5 Sélection de variables

5.4 Le package VSURF

library(VSURF)
data("toys")

set.seed(3101318)
vsurfToys <- VSURF(toys$x, toys$y, mtry = 100)

summary(vsurfToys)

plot(vsurfToys)

set.seed(3101318)
vsurfThresToys <- VSURF_thres(toys$x, toys$y, mtry = 100)

vsurfThresToys$varselect.thres

plot(vsurfToys, step = "thres", imp.mean = FALSE, ylim = c(0, 2e-04))

vsurfInterpToys <- VSURF_interp(toys$x, toys$y, vars = vsurfThresToys$varselect.thres)

vsurfInterpToys$varselect.interp

vsurfPredToys <- VSURF_pred(toys$x, toys$y, err.interp = vsurfInterpToys$err.interp,
    varselect.interp = vsurfInterpToys$varselect.interp)

vsurfPredToys$varselect.pred

set.seed(923321, kind = "L'Ecuyer-CMRG")
vsurfSpam <- VSURF(type ~ ., spamApp, parallel = TRUE, ncores = 3, clusterType = "FORK")

summary(vsurfSpam)
plot(vsurfSpam)
colnames(spamApp[vsurfSpam$varselect.interp])
colnames(spamApp[vsurfSpam$varselect.pred])

vsurfSpam$mean.jump

set.seed(945834)
vsurfSpamPred <- VSURF_pred(type ~ ., spamApp, nmj = 15, err.interp = vsurfSpam$err.interp,
    varselect.interp = vsurfSpam$varselect.interp)

colnames(spamApp[vsurfSpamPred$varselect.pred])

5.5 Réglage des paramètres pour la sélection

vsurfToysStump <- VSURF(toys$x, toys$y, mtry = 100, maxnodes = 2)
summary(vsurfToysStump)
vsurfToysStump$varselect.interp
vsurfToysStump$varselect.pred

vsurfThresToysTuned <- tune(vsurfThresToys, nmin = 3)
vsurfThresToysTuned$varselect.thres

vsurfInterpToysTuned <- tune(vsurfInterpToys, nsd = 5)
vsurfInterpToysTuned$varselect.interp

vsurfPredToysTuned <- VSURF_pred(toys$x, toys$y, err.interp = vsurfInterpToys$err.interp,
    varselect.interp = vsurfInterpToys$varselect.interp, nmj = 3)
vsurfPredToysTuned$varselect.pred

5.6 Exemples

5.6.1 Prédire la concentration d’ozone

library(VSURF)
data("Ozone", package = "mlbench")

set.seed(303601)
OzVSURF <- VSURF(V4 ~ ., data = Ozone, na.action = na.omit)

summary(OzVSURF)
plot(OzVSURF, var.names = TRUE)

number <- c(1:3, 5:13)
number[OzVSURF$varselect.thres]

number[OzVSURF$varselect.interp]

number[OzVSURF$varselect.pred]

5.6.2 Analyser des données génomiques

library(VSURF)
data("vac18", package = "mixOmics")
geneExpr <- vac18$genes
stimu <- vac18$stimulation

set.seed(481933)
vacVSURF <- VSURF(x = geneExpr, y = stimu)

summary(vacVSURF)
plot(vacVSURF)

probeSelPred <- colnames(geneExpr)[vacVSURF$varselect.pred]
probeSelPred

set.seed(627408, kind = "L'Ecuyer-CMRG")
vacVSURFpara <- VSURF(x = geneExpr, y = stimu, parallel = TRUE, ncores = 3, clusterType = "FORK")

summary(vacVSURFpara)