,
max_depth,
min_samples_split,
min_samples_leaf,
max_features,
random_state)
if min_density is not None:
warn("The min_density parameter is deprecated as of version 0.14 "
"and will be removed in 0.16.", DeprecationWarning)
if compute_importances is not None:
warn("Setting compute_importances is no longer required as "
"version 0.14. Variable importances are now computed on the "
"fly when accessing the feature_importances_ attribute. "
"This parameter will be removed in 0.16.",
DeprecationWarning)
def predict_proba(self, X):
"""Predict class probabilities of the input samples X.
Parameters
----------
X : array-like of shape = [n_samples, n_features]
The input samples.
Returns
-------
p : array of shape = [n_samples, n_classes], or a list of n_outputs
such arrays if n_outputs > 1.
The class probabilities of the input samples. Classes are ordered
by arithmetical order.
"""
if getattr(X, "dtype", None) != DTYPE or X.ndim != 2:
X = array2d(X, dtype=DTYPE)
n_samples, n_features = X.shape
if self.tree_ is None:
raise Exception("Tree not initialized. Perform a fit first.")
if self.n_features_ != n_features:
raise ValueError("Number of features of the model must "
" match the input. Model n_features is %s and "
" input n_features is %s "
% (self.n_features_, n_features))
proba = self.tree_.predict(X)
if self.n_outputs_ == 1:
proba = proba[:, :self.n_classes_]
normalizer = proba.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba /= normalizer
return proba
else:
all_proba = []
for k in xrange(self.n_outputs_):
proba_k = proba[:, k, :self.n_classes_[k]]
normalizer = proba_k.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba_k /= normalizer
all_proba.append(proba_k)
return all_proba
def predict_log_proba(self, X):
"""Predict class log-probabilities of the input samples X.
Parameters
----------
X : array-like of shape = [n_samples, n_features]
The input samples.
Returns
-------
p : array of shape = [n_samples, n_classes], or a list of n_outputs
such arrays if n_outputs > 1.
The class log-probabilities of the input samples. Classes are
ordered by arithmetical order.
"""
proba = self.predict_proba(X)
if self.n_outputs_ == 1:
return np.log(proba)
else:
for k in xrange(self.n_outputs_):
proba[k] = np.log(proba[k])
return proba
class DecisionTreeRegressor(BaseDecisionTree, RegressorMixin):
"""A tree regressor.
Parameters
----------
criterion : string, optional (default="mse")
The function to measure the quality of a split. The only supported
criterion is "mse" for the mean squared error.
max_features : int, float, string or None, optional (default=None)
The number of features to consider when looking for the best split:
- If int, then consider `max_features` features at each split.
- If float, then `max_features` is a percentage and
`int(max_features * n_features)` features are considered at each
split.
- If "auto", then `max_features=n_features`.
- If "sqrt", then `max_features=sqrt(n_features)`.
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.
max_depth : integer or None, optional (default=None)
The maximum depth of the tree. If None, then nodes are expanded until
all leaves are pure or until all leaves contain less than
min_samples_split samples.
min_samples_split : integer, optional (default=2)
The minimum number of samples required to split an internal node.
min_samples_leaf : integer, optional (default=1)
The minimum number of samples required to be at a leaf node.
random_state : int, RandomState instance or None, optional (default=None)
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`.
Attributes
----------
`tree_` : Tree object
The underlying Tree object.
`feature_importances_` : array of shape = [n_features]
The feature importances.
The higher, the more important the feature.
The importance of a feature is computed as the
(normalized) total reduction of the criterion brought
by that feature. It is also known as the Gini importance [4]_.
See also
--------
DecisionTreeClassifier
References
----------
.. [1] http://en.wikipedia.org/wiki/Decision_tree_learning
.. [2] L. Breiman, J. Friedman, R. Olshen, and C. Stone, "Classification
and Regression Trees", Wadsworth, Belmont, CA, 1984.
.. [3] T. Hastie, R. Tibshirani and J. Friedman. "Elements of Statistical
Learning", Springer, 2009.
.. [4] L. Breiman, and A. Cutler, "Random Forests",
http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
Examples
--------
>>> from sklearn.datasets import load_boston
>>> from sklearn.cross_validation import cross_val_score
>>> from sklearn.tree import DecisionTreeRegressor
>>> boston = load_boston()
>>> regressor = DecisionTreeRegressor(random_state=0)
>>> cross_val_score(regressor, boston.data, boston.target, cv=10)
... # doctest: +SKIP
...
array([ 0.61..., 0.57..., -0.34..., 0.41..., 0.75...,
0.07..., 0.29..., 0.33..., -1.42..., -1.77...])
"""
def __init__(self,
criterion="mse",
splitter="best",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
max_features=None,
random_state=None,
min_density=None,
compute_importances=None):
super(DecisionTreeRegressor, self).__init__(criterion,
splitter,
max_depth,
min_samples_split,
min_samples_leaf,
max_features,
random_state)
if min_density is not None:
warn("The min_density parameter is deprecated as of version 0.14 "
"and will be removed in 0.16.", DeprecationWarning)
if compute_importances is not None:
warn("Setting compute_importances is no longer required as "
"version 0.14. Variable importances are now computed on the "
"fly when accessing the feature_importances_ attribute. "
"This parameter will be removed in 0.16.",
DeprecationWarning)
class ExtraTreeClassifier(DecisionTreeClassifier):
"""An extremely randomized tree classifier.
Extra-trees differ from classic decision trees in the way they are built.
When looking for the best split to separate the samples of a node into two
groups, random splits are drawn for each of the `max_features` randomly
selected features and the best split among those is chosen. When
`max_features` is set 1, this amounts to building a totally random
decision tree.
Warning: Extra-trees should only be used within ensemble methods.
See also
--------
ExtraTreeRegressor, ExtraTreesClassifier, ExtraTreesRegressor
References
----------
.. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees",
Machine Learning, 63(1), 3-42, 2006.
"""
def __init__(self,
criterion="gini",
splitter="random",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
max_features="auto",
random_state=None,
min_density=None,
compute_importances=None):
super(ExtraTreeClassifier, self).__init__(criterion,
splitter,
max_depth,
min_samples_split,
min_samples_leaf,
max_features,
random_state)
if min_density is not None:
warn("The min_density parameter is deprecated as of version 0.14 "
"and will be removed in 0.16.", DeprecationWarning)
if compute_importances is not None:
warn("Setting compute_importances is no longer required as "
"version 0.14. Variable importances are now computed on the "
"fly when accessing the feature_importances_ attribute. "
"This parameter will be removed in 0.16.",
DeprecationWarning)
class ExtraTreeRegressor(DecisionTreeRegressor):
"""An extremely randomized tree regressor.
Extra-trees differ from classic decision trees in the way they are built.
When looking for the best split to separate the samples of a node into two
groups, random splits are drawn for each of the `max_features` randomly
selected features and the best split among those is chosen. When
`max_features` is set 1, this amounts to building a totally random
decision tree.
Warning: Extra-trees should only be used within ensemble methods.
See also
--------
ExtraTreeClassifier, ExtraTreesClassifier, ExtraTreesRegressor
References
----------
.. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees",
Machine Learning, 63(1), 3-42, 2006.
"""
def __init__(self,
criterion="mse",
splitter="random",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
max_features="auto",
random_state=None,
min_density=None,
compute_importances=None):
super(ExtraTreeRegressor, self).__init__(criterion,
splitter,
max_depth,
min_samples_split,
min_samples_leaf,
max_features,
random_state)
if min_density is not None:
warn("The min_density parameter is deprecated as of version 0.14 "
"and will be removed in 0.16.", DeprecationWarning)
if compute_importances is not None:
warn("Setting compute_importances is no longer required as "
"version 0.14. Variable importances are now computed on the "
"fly when accessing the feature_importances_ attribute. "
"This parameter will be removed in 0.16.",
DeprecationWarning)
|