z**k
发帖数: 378 | 1 My understanding is, for Adaboost M1, the loss function mean(-y*F) is always
strictly decreasing, but this is not the case for the following code. Can
anyone help?
I m following the example of Hastie ESL-II chapter 10.1.
sorry cannot type Chinese here. Thank you very much for help.
#================R Script====================
## Data using example given in T. Hastie, ESL, chapter 10.1
dta <- matrix(rnorm(20000), 2000, 10)
pred <- apply(dta, 1, function(x) sum(x^2))
y <- (pred > qchisq(0.5, 10)) * 2 - 1
## fit y with a two nodes classificaiton tree in x
## randomly sample 19 spliting points and choose the best one
stump <- function(y, x, w) {
## randomly sample 19 splitting points
ss <- quantile(x, probs=seq(0.05, 0.95, by=0.05) + runif(19) * 0.025)
## compute the loss for each splitting point
losses <- numeric(0)
preds <- list()
cnt <- 1
for (s in ss) {
inx <- x < s
G1 <- rep(-1, length(y))
G1[inx] <- 1
losses[cnt] <- sum(as.integer(y != G1) * w)
preds[[cnt]] <- G1
G2 <- -G1
losses[cnt+1] <- sum(as.integer(y != G2) * w)
preds[[cnt+1]] <- G2
cnt <- cnt+2
}
i <- which(losses == min(losses))[1]
preds[[i]]
}
## Start the Adaboost M1 algorithm
w <- rep(1/2000, 2000)
F <- rep(0, 2000)
losses <- rep(NA, 400)
mrates <- rep(NA, 400)
m <- 0
while (m <= 400) {
m <- m + 1
G <- stump(y, dta[, sample(1:10, 1)], w)
err <- sum(w[G != y]) / sum(w)
w <- w * exp(alpha * (y != G))
w <- w / sum(w)
F <- F + alpha * G
losses[m] <- mean(exp(-y*F))
mrates[m] <- mean(y*F < 0)
##cat(sum(exp(-y*F)), "n")
}
table((F > 0)*2 - 1, y)
par(mfrow=c(2,1))
plot(losses, type="l")
plot(mrates, type="l") |
|
