"""
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>
# Haoyin Xu <haoyinxu@gmail.com>
#
# License: BSD 3 clause
import copy
import numbers
from abc import ABCMeta, abstractmethod
from math import ceil
from numbers import Integral, Real
import numpy as np
from scipy.sparse import issparse
from sklearn.base import (
BaseEstimator,
ClassifierMixin,
MultiOutputMixin,
RegressorMixin,
_fit_context,
clone,
is_classifier,
)
from sklearn.utils import Bunch, check_random_state, compute_sample_weight
from sklearn.utils._param_validation import Hidden, Interval, RealNotInt, StrOptions
from sklearn.utils.multiclass import (
_check_partial_fit_first_call,
check_classification_targets,
)
from sklearn.utils.validation import (
_assert_all_finite_element_wise,
_check_sample_weight,
assert_all_finite,
check_is_fitted,
)
from . import _criterion, _splitter, _tree
from ._criterion import BaseCriterion
from ._splitter import BaseSplitter
from ._tree import (
BestFirstTreeBuilder,
DepthFirstTreeBuilder,
Tree,
_build_pruned_tree_ccp,
ccp_pruning_path,
)
from ._utils import _any_isnan_axis0
__all__ = [
"DecisionTreeClassifier",
"DecisionTreeRegressor",
"ExtraTreeClassifier",
"ExtraTreeRegressor",
]
# =============================================================================
# Types and constants
# =============================================================================
DTYPE = _tree.DTYPE
DOUBLE = _tree.DOUBLE
CRITERIA_CLF = {
"gini": _criterion.Gini,
"log_loss": _criterion.Entropy,
"entropy": _criterion.Entropy,
}
CRITERIA_REG = {
"squared_error": _criterion.MSE,
"friedman_mse": _criterion.FriedmanMSE,
"absolute_error": _criterion.MAE,
"poisson": _criterion.Poisson,
}
DENSE_SPLITTERS = {"best": _splitter.BestSplitter, "random": _splitter.RandomSplitter}
SPARSE_SPLITTERS = {
"best": _splitter.BestSparseSplitter,
"random": _splitter.RandomSparseSplitter,
}
# =============================================================================
# Base decision tree
# =============================================================================
class BaseDecisionTree(MultiOutputMixin, BaseEstimator, metaclass=ABCMeta):
"""Base class for decision trees.
Warning: This class should not be used directly.
Use derived classes instead.
"""
_parameter_constraints: dict = {
"splitter": [StrOptions({"best", "random"})],
"max_depth": [Interval(Integral, 1, None, closed="left"), None],
"min_samples_split": [
Interval(Integral, 2, None, closed="left"),
Interval(RealNotInt, 0.0, 1.0, closed="right"),
StrOptions({"sqrt", "log2"}),
],
"min_samples_leaf": [
Interval(Integral, 1, None, closed="left"),
Interval(RealNotInt, 0.0, 1.0, closed="neither"),
],
"min_weight_fraction_leaf": [Interval(Real, 0.0, 0.5, closed="both")],
"max_features": [
Interval(Integral, 1, None, closed="left"),
Interval(RealNotInt, 0.0, 1.0, closed="right"),
StrOptions({"sqrt", "log2"}),
None,
],
"random_state": ["random_state"],
"max_leaf_nodes": [Interval(Integral, 2, None, closed="left"), None],
"min_impurity_decrease": [Interval(Real, 0.0, None, closed="left")],
"ccp_alpha": [Interval(Real, 0.0, None, closed="left")],
"store_leaf_values": ["boolean"],
"monotonic_cst": ["array-like", None],
}
@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_decrease,
class_weight=None,
ccp_alpha=0.0,
store_leaf_values=False,
monotonic_cst=None,
):
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.max_leaf_nodes = max_leaf_nodes
self.random_state = random_state
self.min_impurity_decrease = min_impurity_decrease
self.class_weight = class_weight
self.ccp_alpha = ccp_alpha
self.store_leaf_values = store_leaf_values
self.monotonic_cst = monotonic_cst
def get_depth(self):
"""Return the depth of the decision tree.
The depth of a tree is the maximum distance between the root
and any leaf.
Returns
-------
self.tree_.max_depth : int
The maximum depth of the tree.
"""
check_is_fitted(self)
return self.tree_.max_depth
def get_n_leaves(self):
"""Return the number of leaves of the decision tree.
Returns
-------
self.tree_.n_leaves : int
Number of leaves.
"""
check_is_fitted(self)
return self.tree_.n_leaves
def _support_missing_values(self, X):
return (
not issparse(X)
and self._get_tags()["allow_nan"]
and self.monotonic_cst is None
)
def _compute_missing_values_in_feature_mask(self, X, estimator_name=None):
"""Return boolean mask denoting if there are missing values for each feature.
This method also ensures that X is finite.
Parameter
---------
X : array-like of shape (n_samples, n_features), dtype=DOUBLE
Input data.
estimator_name : str or None, default=None
Name to use when raising an error. Defaults to the class name.
Returns
-------
missing_values_in_feature_mask : ndarray of shape (n_features,), or None
Missing value mask. If missing values are not supported or there
are no missing values, return None.
"""
estimator_name = estimator_name or self.__class__.__name__
common_kwargs = dict(estimator_name=estimator_name, input_name="X")
if not self._support_missing_values(X):
assert_all_finite(X, **common_kwargs)
return None
with np.errstate(over="ignore"):
overall_sum = np.sum(X)
if not np.isfinite(overall_sum):
# Raise a ValueError in case of the presence of an infinite element.
_assert_all_finite_element_wise(X, xp=np, allow_nan=True, **common_kwargs)
# If the sum is not nan, then there are no missing values
if not np.isnan(overall_sum):
return None
missing_values_in_feature_mask = _any_isnan_axis0(X)
return missing_values_in_feature_mask
def _fit(
self,
X,
y,
sample_weight=None,
check_input=True,
missing_values_in_feature_mask=None,
classes=None,
):
random_state = check_random_state(self.random_state)
if check_input:
# Need to validate separately here.
# We can't pass multi_output=True because that would allow y to be
# csr.
# _compute_missing_values_in_feature_mask will check for finite values and
# compute the missing mask if the tree supports missing values
check_X_params = dict(
dtype=DTYPE, accept_sparse="csc", force_all_finite=False
)
check_y_params = dict(ensure_2d=False, dtype=None)
if y is not None or self._get_tags()["requires_y"]:
X, y = self._validate_data(
X, y, validate_separately=(check_X_params, check_y_params)
)
else:
X = self._validate_data(X, **check_X_params)
missing_values_in_feature_mask = (
self._compute_missing_values_in_feature_mask(X)
)
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"
)
if y is not None and self.criterion == "poisson":
if np.any(y < 0):
raise ValueError(
"Some value(s) of y are negative which is"
" not allowed for Poisson regression."
)
if np.sum(y) <= 0:
raise ValueError(
"Sum of y is not positive which is "
"necessary for Poisson regression."
)
# Determine output settings
n_samples, self.n_features_in_ = X.shape
# Do preprocessing if 'y' is passed
is_classification = False
if y is not None:
is_classification = is_classifier(self)
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=int)
if classes is not None:
classes = np.atleast_1d(classes)
if classes.ndim == 1:
classes = np.array([classes])
for k in classes:
self.classes_.append(np.array(k))
self.n_classes_.append(np.array(k).shape[0])
for i in range(n_samples):
for j in range(self.n_outputs_):
y_encoded[i, j] = np.where(self.classes_[j] == y[i, j])[0][
0
]
else:
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
)
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)
if len(y) != n_samples:
raise ValueError(
"Number of labels=%d does not match number of samples=%d"
% (len(y), n_samples)
)
# set decision-tree model parameters
max_depth = np.iinfo(np.int32).max if self.max_depth is None else self.max_depth
if isinstance(self.min_samples_leaf, numbers.Integral):
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, str):
if self.min_samples_split == "sqrt":
min_samples_split = max(1, int(np.sqrt(self.n_features_in_)))
elif self.min_samples_split == "log2":
min_samples_split = max(1, int(np.log2(self.n_features_in_)))
elif isinstance(self.min_samples_split, numbers.Integral):
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)
self.min_samples_split_ = min_samples_split
if isinstance(self.max_features, str):
if self.max_features == "sqrt":
max_features = max(1, int(np.sqrt(self.n_features_in_)))
elif self.max_features == "log2":
max_features = max(1, int(np.log2(self.n_features_in_)))
elif self.max_features is None:
max_features = self.n_features_in_
elif isinstance(self.max_features, numbers.Integral):
max_features = self.max_features
else: # float
if self.max_features > 0.0:
max_features = max(1, int(self.max_features * self.n_features_in_))
else:
max_features = 0
self.max_features_ = max_features
max_leaf_nodes = -1 if self.max_leaf_nodes is None else self.max_leaf_nodes
if sample_weight is not None:
sample_weight = _check_sample_weight(sample_weight, X, DOUBLE)
if y is not None and 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 sample_weight is None:
min_weight_leaf = self.min_weight_fraction_leaf * n_samples
else:
min_weight_leaf = self.min_weight_fraction_leaf * np.sum(sample_weight)
# build the actual tree now with the parameters
self._build_tree(
X=X,
y=y,
sample_weight=sample_weight,
missing_values_in_feature_mask=missing_values_in_feature_mask,
min_samples_leaf=min_samples_leaf,
min_weight_leaf=min_weight_leaf,
max_leaf_nodes=max_leaf_nodes,
min_samples_split=min_samples_split,
max_depth=max_depth,
random_state=random_state,
)
return self
def _build_tree(
self,
X,
y,
sample_weight,
missing_values_in_feature_mask,
min_samples_leaf,
min_weight_leaf,
max_leaf_nodes,
min_samples_split,
max_depth,
random_state,
):
"""Build the actual tree.
Parameters
----------
X : Array-like
X dataset.
y : Array-like
Y targets.
sample_weight : Array-like
Sample weights
min_samples_leaf : float
Number of samples required to be a leaf.
min_weight_leaf : float
Weight of samples required to be a leaf.
max_leaf_nodes : float
Maximum number of leaf nodes allowed in tree.
min_samples_split : float
Minimum number of samples to split on.
max_depth : int
The maximum depth of any tree.
random_state : int
Random seed.
"""
n_samples = X.shape[0]
# Build tree
criterion = self.criterion
if not isinstance(criterion, BaseCriterion):
if is_classifier(self):
criterion = CRITERIA_CLF[self.criterion](
self.n_outputs_, self.n_classes_
)
else:
criterion = CRITERIA_REG[self.criterion](self.n_outputs_, n_samples)
else:
# Make a deepcopy in case the criterion has mutable attributes that
# might be shared and modified concurrently during parallel fitting
criterion = copy.deepcopy(criterion)
SPLITTERS = SPARSE_SPLITTERS if issparse(X) else DENSE_SPLITTERS
if self.monotonic_cst is None:
monotonic_cst = None
else:
if self.n_outputs_ > 1:
raise ValueError(
"Monotonicity constraints are not supported with multiple outputs."
)
# Check to correct monotonicity constraint' specification,
# by applying element-wise logical conjunction
# Note: we do not cast `np.asarray(self.monotonic_cst, dtype=np.int8)`
# straight away here so as to generate error messages for invalid
# values using the original values prior to any dtype related conversion.
monotonic_cst = np.asarray(self.monotonic_cst)
if monotonic_cst.shape[0] != X.shape[1]:
raise ValueError(
"monotonic_cst has shape {} but the input data "
"X has {} features.".format(monotonic_cst.shape[0], X.shape[1])
)
valid_constraints = np.isin(monotonic_cst, (-1, 0, 1))
if not np.all(valid_constraints):
unique_constaints_value = np.unique(monotonic_cst)
raise ValueError(
"monotonic_cst must be None or an array-like of -1, 0 or 1, but"
f" got {unique_constaints_value}"
)
monotonic_cst = np.asarray(monotonic_cst, dtype=np.int8)
if is_classifier(self):
if self.n_classes_[0] > 2:
raise ValueError(
"Monotonicity constraints are not supported with multiclass "
"classification"
)
# Binary classification trees are built by constraining probabilities
# of the *negative class* in order to make the implementation similar
# to regression trees.
# Since self.monotonic_cst encodes constraints on probabilities of the
# *positive class*, all signs must be flipped.
monotonic_cst *= -1
if not isinstance(self.splitter, BaseSplitter):
splitter = SPLITTERS[self.splitter](
criterion,
self.max_features_,
min_samples_leaf,
min_weight_leaf,
random_state,
monotonic_cst,
)
if is_classifier(self):
self.tree_ = Tree(self.n_features_in_, self.n_classes_, self.n_outputs_)
else:
self.tree_ = Tree(
self.n_features_in_,
# TODO: tree shouldn't need this in this case
np.array([1] * self.n_outputs_, dtype=np.intp),
self.n_outputs_,
)
# Use BestFirst if max_leaf_nodes given; use DepthFirst otherwise
if max_leaf_nodes < 0:
self.builder_ = DepthFirstTreeBuilder(
splitter,
min_samples_split,
min_samples_leaf,
min_weight_leaf,
max_depth,
self.min_impurity_decrease,
self.store_leaf_values,
)
else:
self.builder_ = BestFirstTreeBuilder(
splitter,
min_samples_split,
min_samples_leaf,
min_weight_leaf,
max_depth,
max_leaf_nodes,
self.min_impurity_decrease,
self.store_leaf_values,
)
self.builder_.build(
self.tree_, X, y, sample_weight, missing_values_in_feature_mask
)
if self.n_outputs_ == 1 and is_classifier(self):
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
self._prune_tree()
def _validate_X_predict(self, X, check_input):
"""Validate the training data on predict (probabilities)."""
if check_input:
if self._support_missing_values(X):
force_all_finite = "allow-nan"
else:
force_all_finite = True
X = self._validate_data(
X,
dtype=DTYPE,
accept_sparse="csr",
reset=False,
force_all_finite=force_all_finite,
)
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")
else:
# The number of features is checked regardless of `check_input`
self._check_n_features(X, reset=False)
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, 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 : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The predicted classes, or the predict values.
"""
check_is_fitted(self)
X = self._validate_X_predict(X, check_input)
# proba is a count matrix of leaves that fall into
# (n_samples, n_outputs, max_n_classes) array
proba = self.tree_.predict(X)
n_samples = X.shape[0]
# Classification
if is_classifier(self):
if self.n_outputs_ == 1:
return self.classes_.take(np.argmax(proba, axis=1), axis=0)
else:
class_type = self.classes_[0].dtype
predictions = np.zeros((n_samples, self.n_outputs_), dtype=class_type)
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 get_leaf_node_samples(self, X, check_input=True):
"""For each datapoint x in X, get the training samples in the leaf node.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Dataset to apply the forest to.
check_input : bool, default=True
Allow to bypass several input checking.
Returns
-------
leaf_nodes_samples : a list of array-like of length (n_samples,)
Each sample is represented by the indices of the training samples that
reached the leaf node. The ``n_leaf_node_samples`` may vary between
samples, since the number of samples that fall in a leaf node is
variable. Each array has shape (n_leaf_node_samples, n_outputs).
"""
if not self.store_leaf_values:
raise RuntimeError(
"leaf node samples are not stored when store_leaf_values=False"
)
# get indices of leaves per sample (n_samples,)
X_leaves = self.apply(X, check_input=check_input)
n_samples = X_leaves.shape[0]
# get array of samples per leaf (n_node_samples, n_outputs)
leaf_samples = self.tree_.leaf_nodes_samples
leaf_nodes_samples = []
for idx in range(n_samples):
leaf_id = X_leaves[idx]
leaf_nodes_samples.append(leaf_samples[leaf_id])
return leaf_nodes_samples
def predict_quantiles(self, X, quantiles=0.5, method="nearest", check_input=True):
"""Predict class or regression value for X at given quantiles.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Input data.
quantiles : float, optional
The quantiles at which to evaluate, by default 0.5 (median).
method : str, optional
The method to interpolate, by default 'linear'. Can be any keyword
argument accepted by :func:`~np.quantile`.
check_input : bool, optional
Whether or not to check input, by default True.
Returns
-------
predictions : array-like of shape (n_samples, n_outputs, len(quantiles))
The predicted quantiles.
"""
if not self.store_leaf_values:
raise RuntimeError(
"Predicting quantiles requires that the tree stores leaf node samples."
)
check_is_fitted(self)
# Check data
X = self._validate_X_predict(X, check_input)
if not isinstance(quantiles, (np.ndarray, list)):
quantiles = np.array([quantiles])
# get indices of leaves per sample
X_leaves = self.apply(X)
# get array of samples per leaf (n_node_samples, n_outputs)
leaf_samples = self.tree_.leaf_nodes_samples
# compute quantiles (n_samples, n_quantiles, n_outputs)
n_samples = X.shape[0]
n_quantiles = len(quantiles)
proba = np.zeros((n_samples, n_quantiles, self.n_outputs_))
for idx, leaf_id in enumerate(X_leaves):
# predict by taking the quantile across the samples in the leaf for
# each output
try:
proba[idx, ...] = np.quantile(
leaf_samples[leaf_id], quantiles, axis=0, method=method
)
except TypeError:
proba[idx, ...] = np.quantile(
leaf_samples[leaf_id], quantiles, axis=0, interpolation=method
)
# Classification
if is_classifier(self):
if self.n_outputs_ == 1:
# return the class with the highest probability for each quantile
# (n_samples, n_quantiles)
class_preds = np.zeros(
(n_samples, n_quantiles), dtype=self.classes_.dtype
)
for i in range(n_quantiles):
class_pred_per_sample = (
proba[:, i, :].squeeze().astype(self.classes_.dtype)
)
class_preds[:, i] = self.classes_.take(
class_pred_per_sample, axis=0
)
return class_preds
else:
class_type = self.classes_[0].dtype
predictions = np.zeros(
(n_samples, n_quantiles, self.n_outputs_), dtype=class_type
)
for k in range(self.n_outputs_):
for i in range(n_quantiles):
class_pred_per_sample = proba[:, i, k].squeeze().astype(int)
predictions[:, i, k] = self.classes_[k].take(
class_pred_per_sample, axis=0
)
return predictions
# Regression
else:
if self.n_outputs_ == 1:
return proba[:, :, 0]
else:
return proba
def apply(self, X, check_input=True):
"""Return the index of the leaf that each sample is predicted as.
.. versionadded:: 0.17
Parameters
----------
X : {array-like, 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 : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
X_leaves : array-like of 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.
"""
check_is_fitted(self)
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.
.. versionadded:: 0.18
Parameters
----------
X : {array-like, 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 : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
indicator : sparse matrix of shape (n_samples, n_nodes)
Return a node indicator CSR 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)
def _prune_tree(self):
"""Prune tree using Minimal Cost-Complexity Pruning."""
check_is_fitted(self)
if self.ccp_alpha == 0.0:
return
# build pruned tree
if is_classifier(self):
n_classes = np.atleast_1d(self.n_classes_)
pruned_tree = Tree(self.n_features_in_, n_classes, self.n_outputs_)
else:
pruned_tree = Tree(
self.n_features_in_,
# TODO: the tree shouldn't need this param
np.array([1] * self.n_outputs_, dtype=np.intp),
self.n_outputs_,
)
_build_pruned_tree_ccp(pruned_tree, self.tree_, self.ccp_alpha)
self.tree_ = pruned_tree
def cost_complexity_pruning_path(self, X, y, sample_weight=None):
"""Compute the pruning path during Minimal Cost-Complexity Pruning.
See :ref:`minimal_cost_complexity_pruning` for details on the pruning
process.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The target values (class labels) as integers or strings.
sample_weight : array-like of shape (n_samples,), default=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. Splits are also
ignored if they would result in any single class carrying a
negative weight in either child node.
Returns
-------
ccp_path : :class:`~sklearn.utils.Bunch`
Dictionary-like object, with the following attributes.
ccp_alphas : ndarray
Effective alphas of subtree during pruning.
impurities : ndarray
Sum of the impurities of the subtree leaves for the
corresponding alpha value in ``ccp_alphas``.
"""
est = clone(self).set_params(ccp_alpha=0.0)
est.fit(X, y, sample_weight=sample_weight)
return Bunch(**ccp_pruning_path(est.tree_))
@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.
Warning: impurity-based feature importances can be misleading for
high cardinality features (many unique values). See
:func:`sklearn.inspection.permutation_importance` as an alternative.
Returns
-------
feature_importances_ : ndarray of shape (n_features,)
Normalized total reduction of criteria by feature
(Gini importance).
"""
check_is_fitted(self)
return self.tree_.compute_feature_importances()
# =============================================================================
# Public estimators
# =============================================================================
[docs]
class DecisionTreeClassifier(ClassifierMixin, BaseDecisionTree):
"""A decision tree classifier.
Read more in the :ref:`User Guide <tree>`.
Parameters
----------
criterion : {"gini", "entropy", "log_loss"}, default="gini"
The function to measure the quality of a split. Supported criteria are
"gini" for the Gini impurity and "log_loss" and "entropy" both for the
Shannon information gain, see :ref:`tree_mathematical_formulation`.
splitter : {"best", "random"}, 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_depth : int, 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 or float, 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 fraction and
`ceil(min_samples_split * n_samples)` are the minimum
number of samples for each split.
.. versionchanged:: 0.18
Added float values for fractions.
min_samples_leaf : int or float, default=1
The minimum number of samples required to be at a leaf node.
A split point at any depth will only be considered if it leaves at
least ``min_samples_leaf`` training samples in each of the left and
right branches. This may have the effect of smoothing the model,
especially in regression.
- If int, then consider `min_samples_leaf` as the minimum number.
- If float, then `min_samples_leaf` is a fraction and
`ceil(min_samples_leaf * n_samples)` are the minimum
number of samples for each node.
.. versionchanged:: 0.18
Added float values for fractions.
min_weight_fraction_leaf : float, default=0.0
The minimum weighted fraction of the sum total of weights (of all
the input samples) required to be at a leaf node. Samples have
equal weight when sample_weight is not provided.
max_features : int, float or {"sqrt", "log2"}, 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 fraction and
`max(1, int(max_features * n_features_in_))` features are considered at
each split.
- 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.
random_state : int, RandomState instance or None, default=None
Controls the randomness of the estimator. The features are always
randomly permuted at each split, even if ``splitter`` is set to
``"best"``. When ``max_features < n_features``, the algorithm will
select ``max_features`` at random at each split before finding the best
split among them. But the best found split may vary across different
runs, even if ``max_features=n_features``. That is the case, if the
improvement of the criterion is identical for several splits and one
split has to be selected at random. To obtain a deterministic behaviour
during fitting, ``random_state`` has to be fixed to an integer.
See :term:`Glossary <random_state>` for details.
max_leaf_nodes : int, 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.
min_impurity_decrease : float, default=0.0
A node will be split if this split induces a decrease of the impurity
greater than or equal to this value.
The weighted impurity decrease equation is the following::
N_t / N * (impurity - N_t_R / N_t * right_impurity
- N_t_L / N_t * left_impurity)
where ``N`` is the total number of samples, ``N_t`` is the number of
samples at the current node, ``N_t_L`` is the number of samples in the
left child, and ``N_t_R`` is the number of samples in the right child.
``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum,
if ``sample_weight`` is passed.
.. versionadded:: 0.19
class_weight : dict, list of dict or "balanced", default=None
Weights associated with classes in the form ``{class_label: weight}``.
If None, 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.
Note that for multioutput (including multilabel) weights should be
defined for each class of every column in its own dict. For example,
for four-class multilabel classification weights should be
[{0: 1, 1: 1}, {0: 1, 1: 5}, {0: 1, 1: 1}, {0: 1, 1: 1}] instead of
[{1:1}, {2:5}, {3:1}, {4:1}].
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.
ccp_alpha : non-negative float, default=0.0
Complexity parameter used for Minimal Cost-Complexity Pruning. The
subtree with the largest cost complexity that is smaller than
``ccp_alpha`` will be chosen. By default, no pruning is performed. See
:ref:`minimal_cost_complexity_pruning` for details.
.. versionadded:: 0.22
store_leaf_values : bool, default=False
Whether to store the samples that fall into leaves in the ``tree_`` attribute.
Each leaf will store a 2D array corresponding to the samples that fall into it
keyed by node_id.
XXX: This is currently experimental and may change without notice.
Moreover, it can be improved upon since storing the samples twice is not ideal.
One could instead store the indices in ``y_train`` that fall into each leaf,
which would lower RAM/diskspace usage.
monotonic_cst : array-like of int of shape (n_features), default=None
Indicates the monotonicity constraint to enforce on each feature.
- 1: monotonic increase
- 0: no constraint
- -1: monotonic decrease
If monotonic_cst is None, no constraints are applied.
Monotonicity constraints are not supported for:
- multiclass classifications (i.e. when `n_classes > 2`),
- multioutput classifications (i.e. when `n_outputs_ > 1`),
- classifications trained on data with missing values.
The constraints hold over the probability of the positive class.
Read more in the :ref:`User Guide <monotonic_cst_gbdt>`.
.. versionadded:: 1.4
Attributes
----------
classes_ : ndarray of shape (n_classes,) or list of ndarray
The classes labels (single output problem),
or a list of arrays of class labels (multi-output problem).
feature_importances_ : ndarray of shape (n_features,)
The impurity-based 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]_.
Warning: impurity-based feature importances can be misleading for
high cardinality features (many unique values). See
:func:`sklearn.inspection.permutation_importance` as an alternative.
max_features_ : int
The inferred value of max_features.
n_classes_ : int or list of int
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_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
n_outputs_ : int
The number of outputs when ``fit`` is performed.
tree_ : Tree instance
The underlying Tree object. Please refer to
``help(sklearn.tree._tree.Tree)`` for attributes of Tree object and
:ref:`sphx_glr_auto_examples_tree_plot_unveil_tree_structure.py`
for basic usage of these attributes.
builder_ : TreeBuilder instance
The underlying TreeBuilder object.
min_samples_split_ : float
The minimum number of samples needed to split a node in the tree building.
See Also
--------
DecisionTreeRegressor : A decision tree regressor.
Notes
-----
The default values for the parameters controlling the size of the trees
(e.g. ``max_depth``, ``min_samples_leaf``, etc.) lead to fully grown and
unpruned trees which can potentially be very large on some data sets. To
reduce memory consumption, the complexity and size of the trees should be
controlled by setting those parameter values.
The :meth:`predict` method operates using the :func:`numpy.argmax`
function on the outputs of :meth:`predict_proba`. This means that in
case the highest predicted probabilities are tied, the classifier will
predict the tied class with the lowest index in :term:`classes_`.
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",
https://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. ])
"""
_parameter_constraints: dict = {
**BaseDecisionTree._parameter_constraints,
"criterion": [
StrOptions({"gini", "entropy", "log_loss"}),
Hidden(BaseCriterion),
],
"class_weight": [dict, list, StrOptions({"balanced"}), None],
}
def __init__(
self,
*,
criterion="gini",
splitter="best",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features=None,
random_state=None,
max_leaf_nodes=None,
min_impurity_decrease=0.0,
class_weight=None,
ccp_alpha=0.0,
store_leaf_values=False,
monotonic_cst=None,
):
super().__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_decrease=min_impurity_decrease,
monotonic_cst=monotonic_cst,
ccp_alpha=ccp_alpha,
store_leaf_values=store_leaf_values,
)
[docs]
@_fit_context(prefer_skip_nested_validation=True)
def fit(
self,
X,
y,
sample_weight=None,
check_input=True,
classes=None,
):
"""Build a decision tree classifier from the training set (X, y).
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The target values (class labels) as integers or strings.
sample_weight : array-like of shape (n_samples,), default=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. Splits are also
ignored if they would result in any single class carrying a
negative weight in either child node.
check_input : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
classes : array-like of shape (n_classes,), default=None
List of all the classes that can possibly appear in the y vector.
Returns
-------
self : DecisionTreeClassifier
Fitted estimator.
"""
super()._fit(
X,
y,
sample_weight=sample_weight,
check_input=check_input,
classes=classes,
)
return self
[docs]
def partial_fit(self, X, y, sample_weight=None, check_input=True, classes=None):
"""Update a decision tree classifier from the training set (X, y).
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The target values (class labels) as integers or strings.
sample_weight : array-like of shape (n_samples,), default=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. Splits are also
ignored if they would result in any single class carrying a
negative weight in either child node.
check_input : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
classes : array-like of shape (n_classes,), default=None
List of all the classes that can possibly appear in the y vector.
Must be provided at the first call to partial_fit, can be omitted
in subsequent calls.
Returns
-------
self : DecisionTreeClassifier
Fitted estimator.
"""
self._validate_params()
# validate input parameters
first_call = _check_partial_fit_first_call(self, classes=classes)
# Fit if no tree exists yet
if first_call:
self.fit(
X,
y,
sample_weight=sample_weight,
check_input=check_input,
classes=classes,
)
return self
if check_input:
# Need to validate separately here.
# We can't pass multi_ouput=True because that would allow y to be
# csr.
check_X_params = dict(dtype=DTYPE, accept_sparse="csc")
check_y_params = dict(ensure_2d=False, dtype=None)
X, y = self._validate_data(
X, y, reset=False, validate_separately=(check_X_params, check_y_params)
)
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"
)
if X.shape[1] != self.n_features_in_:
raise ValueError(
f"X has {X.shape[1]} features, but {self.__class__.__name__} "
f"is expecting {self.n_features_in_} features as input."
)
y = np.atleast_1d(y)
if y.ndim == 1:
# reshape is necessary to preserve the data contiguity against vs
# [:, np.newaxis] that does not.
y = np.reshape(y, (-1, 1))
check_classification_targets(y)
y = np.copy(y)
classes = self.classes_
if self.n_outputs_ == 1:
classes = [classes]
y_encoded = np.zeros(y.shape, dtype=int)
for i in range(X.shape[0]):
for j in range(self.n_outputs_):
y_encoded[i, j] = np.where(classes[j] == y[i, j])[0][0]
y = y_encoded
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
y = np.ascontiguousarray(y, dtype=DOUBLE)
# Update tree
self.builder_.initialize_node_queue(self.tree_, X, y, sample_weight)
self.builder_.build(self.tree_, X, y, sample_weight)
self._prune_tree()
return self
[docs]
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.
Parameters
----------
X : {array-like, 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 : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
proba : ndarray of shape (n_samples, n_classes) or 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 :term:`classes_`.
"""
check_is_fitted(self)
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
[docs]
def predict_log_proba(self, X):
"""Predict class log-probabilities of the input samples X.
Parameters
----------
X : {array-like, 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
-------
proba : ndarray of shape (n_samples, n_classes) or 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 :term:`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
def _more_tags(self):
# XXX: nan is only support for dense arrays, but we set this for common test to
# pass, specifically: check_estimators_nan_inf
allow_nan = self.splitter == "best" and self.criterion in {
"gini",
"log_loss",
"entropy",
}
return {"multilabel": True, "allow_nan": allow_nan}
[docs]
class DecisionTreeRegressor(RegressorMixin, BaseDecisionTree):
"""A decision tree regressor.
Read more in the :ref:`User Guide <tree>`.
Parameters
----------
criterion : {"squared_error", "friedman_mse", "absolute_error", \
"poisson"}, default="squared_error"
The function to measure the quality of a split. Supported criteria
are "squared_error" for the mean squared error, which is equal to
variance reduction as feature selection criterion and minimizes the L2
loss using the mean of each terminal node, "friedman_mse", which uses
mean squared error with Friedman's improvement score for potential
splits, "absolute_error" for the mean absolute error, which minimizes
the L1 loss using the median of each terminal node, and "poisson" which
uses reduction in Poisson deviance to find splits.
.. versionadded:: 0.18
Mean Absolute Error (MAE) criterion.
.. versionadded:: 0.24
Poisson deviance criterion.
splitter : {"best", "random"}, 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_depth : int, 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 or float, 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 fraction and
`ceil(min_samples_split * n_samples)` are the minimum
number of samples for each split.
.. versionchanged:: 0.18
Added float values for fractions.
min_samples_leaf : int or float, default=1
The minimum number of samples required to be at a leaf node.
A split point at any depth will only be considered if it leaves at
least ``min_samples_leaf`` training samples in each of the left and
right branches. This may have the effect of smoothing the model,
especially in regression.
- If int, then consider `min_samples_leaf` as the minimum number.
- If float, then `min_samples_leaf` is a fraction and
`ceil(min_samples_leaf * n_samples)` are the minimum
number of samples for each node.
.. versionchanged:: 0.18
Added float values for fractions.
min_weight_fraction_leaf : float, default=0.0
The minimum weighted fraction of the sum total of weights (of all
the input samples) required to be at a leaf node. Samples have
equal weight when sample_weight is not provided.
max_features : int, float or {"sqrt", "log2"}, 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 fraction and
`max(1, int(max_features * n_features_in_))` features are considered at each
split.
- 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.
random_state : int, RandomState instance or None, default=None
Controls the randomness of the estimator. The features are always
randomly permuted at each split, even if ``splitter`` is set to
``"best"``. When ``max_features < n_features``, the algorithm will
select ``max_features`` at random at each split before finding the best
split among them. But the best found split may vary across different
runs, even if ``max_features=n_features``. That is the case, if the
improvement of the criterion is identical for several splits and one
split has to be selected at random. To obtain a deterministic behaviour
during fitting, ``random_state`` has to be fixed to an integer.
See :term:`Glossary <random_state>` for details.
max_leaf_nodes : int, 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.
min_impurity_decrease : float, default=0.0
A node will be split if this split induces a decrease of the impurity
greater than or equal to this value.
The weighted impurity decrease equation is the following::
N_t / N * (impurity - N_t_R / N_t * right_impurity
- N_t_L / N_t * left_impurity)
where ``N`` is the total number of samples, ``N_t`` is the number of
samples at the current node, ``N_t_L`` is the number of samples in the
left child, and ``N_t_R`` is the number of samples in the right child.
``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum,
if ``sample_weight`` is passed.
.. versionadded:: 0.19
ccp_alpha : non-negative float, default=0.0
Complexity parameter used for Minimal Cost-Complexity Pruning. The
subtree with the largest cost complexity that is smaller than
``ccp_alpha`` will be chosen. By default, no pruning is performed. See
:ref:`minimal_cost_complexity_pruning` for details.
.. versionadded:: 0.22
store_leaf_values : bool, default=False
Whether to store the samples that fall into leaves in the ``tree_`` attribute.
Each leaf will store a 2D array corresponding to the samples that fall into it
keyed by node_id.
XXX: This is currently experimental and may change without notice.
Moreover, it can be improved upon since storing the samples twice is not ideal.
One could instead store the indices in ``y_train`` that fall into each leaf,
which would lower RAM/diskspace usage.
monotonic_cst : array-like of int of shape (n_features), default=None
Indicates the monotonicity constraint to enforce on each feature.
- 1: monotonic increase
- 0: no constraint
- -1: monotonic decrease
If monotonic_cst is None, no constraints are applied.
Monotonicity constraints are not supported for:
- multioutput regressions (i.e. when `n_outputs_ > 1`),
- regressions trained on data with missing values.
Read more in the :ref:`User Guide <monotonic_cst_gbdt>`.
.. versionadded:: 1.4
Attributes
----------
feature_importances_ : ndarray 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]_.
Warning: impurity-based feature importances can be misleading for
high cardinality features (many unique values). See
:func:`sklearn.inspection.permutation_importance` as an alternative.
max_features_ : int
The inferred value of max_features.
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
n_outputs_ : int
The number of outputs when ``fit`` is performed.
tree_ : Tree instance
The underlying Tree object. Please refer to
``help(sklearn.tree._tree.Tree)`` for attributes of Tree object and
:ref:`sphx_glr_auto_examples_tree_plot_unveil_tree_structure.py`
for basic usage of these attributes.
builder_ : TreeBuilder instance
The underlying TreeBuilder object.
min_samples_split_ : float
The minimum number of samples needed to split a node in the tree building.
See Also
--------
DecisionTreeClassifier : A decision tree classifier.
Notes
-----
The default values for the parameters controlling the size of the trees
(e.g. ``max_depth``, ``min_samples_leaf``, etc.) lead to fully grown and
unpruned trees which can potentially be very large on some data sets. To
reduce memory consumption, the complexity and size of the trees should be
controlled by setting those parameter values.
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",
https://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
Examples
--------
>>> from sklearn.datasets import load_diabetes
>>> from sklearn.model_selection import cross_val_score
>>> from sklearn.tree import DecisionTreeRegressor
>>> X, y = load_diabetes(return_X_y=True)
>>> regressor = DecisionTreeRegressor(random_state=0)
>>> cross_val_score(regressor, X, y, cv=10)
... # doctest: +SKIP
...
array([-0.39..., -0.46..., 0.02..., 0.06..., -0.50...,
0.16..., 0.11..., -0.73..., -0.30..., -0.00...])
"""
_parameter_constraints: dict = {
**BaseDecisionTree._parameter_constraints,
"criterion": [
StrOptions({"squared_error", "friedman_mse", "absolute_error", "poisson"}),
Hidden(BaseCriterion),
],
}
def __init__(
self,
*,
criterion="squared_error",
splitter="best",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features=None,
random_state=None,
max_leaf_nodes=None,
min_impurity_decrease=0.0,
ccp_alpha=0.0,
store_leaf_values=False,
monotonic_cst=None,
):
super().__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_decrease=min_impurity_decrease,
ccp_alpha=ccp_alpha,
store_leaf_values=store_leaf_values,
monotonic_cst=monotonic_cst,
)
[docs]
@_fit_context(prefer_skip_nested_validation=True)
def fit(
self,
X,
y,
sample_weight=None,
check_input=True,
classes=None,
):
"""Build a decision tree regressor from the training set (X, y).
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The target values (real numbers). Use ``dtype=np.float64`` and
``order='C'`` for maximum efficiency.
sample_weight : array-like of shape (n_samples,), default=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.
check_input : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
classes : array-like of shape (n_classes,), default=None
List of all the classes that can possibly appear in the y vector.
Returns
-------
self : DecisionTreeRegressor
Fitted estimator.
"""
super()._fit(
X,
y,
sample_weight=sample_weight,
check_input=check_input,
classes=classes,
)
return self
def _compute_partial_dependence_recursion(self, grid, target_features):
"""Fast partial dependence computation.
Parameters
----------
grid : ndarray of shape (n_samples, n_target_features)
The grid points on which the partial dependence should be
evaluated.
target_features : ndarray of shape (n_target_features)
The set of target features for which the partial dependence
should be evaluated.
Returns
-------
averaged_predictions : ndarray of shape (n_samples,)
The value of the partial dependence function on each grid point.
"""
grid = np.asarray(grid, dtype=DTYPE, order="C")
averaged_predictions = np.zeros(
shape=grid.shape[0], dtype=np.float64, order="C"
)
self.tree_.compute_partial_dependence(
grid, target_features, averaged_predictions
)
return averaged_predictions
def _more_tags(self):
# XXX: nan is only support for dense arrays, but we set this for common test to
# pass, specifically: check_estimators_nan_inf
allow_nan = self.splitter == "best" and self.criterion in {
"squared_error",
"friedman_mse",
"poisson",
}
return {"allow_nan": allow_nan}