- #TODO: parameter ncores (chaque tâche peut aussi demander du parallélisme...)
- cl = parallel::makeCluster( parallel::detectCores() / 4 )
- parallel::clusterExport(cl=cl,
- varlist=c("phiInit","rhoInit","gamInit","mini","maxi","glambda","X","Y","seuil","tau"),
- envir=environment())
- #Pour chaque lambda de la grille, on calcule les coefficients
- out = parLapply( seq_along(glambda), function(lambdaindex)
- {
- n = dim(X)[1]
- p = dim(phiInit)[1]
- m = dim(phiInit)[2]
- k = dim(phiInit)[3]
-
- #TODO: phiInit[selected] et X[selected] sont bien sûr faux; par quoi remplacer ?
- #lambda == 0 c'est normal ? -> ED : oui, ici on calcule le maximum de vraisembance, donc on ne pénalise plus
- res = EMGLLF(phiInit[selected],rhoInit,piInit,gamInit,mini,maxi,gamma,0.,X[selected],Y,tau)
-
- #comment évaluer la dimension à partir du résultat et de [not]selected ?
- #dimension = ...
-
- #on veut calculer la vraisemblance avec toutes nos estimations
- densite = vector("double",n)
- for (r in 1:k)
- {
- delta = Y%*%rho[,,r] - (X[selected]%*%res$phi[selected,,r])
- densite = densite + pi[r] *
- det(rho[,,r])/(sqrt(2*base::pi))^m * exp(-tcrossprod(delta)/2.0)
- }
- llh = c( sum(log(densite[,lambdaIndex])), (dimension+m+1)*k-1 )
- list("phi"=res$phi, "rho"=res$rho, "pi"=res$pi, "llh" = llh)
- })
- parallel::stopCluster(cl)
- out
+ if (ncores > 1)
+ {
+ cl <- parallel::makeCluster(ncores, outfile = "")
+ parallel::clusterExport(cl, envir = environment(), varlist = c("phiInit",
+ "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]
+ sel.lambda <- S[[lambda]]$selected
+ # col.sel = which(colSums(sel.lambda)!=0) #if boolean matrix
+ col.sel <- which(sapply(sel.lambda, length) > 0) #if list of selected vars
+ if (length(col.sel) == 0)
+ return(NULL)
+
+ # lambda == 0 because we compute the EMV: no penalization here
+ res <- EMGLLF(array(phiInit[col.sel, , ],dim=c(length(col.sel),m,k)), rhoInit,
+ piInit, gamInit, mini, maxi, gamma, 0, as.matrix(X[, col.sel]), Y, eps, fast)
+
+ # Eval dimension from the result + selected
+ phiLambda2 <- res$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]], ]
+ dimension <- length(unlist(sel.lambda))
+
+ # Computation of the loglikelihood
+ densite <- vector("double", n)
+ for (r in 1:k)
+ {
+ 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)
+ }
+ llhLambda <- c(sum(log(densite)), (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)
+ }
+
+ if (ncores > 1)
+ parallel::stopCluster(cl)
+
+ out