Labfans是一个针对大学生、工程师和科研工作者的技术社区。 | 论坛首页 | 联系我们(Contact Us) |
![]() |
|
![]() |
#1 |
高级会员
注册日期: 2019-11-21
帖子: 3,006
声望力: 66 ![]() |
![]() My idea is like this: assume I have built a geographically weighted regression model, i.e.for each cell, y ~ β0 + β1*x1 + β2*x2 + β3*x3, I want to create a single map showing the relative importance of the three variables on the response variable y. I want to do this like this: (1) I normalize the three coefficients for each cell into unit 1 by dividing each coefficient by their sum; (2) I utilize a ternary color space to map the three adjusted coefficients to a color code; (3) I get the color code and fill it into the corresponding cell. But I don't know how to implement this in practice, like R, Python or Matlab? Attached is the ternary color space. More... |
![]() |
![]() |