决策树中预测变量重要性是怎么得到的？

tijmujxy 发表于 2016-1-10 10:40
那你看看是不是这个

请问你的截图是那本书里面的，我想去学习下这个问题，多谢

绿水菊 发表于 2016-11-27 17:38
老师，您截图截得是哪本书呀？

是CNKI查到的硕士毕业论文

guoxixi1982 发表于 2017-12-25 11:32
请问你的截图是那本书里面的，我想去学习下这个问题，多谢

是CNKI查到的一篇硕士毕业论文~

tijmujxy 发表于 2016-1-10 10:40
那你看看是不是这个

老师，您好！请问截图是来自哪本书呢？

ethal 发表于 2018-4-21 19:44
老师，您好！请问截图是来自哪本书呢？

是CNKI查到的一篇硕士毕业论文~

我在rpart包的说明书里面找到一段
A variable may appear in the tree many times, either as a primary or a surrogate
variable. An overall measure of variable importance is the sum of the goodness of split
measures for each split for which it was the primary variable, plus goodness * (adjusted
agreement) for all splits in which it was a surrogate. In the printout these are scaled to sum
to 100 and the rounded values are shown, omitting any variable whose proportion is less
than 1%. Imagine two variables which were essentially duplicates of each other; if we did
not count surrogates they would split the importance with neither showing up as strongly
as it should.