#'
#' @export
constructionModelesLassoMLE <- function(phiInit, rhoInit, piInit, gamInit, mini,
- maxi, gamma, X, Y, eps, S, ncores = 3, fast = TRUE, verbose = FALSE)
- {
+ maxi, gamma, X, Y, eps, S, ncores = 3, fast, verbose)
+{
if (ncores > 1)
{
cl <- parallel::makeCluster(ncores, outfile = "")
"rhoInit", "gamInit", "mini", "maxi", "gamma", "X", "Y", "eps", "S",
"ncores", "fast", "verbose"))
}
-
+
# Individual model computation
computeAtLambda <- function(lambda)
{
if (ncores > 1)
require("valse") #nodes start with an empty environment
-
+
if (verbose)
print(paste("Computations for lambda=", lambda))
-
- n <- dim(X)[1]
- p <- dim(phiInit)[1]
- m <- dim(phiInit)[2]
- k <- dim(phiInit)[3]
+
+ n <- nrow(X)
+ p <- ncol(X)
+ m <- ncol(Y)
+ k <- length(piInit)
sel.lambda <- S[[lambda]]$selected
# col.sel = which(colSums(sel.lambda)!=0) #if boolean matrix
col.sel <- which(sapply(sel.lambda, length) > 0) #if list of selected vars
if (length(col.sel) == 0)
return(NULL)
-
+
# lambda == 0 because we compute the EMV: no penalization here
- res <- EMGLLF(phiInit[col.sel, , ], rhoInit, piInit, gamInit, mini, maxi,
- gamma, 0, X[, col.sel], Y, eps, fast)
-
+ res <- EMGLLF(array(phiInit,dim=c(p,m,k))[col.sel, , ], rhoInit, piInit, gamInit,
+ mini, maxi, gamma, 0, as.matrix(X[, col.sel]), Y, eps, fast)
+
# Eval dimension from the result + selected
phiLambda2 <- res$phi
rhoLambda <- res$rho
piLambda <- res$pi
phiLambda <- array(0, dim = c(p, m, k))
- for (j in seq_along(col.sel)) phiLambda[col.sel[j], sel.lambda[[j]], ] <- phiLambda2[j,
- sel.lambda[[j]], ]
+ for (j in seq_along(col.sel))
+ phiLambda[col.sel[j], sel.lambda[[j]], ] <- phiLambda2[j, sel.lambda[[j]], ]
dimension <- length(unlist(sel.lambda))
-
- # Computation of the loglikelihood
- densite <- vector("double", n)
- for (r in 1:k)
+
+ ## Computation of the loglikelihood
+ # Precompute det(rhoLambda[,,r]) for r in 1...k
+ detRho <- sapply(1:k, function(r) gdet(rhoLambda[, , r]))
+ sumLogLLH <- 0
+ for (i in 1:n)
{
- if (length(col.sel) == 1)
- {
- delta <- (Y %*% rhoLambda[, , r] - (X[, col.sel] %*% t(phiLambda[col.sel,
- , r])))
- } else delta <- (Y %*% rhoLambda[, , r] - (X[, col.sel] %*% phiLambda[col.sel,
- , r]))
- densite <- densite + piLambda[r] * det(rhoLambda[, , r])/(sqrt(2 * base::pi))^m *
- exp(-diag(tcrossprod(delta))/2)
+ # Update gam[,]; use log to avoid numerical problems
+ logGam <- sapply(1:k, function(r) {
+ log(piLambda[r]) + log(detRho[r]) - 0.5 *
+ sum((Y[i, ] %*% rhoLambda[, , r] - X[i, ] %*% phiLambda[, , r])^2)
+ })
+
+ logGam <- logGam - max(logGam) #adjust without changing proportions
+ gam <- exp(logGam)
+ norm_fact <- sum(gam)
+ sumLogLLH <- sumLogLLH + log(norm_fact) - log((2 * base::pi)^(m/2))
}
- llhLambda <- c(sum(log(densite)), (dimension + m + 1) * k - 1)
+ llhLambda <- c(sumLogLLH/n, (dimension + m + 1) * k - 1)
list(phi = phiLambda, rho = rhoLambda, pi = piLambda, llh = llhLambda)
}
-
+
# For each lambda, computation of the parameters
- out <- if (ncores > 1)
- parLapply(cl, 1:length(S), computeAtLambda) else lapply(1:length(S), computeAtLambda)
-
+ out <-
+ if (ncores > 1) {
+ parLapply(cl, 1:length(S), computeAtLambda)
+ } else {
+ lapply(1:length(S), computeAtLambda)
+ }
+
if (ncores > 1)
parallel::stopCluster(cl)
-
+
out
}