995 lines
37 KiB
Python
995 lines
37 KiB
Python
"""Bagging meta-estimator."""
|
|
|
|
# Author: Gilles Louppe <g.louppe@gmail.com>
|
|
# License: BSD 3 clause
|
|
|
|
from __future__ import division
|
|
|
|
import itertools
|
|
import numbers
|
|
import numpy as np
|
|
from warnings import warn
|
|
from abc import ABCMeta, abstractmethod
|
|
|
|
from ..base import ClassifierMixin, RegressorMixin
|
|
from ..externals.joblib import Parallel, delayed
|
|
from ..externals.six import with_metaclass
|
|
from ..externals.six.moves import zip
|
|
from ..metrics import r2_score, accuracy_score
|
|
from ..tree import DecisionTreeClassifier, DecisionTreeRegressor
|
|
from ..utils import check_random_state, check_X_y, check_array, column_or_1d
|
|
from ..utils.random import sample_without_replacement
|
|
from ..utils.validation import has_fit_parameter, check_is_fitted
|
|
from ..utils import indices_to_mask, check_consistent_length
|
|
from ..utils.metaestimators import if_delegate_has_method
|
|
from ..utils.multiclass import check_classification_targets
|
|
|
|
from .base import BaseEnsemble, _partition_estimators
|
|
|
|
|
|
__all__ = ["BaggingClassifier",
|
|
"BaggingRegressor"]
|
|
|
|
MAX_INT = np.iinfo(np.int32).max
|
|
|
|
|
|
def _generate_indices(random_state, bootstrap, n_population, n_samples):
|
|
"""Draw randomly sampled indices."""
|
|
# Draw sample indices
|
|
if bootstrap:
|
|
indices = random_state.randint(0, n_population, n_samples)
|
|
else:
|
|
indices = sample_without_replacement(n_population, n_samples,
|
|
random_state=random_state)
|
|
|
|
return indices
|
|
|
|
|
|
def _generate_bagging_indices(random_state, bootstrap_features,
|
|
bootstrap_samples, n_features, n_samples,
|
|
max_features, max_samples):
|
|
"""Randomly draw feature and sample indices."""
|
|
# Get valid random state
|
|
random_state = check_random_state(random_state)
|
|
|
|
# Draw indices
|
|
feature_indices = _generate_indices(random_state, bootstrap_features,
|
|
n_features, max_features)
|
|
sample_indices = _generate_indices(random_state, bootstrap_samples,
|
|
n_samples, max_samples)
|
|
|
|
return feature_indices, sample_indices
|
|
|
|
|
|
def _parallel_build_estimators(n_estimators, ensemble, X, y, sample_weight,
|
|
seeds, total_n_estimators, verbose):
|
|
"""Private function used to build a batch of estimators within a job."""
|
|
# Retrieve settings
|
|
n_samples, n_features = X.shape
|
|
max_features = ensemble._max_features
|
|
max_samples = ensemble._max_samples
|
|
bootstrap = ensemble.bootstrap
|
|
bootstrap_features = ensemble.bootstrap_features
|
|
support_sample_weight = has_fit_parameter(ensemble.base_estimator_,
|
|
"sample_weight")
|
|
if not support_sample_weight and sample_weight is not None:
|
|
raise ValueError("The base estimator doesn't support sample weight")
|
|
|
|
# Build estimators
|
|
estimators = []
|
|
estimators_features = []
|
|
|
|
for i in range(n_estimators):
|
|
if verbose > 1:
|
|
print("Building estimator %d of %d for this parallel run "
|
|
"(total %d)..." % (i + 1, n_estimators, total_n_estimators))
|
|
|
|
random_state = np.random.RandomState(seeds[i])
|
|
estimator = ensemble._make_estimator(append=False,
|
|
random_state=random_state)
|
|
|
|
# Draw random feature, sample indices
|
|
features, indices = _generate_bagging_indices(random_state,
|
|
bootstrap_features,
|
|
bootstrap, n_features,
|
|
n_samples, max_features,
|
|
max_samples)
|
|
|
|
# Draw samples, using sample weights, and then fit
|
|
if support_sample_weight:
|
|
if sample_weight is None:
|
|
curr_sample_weight = np.ones((n_samples,))
|
|
else:
|
|
curr_sample_weight = sample_weight.copy()
|
|
|
|
if bootstrap:
|
|
sample_counts = np.bincount(indices, minlength=n_samples)
|
|
curr_sample_weight *= sample_counts
|
|
else:
|
|
not_indices_mask = ~indices_to_mask(indices, n_samples)
|
|
curr_sample_weight[not_indices_mask] = 0
|
|
|
|
estimator.fit(X[:, features], y, sample_weight=curr_sample_weight)
|
|
|
|
# Draw samples, using a mask, and then fit
|
|
else:
|
|
estimator.fit((X[indices])[:, features], y[indices])
|
|
|
|
estimators.append(estimator)
|
|
estimators_features.append(features)
|
|
|
|
return estimators, estimators_features
|
|
|
|
|
|
def _parallel_predict_proba(estimators, estimators_features, X, n_classes):
|
|
"""Private function used to compute (proba-)predictions within a job."""
|
|
n_samples = X.shape[0]
|
|
proba = np.zeros((n_samples, n_classes))
|
|
|
|
for estimator, features in zip(estimators, estimators_features):
|
|
if hasattr(estimator, "predict_proba"):
|
|
proba_estimator = estimator.predict_proba(X[:, features])
|
|
|
|
if n_classes == len(estimator.classes_):
|
|
proba += proba_estimator
|
|
|
|
else:
|
|
proba[:, estimator.classes_] += \
|
|
proba_estimator[:, range(len(estimator.classes_))]
|
|
|
|
else:
|
|
# Resort to voting
|
|
predictions = estimator.predict(X[:, features])
|
|
|
|
for i in range(n_samples):
|
|
proba[i, predictions[i]] += 1
|
|
|
|
return proba
|
|
|
|
|
|
def _parallel_predict_log_proba(estimators, estimators_features, X, n_classes):
|
|
"""Private function used to compute log probabilities within a job."""
|
|
n_samples = X.shape[0]
|
|
log_proba = np.empty((n_samples, n_classes))
|
|
log_proba.fill(-np.inf)
|
|
all_classes = np.arange(n_classes, dtype=np.int)
|
|
|
|
for estimator, features in zip(estimators, estimators_features):
|
|
log_proba_estimator = estimator.predict_log_proba(X[:, features])
|
|
|
|
if n_classes == len(estimator.classes_):
|
|
log_proba = np.logaddexp(log_proba, log_proba_estimator)
|
|
|
|
else:
|
|
log_proba[:, estimator.classes_] = np.logaddexp(
|
|
log_proba[:, estimator.classes_],
|
|
log_proba_estimator[:, range(len(estimator.classes_))])
|
|
|
|
missing = np.setdiff1d(all_classes, estimator.classes_)
|
|
log_proba[:, missing] = np.logaddexp(log_proba[:, missing],
|
|
-np.inf)
|
|
|
|
return log_proba
|
|
|
|
|
|
def _parallel_decision_function(estimators, estimators_features, X):
|
|
"""Private function used to compute decisions within a job."""
|
|
return sum(estimator.decision_function(X[:, features])
|
|
for estimator, features in zip(estimators,
|
|
estimators_features))
|
|
|
|
|
|
def _parallel_predict_regression(estimators, estimators_features, X):
|
|
"""Private function used to compute predictions within a job."""
|
|
return sum(estimator.predict(X[:, features])
|
|
for estimator, features in zip(estimators,
|
|
estimators_features))
|
|
|
|
|
|
class BaseBagging(with_metaclass(ABCMeta, BaseEnsemble)):
|
|
"""Base class for Bagging meta-estimator.
|
|
|
|
Warning: This class should not be used directly. Use derived classes
|
|
instead.
|
|
"""
|
|
|
|
@abstractmethod
|
|
def __init__(self,
|
|
base_estimator=None,
|
|
n_estimators=10,
|
|
max_samples=1.0,
|
|
max_features=1.0,
|
|
bootstrap=True,
|
|
bootstrap_features=False,
|
|
oob_score=False,
|
|
warm_start=False,
|
|
n_jobs=1,
|
|
random_state=None,
|
|
verbose=0):
|
|
super(BaseBagging, self).__init__(
|
|
base_estimator=base_estimator,
|
|
n_estimators=n_estimators)
|
|
|
|
self.max_samples = max_samples
|
|
self.max_features = max_features
|
|
self.bootstrap = bootstrap
|
|
self.bootstrap_features = bootstrap_features
|
|
self.oob_score = oob_score
|
|
self.warm_start = warm_start
|
|
self.n_jobs = n_jobs
|
|
self.random_state = random_state
|
|
self.verbose = verbose
|
|
|
|
def fit(self, X, y, sample_weight=None):
|
|
"""Build a Bagging ensemble of estimators from the training
|
|
set (X, y).
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix} of shape = [n_samples, n_features]
|
|
The training input samples. Sparse matrices are accepted only if
|
|
they are supported by the base estimator.
|
|
|
|
y : array-like, shape = [n_samples]
|
|
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.
|
|
Note that this is supported only if the base estimator supports
|
|
sample weighting.
|
|
|
|
Returns
|
|
-------
|
|
self : object
|
|
Returns self.
|
|
"""
|
|
return self._fit(X, y, self.max_samples, sample_weight=sample_weight)
|
|
|
|
def _fit(self, X, y, max_samples=None, max_depth=None, sample_weight=None):
|
|
"""Build a Bagging ensemble of estimators from the training
|
|
set (X, y).
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix} of shape = [n_samples, n_features]
|
|
The training input samples. Sparse matrices are accepted only if
|
|
they are supported by the base estimator.
|
|
|
|
y : array-like, shape = [n_samples]
|
|
The target values (class labels in classification, real numbers in
|
|
regression).
|
|
|
|
max_samples : int or float, optional (default=None)
|
|
Argument to use instead of self.max_samples.
|
|
|
|
max_depth : int, optional (default=None)
|
|
Override value used when constructing base estimator. Only
|
|
supported if the base estimator has a max_depth parameter.
|
|
|
|
sample_weight : array-like, shape = [n_samples] or None
|
|
Sample weights. If None, then samples are equally weighted.
|
|
Note that this is supported only if the base estimator supports
|
|
sample weighting.
|
|
|
|
Returns
|
|
-------
|
|
self : object
|
|
Returns self.
|
|
"""
|
|
random_state = check_random_state(self.random_state)
|
|
|
|
# Convert data
|
|
X, y = check_X_y(X, y, ['csr', 'csc'])
|
|
if sample_weight is not None:
|
|
sample_weight = check_array(sample_weight, ensure_2d=False)
|
|
check_consistent_length(y, sample_weight)
|
|
|
|
# Remap output
|
|
n_samples, self.n_features_ = X.shape
|
|
self._n_samples = n_samples
|
|
y = self._validate_y(y)
|
|
|
|
# Check parameters
|
|
self._validate_estimator()
|
|
|
|
if max_depth is not None:
|
|
self.base_estimator_.max_depth = max_depth
|
|
|
|
# Validate max_samples
|
|
if max_samples is None:
|
|
max_samples = self.max_samples
|
|
elif not isinstance(max_samples, (numbers.Integral, np.integer)):
|
|
max_samples = int(max_samples * X.shape[0])
|
|
|
|
if not (0 < max_samples <= X.shape[0]):
|
|
raise ValueError("max_samples must be in (0, n_samples]")
|
|
|
|
# Store validated integer row sampling value
|
|
self._max_samples = max_samples
|
|
|
|
# Validate max_features
|
|
if 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 not (0 < max_features <= self.n_features_):
|
|
raise ValueError("max_features must be in (0, n_features]")
|
|
|
|
# Store validated integer feature sampling value
|
|
self._max_features = max_features
|
|
|
|
# Other checks
|
|
if not self.bootstrap and self.oob_score:
|
|
raise ValueError("Out of bag estimation only available"
|
|
" if bootstrap=True")
|
|
|
|
if self.warm_start and self.oob_score:
|
|
raise ValueError("Out of bag estimate only available"
|
|
" if warm_start=False")
|
|
|
|
if hasattr(self, "oob_score_") and self.warm_start:
|
|
del self.oob_score_
|
|
|
|
if not self.warm_start or not hasattr(self, 'estimators_'):
|
|
# Free allocated memory, if any
|
|
self.estimators_ = []
|
|
self.estimators_features_ = []
|
|
|
|
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.")
|
|
return self
|
|
|
|
# Parallel loop
|
|
n_jobs, n_estimators, starts = _partition_estimators(n_more_estimators,
|
|
self.n_jobs)
|
|
total_n_estimators = sum(n_estimators)
|
|
|
|
# Advance random state to state after training
|
|
# the first n_estimators
|
|
if self.warm_start and len(self.estimators_) > 0:
|
|
random_state.randint(MAX_INT, size=len(self.estimators_))
|
|
|
|
seeds = random_state.randint(MAX_INT, size=n_more_estimators)
|
|
self._seeds = seeds
|
|
|
|
all_results = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
|
|
delayed(_parallel_build_estimators)(
|
|
n_estimators[i],
|
|
self,
|
|
X,
|
|
y,
|
|
sample_weight,
|
|
seeds[starts[i]:starts[i + 1]],
|
|
total_n_estimators,
|
|
verbose=self.verbose)
|
|
for i in range(n_jobs))
|
|
|
|
# Reduce
|
|
self.estimators_ += list(itertools.chain.from_iterable(
|
|
t[0] for t in all_results))
|
|
self.estimators_features_ += list(itertools.chain.from_iterable(
|
|
t[1] for t in all_results))
|
|
|
|
if self.oob_score:
|
|
self._set_oob_score(X, y)
|
|
|
|
return self
|
|
|
|
@abstractmethod
|
|
def _set_oob_score(self, X, y):
|
|
"""Calculate out of bag predictions and score."""
|
|
|
|
def _validate_y(self, y):
|
|
# Default implementation
|
|
return column_or_1d(y, warn=True)
|
|
|
|
def _get_estimators_indices(self):
|
|
# Get drawn indices along both sample and feature axes
|
|
for seed in self._seeds:
|
|
# Operations accessing random_state must be performed identically
|
|
# to those in `_parallel_build_estimators()`
|
|
random_state = np.random.RandomState(seed)
|
|
feature_indices, sample_indices = _generate_bagging_indices(
|
|
random_state, self.bootstrap_features, self.bootstrap,
|
|
self.n_features_, self._n_samples, self._max_features,
|
|
self._max_samples)
|
|
|
|
yield feature_indices, sample_indices
|
|
|
|
@property
|
|
def estimators_samples_(self):
|
|
"""The subset of drawn samples for each base estimator.
|
|
|
|
Returns a dynamically generated list of boolean masks identifying
|
|
the samples used for fitting each member of the ensemble, i.e.,
|
|
the in-bag samples.
|
|
|
|
Note: the list is re-created at each call to the property in order
|
|
to reduce the object memory footprint by not storing the sampling
|
|
data. Thus fetching the property may be slower than expected.
|
|
"""
|
|
sample_masks = []
|
|
for _, sample_indices in self._get_estimators_indices():
|
|
mask = indices_to_mask(sample_indices, self._n_samples)
|
|
sample_masks.append(mask)
|
|
|
|
return sample_masks
|
|
|
|
|
|
class BaggingClassifier(BaseBagging, ClassifierMixin):
|
|
"""A Bagging classifier.
|
|
|
|
A Bagging classifier is an ensemble meta-estimator that fits base
|
|
classifiers each on random subsets of the original dataset and then
|
|
aggregate their individual predictions (either by voting or by averaging)
|
|
to form a final prediction. Such a meta-estimator can typically be used as
|
|
a way to reduce the variance of a black-box estimator (e.g., a decision
|
|
tree), by introducing randomization into its construction procedure and
|
|
then making an ensemble out of it.
|
|
|
|
This algorithm encompasses several works from the literature. When random
|
|
subsets of the dataset are drawn as random subsets of the samples, then
|
|
this algorithm is known as Pasting [1]_. If samples are drawn with
|
|
replacement, then the method is known as Bagging [2]_. When random subsets
|
|
of the dataset are drawn as random subsets of the features, then the method
|
|
is known as Random Subspaces [3]_. Finally, when base estimators are built
|
|
on subsets of both samples and features, then the method is known as
|
|
Random Patches [4]_.
|
|
|
|
Read more in the :ref:`User Guide <bagging>`.
|
|
|
|
Parameters
|
|
----------
|
|
base_estimator : object or None, optional (default=None)
|
|
The base estimator to fit on random subsets of the dataset.
|
|
If None, then the base estimator is a decision tree.
|
|
|
|
n_estimators : int, optional (default=10)
|
|
The number of base estimators in the ensemble.
|
|
|
|
max_samples : int or float, optional (default=1.0)
|
|
The number of samples to draw from X to train each base estimator.
|
|
- If int, then draw `max_samples` samples.
|
|
- If float, then draw `max_samples * X.shape[0]` samples.
|
|
|
|
max_features : int or float, optional (default=1.0)
|
|
The number of features to draw from X to train each base estimator.
|
|
- If int, then draw `max_features` features.
|
|
- If float, then draw `max_features * X.shape[1]` features.
|
|
|
|
bootstrap : boolean, optional (default=True)
|
|
Whether samples are drawn with replacement.
|
|
|
|
bootstrap_features : boolean, optional (default=False)
|
|
Whether features are drawn with replacement.
|
|
|
|
oob_score : bool
|
|
Whether to use out-of-bag samples to estimate
|
|
the generalization error.
|
|
|
|
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 ensemble.
|
|
|
|
.. versionadded:: 0.17
|
|
*warm_start* constructor parameter.
|
|
|
|
n_jobs : int, 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 building process.
|
|
|
|
Attributes
|
|
----------
|
|
base_estimator_ : estimator
|
|
The base estimator from which the ensemble is grown.
|
|
|
|
estimators_ : list of estimators
|
|
The collection of fitted base estimators.
|
|
|
|
estimators_samples_ : list of arrays
|
|
The subset of drawn samples (i.e., the in-bag samples) for each base
|
|
estimator. Each subset is defined by a boolean mask.
|
|
|
|
estimators_features_ : list of arrays
|
|
The subset of drawn features for each base estimator.
|
|
|
|
classes_ : array of shape = [n_classes]
|
|
The classes labels.
|
|
|
|
n_classes_ : int or list
|
|
The number of classes.
|
|
|
|
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, "Pasting small votes for classification in large
|
|
databases and on-line", Machine Learning, 36(1), 85-103, 1999.
|
|
|
|
.. [2] L. Breiman, "Bagging predictors", Machine Learning, 24(2), 123-140,
|
|
1996.
|
|
|
|
.. [3] T. Ho, "The random subspace method for constructing decision
|
|
forests", Pattern Analysis and Machine Intelligence, 20(8), 832-844,
|
|
1998.
|
|
|
|
.. [4] G. Louppe and P. Geurts, "Ensembles on Random Patches", Machine
|
|
Learning and Knowledge Discovery in Databases, 346-361, 2012.
|
|
"""
|
|
def __init__(self,
|
|
base_estimator=None,
|
|
n_estimators=10,
|
|
max_samples=1.0,
|
|
max_features=1.0,
|
|
bootstrap=True,
|
|
bootstrap_features=False,
|
|
oob_score=False,
|
|
warm_start=False,
|
|
n_jobs=1,
|
|
random_state=None,
|
|
verbose=0):
|
|
|
|
super(BaggingClassifier, self).__init__(
|
|
base_estimator,
|
|
n_estimators=n_estimators,
|
|
max_samples=max_samples,
|
|
max_features=max_features,
|
|
bootstrap=bootstrap,
|
|
bootstrap_features=bootstrap_features,
|
|
oob_score=oob_score,
|
|
warm_start=warm_start,
|
|
n_jobs=n_jobs,
|
|
random_state=random_state,
|
|
verbose=verbose)
|
|
|
|
def _validate_estimator(self):
|
|
"""Check the estimator and set the base_estimator_ attribute."""
|
|
super(BaggingClassifier, self)._validate_estimator(
|
|
default=DecisionTreeClassifier())
|
|
|
|
def _set_oob_score(self, X, y):
|
|
n_samples = y.shape[0]
|
|
n_classes_ = self.n_classes_
|
|
classes_ = self.classes_
|
|
|
|
predictions = np.zeros((n_samples, n_classes_))
|
|
|
|
for estimator, samples, features in zip(self.estimators_,
|
|
self.estimators_samples_,
|
|
self.estimators_features_):
|
|
# Create mask for OOB samples
|
|
mask = ~samples
|
|
|
|
if hasattr(estimator, "predict_proba"):
|
|
predictions[mask, :] += estimator.predict_proba(
|
|
(X[mask, :])[:, features])
|
|
|
|
else:
|
|
p = estimator.predict((X[mask, :])[:, features])
|
|
j = 0
|
|
|
|
for i in range(n_samples):
|
|
if mask[i]:
|
|
predictions[i, p[j]] += 1
|
|
j += 1
|
|
|
|
if (predictions.sum(axis=1) == 0).any():
|
|
warn("Some inputs do not have OOB scores. "
|
|
"This probably means too few estimators were used "
|
|
"to compute any reliable oob estimates.")
|
|
|
|
oob_decision_function = (predictions /
|
|
predictions.sum(axis=1)[:, np.newaxis])
|
|
oob_score = accuracy_score(y, np.argmax(predictions, axis=1))
|
|
|
|
self.oob_decision_function_ = oob_decision_function
|
|
self.oob_score_ = oob_score
|
|
|
|
def _validate_y(self, y):
|
|
y = column_or_1d(y, warn=True)
|
|
check_classification_targets(y)
|
|
self.classes_, y = np.unique(y, return_inverse=True)
|
|
self.n_classes_ = len(self.classes_)
|
|
|
|
return y
|
|
|
|
def predict(self, X):
|
|
"""Predict class for X.
|
|
|
|
The predicted class of an input sample is computed as the class with
|
|
the highest mean predicted probability. If base estimators do not
|
|
implement a ``predict_proba`` method, then it resorts to voting.
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix} of shape = [n_samples, n_features]
|
|
The training input samples. Sparse matrices are accepted only if
|
|
they are supported by the base estimator.
|
|
|
|
Returns
|
|
-------
|
|
y : array of shape = [n_samples]
|
|
The predicted classes.
|
|
"""
|
|
predicted_probabilitiy = self.predict_proba(X)
|
|
return self.classes_.take((np.argmax(predicted_probabilitiy, axis=1)),
|
|
axis=0)
|
|
|
|
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 base estimators in the
|
|
ensemble. If base estimators do not implement a ``predict_proba``
|
|
method, then it resorts to voting and the predicted class probabilities
|
|
of an input sample represents the proportion of estimators predicting
|
|
each class.
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix} of shape = [n_samples, n_features]
|
|
The training input samples. Sparse matrices are accepted only if
|
|
they are supported by the base estimator.
|
|
|
|
Returns
|
|
-------
|
|
p : array of shape = [n_samples, n_classes]
|
|
The class probabilities of the input samples. The order of the
|
|
classes corresponds to that in the attribute `classes_`.
|
|
"""
|
|
check_is_fitted(self, "classes_")
|
|
# Check data
|
|
X = check_array(X, accept_sparse=['csr', 'csc'])
|
|
|
|
if self.n_features_ != X.shape[1]:
|
|
raise ValueError("Number of features of the model must "
|
|
"match the input. Model n_features is {0} and "
|
|
"input n_features is {1}."
|
|
"".format(self.n_features_, X.shape[1]))
|
|
|
|
# Parallel loop
|
|
n_jobs, n_estimators, starts = _partition_estimators(self.n_estimators,
|
|
self.n_jobs)
|
|
|
|
all_proba = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
|
|
delayed(_parallel_predict_proba)(
|
|
self.estimators_[starts[i]:starts[i + 1]],
|
|
self.estimators_features_[starts[i]:starts[i + 1]],
|
|
X,
|
|
self.n_classes_)
|
|
for i in range(n_jobs))
|
|
|
|
# Reduce
|
|
proba = sum(all_proba) / 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 base
|
|
estimators in the ensemble.
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix} of shape = [n_samples, n_features]
|
|
The training input samples. Sparse matrices are accepted only if
|
|
they are supported by the base estimator.
|
|
|
|
Returns
|
|
-------
|
|
p : array of shape = [n_samples, n_classes]
|
|
The class log-probabilities of the input samples. The order of the
|
|
classes corresponds to that in the attribute `classes_`.
|
|
"""
|
|
check_is_fitted(self, "classes_")
|
|
if hasattr(self.base_estimator_, "predict_log_proba"):
|
|
# Check data
|
|
X = check_array(X, accept_sparse=['csr', 'csc'])
|
|
|
|
if self.n_features_ != X.shape[1]:
|
|
raise ValueError("Number of features of the model must "
|
|
"match the input. Model n_features is {0} "
|
|
"and input n_features is {1} "
|
|
"".format(self.n_features_, X.shape[1]))
|
|
|
|
# Parallel loop
|
|
n_jobs, n_estimators, starts = _partition_estimators(
|
|
self.n_estimators, self.n_jobs)
|
|
|
|
all_log_proba = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
|
|
delayed(_parallel_predict_log_proba)(
|
|
self.estimators_[starts[i]:starts[i + 1]],
|
|
self.estimators_features_[starts[i]:starts[i + 1]],
|
|
X,
|
|
self.n_classes_)
|
|
for i in range(n_jobs))
|
|
|
|
# Reduce
|
|
log_proba = all_log_proba[0]
|
|
|
|
for j in range(1, len(all_log_proba)):
|
|
log_proba = np.logaddexp(log_proba, all_log_proba[j])
|
|
|
|
log_proba -= np.log(self.n_estimators)
|
|
|
|
return log_proba
|
|
|
|
else:
|
|
return np.log(self.predict_proba(X))
|
|
|
|
@if_delegate_has_method(delegate='base_estimator')
|
|
def decision_function(self, X):
|
|
"""Average of the decision functions of the base classifiers.
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix} of shape = [n_samples, n_features]
|
|
The training input samples. Sparse matrices are accepted only if
|
|
they are supported by the base estimator.
|
|
|
|
Returns
|
|
-------
|
|
score : array, shape = [n_samples, k]
|
|
The decision function of the input samples. The columns correspond
|
|
to the classes in sorted order, as they appear in the attribute
|
|
``classes_``. Regression and binary classification are special
|
|
cases with ``k == 1``, otherwise ``k==n_classes``.
|
|
|
|
"""
|
|
check_is_fitted(self, "classes_")
|
|
|
|
# Check data
|
|
X = check_array(X, accept_sparse=['csr', 'csc'])
|
|
|
|
if self.n_features_ != X.shape[1]:
|
|
raise ValueError("Number of features of the model must "
|
|
"match the input. Model n_features is {0} and "
|
|
"input n_features is {1} "
|
|
"".format(self.n_features_, X.shape[1]))
|
|
|
|
# Parallel loop
|
|
n_jobs, n_estimators, starts = _partition_estimators(self.n_estimators,
|
|
self.n_jobs)
|
|
|
|
all_decisions = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
|
|
delayed(_parallel_decision_function)(
|
|
self.estimators_[starts[i]:starts[i + 1]],
|
|
self.estimators_features_[starts[i]:starts[i + 1]],
|
|
X)
|
|
for i in range(n_jobs))
|
|
|
|
# Reduce
|
|
decisions = sum(all_decisions) / self.n_estimators
|
|
|
|
return decisions
|
|
|
|
|
|
class BaggingRegressor(BaseBagging, RegressorMixin):
|
|
"""A Bagging regressor.
|
|
|
|
A Bagging regressor is an ensemble meta-estimator that fits base
|
|
regressors each on random subsets of the original dataset and then
|
|
aggregate their individual predictions (either by voting or by averaging)
|
|
to form a final prediction. Such a meta-estimator can typically be used as
|
|
a way to reduce the variance of a black-box estimator (e.g., a decision
|
|
tree), by introducing randomization into its construction procedure and
|
|
then making an ensemble out of it.
|
|
|
|
This algorithm encompasses several works from the literature. When random
|
|
subsets of the dataset are drawn as random subsets of the samples, then
|
|
this algorithm is known as Pasting [1]_. If samples are drawn with
|
|
replacement, then the method is known as Bagging [2]_. When random subsets
|
|
of the dataset are drawn as random subsets of the features, then the method
|
|
is known as Random Subspaces [3]_. Finally, when base estimators are built
|
|
on subsets of both samples and features, then the method is known as
|
|
Random Patches [4]_.
|
|
|
|
Read more in the :ref:`User Guide <bagging>`.
|
|
|
|
Parameters
|
|
----------
|
|
base_estimator : object or None, optional (default=None)
|
|
The base estimator to fit on random subsets of the dataset.
|
|
If None, then the base estimator is a decision tree.
|
|
|
|
n_estimators : int, optional (default=10)
|
|
The number of base estimators in the ensemble.
|
|
|
|
max_samples : int or float, optional (default=1.0)
|
|
The number of samples to draw from X to train each base estimator.
|
|
- If int, then draw `max_samples` samples.
|
|
- If float, then draw `max_samples * X.shape[0]` samples.
|
|
|
|
max_features : int or float, optional (default=1.0)
|
|
The number of features to draw from X to train each base estimator.
|
|
- If int, then draw `max_features` features.
|
|
- If float, then draw `max_features * X.shape[1]` features.
|
|
|
|
bootstrap : boolean, optional (default=True)
|
|
Whether samples are drawn with replacement.
|
|
|
|
bootstrap_features : boolean, optional (default=False)
|
|
Whether features are drawn with replacement.
|
|
|
|
oob_score : bool
|
|
Whether to use out-of-bag samples to estimate
|
|
the generalization error.
|
|
|
|
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 ensemble.
|
|
|
|
n_jobs : int, 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 building process.
|
|
|
|
Attributes
|
|
----------
|
|
estimators_ : list of estimators
|
|
The collection of fitted sub-estimators.
|
|
|
|
estimators_samples_ : list of arrays
|
|
The subset of drawn samples (i.e., the in-bag samples) for each base
|
|
estimator. Each subset is defined by a boolean mask.
|
|
|
|
estimators_features_ : list of arrays
|
|
The subset of drawn features for each base estimator.
|
|
|
|
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. If n_estimators is small it might be possible that a data point
|
|
was never left out during the bootstrap. In this case,
|
|
`oob_prediction_` might contain NaN.
|
|
|
|
References
|
|
----------
|
|
|
|
.. [1] L. Breiman, "Pasting small votes for classification in large
|
|
databases and on-line", Machine Learning, 36(1), 85-103, 1999.
|
|
|
|
.. [2] L. Breiman, "Bagging predictors", Machine Learning, 24(2), 123-140,
|
|
1996.
|
|
|
|
.. [3] T. Ho, "The random subspace method for constructing decision
|
|
forests", Pattern Analysis and Machine Intelligence, 20(8), 832-844,
|
|
1998.
|
|
|
|
.. [4] G. Louppe and P. Geurts, "Ensembles on Random Patches", Machine
|
|
Learning and Knowledge Discovery in Databases, 346-361, 2012.
|
|
"""
|
|
|
|
def __init__(self,
|
|
base_estimator=None,
|
|
n_estimators=10,
|
|
max_samples=1.0,
|
|
max_features=1.0,
|
|
bootstrap=True,
|
|
bootstrap_features=False,
|
|
oob_score=False,
|
|
warm_start=False,
|
|
n_jobs=1,
|
|
random_state=None,
|
|
verbose=0):
|
|
super(BaggingRegressor, self).__init__(
|
|
base_estimator,
|
|
n_estimators=n_estimators,
|
|
max_samples=max_samples,
|
|
max_features=max_features,
|
|
bootstrap=bootstrap,
|
|
bootstrap_features=bootstrap_features,
|
|
oob_score=oob_score,
|
|
warm_start=warm_start,
|
|
n_jobs=n_jobs,
|
|
random_state=random_state,
|
|
verbose=verbose)
|
|
|
|
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 estimators in the ensemble.
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix} of shape = [n_samples, n_features]
|
|
The training input samples. Sparse matrices are accepted only if
|
|
they are supported by the base estimator.
|
|
|
|
Returns
|
|
-------
|
|
y : array of shape = [n_samples]
|
|
The predicted values.
|
|
"""
|
|
check_is_fitted(self, "estimators_features_")
|
|
# Check data
|
|
X = check_array(X, accept_sparse=['csr', 'csc'])
|
|
|
|
# Parallel loop
|
|
n_jobs, n_estimators, starts = _partition_estimators(self.n_estimators,
|
|
self.n_jobs)
|
|
|
|
all_y_hat = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
|
|
delayed(_parallel_predict_regression)(
|
|
self.estimators_[starts[i]:starts[i + 1]],
|
|
self.estimators_features_[starts[i]:starts[i + 1]],
|
|
X)
|
|
for i in range(n_jobs))
|
|
|
|
# Reduce
|
|
y_hat = sum(all_y_hat) / self.n_estimators
|
|
|
|
return y_hat
|
|
|
|
def _validate_estimator(self):
|
|
"""Check the estimator and set the base_estimator_ attribute."""
|
|
super(BaggingRegressor, self)._validate_estimator(
|
|
default=DecisionTreeRegressor())
|
|
|
|
def _set_oob_score(self, X, y):
|
|
n_samples = y.shape[0]
|
|
|
|
predictions = np.zeros((n_samples,))
|
|
n_predictions = np.zeros((n_samples,))
|
|
|
|
for estimator, samples, features in zip(self.estimators_,
|
|
self.estimators_samples_,
|
|
self.estimators_features_):
|
|
# Create mask for OOB samples
|
|
mask = ~samples
|
|
|
|
predictions[mask] += estimator.predict((X[mask, :])[:, features])
|
|
n_predictions[mask] += 1
|
|
|
|
if (n_predictions == 0).any():
|
|
warn("Some inputs do not have OOB scores. "
|
|
"This probably means too few estimators were used "
|
|
"to compute any reliable oob estimates.")
|
|
n_predictions[n_predictions == 0] = 1
|
|
|
|
predictions /= n_predictions
|
|
|
|
self.oob_prediction_ = predictions
|
|
self.oob_score_ = r2_score(y, predictions)
|