[英]Negative r squared for linear regression but positive r squared with Random forest regressor
My R squared score for Linear regression is -1.56 but my R squared score for Random Forest regressor is around 0.48.我的线性回归的 R 平方分数是 -1.56,但我的随机森林回归量的 R 平方分数约为 0.48。 Is it okay to get scores like this?
能拿到这样的分数吗?
Is it okay to get scores like this?
能拿到这样的分数吗?
Yes.是的。
Explanation - Linear Regression and Random Forest are two very different models.解释- 线性回归和随机森林是两个非常不同的模型。 It is highly possible that the data on which you are trying to fit the model is so complicated that linear regression does not fit it well.
您尝试拟合 model 的数据很可能非常复杂,以至于线性回归不能很好地拟合它。
Regarding the negative R squared score - It simply means that the linear regression model fits worse than a horizontal line.关于负的 R 平方分数- 这仅仅意味着线性回归 model 拟合比水平线差。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.