泰坦项目

import pandas as pd
import numpy as np
file='D:\新建文件夹 (6)'
data_train=pd.read_csv(file+'/titanic_train.csv')
data_test=pd.read_csv(file+'/titanic_test')  

---

import pandas as pd
import numpy as np
file='D:\新建文件夹 (6)'
data_train=pd.read_csv(file+'/titanic_train.csv')
data_test=pd.read_csv(file+'/titanic_test.csv')

---

data_train.info() 读取数据的列的信息

class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId    891 non-null int64
Survived       891 non-null int64
Pclass         891 non-null int64
Name           891 non-null object
Sex            891 non-null object      可以查看是否有缺失值和总共的行数
Age            714 non-null float64
SibSp          891 non-null int64
Parch          891 non-null int64
Ticket         891 non-null object
Fare           891 non-null float64
Cabin          204 non-null object
Embarked       889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 66.2+ KB'''

---

data_train['Age']=data_train['Age'].fillna(data_train['Age'].median()) 发现有缺失值使用函数进行填充

---

predictors = ["Pclass","Age","SibSp","