1052 lines (853 sloc) 40.6 KB
"""
This module gathers tree-based methods, including decision, regression and
randomized trees. Single and multi-output problems are both handled.
"""
# Authors: Gilles Louppe <g.louppe@gmail.com>
# Peter Prettenhofer <peter.prettenhofer@gmail.com>
# Brian Holt <bdholt1@gmail.com>
# Noel Dawe <noel@dawe.me>
# Satrajit Gosh <satrajit.ghosh@gmail.com>
# Joly Arnaud <arnaud.v.joly@gmail.com>
# Fares Hedayati <fares.hedayati@gmail.com>
# Nelson Liu <nelson@nelsonliu.me>
#
# License: BSD 3 clause
from __future__ import division
import numbers
from abc import ABCMeta
from abc import abstractmethod
from math import ceil
import numpy as np
from scipy.sparse import issparse
from ..base import BaseEstimator
from ..base import ClassifierMixin
from ..base import RegressorMixin
from ..externals import six
from ..feature_selection.from_model import _LearntSelectorMixin
from ..utils import check_array
from ..utils import check_random_state
from ..utils import compute_sample_weight
from ..utils.multiclass import check_classification_targets
from ..exceptions import NotFittedError
from ._criterion import Criterion
from ._splitter import Splitter
from ._tree import DepthFirstTreeBuilder
from ._tree import BestFirstTreeBuilder
from ._tree import Tree
from . import _tree, _splitter, _criterion
__all__ = ["DecisionTreeClassifier",
"DecisionTreeRegressor",
"ExtraTreeClassifier",
"ExtraTreeRegressor"]
# =============================================================================
# Types and constants
# =============================================================================
DTYPE = _tree.DTYPE
DOUBLE = _tree.DOUBLE
CRITERIA_CLF = {"gini": _criterion.Gini, "entropy": _criterion.Entropy}
CRITERIA_REG = {"mse": _criterion.MSE, "friedman_mse": _criterion.FriedmanMSE,
"mae": _criterion.MAE}
DENSE_SPLITTERS = {"best": _splitter.BestSplitter,
"random": _splitter.RandomSplitter}
SPARSE_SPLITTERS = {"best": _splitter.BestSparseSplitter,
"random": _splitter.RandomSparseSplitter}
# =============================================================================
# Base decision tree
# =============================================================================
class BaseDecisionTree(six.with_metaclass(ABCMeta, BaseEstimator,
_LearntSelectorMixin)):
"""Base class for decision trees.
Warning: This class should not be used directly.
Use derived classes instead.
"""
@abstractmethod
def __init__(self,
criterion,
splitter,
max_depth,
min_samples_split,
min_samples_leaf,
min_weight_fraction_leaf,
max_features,
max_leaf_nodes,
random_state,
min_impurity_split,
class_weight=None,
presort=False):
self.criterion = criterion
self.splitter = splitter
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = max_features
self.random_state = random_state
self.max_leaf_nodes = max_leaf_nodes
self.min_impurity_split = min_impurity_split
self.class_weight = class_weight
self.presort = presort
self.n_features_ = None
self.n_outputs_ = None
self.classes_ = None
self.n_classes_ = None
self.tree_ = None
self.max_features_ = None
def fit(self, X, y, sample_weight=None, check_input=True,
X_idx_sorted=None):
"""Build a decision tree from the training set (X, y).
Parameters
----------
X : array-like or sparse matrix, 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). In the regression case, use ``dtype=np.float64`` and
``order='C'`` for maximum efficiency.
sample_weight : array-like, shape = [n_samples] or None
Sample weights. If None, then samples are equally weighted. Splits
that would create child nodes with net zero or negative weight are
ignored while searching for a split in each node. In the case of
classification, splits are also ignored if they would result in any
single class carrying a negative weight in either child node.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
X_idx_sorted : array-like, shape = [n_samples, n_features], optional
The indexes of the sorted training input samples. If many tree
are grown on the same dataset, this allows the ordering to be
cached between trees. If None, the data will be sorted here.
Don't use this parameter unless you know what to do.
Returns
-------
self : object
Returns self.
"""
random_state = check_random_state(self.random_state)
if check_input:
X = check_array(X, dtype=DTYPE, accept_sparse="csc")
y = check_array(y, ensure_2d=False, dtype=None)
if issparse(X):
X.sort_indices()
if X.indices.dtype != np.intc or X.indptr.dtype != np.intc:
raise ValueError("No support for np.int64 index based "
"sparse matrices")
# Determine output settings
n_samples, self.n_features_ = X.shape
is_classification = isinstance(self, ClassifierMixin)
y = np.atleast_1d(y)
expanded_class_weight = None
if y.ndim == 1:
# reshape is necessary to preserve the data contiguity against vs
# [:, np.newaxis] that does not.
y = np.reshape(y, (-1, 1))
self.n_outputs_ = y.shape[1]
if is_classification:
check_classification_targets(y)
y = np.copy(y)
self.classes_ = []
self.n_classes_ = []
if self.class_weight is not None:
y_original = np.copy(y)
y_encoded = np.zeros(y.shape, dtype=np.int)
for k in range(self.n_outputs_):
classes_k, y_encoded[:, k] = np.unique(y[:, k],
return_inverse=True)
self.classes_.append(classes_k)
self.n_classes_.append(classes_k.shape[0])
y = y_encoded
if self.class_weight is not None:
expanded_class_weight = compute_sample_weight(
self.class_weight, y_original)
else:
self.classes_ = [None] * self.n_outputs_
self.n_classes_ = [1] * self.n_outputs_
self.n_classes_ = np.array(self.n_classes_, dtype=np.intp)
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
y = np.ascontiguousarray(y, dtype=DOUBLE)
# Check parameters
max_depth = ((2 ** 31) - 1 if self.max_depth is None
else self.max_depth)
max_leaf_nodes = (-1 if self.max_leaf_nodes is None
else self.max_leaf_nodes)
if isinstance(self.min_samples_leaf, (numbers.Integral, np.integer)):
min_samples_leaf = self.min_samples_leaf
else: # float
min_samples_leaf = int(ceil(self.min_samples_leaf * n_samples))
if isinstance(self.min_samples_split, (numbers.Integral, np.integer)):
min_samples_split = self.min_samples_split
else: # float
min_samples_split = int(ceil(self.min_samples_split * n_samples))
min_samples_split = max(2, min_samples_split)
min_samples_split = max(min_samples_split, 2 * min_samples_leaf)
if isinstance(self.max_features, six.string_types):
if self.max_features == "auto":
if is_classification:
max_features = max(1, int(np.sqrt(self.n_features_)))
else:
max_features = self.n_features_
elif self.max_features == "sqrt":
max_features = max(1, int(np.sqrt(self.n_features_)))
elif self.max_features == "log2":
max_features = max(1, int(np.log2(self.n_features_)))
else:
raise ValueError(
'Invalid value for max_features. Allowed string '
'values are "auto", "sqrt" or "log2".')
elif self.max_features is None:
max_features = self.n_features_
elif isinstance(self.max_features, (numbers.Integral, np.integer)):
max_features = self.max_features
else: # float
if self.max_features > 0.0:
max_features = max(1,
int(self.max_features * self.n_features_))
else:
max_features = 0
self.max_features_ = max_features
if len(y) != n_samples:
raise ValueError("Number of labels=%d does not match "
"number of samples=%d" % (len(y), n_samples))
if not (0. < self.min_samples_split <= 1. or
2 <= self.min_samples_split):
raise ValueError("min_samples_split must be in at least 2"
" or in (0, 1], got %s" % min_samples_split)
if not (0. < self.min_samples_leaf <= 0.5 or
1 <= self.min_samples_leaf):
raise ValueError("min_samples_leaf must be at least than 1 "
"or in (0, 0.5], got %s" % min_samples_leaf)
if not 0 <= self.min_weight_fraction_leaf <= 0.5:
raise ValueError("min_weight_fraction_leaf must in [0, 0.5]")
if max_depth <= 0:
raise ValueError("max_depth must be greater than zero. ")
if not (0 < max_features <= self.n_features_):
raise ValueError("max_features must be in (0, n_features]")
if not isinstance(max_leaf_nodes, (numbers.Integral, np.integer)):
raise ValueError("max_leaf_nodes must be integral number but was "
"%r" % max_leaf_nodes)
if -1 < max_leaf_nodes < 2:
raise ValueError(("max_leaf_nodes {0} must be either smaller than "
"0 or larger than 1").format(max_leaf_nodes))
if sample_weight is not None:
if (getattr(sample_weight, "dtype", None) != DOUBLE or
not sample_weight.flags.contiguous):
sample_weight = np.ascontiguousarray(
sample_weight, dtype=DOUBLE)
if len(sample_weight.shape) > 1:
raise ValueError("Sample weights array has more "
"than one dimension: %d" %
len(sample_weight.shape))
if len(sample_weight) != n_samples:
raise ValueError("Number of weights=%d does not match "
"number of samples=%d" %
(len(sample_weight), n_samples))
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
# Set min_weight_leaf from min_weight_fraction_leaf
if self.min_weight_fraction_leaf != 0. and sample_weight is not None:
min_weight_leaf = (self.min_weight_fraction_leaf *
np.sum(sample_weight))
else:
min_weight_leaf = 0.
if self.min_impurity_split < 0.:
raise ValueError("min_impurity_split must be greater than or equal "
"to 0")
presort = self.presort
# Allow presort to be 'auto', which means True if the dataset is dense,
# otherwise it will be False.
if self.presort == 'auto' and issparse(X):
presort = False
elif self.presort == 'auto':
presort = True
if presort is True and issparse(X):
raise ValueError("Presorting is not supported for sparse "
"matrices.")
# If multiple trees are built on the same dataset, we only want to
# presort once. Splitters now can accept presorted indices if desired,
# but do not handle any presorting themselves. Ensemble algorithms
# which desire presorting must do presorting themselves and pass that
# matrix into each tree.
if X_idx_sorted is None and presort:
X_idx_sorted = np.asfortranarray(np.argsort(X, axis=0),
dtype=np.int32)
if presort and X_idx_sorted.shape != X.shape:
raise ValueError("The shape of X (X.shape = {}) doesn't match "
"the shape of X_idx_sorted (X_idx_sorted"
".shape = {})".format(X.shape,
X_idx_sorted.shape))
# Build tree
criterion = self.criterion
if not isinstance(criterion, Criterion):
if is_classification:
criterion = CRITERIA_CLF[self.criterion](self.n_outputs_,
self.n_classes_)
else:
criterion = CRITERIA_REG[self.criterion](self.n_outputs_,
n_samples)
SPLITTERS = SPARSE_SPLITTERS if issparse(X) else DENSE_SPLITTERS
splitter = self.splitter
if not isinstance(self.splitter, Splitter):
splitter = SPLITTERS[self.splitter](criterion,
self.max_features_,
min_samples_leaf,
min_weight_leaf,
random_state,
self.presort)
self.tree_ = Tree(self.n_features_, self.n_classes_, self.n_outputs_)
# Use BestFirst if max_leaf_nodes given; use DepthFirst otherwise
if max_leaf_nodes < 0:
builder = DepthFirstTreeBuilder(splitter, min_samples_split,
min_samples_leaf,
min_weight_leaf,
max_depth, self.min_impurity_split)
else:
builder = BestFirstTreeBuilder(splitter, min_samples_split,
min_samples_leaf,
min_weight_leaf,
max_depth,
max_leaf_nodes, self.min_impurity_split)
builder.build(self.tree_, X, y, sample_weight, X_idx_sorted)
if self.n_outputs_ == 1:
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
return self
def _validate_X_predict(self, X, check_input):
"""Validate X whenever one tries to predict, apply, predict_proba"""
if self.tree_ is None:
raise NotFittedError("Estimator not fitted, "
"call `fit` before exploiting the model.")
if check_input:
X = check_array(X, dtype=DTYPE, accept_sparse="csr")
if issparse(X) and (X.indices.dtype != np.intc or
X.indptr.dtype != np.intc):
raise ValueError("No support for np.int64 index based "
"sparse matrices")
n_features = X.shape[1]
if self.n_features_ != n_features:
raise ValueError("Number of features of the model must "
"match the input. Model n_features is %s and "
"input n_features is %s "
% (self.n_features_, n_features))
return X
def predict(self, X, check_input=True):
"""Predict class or regression value for X.
For a classification model, the predicted class for each sample in X is
returned. For a regression model, the predicted value based on X is
returned.
Parameters
----------
X : array-like 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``.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Returns
-------
y : array of shape = [n_samples] or [n_samples, n_outputs]
The predicted classes, or the predict values.
"""
X = self._validate_X_predict(X, check_input)
proba = self.tree_.predict(X)
n_samples = X.shape[0]
# Classification
if isinstance(self, ClassifierMixin):
if self.n_outputs_ == 1:
return self.classes_.take(np.argmax(proba, axis=1), axis=0)
else:
predictions = np.zeros((n_samples, self.n_outputs_))
for k in range(self.n_outputs_):
predictions[:, k] = self.classes_[k].take(
np.argmax(proba[:, k], axis=1),
axis=0)
return predictions
# Regression
else:
if self.n_outputs_ == 1:
return proba[:, 0]
else:
return proba[:, :, 0]
def apply(self, X, check_input=True):
"""
Returns the index of the leaf that each sample is predicted as.
.. versionadded:: 0.17
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``.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Returns
-------
X_leaves : array_like, shape = [n_samples,]
For each datapoint x in X, return the index of the leaf x
ends up in. Leaves are numbered within
``[0; self.tree_.node_count)``, possibly with gaps in the
numbering.
"""
X = self._validate_X_predict(X, check_input)
return self.tree_.apply(X)
def decision_path(self, X, check_input=True):
"""Return the decision path in the tree
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``.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Returns
-------
indicator : sparse csr array, shape = [n_samples, n_nodes]
Return a node indicator matrix where non zero elements
indicates that the samples goes through the nodes.
"""
X = self._validate_X_predict(X, check_input)
return self.tree_.decision_path(X)
@property
def feature_importances_(self):
"""Return the feature importances.
The importance of a feature is computed as the (normalized) total
reduction of the criterion brought by that feature.
It is also known as the Gini importance.
Returns
-------
feature_importances_ : array, shape = [n_features]
"""
if self.tree_ is None:
raise NotFittedError("Estimator not fitted, call `fit` before"
" `feature_importances_`.")
return self.tree_.compute_feature_importances()
# =============================================================================
# Public estimators
# =============================================================================
class DecisionTreeClassifier(BaseDecisionTree, ClassifierMixin):
"""A decision tree classifier.
Read more in the :ref:`User Guide <tree>`.
Parameters
----------
criterion : string, optional (default="gini")
The function to measure the quality of a split. Supported criteria are
"gini" for the Gini impurity and "entropy" for the information gain.
splitter : string, optional (default="best")
The strategy used to choose the split at each node. Supported
strategies are "best" to choose the best split and "random" to choose
the best random split.
max_features : int, float, string or None, optional (default=None)
The number of features to consider when looking for the best split:
- If int, then consider `max_features` features at each split.
- If float, then `max_features` is a percentage and
`int(max_features * n_features)` features are considered at each
split.
- If "auto", then `max_features=sqrt(n_features)`.
- If "sqrt", then `max_features=sqrt(n_features)`.
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.
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.
max_depth : int or None, optional (default=None)
The maximum depth of the tree. If None, then nodes are expanded until
all leaves are pure or until all leaves contain less than
min_samples_split samples.
min_samples_split : int, float, optional (default=2)
The minimum number of samples required to split an internal node:
- If int, then consider `min_samples_split` as the minimum number.
- If float, then `min_samples_split` is a percentage and
`ceil(min_samples_split * n_samples)` are the minimum
number of samples for each split.
min_samples_leaf : int, float, optional (default=1)
The minimum number of samples required to be at a leaf node:
- If int, then consider `min_samples_leaf` as the minimum number.
- If float, then `min_samples_leaf` is a percentage and
`ceil(min_samples_leaf * n_samples)` are the minimum
number of samples for each node.
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 a tree 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.
class_weight : dict, list of dicts, "balanced" or None, optional (default=None)
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))``
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.
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`.
min_impurity_split : float, optional (default=1e-7)
Threshold for early stopping in tree growth. A node will split
if its impurity is above the threshold, otherwise it is a leaf.
.. versionadded:: 0.18
presort : bool, optional (default=False)
Whether to presort the data to speed up the finding of best splits in
fitting. For the default settings of a decision tree on large
datasets, setting this to true may slow down the training process.
When using either a smaller dataset or a restricted depth, this may
speed up the training.
Attributes
----------
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).
feature_importances_ : array of shape = [n_features]
The feature importances. The higher, the more important the
feature. The importance of a feature is computed as the (normalized)
total reduction of the criterion brought by that feature. It is also
known as the Gini importance [4]_.
max_features_ : int,
The inferred value of max_features.
n_classes_ : int or list
The number of classes (for single output problems),
or a list containing the number of classes for each
output (for multi-output problems).
n_features_ : int
The number of features when ``fit`` is performed.
n_outputs_ : int
The number of outputs when ``fit`` is performed.
tree_ : Tree object
The underlying Tree object.
See also
--------
DecisionTreeRegressor
References
----------
.. [1] https://en.wikipedia.org/wiki/Decision_tree_learning
.. [2] L. Breiman, J. Friedman, R. Olshen, and C. Stone, "Classification
and Regression Trees", Wadsworth, Belmont, CA, 1984.
.. [3] T. Hastie, R. Tibshirani and J. Friedman. "Elements of Statistical
Learning", Springer, 2009.
.. [4] L. Breiman, and A. Cutler, "Random Forests",
http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
Examples
--------
>>> from sklearn.datasets import load_iris
>>> from sklearn.model_selection import cross_val_score
>>> from sklearn.tree import DecisionTreeClassifier
>>> clf = DecisionTreeClassifier(random_state=0)
>>> iris = load_iris()
>>> cross_val_score(clf, iris.data, iris.target, cv=10)
... # doctest: +SKIP
...
array([ 1. , 0.93..., 0.86..., 0.93..., 0.93...,
0.93..., 0.93..., 1. , 0.93..., 1. ])
"""
def __init__(self,
criterion="gini",
splitter="best",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features=None,
random_state=None,
max_leaf_nodes=None,
min_impurity_split=1e-7,
class_weight=None,
presort=False):
super(DecisionTreeClassifier, self).__init__(
criterion=criterion,
splitter=splitter,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
class_weight=class_weight,
random_state=random_state,
min_impurity_split=min_impurity_split,
presort=presort)
def predict_proba(self, X, check_input=True):
"""Predict class probabilities of the input samples X.
The predicted class probability is the fraction of samples of the same
class in a leaf.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
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_`.
"""
X = self._validate_X_predict(X, check_input)
proba = self.tree_.predict(X)
if self.n_outputs_ == 1:
proba = proba[:, :self.n_classes_]
normalizer = proba.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba /= normalizer
return proba
else:
all_proba = []
for k in range(self.n_outputs_):
proba_k = proba[:, k, :self.n_classes_[k]]
normalizer = proba_k.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba_k /= normalizer
all_proba.append(proba_k)
return all_proba
def predict_log_proba(self, X):
"""Predict class log-probabilities of the input samples X.
Parameters
----------
X : array-like 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 log-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 DecisionTreeRegressor(BaseDecisionTree, RegressorMixin):
"""A decision tree regressor.
Read more in the :ref:`User Guide <tree>`.
Parameters
----------
criterion : string, optional (default="mse")
The function to measure the quality of a split. Supported criteria
are "mse" for the mean squared error, which is equal to variance
reduction as feature selection criterion, and "mae" for the mean
absolute error.
.. versionadded:: 0.18
Mean Absolute Error (MAE) criterion.
splitter : string, optional (default="best")
The strategy used to choose the split at each node. Supported
strategies are "best" to choose the best split and "random" to choose
the best random split.
max_features : int, float, string or None, optional (default=None)
The number of features to consider when looking for the best split:
- If int, then consider `max_features` features at each split.
- If float, then `max_features` is a percentage and
`int(max_features * n_features)` features are considered at each
split.
- If "auto", then `max_features=n_features`.
- If "sqrt", then `max_features=sqrt(n_features)`.
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.
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.
max_depth : int or None, optional (default=None)
The maximum depth of the tree. If None, then nodes are expanded until
all leaves are pure or until all leaves contain less than
min_samples_split samples.
min_samples_split : int, float, optional (default=2)
The minimum number of samples required to split an internal node:
- If int, then consider `min_samples_split` as the minimum number.
- If float, then `min_samples_split` is a percentage and
`ceil(min_samples_split * n_samples)` are the minimum
number of samples for each split.
min_samples_leaf : int, float, optional (default=1)
The minimum number of samples required to be at a leaf node:
- If int, then consider `min_samples_leaf` as the minimum number.
- If float, then `min_samples_leaf` is a percentage and
`ceil(min_samples_leaf * n_samples)` are the minimum
number of samples for each node.
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 a tree 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.
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`.
min_impurity_split : float, optional (default=1e-7)
Threshold for early stopping in tree growth. If the impurity
of a node is below the threshold, the node is a leaf.
.. versionadded:: 0.18
presort : bool, optional (default=False)
Whether to presort the data to speed up the finding of best splits in
fitting. For the default settings of a decision tree on large
datasets, setting this to true may slow down the training process.
When using either a smaller dataset or a restricted depth, this may
speed up the training.
Attributes
----------
feature_importances_ : array of shape = [n_features]
The feature importances.
The higher, the more important the feature.
The importance of a feature is computed as the
(normalized) total reduction of the criterion brought
by that feature. It is also known as the Gini importance [4]_.
max_features_ : int,
The inferred value of max_features.
n_features_ : int
The number of features when ``fit`` is performed.
n_outputs_ : int
The number of outputs when ``fit`` is performed.
tree_ : Tree object
The underlying Tree object.
See also
--------
DecisionTreeClassifier
References
----------
.. [1] https://en.wikipedia.org/wiki/Decision_tree_learning
.. [2] L. Breiman, J. Friedman, R. Olshen, and C. Stone, "Classification
and Regression Trees", Wadsworth, Belmont, CA, 1984.
.. [3] T. Hastie, R. Tibshirani and J. Friedman. "Elements of Statistical
Learning", Springer, 2009.
.. [4] L. Breiman, and A. Cutler, "Random Forests",
http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
Examples
--------
>>> from sklearn.datasets import load_boston
>>> from sklearn.model_selection import cross_val_score
>>> from sklearn.tree import DecisionTreeRegressor
>>> boston = load_boston()
>>> regressor = DecisionTreeRegressor(random_state=0)
>>> cross_val_score(regressor, boston.data, boston.target, cv=10)
... # doctest: +SKIP
...
array([ 0.61..., 0.57..., -0.34..., 0.41..., 0.75...,
0.07..., 0.29..., 0.33..., -1.42..., -1.77...])
"""
def __init__(self,
criterion="mse",
splitter="best",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features=None,
random_state=None,
max_leaf_nodes=None,
min_impurity_split=1e-7,
presort=False):
super(DecisionTreeRegressor, self).__init__(
criterion=criterion,
splitter=splitter,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
random_state=random_state,
min_impurity_split=min_impurity_split,
presort=presort)
class ExtraTreeClassifier(DecisionTreeClassifier):
"""An extremely randomized tree classifier.
Extra-trees differ from classic decision trees in the way they are built.
When looking for the best split to separate the samples of a node into two
groups, random splits are drawn for each of the `max_features` randomly
selected features and the best split among those is chosen. When
`max_features` is set 1, this amounts to building a totally random
decision tree.
Warning: Extra-trees should only be used within ensemble methods.
Read more in the :ref:`User Guide <tree>`.
See also
--------
ExtraTreeRegressor, ExtraTreesClassifier, ExtraTreesRegressor
References
----------
.. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees",
Machine Learning, 63(1), 3-42, 2006.
"""
def __init__(self,
criterion="gini",
splitter="random",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
random_state=None,
max_leaf_nodes=None,
min_impurity_split=1e-7,
class_weight=None):
super(ExtraTreeClassifier, self).__init__(
criterion=criterion,
splitter=splitter,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
class_weight=class_weight,
min_impurity_split=min_impurity_split,
random_state=random_state)
class ExtraTreeRegressor(DecisionTreeRegressor):
"""An extremely randomized tree regressor.
Extra-trees differ from classic decision trees in the way they are built.
When looking for the best split to separate the samples of a node into two
groups, random splits are drawn for each of the `max_features` randomly
selected features and the best split among those is chosen. When
`max_features` is set 1, this amounts to building a totally random
decision tree.
Warning: Extra-trees should only be used within ensemble methods.
Read more in the :ref:`User Guide <tree>`.
See also
--------
ExtraTreeClassifier, ExtraTreesClassifier, ExtraTreesRegressor
References
----------
.. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees",
Machine Learning, 63(1), 3-42, 2006.
"""
def __init__(self,
criterion="mse",
splitter="random",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
random_state=None,
min_impurity_split=1e-7,
max_leaf_nodes=None):
super(ExtraTreeRegressor, self).__init__(
criterion=criterion,
splitter=splitter,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
min_impurity_split=min_impurity_split,
random_state=random_state)