Hello,
The error is in Ranger parameter mtry becoming greater than the number
of variables (columns).
mtry can be set manually in caret::train argument tuneGrid. But for
random forests you must also set the split rule and the minimum node.
library(caret)
library(farff)
boot <- trainControl(method = "cv", number = 10)
# set the maximum mtry manually to ncol(tr)
# this creates a sequence of mtry values
mtry <- var_seq(ncol(tr), len = 3) # 3 is the default value
mtry
# [1] 2 13 24
#[1] 2 13 24
splitrule <- c("variance", "extratrees")
min.node.size <- 1:10
mtrygrid <- expand.grid(mtry, splitrule, min.node.size)
names(mtrygrid) <- c("mtry", "splitrule",
"min.node.size")
c1 <- train(act_effort ~ ., data = tr,
method = "ranger",
tuneLength = 5,
metric = "MAE",
preProc = c("center", "scale", "nzv"),
tuneGrid = mtrygrid,
trControl = boot)
c1
# Random Forest
#
# 30 samples
# 23 predictors
#
# Pre-processing: centered (48), scaled (48), remove (58)
# Resampling: Cross-Validated (10 fold)
# Summary of sample sizes: 28, 27, 27, 28, 27, 27, ...
# Resampling results across tuning parameters:
#
# mtry splitrule min.node.size RMSE Rsquared MAE
# 2 variance 1 256.6391 0.8103759 186.3609
# 2 variance 2 249.7120 0.8628109 183.6696
# 2 variance 3 258.8240 0.8284449 189.0712
#
# [...omit...]
#
# 13 extratrees 10 254.9569 0.8918014 191.2524
# 24 variance 1 177.7188 0.9458652 112.2800
# 24 variance 2 172.6826 0.9204287 108.5943
# 24 variance 3 172.9954 0.9271006 109.2554
# 24 variance 4 172.2467 0.9523067 110.0776
# 24 variance 5 175.2485 0.9283317 112.8798
# 24 variance 6 177.9285 0.9369881 115.8970
# 24 variance 7 180.5959 0.9485035 117.5816
# 24 variance 8 178.8037 0.9358033 117.8725
# 24 variance 9 176.5849 0.9210959 117.0055
# 24 variance 10 178.6439 0.9257969 119.8035
# 24 extratrees 1 219.1368 0.8801770 141.0720
# 24 extratrees 2 216.1900 0.8550002 140.9263
# 24 extratrees 3 212.4138 0.8979379 141.4282
# 24 extratrees 4 218.2631 0.9121471 146.2908
# 24 extratrees 5 212.5679 0.9279598 144.2715
# 24 extratrees 6 218.9856 0.9141754 152.2099
# 24 extratrees 7 222.8540 0.9412682 152.4614
# 24 extratrees 8 228.1156 0.9423414 161.8456
# 24 extratrees 9 226.6182 0.9408306 160.5264
# 24 extratrees 10 226.9280 0.9429413 165.6878
#
# MAE was used to select the optimal model using the smallest value.
# The final values used for the model were mtry = 24, splitrule = variance
# and min.node.size = 2.
plot(c1)
Hope this helps,
Rui Barradas
?s 23:03 de 30/06/2022, Neha gupta escreveu:> Ok, the data is pasted below
>
> But on the same data (everything the same) and with other models like
> RF, SVM etc, it works fine.
>
> > dput(head(tr, 30))
> structure(list(recordnumber = c(0, 0.02, 0.04, 0.06, 0.07, 0.08,
> 0.09, 0.1, 0.11, 0.12, 0.13, 0.14, 0.16, 0.17, 0.18, 0.23, 0.24,
> 0.25, 0.28, 0.29, 0.3, 0.31, 0.32, 0.33, 0.35, 0.36, 0.37, 0.38,
> 0.4, 0.41), projectname = structure(c(1L, 1L, 1L, 1L, 2L, 3L,
> 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
> 4L, 4L, 4L, 4L, 4L, 4L, 5L, 6L), levels = c("de",
"erb", "gal",
> "X", "hst", "slp", "spl",
"Y"), class = "factor"), cat2 = structure(c(3L,
> 3L, 3L, 3L, 3L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L,
> 9L, 11L, 5L, 4L, 6L, 8L, 3L, 9L, 9L, 9L, 9L, 6L, 7L), levels =
> c("Avionics",
> "application_ground", "avionicsmonitoring",
"batchdataprocessing",
> "communications", "datacapture",
"launchprocessing", "missionplanning",
> "monitor_control", "operatingsystem",
"realdataprocessing", "science",
> "simulation", "utility"), class = "factor"),
forg = structure(c(2L,
> 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
> 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), levels =
c("f",
> "g"), class = "factor"), center = structure(c(2L, 2L,
2L, 2L,
> 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
> 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 6L), levels = c("1",
"2",
> "3", "4", "5", "6"), class =
"factor"), year = c(0.5, 0.5, 0.5,
> 0.5, 0.6875, 0.5625, 0.5625, 0.8125, 0.5625, 0.875, 0.5625, 0.75,
> 0.5625, 0.8125, 0.75, 0.9375, 0.9375, 0.9375, 0.6875, 0.6875,
> 0.6875, 0.6875, 0.875, 1, 0.9375, 0.9375, 0.9375, 0.9375, 0.5625,
> 0.25), mode = structure(c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> 3L, 3L, 3L, 3L, 3L), levels = c("embedded", "organic",
"semidetached"
> ), class = "factor"), rely = structure(c(4L, 4L, 4L, 4L, 4L,
> 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 3L, 3L, 3L, 3L,
> 3L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 4L), levels = c("vl",
"l", "n",
> "h", "vh", "xh"), class =
"factor"), data = structure(c(2L, 2L,
> 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
> 5L, 5L, 5L, 5L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 2L), levels = c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), cplx = structure(c(4L,
> 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 4L,
> 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), time = structure(c(3L,
> 3L, 3L, 3L, 3L, 6L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 3L,
> 3L, 5L, 5L, 5L, 5L, 3L, 3L, 3L, 3L, 3L, 3L, 5L, 3L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), stor = structure(c(3L,
> 3L, 3L, 3L, 3L, 6L, 3L, 3L, 3L, 3L, 3L, 3L, 6L, 3L, 3L, 3L, 3L,
> 3L, 5L, 5L, 5L, 5L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 3L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), virt = structure(c(2L,
> 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 4L, 2L, 2L, 2L, 2L, 3L, 3L,
> 3L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), turn = structure(c(2L,
> 2L, 2L, 2L, 2L, 4L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L,
> 3L, 4L, 4L, 4L, 4L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 2L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), acap = structure(c(3L,
> 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L,
> 3L, 5L, 5L, 5L, 5L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 3L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), aexp = structure(c(3L,
> 3L, 3L, 3L, 3L, 4L, 5L, 5L, 5L, 5L, 4L, 5L, 5L, 4L, 5L, 4L, 4L,
> 4L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), pcap = structure(c(3L,
> 3L, 3L, 3L, 3L, 4L, 5L, 4L, 5L, 3L, 4L, 4L, 5L, 4L, 4L, 4L, 4L,
> 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 3L, 4L, 4L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), vexp = structure(c(3L,
> 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 3L, 3L,
> 3L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 3L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), lexp = structure(c(4L,
> 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 2L, 1L, 4L, 4L, 4L, 4L, 3L, 3L,
> 3L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 4L, 3L, 4L, 3L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), modp = structure(c(4L,
> 4L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> 3L, 5L, 5L, 5L, 5L, 4L, 4L, 3L, 3L, 4L, 3L, 4L, 4L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), tool = structure(c(3L,
> 3L, 3L, 3L, 3L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> 3L, 5L, 5L, 5L, 5L, 3L, 3L, 3L, 3L, 4L, 3L, 3L, 1L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), sced = structure(c(2L,
> 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> 3L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 3L), levels =
c("vl",
> "l", "n", "h", "vh",
"xh"), class = "factor"), equivphyskloc = c(0.025534,
> 0.006945, 0.008988, 0.002655, 0.067102, 0.006741, 0.019508, 0.005209,
> 0.101215, 0.010622, 0.101215, 0.019508, 0.152283, 0.031253, 0.014401,
> 0.014401, 0.037892, 0.009294, 0.015729, 0.012154, 0.032377, 0.035339,
> 0.004698, 0.009703, 0.00572, 0.012358, 0.091002, 0.007252, 0.180778,
> 0.307527), act_effort = c(117.6, 31.2, 25.2, 10.8, 352.8, 72,
> 72, 24, 360, 36, 215, 48, 324, 60, 48, 90, 210, 48, 82, 62, 170,
> 192, 18, 50, 42, 60, 444, 42, 1248, 2400)), row.names = c(1L,
> 3L, 5L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 17L, 18L, 19L,
> 24L, 25L, 26L, 29L, 30L, 31L, 32L, 33L, 34L, 36L, 37L, 38L, 39L,
> 41L, 42L), class = "data.frame")
>
>
>
> On Thu, Jun 30, 2022 at 11:28 PM Rui Barradas <ruipbarradas at sapo.pt
> <mailto:ruipbarradas at sapo.pt>> wrote:
>
> Hello,
>
> Please post data in dput format, without it it's difficult to tell.
> If I substitute
>
> mpg for act_effort
> mtcars for tr
>
> keeping everything else, I don't get any errors.
> And the error message says clearly that the error is in tr (data).
>
> Can you post the output of dput(head(tr, 30))?
>
> Rui Barradas
>
>
> ?s 19:32 de 30/06/2022, Neha gupta escreveu:
> > I posted it for the second time as I didn't get any response
from
> group
> > members. I am not sure if some problem is with the question.
> >
> >
> >
> > I cannot run the "ranger" model with caret. I am only
using the
> farff and
> > caret libraries and the following code:
> >
> > boot <- trainControl(method = "cv", number=10)
> >
> > c1 <-train(act_effort ~ ., data = tr,
> >? ? ? ? ? ? ? ? method = "ranger",
> >? ? ? ? ? ? ? ? ?tuneLength = 5,
> >? ? ? ? ? ? ? ? metric = "MAE",
> >? ? ? ? ? ? ? ? preProc = c("center", "scale",
"nzv"),
> >? ? ? ? ? ? ? ? trControl = boot)
> >
> > The error I get is the repeating of the following message until I
> interrupt
> > it.
> >
> > Error: mtry can not be larger than number of variables in data.
> Ranger will
> > EXIT now.
> >
> >? ? ? ?[[alternative HTML version deleted]]
> >
> > ______________________________________________
> > R-help at r-project.org <mailto:R-help at r-project.org>
mailing list
> -- To UNSUBSCRIBE and more, see
> > https://stat.ethz.ch/mailman/listinfo/r-help
> <https://stat.ethz.ch/mailman/listinfo/r-help>
> > PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> <http://www.R-project.org/posting-guide.html>
> > and provide commented, minimal, self-contained, reproducible
code.
>