# \donttest{
# Data simulation
set.seed(1)
simul <- SimulateRegression(
n = 1000, pk = 20,
family = "binomial", ev_xy = 0.8
)
# Data split: selection, training and test set
ids <- Split(
data = simul$ydata,
family = "binomial",
tau = c(0.4, 0.3, 0.3)
)
xselect <- simul$xdata[ids[[1]], ]
yselect <- simul$ydata[ids[[1]], ]
xtrain <- simul$xdata[ids[[2]], ]
ytrain <- simul$ydata[ids[[2]], ]
xtest <- simul$xdata[ids[[3]], ]
ytest <- simul$ydata[ids[[3]], ]
# Stability selection
stab <- VariableSelection(
xdata = xselect,
ydata = yselect,
family = "binomial"
)
# Performances in test set of model refitted in training set
incr <- Incremental(
xdata = xtrain, ydata = ytrain,
new_xdata = xtest, new_ydata = ytest,
stability = stab, n_predictors = 10
)
plot(incr)
# Alternative with multiple training/test splits
incr <- Incremental(
xdata = rbind(xtrain, xtest),
ydata = c(ytrain, ytest),
stability = stab, K = 10, n_predictors = 10
)
plot(incr)
# }
Run the code above in your browser using DataLab