KNN决策树探究泰坦尼克号幸存者问题

import pandas as pd
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.metrics import classification_report
import graphviz   #决策树可视化

  

 

  
1
  
2
  
3
  
4
 

data = pd.read_csv(r"titanic_data.csv")
data.drop("PassengerId",axis = 1,inplace = True)  #删除id这一列

  

 

  
1
  
2
 

data

  

 

  
1
 

891 rows × 4 columns

data.loc[data["Sex"] == "male","Sex"] = 1
data.loc[data["Sex"] == "female","Sex"] = 0

  

 

  
1
  
2
 

data

  

 

  
1
 

891 rows × 4 columns

data.fillna(data["Age"].mean(),inplace = True)  #用均值来填充缺失值

  

 

  
1
 

data

  

 

  
1
 

891 rows × 4 columns

Dtc = DecisionTreeClassifier(max_depth = 5,random_state =8)  #构建决策树
Dtc.fit(data.iloc[:,1:],data["Survived"]) #模型训练
pre = Dtc.predict(data.iloc[:,1:])  #模型预测

  

 

  
1
  
2
  
3
 

print(classification_report(pre,data["Survived"]))   #混淆矩阵

  

 

  
1
 

 precision recall  f1-score   support 0 0.88 0.84 0.86 573 1 0.73 0.79 0.76 318 accuracy 0.82 891 macro avg 0.81 0.82 0.81 891
weighted avg 0.83 0.82 0.82 891

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
 

pre == data["Survived"]   #比较模型预测值与实际值是否一致

  

 

  
1
 

0 True
1 True
2 True
3 True
4 True ...  
886 True
887 True
888 False
889 False
890 True
Name: Survived, Length: 891, dtype: bool

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
 

可视化

dot_data = export_graphviz(Dtc,feature_names = ["Pclass","Sex","Age"],class_names="Survive")

  

 

  
1
 

graph  = graphviz.Source(dot_data)
graph

  

 

  
1
  
2
 

文章来源: beishan.blog.csdn.net，作者：北山啦，版权归原作者所有，如需转载，请联系作者。

原文链接：beishan.blog.csdn.net/article/details/112060492