Implementation:Scikit learn Scikit learn DecisionTreeClassifier

Knowledge Sources	Scikit_learn Scikit-learn Docs
Domains	Machine Learning, Classification
Last Updated	2026-02-08 15:00 GMT

Overview

Concrete tool for decision tree-based classification and regression provided by scikit-learn.

Description

This module implements all tree-based estimator classes: DecisionTreeClassifier, DecisionTreeRegressor, ExtraTreeClassifier, and ExtraTreeRegressor. These estimators build tree models by recursively splitting the feature space using criteria such as Gini impurity, entropy, or log-loss for classification and MSE, MAE, or Poisson deviance for regression. The module supports both depth-first and best-first tree building strategies, cost-complexity pruning, sample weighting, and multi-output problems. Trees can be constrained via max_depth, min_samples_split, min_samples_leaf, and other parameters.

Usage

Use DecisionTreeClassifier for interpretable classification models, as a base estimator for ensemble methods (Random Forest, Gradient Boosting), or when you need feature importance rankings. ExtraTreeClassifier adds randomization to split thresholds for use in Extra-Trees ensembles.

Code Reference

Source Location

• Repository: scikit-learn
• File: sklearn/tree/_classes.py

Signature

class DecisionTreeClassifier(ClassifierMixin, BaseDecisionTree):
    """A decision tree classifier."""

    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,
        monotonic_cst=None,
    ):
        ...

class DecisionTreeRegressor(RegressorMixin, BaseDecisionTree):
    """A decision tree regressor."""
    ...

class ExtraTreeClassifier(DecisionTreeClassifier):
    """An extremely randomized tree classifier."""
    ...

class ExtraTreeRegressor(DecisionTreeRegressor):
    """An extremely randomized tree regressor."""
    ...

Import

from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
from sklearn.tree import ExtraTreeClassifier, ExtraTreeRegressor

I/O Contract

Inputs

Name	Type	Required	Description
X	array-like of shape (n_samples, n_features)	Yes	Training feature data
y	array-like of shape (n_samples,) or (n_samples, n_outputs)	Yes	Target values
criterion	str	No	Split quality function: 'gini', 'entropy', 'log_loss' (default: 'gini')
splitter	str	No	Split strategy: 'best' or 'random' (default: 'best')
max_depth	int or None	No	Maximum tree depth (default: None, fully grown)
min_samples_split	int or float	No	Minimum samples to split a node (default: 2)
min_samples_leaf	int or float	No	Minimum samples per leaf (default: 1)
max_features	int, float, str, or None	No	Features considered per split (default: None)
ccp_alpha	float	No	Cost-complexity pruning parameter (default: 0.0)
class_weight	dict or 'balanced' or None	No	Class weight mapping (default: None)

Outputs

Name	Type	Description
classes_	ndarray	Unique class labels
feature_importances_	ndarray of shape (n_features,)	Gini-based feature importance scores
tree_	Tree	Internal tree structure object
n_classes_	int or list	Number of classes per output
max_features_	int	Inferred value of max_features

Usage Examples

Basic Usage

from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

clf = DecisionTreeClassifier(max_depth=3, random_state=42)
clf.fit(X_train, y_train)
print("Accuracy:", clf.score(X_test, y_test))
print("Feature importances:", clf.feature_importances_)

Related Pages

• Principle:Scikit_learn_Scikit_learn_Decision_Tree_Learning