Implementation:Scikit learn Scikit learn ExportTree

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

Overview

Concrete tool for exporting and visualizing decision trees in various formats provided by scikit-learn.

Description

This module defines export functions for decision trees, enabling visualization in Graphviz DOT format and plain text format. The export_graphviz function produces DOT language output suitable for rendering with Graphviz tools, supporting colored nodes, feature/class names, and impurity annotations. The export_text function generates a human-readable text representation of the decision tree rules. The module also includes internal helper classes (_DOTTreeExporter, _MPLTreeExporter) for different rendering backends.

Usage

Use export_graphviz to create publication-quality tree visualizations via Graphviz, or export_text for quick text-based inspection of tree decision rules in notebooks or command-line output.

Code Reference

Source Location

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

Signature

@validate_params(...)
def export_graphviz(
    decision_tree,
    out_file=None,
    *,
    max_depth=None,
    feature_names=None,
    class_names=None,
    label="all",
    filled=False,
    leaves_parallel=False,
    impurity=True,
    node_ids=False,
    proportion=False,
    rotate=False,
    rounded=False,
    special_characters=False,
    precision=3,
    fontname="helvetica",
)

@validate_params(...)
def export_text(
    decision_tree,
    *,
    feature_names=None,
    class_names=None,
    max_depth=10,
    spacing=3,
    decimals=2,
    show_weights=False,
)

Import

from sklearn.tree import export_graphviz, export_text

I/O Contract

Inputs

Name	Type	Required	Description
decision_tree	decision tree estimator	Yes	Fitted decision tree classifier or regressor
out_file	file object or str or None	No	Output file for Graphviz DOT data (default: None returns string)
max_depth	int or None	No	Maximum depth of tree to export (default: None for full tree)
feature_names	list of str or None	No	Feature names for node labels (default: None)
class_names	list of str or bool or None	No	Class names for leaf labels (default: None)
filled	bool	No	Color nodes by majority class or value (default: False)
rounded	bool	No	Use rounded node boxes in Graphviz (default: False)
precision	int	No	Number of decimal places for values (default: 3)
spacing	int	No	Indentation spacing for export_text (default: 3)

Outputs

Name	Type	Description
dot_data	str	Graphviz DOT format string (export_graphviz)
text_report	str	Text representation of tree rules (export_text)

Usage Examples

Basic Usage

from sklearn.tree import DecisionTreeClassifier, export_text, export_graphviz
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)
clf = DecisionTreeClassifier(max_depth=3, random_state=42)
clf.fit(X, y)

# Text export
print(export_text(clf, feature_names=load_iris().feature_names))

# Graphviz export
dot_data = export_graphviz(clf, feature_names=load_iris().feature_names,
                            class_names=load_iris().target_names,
                            filled=True, rounded=True)

Related Pages

• Principle:Scikit_learn_Scikit_learn_Decision_Tree_Learning