主要流程:1.下载数据集。2.数据集划分。3.选择模型及拟合。4.预测
1.
#下载数据集
from sklearn.datasets import load_boston
boston = load_boston()
#查看数据键值
boston.keys()
#dict_keys(['data', 'target', 'feature_names', 'DESCR', 'filename'])
x = boston['data']
y = boston['target']
#查看数据结构
x.shape
#(506, 13) #506个样本,13个属性
2.
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2)
3.
#选择模型拟合训练集
from sklearn.linear_model import LinearRegression
lr = LinearRegression()
lr.fit(x_train,y_train)
4.
#使用测试集测试数据
y_ = lr.predict(x_test)
#预测值与真实值的差距
(y_test-y_).round(2)