【无标题】

最新推荐文章于 2024-07-09 09:31:14 发布

老龙QAQ

最新推荐文章于 2024-07-09 09:31:14 发布

阅读量176

点赞数

分类专栏：学习笔记文章标签：机器学习 python 人工智能

本文链接：https://blog.csdn.net/weixin_52167116/article/details/127236635

版权

学习笔记专栏收录该内容

8 篇文章 0 订阅

订阅专栏

10.9学习笔记 -决策树

from sklearn.datasets import load_boston
from sklearn.datasets import load_iris

from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import DecisionTreeRegressor
from sklearn.tree import plot_tree

from sklearn.neighbors import KNeighborsRegressor
from sklearn.neighbors import KNeighborsClassifier

from sklearn.model_selection import train_test_split

"""
加载数据集

"""

X,y = load_boston(return_X_y=True)


"""
切分数据集

"""

X_train, X_test, y_train, y_test = train_test_split(X,
                                                    y,
                                                    test_size=0.15,
                                                    random_state=1)

"""
使用回归树

"""
# 构建模型
#dtr = DecisionTreeRegressor()
dtr = DecisionTreeRegressor(max_depth=2)

# 训练模型
dtr.fit(X=X_train,y=y_train)

# 预测模型
y_pred = dtr.predict(X_test)

# 均方误差
((y_test - y_pred) **2).mean()

"""
与KNN比较

"""
# 构建模型
knn = KNeighborsRegressor(n_neighbors=5)

# 训练模型
knn.fit(X=X_train, y=y_train)

# 模型预测
y_pred = knn.predict(X_test)

# 均方误差
((y_test - y_pred) **2).mean()

"""
分类任务
    加载数据

"""
X,y = load_iris(return_X_y=True)

"""
切分数据集

"""
X_train, X_test, y_train, y_test = train_test_split(X,
                                                    y,
                                                    test_size=0.15,
                                                    random_state=1)
"""
使用回归树

"""
# 构建模型
dtc = DecisionTreeClassifier()

# 训练模型
dtc.fit(X=X_train,y=y_train)

# 预测模型
y_pred = dtc.predict(X_test)

# 均方误差
(y_test == y_pred).mean()



plot_tree(decision_tree=dtr)
"""
x[12] <= 9.725   用第12个特征（最后一个特征）判断，小于9.725左拐，反之亦然
mse = 83.007     均方误差
sampls =430      样本数



"""