【Python机器学习】决策树算法对泰坦尼克号人员幸存预测

1.介绍

使用python的机器学习包sklearn完成试验，IDE是jupyter notebook。

2.代码

# 导入数据集
import pandas as pd 
datas_train = pd.read_csv('TTNKHP/train.csv') # 训练集数据
# 查看数据前几条
datas_train.head()
# 收集特征值和目标值
x = datas_train[['Pclass','Sex','Age','SibSp','Parch']]
y = datas_train['Survived']
#  填充缺失值
x['Age'].fillna(x['Age'].mean(),inplace=True)
# 转为字典类型
x = x.to_dict(orient='records')
# 数据集划分
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(x,y)
# 特征抽取
from sklearn.feature_extraction import DictVectorizer
transter = DictVectorizer()
x_train= transter.fit_transform(x_train)
x_test = transter.transform(x_test)
# 使用网格搜索和交叉验证进行调参
from sklearn.tree import DecisionTreeClassifier
medicter = DecisionTreeClassifier(criterion='entropy')
from sklearn.model_selection import GridSearchCV
GSCV = GridSearchCV(medicter,param_grid={'max_depth':[1,2,3,4,5,6,7,8,9,10,11,12,13]},cv=4)
GSCV.fit(x_train,y_train)
# 输出信息
GSCV.score(x_test,y_test)
GSCV.best_params_
#0.8340807174887892
#{'max_depth': 4}