决策树模型2

决策树分类

# 导入数据集
# data返回一个字典
from sklearn.datasets import load_iris
import numpy as np
data = load_iris()

x = data['data']
y = data['target']

# 直接看y是三分类，先看看二分类
x = x[50:]
y = y[50:]

# 数据集划分
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size = 0.2,random_state = 0) # 如果想固定划分结果，用种子

# 导入决策树模型
from sklearn.tree import DecisionTreeClassifier
# 实例化模型
model = DecisionTreeClassifier(max_depth = 5) # 可设置参数，见前post
# 训练模型
model.fit(x_train,y_train)

# 预测数据
y_train_pred = model.predict(x_train)
y_test_pred = model.predict(x_test)

# 准确率
from sklearn.metrics import accuracy_score
accuracy_score(y_train_pred,y_train)
accuracy_score(y_test_pred,y_test) # 通过调整参数获得不同的准确率

决策树回归

# 导入数据集
# data返回一个字典
from sklearn.datasets import load_boston
import numpy as np
data = load_boston()

x = data['data']
y = data['target']

# 数据集划分
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(x,y,test_size = 0.2,random_state = 0) # 如果想固定划分结果，用种子

# 导入模型
from sklearn.tree import DecisionTreeRegressor
# 实例化模型
model = DecisionTreeRegressor(max_depth = 5) # 可设置参数，见前post
# 训练模型
model.fit(X_train,y_train)

# 预测数据
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)

# 准确率
from sklearn.metrics import mean_squared_error
mean_squared_error(y_train_pred,y_train) # 因为针对单个数据进行训练，一般结果会很好
mean_squared_error(y_test_pred,y_test) # 也能差一些，因为涉及到过拟合
from sklearn.metrics import r2_score
r2_score(y_train_pred,y_train) 
r2_score(y_test_pred,y_test) # 也可以看出是过拟合