#%%#我还是使用sklearn吧。。import numpy as npfrom sklearn import datasetsfrom sklearn.model_selection import train_test_splitboston = datasets.load_boston()X = boston.datay = boston.targetX = X[y < 50]y = y[y < 50]
X_train,X_test,y_train,y_test = train_test_split(X,y)
from sklearn.linear_model import LinearRegressionlin_reg1 = LinearRegression()%time lin_reg1.fit(X_train,y_train)print(lin_reg1.score(X_test,y_test))print(lin_reg1.coef_)
Wall time: 998 µs0.7938748117566617[-9.73603259e-02 3.07679209e-02 -2.40146783e-03 7.11942254e-01-1.17404300e+01 4.09422424e+00 -3.01307879e-02 -1.12181269e+002.56969258e-01 -1.47222778e-02 -7.81371111e-01 6.58684222e-03-3.26238047e-01
数据标准化
#数据标准化from sklearn.preprocessing import StandardScalerstandardScaler = StandardScaler()standardScaler.fit(X_train)
X_train_standard = standardScaler.transform(X_train)print(X_train_standard[:10])
lin_reg2 = LinearRegression()%time lin_reg2.fit(X_train_standard,y_train)
Wall time: 986 µs
X_test_standard = standardScaler.transform(X_test)print(lin_reg2.score(X_test_standard,y_test))
0.7938748117566619
