Solved – Odd error with caret function rfe

caretr

library(caret)
set.seed(1) 
x <- data.frame(runif(10),runif(10))
y <- rnorm(10)
rfeModel <- rfe(x,y,rfeControl = rfeControl(functions = lmFuncs))

returns:

Error in { : task 1 failed – "undefined columns selected"

While this code:

data(BloodBrain)

x <- scale(bbbDescr[,-nearZeroVar(bbbDescr)])
x <- x[, -findCorrelation(cor(x), .8)]
x <- as.data.frame(x)

lmProfile <- rfe(x, logBBB,rfeControl = rfeControl(functions = lmFuncs))

Works fine. What am I doing wrong in the 1st example? (I get the same error in R 2.14.0 and 2.13.2)

Best Answer

You have to specify the sizes argument ($\leq 2$ in your example). The default value in rfe is sizes=2^(2:4), but you only have two features.

?rfe

Arguments

...

sizes

a numeric vector of integers corresponding to the number of features that should be retained

Related Solutions

Solved – caret rfe variable selection and test prediction

For #1:

Using feature selection on the training set and predicting the test set is fine.
You could use the selected set with other models. However, these predictors may not work well for other models. Second, the performance of the following models will be estimated to be inappropriately optimistic (Since the next model training does not know that the features were selected).
The elastic net does its own feature selection, so why would you use that model after selection?

For #2, use more resamples.

Max

Solved – How to use rfe object with function pickSizeTolerance in R package caret

Ok, functions pickSizeTolerance and pickSizeBest are well documented in caret's ?rfFuncs

The above written reproducible code can be further used following the documentation's example :

example <- data.frame(RMSE =rfProfile$results$RMSE, Variables = c(2:4))

## Percent Loss in performance (positive)
example$PctLoss <- (example$RMSE - min(example$RMSE))/min(example$RMSE)*100

xyplot(RMSE ~ Variables, data= example)
xyplot(PctLoss ~ Variables, data= example)

absoluteBest <- pickSizeBest(example, metric = "RMSE", maximize = FALSE)
within5Pct <- pickSizeTolerance(example, metric = "RMSE", maximize = FALSE)

cat("numerically optimal:",
    example$RMSE[absoluteBest],
        "RMSE in position",
        absoluteBest, "\n")
cat("Accepting a 1.5 pct loss:",
    example$RMSE[within5Pct],
"RMSE in position",
within5Pct, "\n")

Best Answer

Related Solutions

Solved – caret rfe variable selection and test prediction

Solved – How to use rfe object with function pickSizeTolerance in R package caret

Related Question