#对癌症数据集使用决策树分类
from sklearn.tree import DecisionTreeClassifier
cancer =load_breast_cancer()X_train,X_test,y_train,y_test = train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=42)
tree = DecisionTreeClassifier(random_state=0)
tree.fit(X_train,y_train)
print("Accuracy on training set:{:3f}".format(tree.score(X_train,y_train)))
print("Accuracy on testing set:{:3f}".format(tree.score(X_test,y_test)))
Accuracy on training set:1.000000 Accuracy on testing set:0.937063