Replies: 1 comment
-
Hey, sorry I missed this discussion. You could pass the appropriate functions to lam = 3
box_cox_target_transformer = TargetTransformRegressor(
regressor,
func=lambda x: (x ** lam - 1) / lam,
inverse_func=lambda y: y * lam ** 1 / lam + 1
) Note that I haven't tested this code. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
In the nowcasting example here it is mentioned that boxcox transforms are often used in these types of problems. How would you envision it working in an example with river? The
TargetStandardScaler
is straightforward but I don't see how to do the 'rolling' box cox transform to keep the lambda value for doing the inverse box cox. Any recommendations?Beta Was this translation helpful? Give feedback.
All reactions