X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FselectVariables.R;h=65fbde546b2c298cd4fccca285a91a8655534cfe;hb=fb6e49cb85308c3f99cc98fe955aa7c36839c819;hp=46fb3f33165106d2d4f3a91943b81ac7709b7b74;hpb=f33f35efc9a01f93bb61959522d90ee6a76b892e;p=valse.git

diff --git a/pkg/R/selectVariables.R b/pkg/R/selectVariables.R
index 46fb3f3..65fbde5 100644
--- a/pkg/R/selectVariables.R
+++ b/pkg/R/selectVariables.R
@@ -1,4 +1,5 @@
 #' selectVariables
+#'
 #' It is a function which construct, for a given lambda, the sets of relevant variables.
 #'
 #' @param phiInit an initial estimator for phi (size: p*m*k)
@@ -13,36 +14,62 @@
 #' @param Y			 matrix of responses
 #' @param thres	 threshold to consider a coefficient to be equal to 0
 #' @param tau		 threshold to say that EM algorithm has converged
+#' @param ncores Number or cores for parallel execution (1 to disable)
 #'
 #' @return a list of outputs, for each lambda in grid: selected,Rho,Pi
 #'
 #' @examples TODO
 #'
 #' @export
-selectVariables = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda,X,Y,seuil,tau)
+#'
+selectVariables = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda,
+                           X,Y,thresh,tau, ncores=3, fast=TRUE)
 {
-	#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)
-	{
-		p = dim(phiInit)[1]
-		m = dim(phiInit)[2]
-
-		params = EMGLLF(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda[lambdaIndex],X,Y,tau)
-
-		#selectedVariables: list where element j contains vector of selected variables in [1,m]
-		selectedVariables = lapply(1:p, function(j) {
-			#from boolean matrix mxk of selected variables obtain the corresponding boolean m-vector,
-			#and finally return the corresponding indices
-			seq_len(m)[ apply( abs(params$phi[j,,]) > seuil, 1, any ) ]
-		})
-
-		list("selected"=selectedVariables,"Rho"=params$Rho,"Pi"=params$Pi)
-	})
-	parallel::stopCluster(cl)
-	out
+  if (ncores > 1)
+  {
+    cl = parallel::makeCluster(ncores, outfile='')
+    parallel::clusterExport(cl=cl,
+                            varlist=c("phiInit","rhoInit","gamInit","mini","maxi","glambda","X","Y","thresh","tau"),
+                            envir=environment())
+  }
+  
+  # Computation for a fixed lambda
+  computeCoefs <- function(lambda)
+  {
+    params = EMGLLF(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,tau,fast)
+    
+    p = dim(phiInit)[1]
+    m = dim(phiInit)[2]
+    
+    #selectedVariables: list where element j contains vector of selected variables in [1,m]
+    selectedVariables = lapply(1:p, function(j) {
+      #from boolean matrix mxk of selected variables obtain the corresponding boolean m-vector,
+      #and finally return the corresponding indices
+      seq_len(m)[ apply( abs(params$phi[j,,]) > thresh, 1, any ) ]
+    })
+    
+    list("selected"=selectedVariables,"Rho"=params$rho,"Pi"=params$pi)
+  }
+  
+  # For each lambda in the grid, we compute the coefficients
+  out <-
+    if (ncores > 1)
+      parLapply(cl, glambda, computeCoefs)
+  else
+    lapply(glambda, computeCoefs)
+  if (ncores > 1)
+    parallel::stopCluster(cl)
+  # Suppress models which are computed twice
+  #En fait, ca ca fait la comparaison de tous les parametres
+  #On veut juste supprimer ceux qui ont les memes variables sélectionnées
+  #sha1_array <- lapply(out, digest::sha1)
+  #out[ duplicated(sha1_array) ]
+  selec = lapply(out, function(model) model$selected)
+  ind_dup = duplicated(selec)
+  ind_uniq = which(!ind_dup)
+  out2 = list()
+  for (l in 1:length(ind_uniq)){
+    out2[[l]] = out[[ind_uniq[l]]]
+  }
+  out2
 }