Reputation: 63
i use rpart run a regression tree
library(MASS)
N = 1000
episolon = rnorm(N, 0, 0.01)
x1 = rnorm(N, 0, sd=1)
x2 = rnorm(N, 0, sd=1)
eta_x = 1/2*x1+x2
Kappa_x = 1/2*x1
w = rbinom(N, 1, 0.5)
treatment = w
makeY = function(eta, Kappa){
Y = eta+1/2*(2*w-1)*Kappa+episolon
}
Y1 = makeY(eta_x, Kappa_x)
fit = rpart(Y1 ~ x1 + x2)
plot(fit)
text(fit)
compute numbers of leaf in rpart
I want to have a function to give me there are 12 leaves in this tree
Upvotes: 1
Views: 2010
Reputation: 37661
The fit
object has all the information that you need. You can examine it using str(fit)
.
Two ways to find the number of leaves are:
sum(fit$frame$ncompete == 0)
[1] 11
AND
sum(fit$frame$var == "<leaf>")
[1] 11
Upvotes: 3