1 import numpy as np
 2 import pandas as pd
 3 from sklearn.feature_extraction import DictVectorizer
 4 from sklearn.model_selection import train_test_split
 5 from sklearn.tree import DecisionTreeClassifier
 6 from sklearn.metrics import r2_score
 7 
 8 
 9 def titanic_tree():
10     # 獲取資料
11     df = pd.read_csv('
 
Titanic.csv')
12     # df = df.fillna(0)
13     # dict_train = df.loc[:, ['Pclass', 'Age', 'Sex']].to_dict(orient='record')
14     # dict_target = pd.DataFrame(df['Survived'], columns=['Survived']).to_dict(orient='record')
15     # x_train, x_test, y_train, y_test = train_test_split(dict_train, dict_target, test_size=0.25)
 

16 
17     # 處理資料，找出特徵值和目標值
18     x = df.loc[:, ['Pclass', 'Age', 'Sex']]
19     y = df.loc[:, ['Survived']]
20     # 缺失值處理
21     x['Age'].fillna(x['Age'].mean(), inplace=True)
22     # 分割資料集到訓練集和測試集
23     x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
24     # print(y_test)
 

25     dv_train = DictVectorizer(sparse=False)
26     x_train = dv_train.fit_transform(x_train.to_dict(orient='record'))
27     x_test = dv_train.transform(x_test.to_dict(orient='record'))
28 
29     dv_target = DictVectorizer(sparse=False)
30     y_target = dv_target.fit_transform(y_train.to_dict(orient='record'))
31     y_test = dv_target.transform(y_test.to_dict(orient='record'))
32     # print(y_test)
33     # 用決策樹進行預測
34     d_tree = DecisionTreeClassifier()
35     d_tree.fit(x_train, y_train)
36 
37     data_predict = {
38         'Pclass': 1,
39         'Age': 38,
40         'Sex': 'female'
41 
42     }
43 
44     x_data = dv_train.transform(data_predict)
45     print(dv_target.inverse_transform(d_tree.predict(x_data).reshape(-1,1)))
46     # print(d_tree.predict(x_test))
47     # print(y_test)
48     # 預測準確率
49     # print(d_tree.score(x_test, y_test))
50 
51 
52 if __name__ == '__main__':
53     titanic_tree()