Visualizing Decision Trees in Python: Interpreting Results and Gaining Insights

Decision Trees are a popular Machine Learning algorithm used for both classification and regression tasks. They are simple to understand, easy to interpret, and provide valuable insights. In this article, we will learn how to visualize decision trees in Python using Scikit-learn, Graphviz, and Matplotlib libraries.

Table of Contents

  1. Introduction to Decision Trees
  2. Installing Required Libraries
  3. Visualizing Decision Trees with Scikit-learn and Graphviz
  4. Visualizing Decision Trees with Matplotlib
  5. Interpreting Decision Trees
  6. Conclusion

Introduction to Decision Trees

Decision Trees are a non-parametric supervised learning method used for classification and regression tasks. They work by recursively splitting the input space into regions and predicting the output based on the majority class or average value in the region.

Key advantages of decision trees include:

  • Easy to understand and interpret
  • Can handle both numerical and categorical data
  • Robust to outliers and noisy data

Installing Required Libraries

Before we begin, make sure you have the following libraries installed:

  • Scikit-learn: A popular Machine Learning library in Python
  • Graphviz: A library for creating graph visualizations
  • Matplotlib: A library for creating static, interactive, and animated visualizations in Python

You can install them using the following commands:

pip install scikit-learn
pip install graphviz
pip install matplotlib

Visualizing Decision Trees with Scikit-learn and Graphviz

Scikit-learn provides a plot_tree function that enables the visualization of decision trees. To create a decision tree, we will use the famous Iris dataset. First, let's import the necessary libraries and load the dataset.

import graphviz
from sklearn import datasets
from sklearn.tree import DecisionTreeClassifier, export_graphviz

iris = datasets.load_iris()
X =
y =

# Create the decision tree classifier
clf = DecisionTreeClassifier(), y)

Now, we can visualize the decision tree using Graphviz.

dot_data = export_graphviz(clf, out_file=None,
                           filled=True, rounded=True,
graph = graphviz.Source(dot_data)

This code snippet will display the decision tree as a graph with nodes and edges, where each node represents a decision rule, and each edge represents the decision outcome.

Visualizing Decision Trees with Matplotlib

Another way to visualize decision trees is by using the Matplotlib library. Scikit-learn provides a plot_tree function that can be used with Matplotlib to generate the decision tree graph.

import matplotlib.pyplot as plt
from sklearn.tree import plot_tree

plt.figure(figsize=(20, 10))
plot_tree(clf, feature_names=iris.feature_names,
          class_names=iris.target_names, filled=True, rounded=True)

This code snippet will generate a similar decision tree graph as before, but this time using Matplotlib's visualization capabilities.

Interpreting Decision Trees

When interpreting a decision tree, start at the root node and traverse the tree by following the decision rules that apply to the input data. The final node (leaf node) will provide the predicted class or value.

Key components to look for when interpreting a decision tree include:

  • Decision Rule: The condition used to split the data at each node
  • Gini Impurity: A measure of how mixed the classes are in a node (lower values indicate a pure node)
  • Samples: The number of samples in the node
  • Value: The distribution of samples across the classes
  • Class: The majority class in the node


In this article, we learned how to visualize decision trees in Python using Scikit-learn, Graphviz, and Matplotlib libraries. Visualizing decision trees is essential for interpreting the results and gaining valuable insights into the decision-making process. By understanding the structure and rules of the decision tree, you can improve model performance and make more informed decisions.

An AI coworker, not just a copilot

View VelocityAI