import pandas as pd
#本地读取训练集和测试集
train=pd.read_csv('train.csv')
test=pd.read_csv('test.csv')
#输出基本信息
print(train.info())
print(test.info())
selected_features=['Pclass','Sex','Age','Emarked','SibSip','Parch','Fare']
X_train=train[selected_features]
X_test=test[selected_features]
y_train=train['Survived']
一、填充缺失值
使用特征的众数或者平均值填充
#Emarked特征存在缺失值,需要补充
#某个特征,水平分类计数
print(X_train['Emarked'].value_counts())
print(X_test['Emarked'].value_counts())
#使用出现频率最高的水平填充缺失值
X_train['Emarked'].fillna('S',inplace=True)
X_test['Emarked'].fillna('S',inplace=True)
X_train['Age'].fillna(X_train['Age'].mean(