/usr/lib/python3/dist-packages/sklearn/ensemble/forest.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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 | """Forest of trees-based ensemble methods
Those methods include random forests and extremely randomized trees.
The module structure is the following:
- The ``BaseForest`` base class implements a common ``fit`` method for all
the estimators in the module. The ``fit`` method of the base ``Forest``
class calls the ``fit`` method of each sub-estimator on random samples
(with replacement, a.k.a. bootstrap) of the training set.
The init of the sub-estimator is further delegated to the
``BaseEnsemble`` constructor.
- The ``ForestClassifier`` and ``ForestRegressor`` base classes further
implement the prediction logic by computing an average of the predicted
outcomes of the sub-estimators.
- The ``RandomForestClassifier`` and ``RandomForestRegressor`` derived
classes provide the user with concrete implementations of
the forest ensemble method using classical, deterministic
``DecisionTreeClassifier`` and ``DecisionTreeRegressor`` as
sub-estimator implementations.
- The ``ExtraTreesClassifier`` and ``ExtraTreesRegressor`` derived
classes provide the user with concrete implementations of the
forest ensemble method using the extremely randomized trees
``ExtraTreeClassifier`` and ``ExtraTreeRegressor`` as
sub-estimator implementations.
Single and multi-output problems are both handled.
"""
# Authors: Gilles Louppe <g.louppe@gmail.com>
# Brian Holt <bdholt1@gmail.com>
# Joly Arnaud <arnaud.v.joly@gmail.com>
# Fares Hedayati <fares.hedayati@gmail.com>
#
# License: BSD 3 clause
from __future__ import division
import warnings
from warnings import warn
from abc import ABCMeta, abstractmethod
import numpy as np
from scipy.sparse import issparse
from ..base import ClassifierMixin, RegressorMixin
from ..externals.joblib import Parallel, delayed
from ..externals import six
from ..feature_selection.from_model import _LearntSelectorMixin
from ..metrics import r2_score
from ..preprocessing import OneHotEncoder
from ..tree import (DecisionTreeClassifier, DecisionTreeRegressor,
ExtraTreeClassifier, ExtraTreeRegressor)
from ..tree._tree import DTYPE, DOUBLE
from ..utils import check_random_state, check_array, compute_sample_weight
from ..utils.validation import DataConversionWarning, NotFittedError
from .base import BaseEnsemble, _partition_estimators
from ..utils.fixes import bincount
from ..utils.multiclass import check_classification_targets
__all__ = ["RandomForestClassifier",
"RandomForestRegressor",
"ExtraTreesClassifier",
"ExtraTreesRegressor",
"RandomTreesEmbedding"]
MAX_INT = np.iinfo(np.int32).max
def _generate_sample_indices(random_state, n_samples):
"""Private function used to _parallel_build_trees function."""
random_instance = check_random_state(random_state)
sample_indices = random_instance.randint(0, n_samples, n_samples)
return sample_indices
def _generate_unsampled_indices(random_state, n_samples):
"""Private function used to forest._set_oob_score fuction."""
sample_indices = _generate_sample_indices(random_state, n_samples)
sample_counts = bincount(sample_indices, minlength=n_samples)
unsampled_mask = sample_counts == 0
indices_range = np.arange(n_samples)
unsampled_indices = indices_range[unsampled_mask]
return unsampled_indices
def _parallel_build_trees(tree, forest, X, y, sample_weight, tree_idx, n_trees,
verbose=0, class_weight=None):
"""Private function used to fit a single tree in parallel."""
if verbose > 1:
print("building tree %d of %d" % (tree_idx + 1, n_trees))
if forest.bootstrap:
n_samples = X.shape[0]
if sample_weight is None:
curr_sample_weight = np.ones((n_samples,), dtype=np.float64)
else:
curr_sample_weight = sample_weight.copy()
indices = _generate_sample_indices(tree.random_state, n_samples)
sample_counts = bincount(indices, minlength=n_samples)
curr_sample_weight *= sample_counts
if class_weight == 'subsample':
with warnings.catch_warnings():
warnings.simplefilter('ignore', DeprecationWarning)
curr_sample_weight *= compute_sample_weight('auto', y, indices)
elif class_weight == 'balanced_subsample':
curr_sample_weight *= compute_sample_weight('balanced', y, indices)
tree.fit(X, y, sample_weight=curr_sample_weight, check_input=False)
else:
tree.fit(X, y, sample_weight=sample_weight, check_input=False)
return tree
def _parallel_helper(obj, methodname, *args, **kwargs):
"""Private helper to workaround Python 2 pickle limitations"""
return getattr(obj, methodname)(*args, **kwargs)
class BaseForest(six.with_metaclass(ABCMeta, BaseEnsemble,
_LearntSelectorMixin)):
"""Base class for forests of trees.
Warning: This class should not be used directly. Use derived classes
instead.
"""
@abstractmethod
def __init__(self,
base_estimator,
n_estimators=10,
estimator_params=tuple(),
bootstrap=False,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False,
class_weight=None):
super(BaseForest, self).__init__(
base_estimator=base_estimator,
n_estimators=n_estimators,
estimator_params=estimator_params)
self.bootstrap = bootstrap
self.oob_score = oob_score
self.n_jobs = n_jobs
self.random_state = random_state
self.verbose = verbose
self.warm_start = warm_start
self.class_weight = class_weight
def apply(self, X):
"""Apply trees in the forest to X, return leaf indices.
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
Returns
-------
X_leaves : array_like, shape = [n_samples, n_estimators]
For each datapoint x in X and for each tree in the forest,
return the index of the leaf x ends up in.
"""
X = self._validate_X_predict(X)
results = Parallel(n_jobs=self.n_jobs, verbose=self.verbose,
backend="threading")(
delayed(_parallel_helper)(tree, 'apply', X, check_input=False)
for tree in self.estimators_)
return np.array(results).T
def fit(self, X, y, sample_weight=None):
"""Build a forest of trees from the training set (X, y).
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (class labels in classification, real numbers in
regression).
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.
Returns
-------
self : object
Returns self.
"""
# Validate or convert input data
X = check_array(X, dtype=DTYPE, accept_sparse="csc")
if issparse(X):
# Pre-sort indices to avoid that each individual tree of the
# ensemble sorts the indices.
X.sort_indices()
# Remap output
n_samples, self.n_features_ = X.shape
y = np.atleast_1d(y)
if y.ndim == 2 and y.shape[1] == 1:
warn("A column-vector y was passed when a 1d array was"
" expected. Please change the shape of y to "
"(n_samples,), for example using ravel().",
DataConversionWarning, stacklevel=2)
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]
y, expanded_class_weight = self._validate_y_class_weight(y)
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
y = np.ascontiguousarray(y, dtype=DOUBLE)
if expanded_class_weight is not None:
if sample_weight is not None:
sample_weight = sample_weight * expanded_class_weight
else:
sample_weight = expanded_class_weight
# Check parameters
self._validate_estimator()
if not self.bootstrap and self.oob_score:
raise ValueError("Out of bag estimation only available"
" if bootstrap=True")
random_state = check_random_state(self.random_state)
if not self.warm_start:
# Free allocated memory, if any
self.estimators_ = []
n_more_estimators = self.n_estimators - len(self.estimators_)
if n_more_estimators < 0:
raise ValueError('n_estimators=%d must be larger or equal to '
'len(estimators_)=%d when warm_start==True'
% (self.n_estimators, len(self.estimators_)))
elif n_more_estimators == 0:
warn("Warm-start fitting without increasing n_estimators does not "
"fit new trees.")
else:
if self.warm_start and len(self.estimators_) > 0:
# We draw from the random state to get the random state we
# would have got if we hadn't used a warm_start.
random_state.randint(MAX_INT, size=len(self.estimators_))
trees = []
for i in range(n_more_estimators):
tree = self._make_estimator(append=False)
tree.set_params(random_state=random_state.randint(MAX_INT))
trees.append(tree)
# Parallel loop: we use the threading backend as the Cython code
# for fitting the trees is internally releasing the Python GIL
# making threading always more efficient than multiprocessing in
# that case.
trees = Parallel(n_jobs=self.n_jobs, verbose=self.verbose,
backend="threading")(
delayed(_parallel_build_trees)(
t, self, X, y, sample_weight, i, len(trees),
verbose=self.verbose, class_weight=self.class_weight)
for i, t in enumerate(trees))
# Collect newly grown trees
self.estimators_.extend(trees)
if self.oob_score:
self._set_oob_score(X, y)
# Decapsulate classes_ attributes
if hasattr(self, "classes_") and self.n_outputs_ == 1:
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
return self
@abstractmethod
def _set_oob_score(self, X, y):
"""Calculate out of bag predictions and score."""
def _validate_y_class_weight(self, y):
# Default implementation
return y, None
def _validate_X_predict(self, X):
"""Validate X whenever one tries to predict, apply, predict_proba"""
if self.estimators_ is None or len(self.estimators_) == 0:
raise NotFittedError("Estimator not fitted, "
"call `fit` before exploiting the model.")
return self.estimators_[0]._validate_X_predict(X, check_input=True)
@property
def feature_importances_(self):
"""Return the feature importances (the higher, the more important the
feature).
Returns
-------
feature_importances_ : array, shape = [n_features]
"""
if self.estimators_ is None or len(self.estimators_) == 0:
raise NotFittedError("Estimator not fitted, "
"call `fit` before `feature_importances_`.")
all_importances = Parallel(n_jobs=self.n_jobs,
backend="threading")(
delayed(getattr)(tree, 'feature_importances_')
for tree in self.estimators_)
return sum(all_importances) / len(self.estimators_)
class ForestClassifier(six.with_metaclass(ABCMeta, BaseForest,
ClassifierMixin)):
"""Base class for forest of trees-based classifiers.
Warning: This class should not be used directly. Use derived classes
instead.
"""
@abstractmethod
def __init__(self,
base_estimator,
n_estimators=10,
estimator_params=tuple(),
bootstrap=False,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False,
class_weight=None):
super(ForestClassifier, self).__init__(
base_estimator,
n_estimators=n_estimators,
estimator_params=estimator_params,
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start,
class_weight=class_weight)
def _set_oob_score(self, X, y):
"""Compute out-of-bag score"""
X = check_array(X, dtype=DTYPE, accept_sparse='csr')
n_classes_ = self.n_classes_
n_samples = y.shape[0]
oob_decision_function = []
oob_score = 0.0
predictions = []
for k in range(self.n_outputs_):
predictions.append(np.zeros((n_samples, n_classes_[k])))
for estimator in self.estimators_:
unsampled_indices = _generate_unsampled_indices(
estimator.random_state, n_samples)
p_estimator = estimator.predict_proba(X[unsampled_indices, :],
check_input=False)
if self.n_outputs_ == 1:
p_estimator = [p_estimator]
for k in range(self.n_outputs_):
predictions[k][unsampled_indices, :] += p_estimator[k]
for k in range(self.n_outputs_):
if (predictions[k].sum(axis=1) == 0).any():
warn("Some inputs do not have OOB scores. "
"This probably means too few trees were used "
"to compute any reliable oob estimates.")
decision = (predictions[k] /
predictions[k].sum(axis=1)[:, np.newaxis])
oob_decision_function.append(decision)
oob_score += np.mean(y[:, k] ==
np.argmax(predictions[k], axis=1), axis=0)
if self.n_outputs_ == 1:
self.oob_decision_function_ = oob_decision_function[0]
else:
self.oob_decision_function_ = oob_decision_function
self.oob_score_ = oob_score / self.n_outputs_
def _validate_y_class_weight(self, y):
check_classification_targets(y)
y = np.copy(y)
expanded_class_weight = None
if self.class_weight is not None:
y_original = np.copy(y)
self.classes_ = []
self.n_classes_ = []
y_store_unique_indices = np.zeros(y.shape, dtype=np.int)
for k in range(self.n_outputs_):
classes_k, y_store_unique_indices[:, k] = np.unique(y[:, k], return_inverse=True)
self.classes_.append(classes_k)
self.n_classes_.append(classes_k.shape[0])
y = y_store_unique_indices
if self.class_weight is not None:
valid_presets = ('auto', 'balanced', 'subsample', 'balanced_subsample')
if isinstance(self.class_weight, six.string_types):
if self.class_weight not in valid_presets:
raise ValueError('Valid presets for class_weight include '
'"balanced" and "balanced_subsample". Given "%s".'
% self.class_weight)
if self.class_weight == "subsample":
warn("class_weight='subsample' is deprecated in 0.17 and"
"will be removed in 0.19. It was replaced by "
"class_weight='balanced_subsample' using the balanced"
"strategy.", DeprecationWarning)
if self.warm_start:
warn('class_weight presets "balanced" or "balanced_subsample" are '
'not recommended for warm_start if the fitted data '
'differs from the full dataset. In order to use '
'"balanced" weights, use compute_class_weight("balanced", '
'classes, y). In place of y you can use a large '
'enough sample of the full training set target to '
'properly estimate the class frequency '
'distributions. Pass the resulting weights as the '
'class_weight parameter.')
if (self.class_weight not in ['subsample', 'balanced_subsample'] or
not self.bootstrap):
if self.class_weight == 'subsample':
class_weight = 'auto'
elif self.class_weight == "balanced_subsample":
class_weight = "balanced"
else:
class_weight = self.class_weight
with warnings.catch_warnings():
if class_weight == "auto":
warnings.simplefilter('ignore', DeprecationWarning)
expanded_class_weight = compute_sample_weight(class_weight,
y_original)
return y, expanded_class_weight
def predict(self, X):
"""Predict class for X.
The predicted class of an input sample is a vote by the trees in
the forest, weighted by their probability estimates. That is,
the predicted class is the one with highest mean probability
estimate across the trees.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
Returns
-------
y : array of shape = [n_samples] or [n_samples, n_outputs]
The predicted classes.
"""
proba = self.predict_proba(X)
if self.n_outputs_ == 1:
return self.classes_.take(np.argmax(proba, axis=1), axis=0)
else:
n_samples = proba[0].shape[0]
predictions = np.zeros((n_samples, self.n_outputs_))
for k in range(self.n_outputs_):
predictions[:, k] = self.classes_[k].take(np.argmax(proba[k],
axis=1),
axis=0)
return predictions
def predict_proba(self, X):
"""Predict class probabilities for X.
The predicted class probabilities of an input sample is computed as
the mean predicted class probabilities of the trees in the forest. The
class probability of a single tree is the fraction of samples of the same
class in a leaf.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
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. The order of the
classes corresponds to that in the attribute `classes_`.
"""
# Check data
X = self._validate_X_predict(X)
# Assign chunk of trees to jobs
n_jobs, _, _ = _partition_estimators(self.n_estimators, self.n_jobs)
# Parallel loop
all_proba = Parallel(n_jobs=n_jobs, verbose=self.verbose,
backend="threading")(
delayed(_parallel_helper)(e, 'predict_proba', X,
check_input=False)
for e in self.estimators_)
# Reduce
proba = all_proba[0]
if self.n_outputs_ == 1:
for j in range(1, len(all_proba)):
proba += all_proba[j]
proba /= len(self.estimators_)
else:
for j in range(1, len(all_proba)):
for k in range(self.n_outputs_):
proba[k] += all_proba[j][k]
for k in range(self.n_outputs_):
proba[k] /= self.n_estimators
return proba
def predict_log_proba(self, X):
"""Predict class log-probabilities for X.
The predicted class log-probabilities of an input sample is computed as
the log of the mean predicted class probabilities of the trees in the
forest.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
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. The order of the
classes corresponds to that in the attribute `classes_`.
"""
proba = self.predict_proba(X)
if self.n_outputs_ == 1:
return np.log(proba)
else:
for k in range(self.n_outputs_):
proba[k] = np.log(proba[k])
return proba
class ForestRegressor(six.with_metaclass(ABCMeta, BaseForest, RegressorMixin)):
"""Base class for forest of trees-based regressors.
Warning: This class should not be used directly. Use derived classes
instead.
"""
@abstractmethod
def __init__(self,
base_estimator,
n_estimators=10,
estimator_params=tuple(),
bootstrap=False,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False):
super(ForestRegressor, self).__init__(
base_estimator,
n_estimators=n_estimators,
estimator_params=estimator_params,
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start)
def predict(self, X):
"""Predict regression target for X.
The predicted regression target of an input sample is computed as the
mean predicted regression targets of the trees in the forest.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
Returns
-------
y : array of shape = [n_samples] or [n_samples, n_outputs]
The predicted values.
"""
# Check data
X = self._validate_X_predict(X)
# Assign chunk of trees to jobs
n_jobs, _, _ = _partition_estimators(self.n_estimators, self.n_jobs)
# Parallel loop
all_y_hat = Parallel(n_jobs=n_jobs, verbose=self.verbose,
backend="threading")(
delayed(_parallel_helper)(e, 'predict', X, check_input=False)
for e in self.estimators_)
# Reduce
y_hat = sum(all_y_hat) / len(self.estimators_)
return y_hat
def _set_oob_score(self, X, y):
"""Compute out-of-bag scores"""
X = check_array(X, dtype=DTYPE, accept_sparse='csr')
n_samples = y.shape[0]
predictions = np.zeros((n_samples, self.n_outputs_))
n_predictions = np.zeros((n_samples, self.n_outputs_))
for estimator in self.estimators_:
unsampled_indices = _generate_unsampled_indices(
estimator.random_state, n_samples)
p_estimator = estimator.predict(
X[unsampled_indices, :], check_input=False)
if self.n_outputs_ == 1:
p_estimator = p_estimator[:, np.newaxis]
predictions[unsampled_indices, :] += p_estimator
n_predictions[unsampled_indices, :] += 1
if (n_predictions == 0).any():
warn("Some inputs do not have OOB scores. "
"This probably means too few trees were used "
"to compute any reliable oob estimates.")
n_predictions[n_predictions == 0] = 1
predictions /= n_predictions
self.oob_prediction_ = predictions
if self.n_outputs_ == 1:
self.oob_prediction_ = \
self.oob_prediction_.reshape((n_samples, ))
self.oob_score_ = 0.0
for k in range(self.n_outputs_):
self.oob_score_ += r2_score(y[:, k],
predictions[:, k])
self.oob_score_ /= self.n_outputs_
class RandomForestClassifier(ForestClassifier):
"""A random forest classifier.
A random forest is a meta estimator that fits a number of decision tree
classifiers on various sub-samples of the dataset and use averaging to
improve the predictive accuracy and control over-fitting.
The sub-sample size is always the same as the original
input sample size but the samples are drawn with replacement if
`bootstrap=True` (default).
Read more in the :ref:`User Guide <forest>`.
Parameters
----------
n_estimators : integer, optional (default=10)
The number of trees in the forest.
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.
Note: this parameter is tree-specific.
max_features : int, float, string or None, optional (default="auto")
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)` (same as "auto").
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.
Note: the search for a split does not stop until at least one
valid partition of the node samples is found, even if it requires to
effectively inspect more than ``max_features`` features.
Note: this parameter is tree-specific.
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.
Ignored if ``max_leaf_nodes`` is not None.
Note: this parameter is tree-specific.
min_samples_split : integer, optional (default=2)
The minimum number of samples required to split an internal node.
Note: this parameter is tree-specific.
min_samples_leaf : integer, optional (default=1)
The minimum number of samples in newly created leaves. A split is
discarded if after the split, one of the leaves would contain less then
``min_samples_leaf`` samples.
Note: this parameter is tree-specific.
min_weight_fraction_leaf : float, optional (default=0.)
The minimum weighted fraction of the input samples required to be at a
leaf node.
Note: this parameter is tree-specific.
max_leaf_nodes : int or None, optional (default=None)
Grow trees with ``max_leaf_nodes`` in best-first fashion.
Best nodes are defined as relative reduction in impurity.
If None then unlimited number of leaf nodes.
If not None then ``max_depth`` will be ignored.
Note: this parameter is tree-specific.
bootstrap : boolean, optional (default=True)
Whether bootstrap samples are used when building trees.
oob_score : bool
Whether to use out-of-bag samples to estimate
the generalization error.
n_jobs : integer, optional (default=1)
The number of jobs to run in parallel for both `fit` and `predict`.
If -1, then the number of jobs is set to the number of cores.
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`.
verbose : int, optional (default=0)
Controls the verbosity of the tree building process.
warm_start : bool, optional (default=False)
When set to ``True``, reuse the solution of the previous call to fit
and add more estimators to the ensemble, otherwise, just fit a whole
new forest.
class_weight : dict, list of dicts, "balanced", "balanced_subsample" or None, optional
Weights associated with classes in the form ``{class_label: weight}``.
If not given, all classes are supposed to have weight one. For
multi-output problems, a list of dicts can be provided in the same
order as the columns of y.
The "balanced" mode uses the values of y to automatically adjust
weights inversely proportional to class frequencies in the input data
as ``n_samples / (n_classes * np.bincount(y))``
The "balanced_subsample" mode is the same as "balanced" except that weights are
computed based on the bootstrap sample for every tree grown.
For multi-output, the weights of each column of y will be multiplied.
Note that these weights will be multiplied with sample_weight (passed
through the fit method) if sample_weight is specified.
Attributes
----------
estimators_ : list of DecisionTreeClassifier
The collection of fitted sub-estimators.
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 (single output problem), or a list containing the
number of classes for each output (multi-output problem).
n_features_ : int
The number of features when ``fit`` is performed.
n_outputs_ : int
The number of outputs when ``fit`` is performed.
feature_importances_ : array of shape = [n_features]
The feature importances (the higher, the more important the feature).
oob_score_ : float
Score of the training dataset obtained using an out-of-bag estimate.
oob_decision_function_ : array of shape = [n_samples, n_classes]
Decision function computed with out-of-bag estimate on the training
set. If n_estimators is small it might be possible that a data point
was never left out during the bootstrap. In this case,
`oob_decision_function_` might contain NaN.
References
----------
.. [1] L. Breiman, "Random Forests", Machine Learning, 45(1), 5-32, 2001.
See also
--------
DecisionTreeClassifier, ExtraTreesClassifier
"""
def __init__(self,
n_estimators=10,
criterion="gini",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
max_leaf_nodes=None,
bootstrap=True,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False,
class_weight=None):
super(RandomForestClassifier, self).__init__(
base_estimator=DecisionTreeClassifier(),
n_estimators=n_estimators,
estimator_params=("criterion", "max_depth", "min_samples_split",
"min_samples_leaf", "min_weight_fraction_leaf",
"max_features", "max_leaf_nodes",
"random_state"),
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start,
class_weight=class_weight)
self.criterion = criterion
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = max_features
self.max_leaf_nodes = max_leaf_nodes
class RandomForestRegressor(ForestRegressor):
"""A random forest regressor.
A random forest is a meta estimator that fits a number of classifying
decision trees on various sub-samples of the dataset and use averaging
to improve the predictive accuracy and control over-fitting.
The sub-sample size is always the same as the original
input sample size but the samples are drawn with replacement if
`bootstrap=True` (default).
Read more in the :ref:`User Guide <forest>`.
Parameters
----------
n_estimators : integer, optional (default=10)
The number of trees in the forest.
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.
Note: this parameter is tree-specific.
max_features : int, float, string or None, optional (default="auto")
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`.
Note: the search for a split does not stop until at least one
valid partition of the node samples is found, even if it requires to
effectively inspect more than ``max_features`` features.
Note: this parameter is tree-specific.
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.
Ignored if ``max_leaf_nodes`` is not None.
Note: this parameter is tree-specific.
min_samples_split : integer, optional (default=2)
The minimum number of samples required to split an internal node.
Note: this parameter is tree-specific.
min_samples_leaf : integer, optional (default=1)
The minimum number of samples in newly created leaves. A split is
discarded if after the split, one of the leaves would contain less then
``min_samples_leaf`` samples.
Note: this parameter is tree-specific.
min_weight_fraction_leaf : float, optional (default=0.)
The minimum weighted fraction of the input samples required to be at a
leaf node.
Note: this parameter is tree-specific.
max_leaf_nodes : int or None, optional (default=None)
Grow trees with ``max_leaf_nodes`` in best-first fashion.
Best nodes are defined as relative reduction in impurity.
If None then unlimited number of leaf nodes.
If not None then ``max_depth`` will be ignored.
Note: this parameter is tree-specific.
bootstrap : boolean, optional (default=True)
Whether bootstrap samples are used when building trees.
oob_score : bool
whether to use out-of-bag samples to estimate
the generalization error.
n_jobs : integer, optional (default=1)
The number of jobs to run in parallel for both `fit` and `predict`.
If -1, then the number of jobs is set to the number of cores.
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`.
verbose : int, optional (default=0)
Controls the verbosity of the tree building process.
warm_start : bool, optional (default=False)
When set to ``True``, reuse the solution of the previous call to fit
and add more estimators to the ensemble, otherwise, just fit a whole
new forest.
Attributes
----------
estimators_ : list of DecisionTreeRegressor
The collection of fitted sub-estimators.
feature_importances_ : array of shape = [n_features]
The feature importances (the higher, the more important the feature).
n_features_ : int
The number of features when ``fit`` is performed.
n_outputs_ : int
The number of outputs when ``fit`` is performed.
oob_score_ : float
Score of the training dataset obtained using an out-of-bag estimate.
oob_prediction_ : array of shape = [n_samples]
Prediction computed with out-of-bag estimate on the training set.
References
----------
.. [1] L. Breiman, "Random Forests", Machine Learning, 45(1), 5-32, 2001.
See also
--------
DecisionTreeRegressor, ExtraTreesRegressor
"""
def __init__(self,
n_estimators=10,
criterion="mse",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
max_leaf_nodes=None,
bootstrap=True,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False):
super(RandomForestRegressor, self).__init__(
base_estimator=DecisionTreeRegressor(),
n_estimators=n_estimators,
estimator_params=("criterion", "max_depth", "min_samples_split",
"min_samples_leaf", "min_weight_fraction_leaf",
"max_features", "max_leaf_nodes",
"random_state"),
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start)
self.criterion = criterion
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = max_features
self.max_leaf_nodes = max_leaf_nodes
class ExtraTreesClassifier(ForestClassifier):
"""An extra-trees classifier.
This class implements a meta estimator that fits a number of
randomized decision trees (a.k.a. extra-trees) on various sub-samples
of the dataset and use averaging to improve the predictive accuracy
and control over-fitting.
Read more in the :ref:`User Guide <forest>`.
Parameters
----------
n_estimators : integer, optional (default=10)
The number of trees in the forest.
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.
Note: this parameter is tree-specific.
max_features : int, float, string or None, optional (default="auto")
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`.
Note: the search for a split does not stop until at least one
valid partition of the node samples is found, even if it requires to
effectively inspect more than ``max_features`` features.
Note: this parameter is tree-specific.
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.
Ignored if ``max_leaf_nodes`` is not None.
Note: this parameter is tree-specific.
min_samples_split : integer, optional (default=2)
The minimum number of samples required to split an internal node.
Note: this parameter is tree-specific.
min_samples_leaf : integer, optional (default=1)
The minimum number of samples in newly created leaves. A split is
discarded if after the split, one of the leaves would contain less then
``min_samples_leaf`` samples.
Note: this parameter is tree-specific.
min_weight_fraction_leaf : float, optional (default=0.)
The minimum weighted fraction of the input samples required to be at a
leaf node.
Note: this parameter is tree-specific.
max_leaf_nodes : int or None, optional (default=None)
Grow trees with ``max_leaf_nodes`` in best-first fashion.
Best nodes are defined as relative reduction in impurity.
If None then unlimited number of leaf nodes.
If not None then ``max_depth`` will be ignored.
Note: this parameter is tree-specific.
bootstrap : boolean, optional (default=False)
Whether bootstrap samples are used when building trees.
oob_score : bool
Whether to use out-of-bag samples to estimate
the generalization error.
n_jobs : integer, optional (default=1)
The number of jobs to run in parallel for both `fit` and `predict`.
If -1, then the number of jobs is set to the number of cores.
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`.
verbose : int, optional (default=0)
Controls the verbosity of the tree building process.
warm_start : bool, optional (default=False)
When set to ``True``, reuse the solution of the previous call to fit
and add more estimators to the ensemble, otherwise, just fit a whole
new forest.
class_weight : dict, list of dicts, "balanced", "balanced_subsample" or None, optional
Weights associated with classes in the form ``{class_label: weight}``.
If not given, all classes are supposed to have weight one. For
multi-output problems, a list of dicts can be provided in the same
order as the columns of y.
The "balanced" mode uses the values of y to automatically adjust
weights inversely proportional to class frequencies in the input data
as ``n_samples / (n_classes * np.bincount(y))``
The "balanced_subsample" mode is the same as "balanced" except that weights are
computed based on the bootstrap sample for every tree grown.
For multi-output, the weights of each column of y will be multiplied.
Note that these weights will be multiplied with sample_weight (passed
through the fit method) if sample_weight is specified.
Attributes
----------
estimators_ : list of DecisionTreeClassifier
The collection of fitted sub-estimators.
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 (single output problem), or a list containing the
number of classes for each output (multi-output problem).
feature_importances_ : array of shape = [n_features]
The feature importances (the higher, the more important the feature).
n_features_ : int
The number of features when ``fit`` is performed.
n_outputs_ : int
The number of outputs when ``fit`` is performed.
oob_score_ : float
Score of the training dataset obtained using an out-of-bag estimate.
oob_decision_function_ : array of shape = [n_samples, n_classes]
Decision function computed with out-of-bag estimate on the training
set. If n_estimators is small it might be possible that a data point
was never left out during the bootstrap. In this case,
`oob_decision_function_` might contain NaN.
References
----------
.. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees",
Machine Learning, 63(1), 3-42, 2006.
See also
--------
sklearn.tree.ExtraTreeClassifier : Base classifier for this ensemble.
RandomForestClassifier : Ensemble Classifier based on trees with optimal
splits.
"""
def __init__(self,
n_estimators=10,
criterion="gini",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
max_leaf_nodes=None,
bootstrap=False,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False,
class_weight=None):
super(ExtraTreesClassifier, self).__init__(
base_estimator=ExtraTreeClassifier(),
n_estimators=n_estimators,
estimator_params=("criterion", "max_depth", "min_samples_split",
"min_samples_leaf", "min_weight_fraction_leaf",
"max_features", "max_leaf_nodes", "random_state"),
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start,
class_weight=class_weight)
self.criterion = criterion
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = max_features
self.max_leaf_nodes = max_leaf_nodes
class ExtraTreesRegressor(ForestRegressor):
"""An extra-trees regressor.
This class implements a meta estimator that fits a number of
randomized decision trees (a.k.a. extra-trees) on various sub-samples
of the dataset and use averaging to improve the predictive accuracy
and control over-fitting.
Read more in the :ref:`User Guide <forest>`.
Parameters
----------
n_estimators : integer, optional (default=10)
The number of trees in the forest.
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.
Note: this parameter is tree-specific.
max_features : int, float, string or None, optional (default="auto")
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`.
Note: the search for a split does not stop until at least one
valid partition of the node samples is found, even if it requires to
effectively inspect more than ``max_features`` features.
Note: this parameter is tree-specific.
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.
Ignored if ``max_leaf_nodes`` is not None.
Note: this parameter is tree-specific.
min_samples_split : integer, optional (default=2)
The minimum number of samples required to split an internal node.
Note: this parameter is tree-specific.
min_samples_leaf : integer, optional (default=1)
The minimum number of samples in newly created leaves. A split is
discarded if after the split, one of the leaves would contain less then
``min_samples_leaf`` samples.
Note: this parameter is tree-specific.
min_weight_fraction_leaf : float, optional (default=0.)
The minimum weighted fraction of the input samples required to be at a
leaf node.
Note: this parameter is tree-specific.
max_leaf_nodes : int or None, optional (default=None)
Grow trees with ``max_leaf_nodes`` in best-first fashion.
Best nodes are defined as relative reduction in impurity.
If None then unlimited number of leaf nodes.
If not None then ``max_depth`` will be ignored.
Note: this parameter is tree-specific.
bootstrap : boolean, optional (default=False)
Whether bootstrap samples are used when building trees.
Note: this parameter is tree-specific.
oob_score : bool
Whether to use out-of-bag samples to estimate
the generalization error.
n_jobs : integer, optional (default=1)
The number of jobs to run in parallel for both `fit` and `predict`.
If -1, then the number of jobs is set to the number of cores.
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`.
verbose : int, optional (default=0)
Controls the verbosity of the tree building process.
warm_start : bool, optional (default=False)
When set to ``True``, reuse the solution of the previous call to fit
and add more estimators to the ensemble, otherwise, just fit a whole
new forest.
Attributes
----------
estimators_ : list of DecisionTreeRegressor
The collection of fitted sub-estimators.
feature_importances_ : array of shape = [n_features]
The feature importances (the higher, the more important the feature).
n_features_ : int
The number of features.
n_outputs_ : int
The number of outputs.
oob_score_ : float
Score of the training dataset obtained using an out-of-bag estimate.
oob_prediction_ : array of shape = [n_samples]
Prediction computed with out-of-bag estimate on the training set.
References
----------
.. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees",
Machine Learning, 63(1), 3-42, 2006.
See also
--------
sklearn.tree.ExtraTreeRegressor: Base estimator for this ensemble.
RandomForestRegressor: Ensemble regressor using trees with optimal splits.
"""
def __init__(self,
n_estimators=10,
criterion="mse",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
max_leaf_nodes=None,
bootstrap=False,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False):
super(ExtraTreesRegressor, self).__init__(
base_estimator=ExtraTreeRegressor(),
n_estimators=n_estimators,
estimator_params=("criterion", "max_depth", "min_samples_split",
"min_samples_leaf", "min_weight_fraction_leaf",
"max_features", "max_leaf_nodes",
"random_state"),
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start)
self.criterion = criterion
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = max_features
self.max_leaf_nodes = max_leaf_nodes
class RandomTreesEmbedding(BaseForest):
"""An ensemble of totally random trees.
An unsupervised transformation of a dataset to a high-dimensional
sparse representation. A datapoint is coded according to which leaf of
each tree it is sorted into. Using a one-hot encoding of the leaves,
this leads to a binary coding with as many ones as there are trees in
the forest.
The dimensionality of the resulting representation is
``n_out <= n_estimators * max_leaf_nodes``. If ``max_leaf_nodes == None``,
the number of leaf nodes is at most ``n_estimators * 2 ** max_depth``.
Read more in the :ref:`User Guide <random_trees_embedding>`.
Parameters
----------
n_estimators : int
Number of trees in the forest.
max_depth : int
The maximum depth of each tree. If None, then nodes are expanded until
all leaves are pure or until all leaves contain less than
min_samples_split samples.
Ignored if ``max_leaf_nodes`` is not None.
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 in newly created leaves. A split is
discarded if after the split, one of the leaves would contain less then
``min_samples_leaf`` samples.
min_weight_fraction_leaf : float, optional (default=0.)
The minimum weighted fraction of the input samples required to be at a
leaf node.
max_leaf_nodes : int or None, optional (default=None)
Grow trees with ``max_leaf_nodes`` in best-first fashion.
Best nodes are defined as relative reduction in impurity.
If None then unlimited number of leaf nodes.
If not None then ``max_depth`` will be ignored.
sparse_output : bool, optional (default=True)
Whether or not to return a sparse CSR matrix, as default behavior,
or to return a dense array compatible with dense pipeline operators.
n_jobs : integer, optional (default=1)
The number of jobs to run in parallel for both `fit` and `predict`.
If -1, then the number of jobs is set to the number of cores.
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`.
verbose : int, optional (default=0)
Controls the verbosity of the tree building process.
warm_start : bool, optional (default=False)
When set to ``True``, reuse the solution of the previous call to fit
and add more estimators to the ensemble, otherwise, just fit a whole
new forest.
Attributes
----------
estimators_ : list of DecisionTreeClassifier
The collection of fitted sub-estimators.
References
----------
.. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees",
Machine Learning, 63(1), 3-42, 2006.
.. [2] Moosmann, F. and Triggs, B. and Jurie, F. "Fast discriminative
visual codebooks using randomized clustering forests"
NIPS 2007
"""
def __init__(self,
n_estimators=10,
max_depth=5,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_leaf_nodes=None,
sparse_output=True,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False):
super(RandomTreesEmbedding, self).__init__(
base_estimator=ExtraTreeRegressor(),
n_estimators=n_estimators,
estimator_params=("criterion", "max_depth", "min_samples_split",
"min_samples_leaf", "min_weight_fraction_leaf",
"max_features", "max_leaf_nodes",
"random_state"),
bootstrap=False,
oob_score=False,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start)
self.criterion = 'mse'
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = 1
self.max_leaf_nodes = max_leaf_nodes
self.sparse_output = sparse_output
def _set_oob_score(self, X, y):
raise NotImplementedError("OOB score not supported by tree embedding")
def fit(self, X, y=None, sample_weight=None):
"""Fit estimator.
Parameters
----------
X : array-like or sparse matrix, shape=(n_samples, n_features)
The input samples. Use ``dtype=np.float32`` for maximum
efficiency. Sparse matrices are also supported, use sparse
``csc_matrix`` for maximum efficiency.
Returns
-------
self : object
Returns self.
"""
self.fit_transform(X, y, sample_weight=sample_weight)
return self
def fit_transform(self, X, y=None, sample_weight=None):
"""Fit estimator and transform dataset.
Parameters
----------
X : array-like or sparse matrix, shape=(n_samples, n_features)
Input data used to build forests. Use ``dtype=np.float32`` for
maximum efficiency.
Returns
-------
X_transformed : sparse matrix, shape=(n_samples, n_out)
Transformed dataset.
"""
# ensure_2d=False because there are actually unit test checking we fail
# for 1d.
X = check_array(X, accept_sparse=['csc'], ensure_2d=False)
if issparse(X):
# Pre-sort indices to avoid that each individual tree of the
# ensemble sorts the indices.
X.sort_indices()
rnd = check_random_state(self.random_state)
y = rnd.uniform(size=X.shape[0])
super(RandomTreesEmbedding, self).fit(X, y,
sample_weight=sample_weight)
self.one_hot_encoder_ = OneHotEncoder(sparse=self.sparse_output)
return self.one_hot_encoder_.fit_transform(self.apply(X))
def transform(self, X):
"""Transform dataset.
Parameters
----------
X : array-like or sparse matrix, shape=(n_samples, n_features)
Input data to be transformed. Use ``dtype=np.float32`` for maximum
efficiency. Sparse matrices are also supported, use sparse
``csr_matrix`` for maximum efficiency.
Returns
-------
X_transformed : sparse matrix, shape=(n_samples, n_out)
Transformed dataset.
"""
return self.one_hot_encoder_.transform(self.apply(X))
|