python决策树

一、CART算法的实现

#encoding:utf-8
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import load_digits
#准备数据
digit = load_digits()
data  = digit.data
target = digit.target
#随机抽取33%的数据做测试集，其余为训练集
train_data,test_data,train_target,test_target = train_test_split(data,target,test_size=0.33,random_state=0)
#创建CART分类树
clf = DecisionTreeClassifier(criterion=‘gini‘)
#拟合构造CART分类树
clf = clf.fit(train_data,train_target)
#用CART分类树做预测
test_predict = clf.predict(test_data)
#将结果输出
print(‘实际结果为：‘,test_target,‘--预测结果为：‘,test_predict)
#预测结果的准确率
score = accuracy_score(test_target,test_predict)
print("CART分类树准确率%.4f" % score)