X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2FconstructionModelesLassoMLE.R;h=ba6f125cb16d94c6de8bdc65dd855578398b12c5;hp=6c37751b465d6a6d635f0029a8a5b9f94b201966;hb=43d76c49d2f98490abc782c7e8a8b94baee40247;hpb=2279a641f2bee1db586e7ab1e13726d111d5daaf

diff --git a/pkg/R/constructionModelesLassoMLE.R b/pkg/R/constructionModelesLassoMLE.R
index 6c37751..ba6f125 100644
--- a/pkg/R/constructionModelesLassoMLE.R
+++ b/pkg/R/constructionModelesLassoMLE.R
@@ -1,86 +1,91 @@
 #' constructionModelesLassoMLE
 #'
-#' TODO: description
+#' Construct a collection of models with the Lasso-MLE procedure.
+#' 
+#' @param phiInit an initialization for phi, get by initSmallEM.R
+#' @param rhoInit an initialization for rho, get by initSmallEM.R
+#' @param piInit an initialization for pi, get by initSmallEM.R
+#' @param gamInit an initialization for gam, get by initSmallEM.R
+#' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
+#' @param maxi integer, maximum number of iterations in the EM algorithm, by default = 100
+#' @param gamma integer for the power in the penaly, by default = 1
+#' @param X matrix of covariates (of size n*p)
+#' @param Y matrix of responses (of size n*m)
+#' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
+#' @param S output of selectVariables.R
+#' @param ncores Number of cores, by default = 3
+#' @param fast TRUE to use compiled C code, FALSE for R code only
+#' @param verbose TRUE to show some execution traces
+#' 
+#' @return a list with several models, defined by phi, rho, pi, llh
 #'
-#' @param ...
-#'
-#' @return ...
-#'
-#' export
-constructionModelesLassoMLE = function(phiInit, rhoInit, piInit, gamInit, mini, maxi,
-	gamma, X, Y, seuil, tau, selected, ncores=3, verbose=FALSE)
+#' @export
+constructionModelesLassoMLE = function( phiInit, rhoInit, piInit, gamInit, mini, maxi,gamma, X, Y,
+	 eps, S, ncores=3, fast=TRUE, verbose=FALSE)
 {
-  if (ncores > 1)
+	if (ncores > 1)
 	{
-    cl = parallel::makeCluster(ncores)
-    parallel::clusterExport( cl, envir=environment(),
-			varlist=c("phiInit","rhoInit","gamInit","mini","maxi","gamma","X","Y","seuil",
-			"tau","selected","ncores","verbose") )
+		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 ampty environment
+			require("valse") #nodes start with an empty environment
 
-    if (verbose)
+		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 = selected[[lambda]]
+		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,tau)
+			X[,col.sel], Y, eps, fast)
 		
 		# Eval dimension from the result + selected
-		phiLambda2 = res_EM$phi
-		rhoLambda = res_EM$rho
-		piLambda = res_EM$pi
-    phiLambda = array(0, dim = c(p,m,k))
+		phiLambda2 = res$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 = 0
-		for (j in 1:p)
-		{
-			b = setdiff(1:m, sel.lambda[,j])
-			if (length(b) > 0)
-				phiLambda[j,b,] = 0.0
-			dimension = dimension + sum(sel.lambda[,j]!=0)
-		}
+			phiLambda[col.sel[j],sel.lambda[[j]],] = phiLambda2[j,sel.lambda[[j]],]
+		dimension = length(unlist(sel.lambda))
 
-		# on veut calculer la vraisemblance avec toutes nos estimations
+		# Computation of the loglikelihood
 		densite = vector("double",n)
 		for (r in 1:k)
 		{
-			delta = Y%*%rhoLambda[,,r] - (X[, col.sel]%*%phiLambda[col.sel,,r])
+		  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(-tcrossprod(delta)/2.0)
+				det(rhoLambda[,,r])/(sqrt(2*base::pi))^m * exp(-diag(tcrossprod(delta))/2.0)
 		}
 		llhLambda = c( sum(log(densite)), (dimension+m+1)*k-1 )
 		list("phi"= phiLambda, "rho"= rhoLambda, "pi"= piLambda, "llh" = llhLambda)
 	}
 
-	#Pour chaque lambda de la grille, on calcule les coefficients
-  out =
+	# For each lambda, computation of the parameters
+	out =
 		if (ncores > 1)
-			parLapply(cl, seq_along(glambda), computeAtLambda)
+			parLapply(cl, 1:length(S), computeAtLambda)
 		else
-			lapply(seq_along(glambda), computeAtLambda)
+			lapply(1:length(S), computeAtLambda)
 
 	if (ncores > 1)
-    parallel::stopCluster(cl)
+		parallel::stopCluster(cl)
 
 	out
 }