python - 运行时错误: The classifier does not expose "coef_" or "feature_importances_" attributes

Question

在我的代码中，它引发运行时错误。在这里，我尝试将 RFE 拟合为回归数据。

from sklearn.feature_selection import RFE
from sklearn.svm import SVR           
from sklearn.feature_selection import SelectKBest
from sklearn.preprocessing import *

scaler = StandardScaler().fit(trainFeatures)
xscaled = scaler.transform(trainFeatures)
estimator = SVR()
selector = RFE(estimator, dimension, step=1)
selector = selector.fit(xscaled, trainOutput.ravel())
selectedFeatures = selector.transform(xscaled)

Answer 1

根据this link ，RFE仅在内核线性时与SVR一起工作。

默认情况下，它是“rbf”，所以这样做:

estimator = SVR(kernel="linear")