1316 lines
47 KiB
Python
1316 lines
47 KiB
Python
"""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>
|
|
# License: BSD 3 clause
|
|
|
|
from __future__ import division
|
|
|
|
import itertools
|
|
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 import six
|
|
from ..externals.six.moves import xrange
|
|
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 array2d, check_random_state, check_arrays, safe_asarray
|
|
from ..utils.validation import DataConversionWarning
|
|
from ..utils.fixes import bincount, unique
|
|
|
|
from .base import BaseEnsemble, _partition_estimators
|
|
|
|
__all__ = ["RandomForestClassifier",
|
|
"RandomForestRegressor",
|
|
"ExtraTreesClassifier",
|
|
"ExtraTreesRegressor"]
|
|
|
|
MAX_INT = np.iinfo(np.int32).max
|
|
|
|
|
|
def _parallel_build_trees(n_trees, forest, X, y,
|
|
sample_weight, seeds, verbose):
|
|
"""Private function used to build a batch of trees within a job."""
|
|
trees = []
|
|
|
|
for i in range(n_trees):
|
|
random_state = check_random_state(seeds[i])
|
|
if verbose > 1:
|
|
print("building tree %d of %d" % (i + 1, n_trees))
|
|
seed = random_state.randint(MAX_INT)
|
|
|
|
tree = forest._make_estimator(append=False)
|
|
tree.set_params(random_state=seed)
|
|
|
|
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 = random_state.randint(0, n_samples, n_samples)
|
|
sample_counts = bincount(indices, minlength=n_samples)
|
|
curr_sample_weight *= sample_counts
|
|
|
|
tree.fit(X, y,
|
|
sample_weight=curr_sample_weight,
|
|
check_input=False)
|
|
|
|
tree.indices_ = sample_counts > 0.
|
|
|
|
else:
|
|
tree.fit(X, y,
|
|
sample_weight=sample_weight,
|
|
check_input=False)
|
|
|
|
trees.append(tree)
|
|
|
|
return trees
|
|
|
|
|
|
def _parallel_predict_proba(trees, X, n_classes, n_outputs):
|
|
"""Private function used to compute a batch of predictions within a job."""
|
|
n_samples = X.shape[0]
|
|
|
|
if n_outputs == 1:
|
|
proba = np.zeros((n_samples, n_classes))
|
|
|
|
for tree in trees:
|
|
proba_tree = tree.predict_proba(X)
|
|
|
|
if n_classes == tree.n_classes_:
|
|
proba += proba_tree
|
|
|
|
else:
|
|
proba[:, tree.classes_] += \
|
|
proba_tree[:, range(len(tree.classes_))]
|
|
|
|
else:
|
|
proba = []
|
|
|
|
for k in xrange(n_outputs):
|
|
proba.append(np.zeros((n_samples, n_classes[k])))
|
|
|
|
for tree in trees:
|
|
proba_tree = tree.predict_proba(X)
|
|
|
|
for k in xrange(n_outputs):
|
|
if n_classes[k] == tree.n_classes_[k]:
|
|
proba[k] += proba_tree[k]
|
|
|
|
else:
|
|
proba[k][:, tree.classes_] += \
|
|
proba_tree[k][:, range(len(tree.classes_))]
|
|
|
|
return proba
|
|
|
|
|
|
def _parallel_predict_regression(trees, X):
|
|
"""Private function used to compute a batch of predictions within a job."""
|
|
return sum(tree.predict(X) for tree in trees)
|
|
|
|
|
|
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):
|
|
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
|
|
|
|
def apply(self, X):
|
|
"""Apply trees in the forest to X, return leaf indices.
|
|
|
|
Parameters
|
|
----------
|
|
X : array-like, shape = [n_samples, n_features]
|
|
Input data.
|
|
|
|
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 = array2d(X, dtype=DTYPE)
|
|
return np.array([est.tree_.apply(X) for est in self.estimators_]).T
|
|
|
|
def fit(self, X, y, sample_weight=None):
|
|
"""Build a forest of trees from the training set (X, y).
|
|
|
|
Parameters
|
|
----------
|
|
X : array-like of shape = [n_samples, n_features]
|
|
The training input samples.
|
|
|
|
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).
|
|
|
|
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.
|
|
"""
|
|
random_state = check_random_state(self.random_state)
|
|
|
|
# Convert data
|
|
X, = check_arrays(X, dtype=DTYPE, sparse_format="dense",
|
|
check_ccontiguous=True)
|
|
|
|
# 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 = self._validate_y(y)
|
|
|
|
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
|
|
y = np.ascontiguousarray(y, dtype=DOUBLE)
|
|
|
|
# Check parameters
|
|
self._validate_estimator()
|
|
|
|
if not self.bootstrap and self.oob_score:
|
|
raise ValueError("Out of bag estimation only available"
|
|
" if bootstrap=True")
|
|
|
|
# Assign chunk of trees to jobs
|
|
n_jobs, n_trees, _ = _partition_estimators(self)
|
|
|
|
# Precalculate the random states
|
|
seeds = [random_state.randint(MAX_INT, size=i) for i in n_trees]
|
|
|
|
# Free allocated memory, if any
|
|
self.estimators_ = None
|
|
|
|
# Parallel loop
|
|
all_trees = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
|
|
delayed(_parallel_build_trees)(
|
|
n_trees[i],
|
|
self,
|
|
X,
|
|
y,
|
|
sample_weight,
|
|
seeds[i],
|
|
verbose=self.verbose)
|
|
for i in range(n_jobs))
|
|
|
|
# Reduce
|
|
self.estimators_ = list(itertools.chain(*all_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(self, y):
|
|
# Default implementation
|
|
return y
|
|
|
|
@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 ValueError("Estimator not fitted, "
|
|
"call `fit` before `feature_importances_`.")
|
|
|
|
return sum(tree.feature_importances_
|
|
for tree in self.estimators_) / self.n_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):
|
|
|
|
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)
|
|
|
|
def _set_oob_score(self, X, y):
|
|
n_classes_ = self.n_classes_
|
|
classes_ = self.classes_
|
|
n_samples = y.shape[0]
|
|
|
|
oob_decision_function = []
|
|
oob_score = 0.0
|
|
predictions = []
|
|
|
|
for k in xrange(self.n_outputs_):
|
|
predictions.append(np.zeros((n_samples,
|
|
n_classes_[k])))
|
|
|
|
for estimator in self.estimators_:
|
|
mask = np.ones(n_samples, dtype=np.bool)
|
|
mask[estimator.indices_] = False
|
|
p_estimator = estimator.predict_proba(X[mask, :])
|
|
|
|
if self.n_outputs_ == 1:
|
|
p_estimator = [p_estimator]
|
|
|
|
for k in xrange(self.n_outputs_):
|
|
predictions[k][mask, :] += p_estimator[k]
|
|
|
|
for k in xrange(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] == classes_[k].take(
|
|
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(self, y):
|
|
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])
|
|
|
|
return y
|
|
|
|
def predict(self, X):
|
|
"""Predict class for X.
|
|
|
|
The predicted class of an input sample is computed as the majority
|
|
prediction of the trees in the forest.
|
|
|
|
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.
|
|
"""
|
|
n_samples = len(X)
|
|
proba = self.predict_proba(X)
|
|
|
|
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
|
|
|
|
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.
|
|
|
|
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.
|
|
"""
|
|
# Check data
|
|
if getattr(X, "dtype", None) != DTYPE or X.ndim != 2:
|
|
X = array2d(X, dtype=DTYPE)
|
|
|
|
# Assign chunk of trees to jobs
|
|
n_jobs, n_trees, starts = _partition_estimators(self)
|
|
|
|
# Parallel loop
|
|
all_proba = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
|
|
delayed(_parallel_predict_proba)(
|
|
self.estimators_[starts[i]:starts[i + 1]],
|
|
X,
|
|
self.n_classes_,
|
|
self.n_outputs_)
|
|
for i in range(n_jobs))
|
|
|
|
# Reduce
|
|
proba = all_proba[0]
|
|
|
|
if self.n_outputs_ == 1:
|
|
for j in xrange(1, len(all_proba)):
|
|
proba += all_proba[j]
|
|
|
|
proba /= self.n_estimators
|
|
|
|
else:
|
|
for j in xrange(1, len(all_proba)):
|
|
for k in xrange(self.n_outputs_):
|
|
proba[k] += all_proba[j][k]
|
|
|
|
for k in xrange(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 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 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):
|
|
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)
|
|
|
|
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 of shape = [n_samples, n_features]
|
|
The input samples.
|
|
|
|
Returns
|
|
-------
|
|
y: array of shape = [n_samples] or [n_samples, n_outputs]
|
|
The predicted values.
|
|
"""
|
|
# Check data
|
|
if getattr(X, "dtype", None) != DTYPE or X.ndim != 2:
|
|
X = array2d(X, dtype=DTYPE)
|
|
|
|
# Assign chunk of trees to jobs
|
|
n_jobs, n_trees, starts = _partition_estimators(self)
|
|
|
|
# Parallel loop
|
|
all_y_hat = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
|
|
delayed(_parallel_predict_regression)(
|
|
self.estimators_[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 _set_oob_score(self, X, y):
|
|
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_:
|
|
mask = np.ones(n_samples, dtype=np.bool)
|
|
mask[estimator.indices_] = False
|
|
p_estimator = estimator.predict(X[mask, :])
|
|
|
|
if self.n_outputs_ == 1:
|
|
p_estimator = p_estimator[:, np.newaxis]
|
|
|
|
predictions[mask, :] += p_estimator
|
|
n_predictions[mask, :] += 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 xrange(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.
|
|
|
|
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: 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.
|
|
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.
|
|
|
|
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.
|
|
|
|
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).
|
|
|
|
`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,
|
|
max_features="auto",
|
|
bootstrap=True,
|
|
oob_score=False,
|
|
n_jobs=1,
|
|
random_state=None,
|
|
verbose=0,
|
|
min_density=None,
|
|
compute_importances=None):
|
|
super(RandomForestClassifier, self).__init__(
|
|
base_estimator=DecisionTreeClassifier(),
|
|
n_estimators=n_estimators,
|
|
estimator_params=("criterion", "max_depth", "min_samples_split",
|
|
"min_samples_leaf", "max_features",
|
|
"random_state"),
|
|
bootstrap=bootstrap,
|
|
oob_score=oob_score,
|
|
n_jobs=n_jobs,
|
|
random_state=random_state,
|
|
verbose=verbose)
|
|
|
|
self.criterion = criterion
|
|
self.max_depth = max_depth
|
|
self.min_samples_split = min_samples_split
|
|
self.min_samples_leaf = min_samples_leaf
|
|
self.max_features = max_features
|
|
|
|
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 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.
|
|
|
|
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: 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.
|
|
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.
|
|
|
|
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.
|
|
|
|
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).
|
|
|
|
`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,
|
|
max_features="auto",
|
|
bootstrap=True,
|
|
oob_score=False,
|
|
n_jobs=1,
|
|
random_state=None,
|
|
verbose=0,
|
|
min_density=None,
|
|
compute_importances=None):
|
|
super(RandomForestRegressor, self).__init__(
|
|
base_estimator=DecisionTreeRegressor(),
|
|
n_estimators=n_estimators,
|
|
estimator_params=("criterion", "max_depth", "min_samples_split",
|
|
"min_samples_leaf", "max_features",
|
|
"random_state"),
|
|
bootstrap=bootstrap,
|
|
oob_score=oob_score,
|
|
n_jobs=n_jobs,
|
|
random_state=random_state,
|
|
verbose=verbose)
|
|
|
|
self.criterion = criterion
|
|
self.max_depth = max_depth
|
|
self.min_samples_split = min_samples_split
|
|
self.min_samples_leaf = min_samples_leaf
|
|
self.max_features = max_features
|
|
|
|
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 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.
|
|
|
|
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: 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.
|
|
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.
|
|
|
|
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.
|
|
|
|
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).
|
|
|
|
`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,
|
|
max_features="auto",
|
|
bootstrap=False,
|
|
oob_score=False,
|
|
n_jobs=1,
|
|
random_state=None,
|
|
verbose=0,
|
|
min_density=None,
|
|
compute_importances=None):
|
|
super(ExtraTreesClassifier, self).__init__(
|
|
base_estimator=ExtraTreeClassifier(),
|
|
n_estimators=n_estimators,
|
|
estimator_params=("criterion", "max_depth", "min_samples_split",
|
|
"min_samples_leaf", "max_features",
|
|
"random_state"),
|
|
bootstrap=bootstrap,
|
|
oob_score=oob_score,
|
|
n_jobs=n_jobs,
|
|
random_state=random_state,
|
|
verbose=verbose)
|
|
|
|
self.criterion = criterion
|
|
self.max_depth = max_depth
|
|
self.min_samples_split = min_samples_split
|
|
self.min_samples_leaf = min_samples_leaf
|
|
self.max_features = max_features
|
|
|
|
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 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.
|
|
|
|
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: 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.
|
|
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.
|
|
|
|
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.
|
|
|
|
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).
|
|
|
|
`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,
|
|
max_features="auto",
|
|
bootstrap=False,
|
|
oob_score=False,
|
|
n_jobs=1,
|
|
random_state=None,
|
|
verbose=0,
|
|
min_density=None,
|
|
compute_importances=None):
|
|
super(ExtraTreesRegressor, self).__init__(
|
|
base_estimator=ExtraTreeRegressor(),
|
|
n_estimators=n_estimators,
|
|
estimator_params=("criterion", "max_depth", "min_samples_split",
|
|
"min_samples_leaf", "max_features",
|
|
"random_state"),
|
|
bootstrap=bootstrap,
|
|
oob_score=oob_score,
|
|
n_jobs=n_jobs,
|
|
random_state=random_state,
|
|
verbose=verbose)
|
|
|
|
self.criterion = criterion
|
|
self.max_depth = max_depth
|
|
self.min_samples_split = min_samples_split
|
|
self.min_samples_leaf = min_samples_leaf
|
|
self.max_features = max_features
|
|
|
|
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 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 trees in the forest.
|
|
|
|
The dimensionality of the resulting representation is approximately
|
|
``n_estimators * 2 ** max_depth``.
|
|
|
|
Parameters
|
|
----------
|
|
n_estimators : int
|
|
Number of trees in the forest.
|
|
|
|
max_depth : int
|
|
Maximum depth of each tree.
|
|
|
|
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.
|
|
|
|
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.
|
|
|
|
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,
|
|
n_jobs=1,
|
|
random_state=None,
|
|
verbose=0,
|
|
min_density=None):
|
|
super(RandomTreesEmbedding, self).__init__(
|
|
base_estimator=ExtraTreeRegressor(),
|
|
n_estimators=n_estimators,
|
|
estimator_params=("criterion", "max_depth", "min_samples_split",
|
|
"min_samples_leaf", "max_features",
|
|
"random_state"),
|
|
bootstrap=False,
|
|
oob_score=False,
|
|
n_jobs=n_jobs,
|
|
random_state=random_state,
|
|
verbose=verbose)
|
|
|
|
self.criterion = 'mse'
|
|
self.max_depth = max_depth
|
|
self.min_samples_split = min_samples_split
|
|
self.min_samples_leaf = min_samples_leaf
|
|
self.max_features = 1
|
|
|
|
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)
|
|
|
|
def _set_oob_score(*args):
|
|
raise NotImplementedError("OOB score not supported by tree embedding")
|
|
|
|
def fit(self, X, y=None):
|
|
"""Fit estimator.
|
|
|
|
Parameters
|
|
----------
|
|
X : array-like, shape=(n_samples, n_features)
|
|
Input data used to build forests.
|
|
"""
|
|
self.fit_transform(X, y)
|
|
return self
|
|
|
|
def fit_transform(self, X, y=None):
|
|
"""Fit estimator and transform dataset.
|
|
|
|
Parameters
|
|
----------
|
|
X : array-like, shape=(n_samples, n_features)
|
|
Input data used to build forests.
|
|
|
|
Returns
|
|
-------
|
|
X_transformed: sparse matrix, shape=(n_samples, n_out)
|
|
Transformed dataset.
|
|
"""
|
|
X = safe_asarray(X)
|
|
rnd = check_random_state(self.random_state)
|
|
y = rnd.uniform(size=X.shape[0])
|
|
super(RandomTreesEmbedding, self).fit(X, y)
|
|
self.one_hot_encoder_ = OneHotEncoder()
|
|
return self.one_hot_encoder_.fit_transform(self.apply(X))
|
|
|
|
def transform(self, X):
|
|
"""Transform dataset.
|
|
|
|
Parameters
|
|
----------
|
|
X : array-like, shape=(n_samples, n_features)
|
|
Input data to be transformed.
|
|
|
|
Returns
|
|
-------
|
|
X_transformed: sparse matrix, shape=(n_samples, n_out)
|
|
Transformed dataset.
|
|
"""
|
|
return self.one_hot_encoder_.transform(self.apply(X))
|