Tutorial 15: Decision Trees

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier, export_text
from sklearn.metrics import accuracy_score

X, y = load_breast_cancer(return_X_y=True)
feature_names = load_breast_cancer().feature_names

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

for depth in [3, None]:
    tree = DecisionTreeClassifier(max_depth=depth, random_state=42)
    tree.fit(X_train, y_train)
    train_acc = accuracy_score(y_train, tree.predict(X_train))
    test_acc = accuracy_score(y_test, tree.predict(X_test))
    label = depth if depth else "unlimited"
    print(f"max_depth={label:10s}  train={train_acc:.3f}  test={test_acc:.3f}")

# Interpretable tree
tree = DecisionTreeClassifier(max_depth=3, random_state=42)
tree.fit(X_train, y_train)
print("\nTree rules (depth=3):")
print(export_text(tree, feature_names=list(feature_names)))

importances = sorted(zip(feature_names, tree.feature_importances_), key=lambda x: -x[1])
print("\nTop 5 features:")
for name, imp in importances[:5]:
    print(f"  {name}: {imp:.4f}")