X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2FconstructionModelesLassoMLE.R;h=e8013a2dbc76cc11cb401f2259a5fa924309865c;hp=50879c935aea7e04042024e2f51a071cb554fa7f;hb=08f4604c778da8af7e26b52b1d433a6be82c3139;hpb=f33f35efc9a01f93bb61959522d90ee6a76b892e

diff --git a/pkg/R/constructionModelesLassoMLE.R b/pkg/R/constructionModelesLassoMLE.R
index 50879c9..e8013a2 100644
--- a/pkg/R/constructionModelesLassoMLE.R
+++ b/pkg/R/constructionModelesLassoMLE.R
@@ -1,37 +1,79 @@
-constructionModelesLassoMLE = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda,
-	X,Y,seuil,tau,selected)
+#' constructionModelesLassoMLE
+#'
+#' TODO: description
+#'
+#' @param ...
+#'
+#' @return ...
+#'
+#' export
+constructionModelesLassoMLE = function(phiInit, rhoInit, piInit, gamInit, mini, maxi,
+	gamma, X, Y, thresh, tau, S, ncores=3, artefact = 1e3, verbose=FALSE)
 {
-	#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)
+	if (ncores > 1)
 	{
+		cl = parallel::makeCluster(ncores)
+		parallel::clusterExport( cl, envir=environment(),
+			varlist=c("phiInit","rhoInit","gamInit","mini","maxi","gamma","X","Y","thresh",
+			"tau","S","ncores","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]
 
-		#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)
+		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
 
-		#comment évaluer la dimension à partir du résultat et de [not]selected ?
-    #dimension = ...
+		if (length(col.sel) == 0)
+			return (NULL)
 
-    #on veut calculer la vraisemblance avec toutes nos estimations
+		# 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,tau)
+		
+		# Eval dimension from the result + selected
+		phiLambda2 = res$phi
+		rhoLambda = res$rho
+		piLambda = res$pi
+		phiLambda = array(0, dim = c(p,m,k))
+		for (j in seq_along(col.sel))
+			phiLambda[col.sel[j],,] = phiLambda2[j,,]
+		dimension = length(unlist(sel.lambda))
+
+		# Computation of the loglikelihood
 		densite = vector("double",n)
 		for (r in 1:k)
 		{
-			delta = Y%*%rho[,,r] - (X[selected]%*%res$phi[selected,,r])
-			densite = densite + pi[r] *
-				det(rho[,,r])/(sqrt(2*base::pi))^m * exp(-tcrossprod(delta)/2.0)
+			delta = (Y%*%rhoLambda[,,r] - (X[, col.sel]%*%phiLambda[col.sel,,r]))/artefact
+			print(max(delta))
+			densite = densite + piLambda[r] *
+				det(rhoLambda[,,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)
+		llhLambda = c( sum(artefact^2 * 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
 }