2 信息熵
3.1 决策树构建流程
5 CART决策树（分类&回归）
6 泰坦尼克号生存预测案例
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier,plot_tree
import matplotlib.pyplot as plt
from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,classification_report
# 获取数据
data=pd.read_csv('titanic/train.csv')
# data.info()
# 数据处理
x=data[['Sex','Age','Pclass']]
y=data['Survived']
# x.head()
# 热编码
x=pd.get_dummies(x)
# 缺失值填充
x['Age']=x['Age'].fillna(x['Age'].mean())
# x.head()
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=22)
# 模型训练
tree=DecisionTreeClassifier(criterion='gini',max_depth=6)
tree.fit(x_train,y_train)
# 模型预测
y_predict=tree.predict(x_test)
# print(y_predict)
# 模型评估
print('accuracy_score',accuracy_score(y_test,y_predict))
print('precision_score',precision_score(y_test,y_predict))
print('recall_score',recall_score(y_test,y_predict))
print('f1_score',f1_score(y_test,y_predict))
print(classification_report(y_test,y_predict))
# 绘制树
plt.figure(figsize=(30,20))
plot_tree(tree,filled=True,feature_names=['Age','Pclass','Sex_female','Sex_male'],class_names=['died','survived'])
plt.show()
7 CART回归树
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor,plot_tree
import matplotlib.pyplot as plt# 构建数据
x=np.array(list(range(1,11))).reshape(-1,1)
print(x.shape)
y=np.array([5.56,5.7,5.91,6.4,6.8,7.05,8.9,8.7,9,9.05])
# print(x)# 模型训练
model1=LinearRegression()
model2=DecisionTreeRegressor(max_depth=1)
model3=DecisionTreeRegressor(max_depth=3)model1.fit(x,y)
model2.fit(x,y)
model3.fit(x,y)
# 模型预测
x_test=np.arange(0.0,10.0,0.01).reshape(-1,1)
print(x_test.shape)
y1=model1.predict(x_test)
y2=model2.predict(x_test)
y3=model3.predict(x_test)plt.scatter(x,y)
plt.plot(x_test,y1)
plt.plot(x_test,y2)
plt.plot(x_test,y3)
plt.grid()
plt.show()plt.figure(figsize=(30,20))
plot_tree(model3,filled=True)
plt.show()
