变量重要性:检查您的理解
使用集合让一切井井有条
根据您的偏好保存内容并对其进行分类。
请回答以下问题,挑战一下自己。
问题 1
假设特征 f1 的“分块得分总和”变量重要性大于特征 f2 的“节点数”变量重要性。在本例中,以下哪个陈述是正确的?
如未另行说明,那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可,并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情,请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
最后更新时间 (UTC):2025-02-25。
[null,null,["最后更新时间 (UTC):2025-02-25。"],[[["\u003cp\u003eComparing "sum of the split score" and "number of nodes" variable importance across different features is not appropriate for determining feature importance.\u003c/p\u003e\n"],["\u003cp\u003eThese two variable importance measures are calculated differently and thus, cannot be directly compared to ascertain the relative importance of features f1 and f2.\u003c/p\u003e\n"]]],[],null,["# Variable importances: Check your understanding\n\n\u003cbr /\u003e\n\nChallenge yourself with the following question.\n\nQuestion 1\n----------\n\nSuppose the \"sum of the split score\" variable importance of feature f1 is greater than the \"number of nodes\" variable importance of feature f2. In this case, which of the following statements is correct? \nf1 is more important than f2. \nf1 is less important than f2. \nf1 is neither more important nor less important than f2. \nWell done."]]