kaggle : https://www.kaggle.com/c/titanic
这里做一个简单笔记记录
提交准确率:0.83
代码详解:
#读取训练集
train = pd.read_csv('/Users/Cheney/Downloads/kaggle(方老师)/train.csv')
#读取测试集
test = pd.read_csv('/Users/Cheney/Downloads/kaggle(方老师)/test.csv')
2、特征选取
选取数据中的features进行训练,根据对题目的分析,可知’PassengerId’是冗余信息,而’Name’,’Ticket’,'Cabin'三者对于乘客生存无明显影响,所以不选取。其余七项为选取的训练features
#features选取
X_train = train[['Pclass','Sex','Age','Embarked','SibSp','Parch','Fare']]
X_test = test[['Pclass','Sex','Age','Embarked','SibSp','Parch','Fare']]