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 ce7d3b3..869e7bf 100644 (file)
--- a/pkg/R/selectVariables.R
+++ b/pkg/R/selectVariables.R
@@ -14,6 +14,7 @@
 #' @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
 #'
@@ -22,7 +23,7 @@
 #' @export
 #'
 selectVariables = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda,
-       X,Y,thresh,tau, ncores=1) #ncores==1 ==> no //
+       X,Y,thresh,tau, ncores=3)
 {
        if (ncores > 1)
        {
@@ -44,19 +45,24 @@ selectVariables = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambd
                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$phi[j,,]) > thresh, 1, any ) ]
+                 seq_len(m)[ apply( abs(params$phi[j,,]) > thresh, 1, any ) ]
                })
 
-               list("selected"=selectedVariables,"Rho"=params$Rho,"Pi"=params$Pi)
+               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, seq_along(glambda, computeCoefs)
+                       parLapply(cl, glambda, computeCoefs)
                else
-                       lapply(seq_along(glambda), computeCoefs)
+                       lapply(glambda, computeCoefs)
        if (ncores > 1)
                parallel::stopCluster(cl)
+
+       # Suppression doublons
+       sha1_array <- lapply(out, digest::sha1)
+       out[ !duplicated(sha1_array) ]
+
        out
 }