remove selectiontotale, parallelize main.R + add conditional verbose traces

[valse.git] / pkg / R / selectVariables.R

diff --git a/pkg/R/selectVariables.R b/pkg/R/selectVariables.R
index 46fb3f3..869e7bf 100644 (file)
--- 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 +14,55 @@
 #' @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)
 {
-       #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=cl,
+                       varlist=c("phiInit","rhoInit","gamInit","mini","maxi","glambda","X","Y","thresh","tau"),
+                       envir=environment())
+       }
+
+       # Calcul pour un lambda
+       computeCoefs <-function(lambda)
+       {
+               params = EMGLLF(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,tau)
+
                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$phi[j,,]) > seuil, 1, any ) ]
+                 seq_len(m)[ apply( abs(params$phi[j,,]) > thresh, 1, any ) ]
                })
 
-               list("selected"=selectedVariables,"Rho"=params$Rho,"Pi"=params$Pi)
-       })
-       parallel::stopCluster(cl)
+               list("selected"=selectedVariables,"Rho"=params$rho,"Pi"=params$pi)
+       }
+
+       # Pour chaque lambda de la grille, on calcule les coefficients
+       out <-
+               if (ncores > 1)
+                       parLapply(cl, glambda, computeCoefs)
+               else
+                       lapply(glambda, computeCoefs)
+       if (ncores > 1)
+               parallel::stopCluster(cl)
+
+       # Suppression doublons
+       sha1_array <- lapply(out, digest::sha1)
+       out[ !duplicated(sha1_array) ]
+
        out
 }