I'm following the Caret package tutorial for constructing customized functions for a recursive feature elimination. I can reproduce the provided example which is a random forest regression. However, when I modify the code to deal with classification, I receive an odd error:

`library(caret) library(mlbench) library(Hmisc) library(randomForest) n <- 100 p <- 40 sigma <- 1 set.seed(1) sim <- mlbench.friedman1(n, sd = sigma) colnames(sim$x) <- c(paste("real", 1:5, sep = ""), paste("bogus", 1:5, sep = "")) bogus <- matrix(rnorm(n * p), nrow = n) colnames(bogus) <- paste("bogus", 5+(1:ncol(bogus)), sep = "") x <- cbind(sim$x, bogus) y <- sim$y #customizing tutorial example for binary outcome y[y <= 12] <- 0 y[y> 12] <- 1 y <- factor(y) normalization <- preProcess(x) x <- predict(normalization, x) x <- as.data.frame(x) subsets <- c(1:5, 10, 15, 20, 25) rfRFE <- list(summary = defaultSummary, fit = function(x, y, first, last, ...){ library(randomForest) randomForest(x, y, importance = first, ...) }, pred = function(object, x) predict(object, x), rank = function(object, x, y) { vimp <- varImp(object) vimp <- vimp[order(vimp$Overall,decreasing = TRUE),,drop = FALSE] vimp$var <- rownames(vimp) vimp }, selectSize = pickSizeBest, selectVar = pickVars) ctrl <- rfeControl(functions = lmFuncs, method = "repeatedcv", repeats = 5, verbose = FALSE) ctrl$functions <- rfRFE ctrl$returnResamp <- "all" set.seed(10) rfProfile <- rfe(x, y, sizes = subsets, rfeControl = ctrl) rfProfile `

The error is:

`Error in {: task 1 failed - "argument 1 is not a vector" `

My question is how should one go about defining `rfRFE`

for random forest models with binary response variables?

**Contents**hide

#### Best Answer

You need to make sure the response variable is a factor with level names starting with a letter

### Similar Posts:

- Solved – pickSizeBest() for recursive feature elimination
- Solved – How to use rfe object with function pickSizeTolerance in R package caret
- Solved – R Caret train / rfe optimize for positive predictive value instead of Accuracy or Kappa
- Solved – How to get lmFuncs functions of the rfe function in caret to do a logistic regression
- Solved – Error with caret, using “out-of-bag” re-sampling