Reputation: 14604
I would like to modify the function party / varimp.
The function takes a very long time to run, and I would like to print the progress inside the main loop.
I took the code from the function after calling it in R; I edited the code and pasted in in R to override the package original code.
My new code is (the only modif is a small part at the bottom marked 'MY EDIT'):
varimp <- function (object, mincriterion = 0, conditional = FALSE, threshold = 0.2,
nperm = 1, OOB = TRUE, pre1.0_0 = conditional)
{
response <- object@responses
if (length(response@variables) == 1 && inherits(response@variables[[1]],
"Surv"))
return(varimpsurv(object, mincriterion, conditional,
threshold, nperm, OOB, pre1.0_0))
input <- object@data@get("input")
xnames <- colnames(input)
inp <- initVariableFrame(input, trafo = NULL)
y <- object@responses@variables[[1]]
if (length(response@variables) != 1)
stop("cannot compute variable importance measure for multivariate response")
if (conditional || pre1.0_0) {
if (!all(complete.cases(inp@variables)))
stop("cannot compute variable importance measure with missing values")
}
CLASS <- all(response@is_nominal)
ORDERED <- all(response@is_ordinal)
if (CLASS) {
error <- function(x, oob) mean((levels(y)[sapply(x, which.max)] !=
y)[oob])
}
else {
if (ORDERED) {
error <- function(x, oob) mean((sapply(x, which.max) !=
y)[oob])
}
else {
error <- function(x, oob) mean((unlist(x) - y)[oob]^2)
}
}
w <- object@initweights
if (max(abs(w - 1)) > sqrt(.Machine$double.eps))
warning(sQuote("varimp"), " with non-unity weights might give misleading results")
perror <- matrix(0, nrow = nperm * length(object@ensemble),
ncol = length(xnames))
colnames(perror) <- xnames
for (b in 1:length(object@ensemble)) {
tree <- object@ensemble[[b]]
if (OOB) {
oob <- object@weights[[b]] == 0
}
else {
oob <- rep(TRUE, length(y))
}
p <- .Call("R_predict", tree, inp, mincriterion, -1L,
PACKAGE = "party")
eoob <- error(p, oob)
for (j in unique(varIDs(tree))) {
for (per in 1:nperm) {
if (conditional || pre1.0_0) {
tmp <- inp
ccl <- create_cond_list(conditional, threshold,
xnames[j], input)
if (is.null(ccl)) {
perm <- sample(which(oob))
}
else {
perm <- conditional_perm(ccl, xnames, input,
tree, oob)
}
tmp@variables[[j]][which(oob)] <- tmp@variables[[j]][perm]
p <- .Call("R_predict", tree, tmp, mincriterion,
-1L, PACKAGE = "party")
}
else {
p <- .Call("R_predict", tree, inp, mincriterion,
as.integer(j), PACKAGE = "party")
}
perror[(per + (b - 1) * nperm), j] <- (error(p,
oob) - eoob)
}
}
######################
# MY EDIT
print(b)
flush.console()
######################
}
perror <- as.data.frame(perror)
return(MeanDecreaseAccuracy = colMeans(perror))
}
But when using it, I now get an error:
> data.cforest.varimp <- varimp(data.cforest, conditional = TRUE)
Error in unique(varIDs(tree)) : could not find function "varIDs"
This error comes in a part of the code that I did not modify, so I do not understand.
Is the problem in my new code, or in the way I try to modify an existing package?
Upvotes: 1
Views: 478
Reputation: 14604
Yes Joran's tip worked:
environment(varimp) <- asNamespace('party')
Upvotes: 1