Decision trees vs. neural networks
Build a decision tree classifier to classify income levels based on multiple features including age, education level, and hours worked per week, and extract the learned rules that explain the decision. Then, compare its performance with an MLPClassifier trained on the same data.
X_train, X_test, y_train, and y_test are pre-loaded for you. The accuracy_score and export_text functions are also imported for you.
This exercise is part of the course
Explainable AI in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
model = DecisionTreeClassifier(random_state=42, max_depth=2)
model.fit(X_train, y_train)
# Extract the rules
rules = ____
print(rules)
y_pred = model.predict(X_test)
# Compute accuracy
accuracy = ____
print(f"Accuracy: {accuracy:.2f}")