分割训练集和测试集——鸢尾花数据集为例

from sklearn.datasets import load_iris

data=load_iris() #导入数据和标签

data_X=data.data

data_y=data.target

# 导入模块

from sklearn.model_selection import train_test_split

 # 划分为训练集和测试集数据X_train,X_test,y_train,y_test=train_test_split(data_X,data_y,test_size=0.2,random_state=111)

数据特征工程（预处理）

from sklearn.preprocessing import StandardScaler  # 标准化

from sklearn.preprocessing import MinMaxScaler # 归一化

# 标准化

ss=StandardScaler()X_scaled=ss.fit_transform(X_train)

# 归一化

mm=MinMaxScaler()X_scaled=mm.fit_transform(X_train)