sklearn.linear_model.LassoLarsIC提早停止

Question

這是什麼意思？當我使用sklearn.linear_model.LassoLarsIC時，它會彈出：「提早停止拉爾斯路徑，因爲殘留物很小並且alpha的當前值不再被很好地控制」

Answer 1

在行之前有一條評論sklearn/linear_model/least_angle.py它吐出警告：

# alpha is increasing. This is because the updates of Cov are 
# bringing in too much numerical error that is greater than 
# than the remaining correlation with the 
# regressors. Time to bail out 

我希望它可以幫助...