泰坦尼克号生存

``python

import pandas as pd

from sklearn.tree import DecisionTreeClassifier

from sklearn.preprocessing import LabelEncoder

from sklearn.model_selection import train_test_split

from sklearn.metrics import accuracy_score

from sklearn import tree

import graphviz

 

# 加载训练数据和测试数据

train_data = pd.read_csv('train.csv')

test_data = pd.read_csv('test.csv')

 

# 数据预处理

# 处理缺失值

train_data = train_data.dropna(subset=['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked'])

test_data = test_data.dropna(subset=['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked'])

 

# 特征选择

features = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fa