From: Benjamin Auder <benjamin.auder@somewhere>
Date: Mon, 3 Apr 2017 11:07:37 +0000 (+0200)
Subject: work on constructionModeles + main (2 levels or //isation)
X-Git-Url: https://git.auder.net/%7B%7B%20asset%28%27mixstore/images/pieces/assets/doc/mini-custom.min.css?a=commitdiff_plain;h=2279a641f2bee1db586e7ab1e13726d111d5daaf;p=valse.git

work on constructionModeles + main (2 levels or //isation)
---

diff --git a/pkg/R/constructionModelesLassoMLE.R b/pkg/R/constructionModelesLassoMLE.R
index d2bb9a5..6c37751 100644
--- a/pkg/R/constructionModelesLassoMLE.R
+++ b/pkg/R/constructionModelesLassoMLE.R
@@ -1,90 +1,86 @@
-constructionModelesLassoMLE = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,
-                                       X,Y,seuil,tau,selected, parallel = FALSE)
+#' constructionModelesLassoMLE
+#'
+#' TODO: description
+#'
+#' @param ...
+#'
+#' @return ...
+#'
+#' export
+constructionModelesLassoMLE = function(phiInit, rhoInit, piInit, gamInit, mini, maxi,
+	gamma, X, Y, seuil, tau, selected, ncores=3, verbose=FALSE)
 {
-  if (parallel) {
-    #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","X","Y","seuil","tau"),
-                            envir=environment())
-    #Pour chaque lambda de la grille, on calcule les coefficients
-    out = parLapply( seq_along(glambda), function(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)
-      
-      #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$phi[selected,,r])
-        densite = densite + pi[r] *
-          det(rho[,,r])/(sqrt(2*base::pi))^m * exp(-tcrossprod(delta)/2.0)
-      }
-      llh = c( sum(log(densite[,lambda])), (dimension+m+1)*k-1 )
-      list("phi"=res$phi, "rho"=res$rho, "pi"=res$pi, "llh" = llh)
-    })
-    parallel::stopCluster(cl)
-    out
-  }
-  else {
-    #Pour chaque lambda de la grille, on calcule les coefficients
-    n = dim(X)[1]
-    p = dim(phiInit)[1]
-    m = dim(phiInit)[2]
-    k = dim(phiInit)[3]
-    L = length(selected)
-    phi = list()
+  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") )
+	}
+
+	# Individual model computation
+	computeAtLambda <- function(lambda)
+	{
+		if (ncores > 1)
+			require("valse") #// nodes start with an ampty 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 = selected[[lambda]]
+#		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)
+		
+		# Eval dimension from the result + selected
+		phiLambda2 = res_EM$phi
+		rhoLambda = res_EM$rho
+		piLambda = res_EM$pi
     phiLambda = array(0, dim = c(p,m,k))
-    rho = list()
-    pi = list()
-    llh = list()
-    
-    out = lapply( seq_along(selected), function(lambda)
-    {
-      print(lambda)
-      sel.lambda = selected[[lambda]]
-      col.sel = which(colSums(sel.lambda)!=0)
-      if (length(col.sel)>0){
-        res_EM = EMGLLF(phiInit[col.sel,,],rhoInit,piInit,gamInit,mini,maxi,gamma,0.,X[,col.sel],Y,tau)
-        phiLambda2 = res_EM$phi
-        rhoLambda = res_EM$rho
-        piLambda = res_EM$pi
-        for (j in 1:length(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)
-        }
-        
-        #on veut calculer la vraisemblance avec toutes nos estimations
-        densite = vector("double",n)
-        for (r in 1:k)
-        {
-          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)
-        }
-        llhLambda = c( sum(log(densite)), (dimension+m+1)*k-1 )
-        list("phi"= phiLambda, "rho"= rhoLambda, "pi"= piLambda, "llh" = llhLambda)
-      }
-    }
-    )
-    return(out)
-  }
+		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)
+		}
+
+		# on veut calculer la vraisemblance avec toutes nos estimations
+		densite = vector("double",n)
+		for (r in 1:k)
+		{
+			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)
+		}
+		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 =
+		if (ncores > 1)
+			parLapply(cl, seq_along(glambda), computeAtLambda)
+		else
+			lapply(seq_along(glambda), computeAtLambda)
+
+	if (ncores > 1)
+    parallel::stopCluster(cl)
+
+	out
 }
diff --git a/pkg/R/constructionModelesLassoRank.R b/pkg/R/constructionModelesLassoRank.R
index 9254473..c219d75 100644
--- a/pkg/R/constructionModelesLassoRank.R
+++ b/pkg/R/constructionModelesLassoRank.R
@@ -1,4 +1,14 @@
-constructionModelesLassoRank = function(pi,rho,mini,maxi,X,Y,tau,A1,rangmin,rangmax)
+#' constructionModelesLassoRank
+#'
+#' TODO: description
+#'
+#' @param ...
+#'
+#' @return ...
+#'
+#' export
+constructionModelesLassoRank = function(pi, rho, mini, maxi, X, Y, tau, A1, rangmin,
+	rangmax, ncores, verbose=FALSE)
 {
   #get matrix sizes
   n = dim(X)[1]
@@ -27,7 +37,9 @@ constructionModelesLassoRank = function(pi,rho,mini,maxi,X,Y,tau,A1,rangmin,rang
 	# output parameters
   phi = array(0, dim=c(p,m,k,L*Size))
   llh = matrix(0, L*Size, 2) #log-likelihood
-  for(lambdaIndex in 1:L)
+
+	# TODO: // loop
+	for(lambdaIndex in 1:L)
 	{
     # on ne garde que les colonnes actives
     # 'active' sera l'ensemble des variables informatives
diff --git a/pkg/R/main.R b/pkg/R/main.R
index 7b78a15..8ce5117 100644
--- a/pkg/R/main.R
+++ b/pkg/R/main.R
@@ -20,9 +20,9 @@
 #' @examples
 #' #TODO: a few examples
 #' @export
-valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 10,
-                 maxi = 50,eps = 1e-4,kmin = 2,kmax = 2,
-                 rang.min = 1,rang.max = 10, ncores_k=1, ncores_lambda=3, verbose=FALSE)
+valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, maxi=50,
+	eps=1e-4, kmin=2, kmax=2, rang.min=1, rang.max=10, ncores_outer=1, ncores_inner=3,
+	verbose=FALSE)
 {
   p = dim(X)[2]
   m = dim(Y)[2]
@@ -32,18 +32,18 @@ valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 1
   if (verbose)
 		print("main loop: over all k and all lambda")
 
-	if (ncores_k > 1)
+	if (ncores_outer > 1)
 	{
-		cl = parallel::makeCluster(ncores_k)
+		cl = parallel::makeCluster(ncores_outer)
 		parallel::clusterExport( cl=cl, envir=environment(), varlist=c("X","Y","procedure",
 			"selecMod","gamma","mini","maxi","eps","kmin","kmax","rang.min","rang.max",
-			"ncores_k","ncores_lambda","verbose","p","m","k","tableauRecap") )
+			"ncores_outer","ncores_inner","verbose","p","m","k","tableauRecap") )
 	}
 
 	# Compute model with k components
 	computeModel <- function(k)
 	{
-		if (ncores_k > 1)
+		if (ncores_outer > 1)
 			require("valse") #nodes start with an empty environment
 
 		if (verbose)
@@ -65,7 +65,7 @@ valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 1
     #from the grid: A1 corresponding to selected variables, and
     #A2 corresponding to unselected variables.
     S = selectVariables(P$phiInit,P$rhoInit,P$piInit,P$gamInit,mini,maxi,gamma,
-			grid_lambda,X,Y,1e-8,eps,ncores_lambda)
+			grid_lambda,X,Y,1e-8,eps,ncores_inner)
 
     if (procedure == 'LassoMLE')
 		{
@@ -74,12 +74,7 @@ valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 1
       #compute parameter estimations, with the Maximum Likelihood
       #Estimator, restricted on selected variables.
       model = constructionModelesLassoMLE(phiInit, rhoInit, piInit, gamInit, mini,
-				maxi, gamma, X, Y, thresh, eps, S$selected)
-      llh = matrix(ncol = 2)
-      for (l in seq_along(model[[k]]))
-        llh = rbind(llh, model[[k]][[l]]$llh)
-      LLH = llh[-1,1]
-      D = llh[-1,2]
+				maxi, gamma, X, Y, thresh, eps, S$selected, ncores_inner, verbose)
     }
 		else
 		{
@@ -88,25 +83,25 @@ valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 1
       #compute parameter estimations, with the Low Rank
       #Estimator, restricted on selected variables.
       model = constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
-				rank.min, rank.max)
+				rank.min, rank.max, ncores_inner, verbose)
 
       ################################################
       ### Regarder la SUITE  
-      phi = runProcedure2()$phi
-      Phi2 = Phi
-      if (dim(Phi2)[1] == 0)
-        Phi[, , 1:k,] <- phi
-      else
-      {
-        Phi <- array(0, dim = c(p, m, kmax, dim(Phi2)[4] + dim(phi)[4]))
-        Phi[, , 1:(dim(Phi2)[3]), 1:(dim(Phi2)[4])] <<- Phi2
-        Phi[, , 1:k,-(1:(dim(Phi2)[4]))] <<- phi
-      }
+#      phi = runProcedure2()$phi
+#      Phi2 = Phi
+#      if (dim(Phi2)[1] == 0)
+#        Phi[, , 1:k,] <- phi
+#      else
+#      {
+#        Phi <- array(0, dim = c(p, m, kmax, dim(Phi2)[4] + dim(phi)[4]))
+#        Phi[, , 1:(dim(Phi2)[3]), 1:(dim(Phi2)[4])] <<- Phi2
+#        Phi[, , 1:k,-(1:(dim(Phi2)[4]))] <<- phi
+#      }
     }
-    tableauRecap[[k]] = matrix(c(LLH, D, rep(k, length(model[[k]])), 1:length(model[[k]])), ncol = 4))
+    model
   }
 
-	model <-
+	model_list <-
 		if (ncores_k > 1)
 			parLapply(cl, kmin:kmax, computeModel)
 		else
@@ -114,9 +109,19 @@ valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 1
 	if (ncores_k > 1)
 		parallel::stopCluster(cl)
 
+	# Get summary "tableauRecap" from models
+	tableauRecap = t( sapply( seq_along(model_list), function(model) {
+		llh = matrix(ncol = 2)
+    for (l in seq_along(model))
+      llh = rbind(llh, model[[l]]$llh)
+    LLH = llh[-1,1]
+    D = llh[-1,2]
+		c(LLH, D, rep(k, length(model)), 1:length(model))
+	} ) )
+
 	if (verbose)
 		print('Model selection')
-	tableauRecap = do.call( rbind, tableaurecap ) #stack list cells into a matrix
+	tableauRecap = do.call( rbind, tableauRecap ) #stack list cells into a matrix
   tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
   tableauRecap = tableauRecap[(tableauRecap[,1])!=Inf,]
   data = cbind(1:dim(tableauRecap)[1], tableauRecap[,2], tableauRecap[,2], tableauRecap[,1])