机器学习第一篇：数据预处理

#导入pandas库
import pandas as pd

#导入数据
data=pd.read_csv('Data.csv') 

#缺失值处理
data['Age']=data['Age'].fillna(data['Age'].mean())
data['Salary']=data['Salary'].fillna(data['Salary'].mean())

#提取数据
X = data.iloc[:, :-1]
y = data.iloc[:, 3]

#独热编码
X = pd.get_dummies(X)  

#标签编码
from sklearn.preprocessing import LabelEncoder   
le = LabelEncoder()
y = le.fit_transform(y) #就看成数据标准化的过程

#数据的拆分
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0) 

#数据标准化
from sklearn.preprocessing import StandardScaler  #标准化
from sklearn.preprocessing import MinMaxScaler    #0,1 标准化 
scaler=StandardScaler().fit(x_train)
x_train_scaled=scaler.transform(x_train)
x_test_scaled=scaler.transform(x_test)