I am running into problems when applying recursive feature selection to nnet models with caret::rfe; I get the following error message:
Error in { : task 1 failed - "undefined columns selected"
The actual task is more complex than the following example, but I am confident that this is a similar problem:
library(caret)
rfe(x = iris[,1:3],
y = iris[,4]/max(iris[,4]),
sizes = c(2),
method="nnet",
rfeControl = rfeControl(functions = caretFuncs)
)
I know this error can occur when trying to select more features than there are available in x (e.g. see https://stats.stackexchange.com/questions/18362/odd-error-with-caret-function-rfe), but this does not seem to be the problem here. I also ran very similar calls in earlier versions of caret, without this problem occurring.
I use R 3.3.1 and caret 6.0.71.
Thank you very much for your help.
EDIT: I went through the archived versions of caret and found that the example code is working in caret versions <= 6.0.62.
I went through the archived versions of caret and found that the example code is working in caret versions <= 6.0.62. This also solves the problems my original code had. I reported this issue on the caret github.
EDIT: The problem is now fixed : https://github.com/topepo/caret/issues/485
Related
I am crossposting this from https://stats.stackexchange.com/questions/488201/alternatives-to-or-fix-for-lmerconveniencefunctions-for-use-with-lme4 as it was suggested that people might have more relevant knowledge here.
Recently I updated from R version 3.6 to version 4.0 for my analyses, and noticed that LMERConvenienceFunctions stopped working. Specifically, I use it in conjunction with LME4.
Whenever I try to use the bfFixefLMER_F.fnc (backfitting of fixed effects in LMER models) or pamer.fnc (compute upper- and lower-bound p-values for the analysis of variance or deviance) for a LMER model fitted through LME4, regardless of dataset, I am met with the error "Error in pf(anova.table[term, "F value"], anova.table[term, "Df"], nrow(model#frame) - : Non-numeric argument to mathematical function". I have tried this on two separate computers with the same result. Now, as far as I can tell, LMERConvenienceFunctions hasn't been updated since 2015, so I'm not holding out hope that a fix is forthcoming.
I tried reverting to R 3.6.2, but found the same error using the versions of LME4 that were out shortly before R 4.0 came out. I have finally found the previous version I was using, so this will (hopefully) fix it for my current analysis, but doesn't help if I want to use the most recent version of R and LME4 going forwards.
Other functions of LMERConvenience (namely fitLMER.fnc and mcp.fnc) seem to be working properly, so it doesn't seem to be a systematic issue, but it is definitely one that significantly impedes my work.
Does anyone have any suggestions for alternative packages, or could anyone offer any advice on editing the LMERConvenienceFunctions package so that I can get the broken functions working again? I don't have any experience with changing the coding within packages, so would be starting from bare basics there.
I am also aware that there are some workarounds through adding extra code in my R script, as I did find in my searching for an answer that it had previously been a problem with the same package in 2014 (https://stat.ethz.ch/pipermail/r-sig-mixed-models/2014q2/022264.html), but I am not familiar with writing that kind of code, so would appreciate any guidance there as well.
I managed to get some help from the lovely people working with LME4 on github; for anyone who has this issue in the future, there are a few things of note:
I have emailed the listed maintainer of LMERConvenienceFunctions asking for them to update the CRAN version so that it abides by the rules of CRAN. Hopefully he does this.
For a fix for those using LME4 and LMERConvenienceFunctions, but who are NOT also using lmerTest, recently the anova table headers "Chi Df" and"Df" were updated to "Df" and "npar" respectively (reasons outlined here:https://github.com/lme4/lme4/issues/528). This is an issue for LMERConvenienceFunctions because pamer.fnc called to Df, so needs to be updated to call to npar instead. Further, bfFixefLMER_F.fnc calls to pamer.fnc, so is fixed when pamer.fnc is updated. For anyone unsure how, I found the code using getAnywhere() and modified it, so just copy the code below and paste it once right near the start of the file:
pamer.fnc <- function (model, ndigits = 4)
{
if (length(rownames(anova(model))) == 0) {
cat("nothing to evaluate: model has only an intercept.\n\n")
cat("printing model fixed effects:\n")
fixef(model)
}
else {
dims <- NULL
rank.X = qr(model#pp$X)$rank
anova.table = anova(model)
anova.table = cbind(anova.table, upper.den.df = nrow(model#frame) -
rank.X)
p.values.upper = as.numeric()
p.values.lower = as.numeric()
for (term in row.names(anova.table)) {
p.values.upper = c(p.values.upper, round(1 - pf(anova.table[term,
"F value"], anova.table[term, "npar"],
nrow(model#frame) - rank.X), ndigits))
model.ranef <- ranef(model)
lower.bound <- 0
for (i in 1:length(names(model.ranef))) {
dims <- dim(model.ranef[[i]])
lower.bound <- lower.bound + dims[1] * dims[2]
}
p.values.lower = c(p.values.lower, 1 - pf(anova.table[term,
"F value"], anova.table[term, "npar"],
nrow(model#frame) - rank.X - lower.bound))
}
dv <- gsub(" ", "", gsub("(.*)~.*",
"\\1", as.character(model#call)[2]))
ss.tot <- sum((model#frame[, dv] - mean(model#frame[,
dv]))^2)
aov.table <- as.data.frame(anova(model))
expl.dev <- vector("numeric")
for (i in rownames(aov.table)) {
expl.dev <- c(expl.dev, aov.table[i, 2]/ss.tot)
}
names(expl.dev) <- rownames(aov.table)
anova.table = round(cbind(anova.table, upper.p.val = p.values.upper,
lower.den.df = nrow(model#frame) - rank.X - lower.bound,
lower.p.val = p.values.lower, `expl.dev.(%)` = expl.dev *
100), ndigits)
return(anova.table)
}
}
(You may also need to run the function script for bfFixefLMER_F.fnc separately again, to let R know that bfFixefLMER_F.fnc should be calling from the updated version of pamer.fnc)
For a fix for those using LME4 and LMERConvenienceFunctions, but who ARE also using lmerTest, you will need to either 1) use numDF instead of npar, or 2) replace "anova.table = anova(model)" with "anova.table = anova(model, dff = "lme4") in versions of lmerTest 3.0 onwards. This appears to be due to the anova.lmerModLmerTest function (added in lmerTest 3.0) overwriting what the call to anova() does, with a Type III Satterthwaite analysis listed before lme4, leading to it being defaulted to when dff is not specified.
Using the following code
trnCtrl=trainControl(method='repeatedCV', number=10, repeats=5)
I get the error
Warning message: repeats has no meaning for this resampling method.
Even stranger, it worked fine until I did a reinstall of Caret. Note that I have already removed R, and reinstalled all packages 2x...
I appreciate that this is an old question but after looking through the Caret source code all I can deduce is that the problem is occurring when declaring the sampling method.
The following snippet has been pulled directly from the Caret repo:
if(!is.na(repeats) & !(method %in% c("repeatedcv", "adaptive_cv")))
warning("`repeats` has no meaning for this resampling method.", call. = FALSE)
My guess is the condition is failing when evaluating the method. You've specified the method as repeatedCV whereas it's actually named repeatedcv.
Again I appreciate that this question is old and it could well be the name has changed since 2013. In which case, ignore this answer.
I also got the same error and the reason was I typed "repeatecv", wrong method.
When I changed to right name, "repeatedcv" it worked.
Try,
trnCtrl=trainControl(method='repeatedcv', number=10, repeats=5)
I'm using h2o package and trying to create a learner using the below given code
install.packages("h2o")
library("h2o")
h2o.learner <- makeLearner("regr.h2o.deeplearning",predict.type = "response")
But I'm getting this error
> h2o.learner <- makeLearner("regr.h2o.deeplearning",predict.type = "response")
Error: could not find function "makeLearner"
Note: Few months back I used this code without any problem.
Any idea what could be possible thing for this error?
The correct code for this is simply
library(mlr)
h2o.learner = makeLearner("regr.h2o.deeplearning")
The makeLearner() is not part of H2O. It appears to be part of the mlr package. It also seems that mlr does have h2o support, so it might be as simple as adding a library(mlr) to the top of your script? (Making sure that the mlr package has been installed, already, of course.)
I use R version 2.15.1 (2012-06-22) and mgcv version 1.7-22
I load the following set of packages in R:
library(sqldf)
library(timeDate)
library(forecast)
library(xts)
library(tseries)
library(MASS)
library(mgcv)
It happens that I can not run a simple model (I omit the code). Even the sample code taken from the help pages:
dat = gamSim(1,n=400,dist="normal",scale=2)
b = gam(y~s(x0)+s(x1)+s(x2)+s(x3),data=dat)
gives an error:
Error in qr.qty(qrc, sm$S[[l]]) :
NA/NaN/Inf in foreign function call (arg 5)
In addition: Warning message:
In smoothCon(split$smooth.spec[[i]], data, knots, absorb.cons, scale.penalty = scale.penalty, :
number of items to replace is not a multiple of replacement length
Note that everything works fine, if I just load the package mgcv and then use the sample code right away. It also works if I just load all the packages and run the sample code. It just does not work if I
load all packages
do some file reading, sqldf statements, ts operations and some models from package forecast.
if I then apply GAM, it does not work anymore.
Apparently the variable definitions in the general environment mess up the functioning of the package.
Are there any known issues? Are there general rules that I have to obey if I load various packages? Can I write code that "disturbed" the package mgcv?
# Richard there are 2 GAM related packages: gam and mgcv. Loading both libraries at the same time usually causes a conflict.
Loading mgcv as the first package solved my problem ... strange but true.
I'm working with the R package stargazer. I have a Zelig model that I can't get stargazer to create Latex code for.
logit9.1 <- zelig(winner ~ treatment + count_parties + resp_OECD24 + DirExp + IndExp,
data = outcome, model = "logit" ,robust = TRUE)
stargazer(logit9.1)
Error in if (zelig.object$family$family == "gaussian") { :
argument is of length zero
If I change model="normal", I get the same error message. model="gaussian" is not a supported model in zelig(). The stargazer documentation says that it works with zelig objects.
stargazer v. 2.0 is now available on CRAN. The package has been updated to reflect changes made to Zelig objects, and has a bunch of other new features. Zelig has not always been perfect about backward compatibility of the object it creates, so the old version of stargazer() might have trouble. Perhaps you should try running your code with the latest version, and see if it works.