[R] Partial Dependence and RandomForest
murph636 at umn.edu
Wed Apr 11 20:44:06 CEST 2012
I am interested in clarifying something more conceptual, so I won't be
providing any data or code here.
>From what I understand, partial dependence plots can help you understand the
relative dependence on a variable, and the subsequent values of that
variable, after "averaging out the effects" of the other input variables.
This is great, but what I am interested in knowing is how that relates to
each predictor class, not just the overall prediction.
Is it possible to plot partial dependence per class? Specifically, I'd like
to know the important threshold values of my most important variables.
Thank you for your time,
View this message in context: http://r.789695.n4.nabble.com/Partial-Dependence-and-RandomForest-tp4549705p4549705.html
Sent from the R help mailing list archive at Nabble.com.
More information about the R-help