机器学习2：KNN决策树探究泰坦尼克号幸存者问题

朱雀 2023-01-01 07:59 117阅读 0赞

> KNN决策树探究泰坦尼克号幸存者问题

![在这里插入图片描述][resize_m_lfit_w_962_pic_center]

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

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

data

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>Survived</th> 
   <th>Pclass</th> 
   <th>Sex</th> 
   <th>Age</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>0</td> 
   <td>3</td> 
   <td>male</td> 
   <td>22.0</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>1</td> 
   <td>1</td> 
   <td>female</td> 
   <td>38.0</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>1</td> 
   <td>3</td> 
   <td>female</td> 
   <td>26.0</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>1</td> 
   <td>1</td> 
   <td>female</td> 
   <td>35.0</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>0</td> 
   <td>3</td> 
   <td>male</td> 
   <td>35.0</td> 
  </tr> 
  <tr> 
   <th>...</th> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
  </tr> 
  <tr> 
   <th>886</th> 
   <td>0</td> 
   <td>2</td> 
   <td>male</td> 
   <td>27.0</td> 
  </tr> 
  <tr> 
   <th>887</th> 
   <td>1</td> 
   <td>1</td> 
   <td>female</td> 
   <td>19.0</td> 
  </tr> 
  <tr> 
   <th>888</th> 
   <td>0</td> 
   <td>3</td> 
   <td>female</td> 
   <td>NaN</td> 
  </tr> 
  <tr> 
   <th>889</th> 
   <td>1</td> 
   <td>1</td> 
   <td>male</td> 
   <td>26.0</td> 
  </tr> 
  <tr> 
   <th>890</th> 
   <td>0</td> 
   <td>3</td> 
   <td>male</td> 
   <td>32.0</td> 
  </tr> 
 </tbody> 
</table>

891 rows × 4 columns

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

data

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>Survived</th> 
   <th>Pclass</th> 
   <th>Sex</th> 
   <th>Age</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>0</td> 
   <td>3</td> 
   <td>1</td> 
   <td>22.0</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>38.0</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>1</td> 
   <td>3</td> 
   <td>0</td> 
   <td>26.0</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>35.0</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>0</td> 
   <td>3</td> 
   <td>1</td> 
   <td>35.0</td> 
  </tr> 
  <tr> 
   <th>...</th> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
  </tr> 
  <tr> 
   <th>886</th> 
   <td>0</td> 
   <td>2</td> 
   <td>1</td> 
   <td>27.0</td> 
  </tr> 
  <tr> 
   <th>887</th> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>19.0</td> 
  </tr> 
  <tr> 
   <th>888</th> 
   <td>0</td> 
   <td>3</td> 
   <td>0</td> 
   <td>NaN</td> 
  </tr> 
  <tr> 
   <th>889</th> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>26.0</td> 
  </tr> 
  <tr> 
   <th>890</th> 
   <td>0</td> 
   <td>3</td> 
   <td>1</td> 
   <td>32.0</td> 
  </tr> 
 </tbody> 
</table>

891 rows × 4 columns

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

data

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>Survived</th> 
   <th>Pclass</th> 
   <th>Sex</th> 
   <th>Age</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>0</td> 
   <td>3</td> 
   <td>1</td> 
   <td>22.000000</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>38.000000</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>1</td> 
   <td>3</td> 
   <td>0</td> 
   <td>26.000000</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>35.000000</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>0</td> 
   <td>3</td> 
   <td>1</td> 
   <td>35.000000</td> 
  </tr> 
  <tr> 
   <th>...</th> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
  </tr> 
  <tr> 
   <th>886</th> 
   <td>0</td> 
   <td>2</td> 
   <td>1</td> 
   <td>27.000000</td> 
  </tr> 
  <tr> 
   <th>887</th> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>19.000000</td> 
  </tr> 
  <tr> 
   <th>888</th> 
   <td>0</td> 
   <td>3</td> 
   <td>0</td> 
   <td>29.699118</td> 
  </tr> 
  <tr> 
   <th>889</th> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>26.000000</td> 
  </tr> 
  <tr> 
   <th>890</th> 
   <td>0</td> 
   <td>3</td> 
   <td>1</td> 
   <td>32.000000</td> 
  </tr> 
 </tbody> 
</table>

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

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

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

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

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

# 可视化 #

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

graph  = graphviz.Source(dot_data)
    graph

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQ1MTc2NTQ4_size_16_color_FFFFFF_t_70_pic_center]

[resize_m_lfit_w_962_pic_center]: /images/20221120/6b8d122058b447f1b85dfd2b7ebe29bb.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQ1MTc2NTQ4_size_16_color_FFFFFF_t_70_pic_center]: /images/20221120/acb9b2605c23459b8f3f8351b936be23.png