From 4cc632c9a1e1d93e9a43a402d1361f23afc50e5e Mon Sep 17 00:00:00 2001
From: Benjamin Auder <benjamin.auder@somewhere>
Date: Mon, 3 Apr 2017 12:00:08 +0200
Subject: [PATCH] remove selectiontotale, parallelize main.R + add conditional
 verbose traces

---
 pkg/R/main.R            | 94 ++++++++++++++++++++++++-----------------
 pkg/R/selectVariables.R |  6 ++-
 pkg/R/selectiontotale.R | 56 ------------------------
 3 files changed, 59 insertions(+), 97 deletions(-)
 delete mode 100644 pkg/R/selectiontotale.R

diff --git a/pkg/R/main.R b/pkg/R/main.R
index f080954..7b78a15 100644
--- a/pkg/R/main.R
+++ b/pkg/R/main.R
@@ -22,55 +22,59 @@
 #' @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)
+                 rang.min = 1,rang.max = 10, ncores_k=1, ncores_lambda=3, verbose=FALSE)
 {
-  ####################
-  # compute all models
-  ####################
-
   p = dim(X)[2]
   m = dim(Y)[2]
   n = dim(X)[1]
-  
-  model = list()
-  tableauRecap = array(0, dim=c(1000,4))
-  cpt = 0
-  print("main loop: over all k and all lambda")
-  
-  for (k in kmin:kmax)
+
+  tableauRecap = list()
+  if (verbose)
+		print("main loop: over all k and all lambda")
+
+	if (ncores_k > 1)
 	{
-    print(k)
-    print("Parameters initialization")
+		cl = parallel::makeCluster(ncores_k)
+		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") )
+	}
+
+	# Compute model with k components
+	computeModel <- function(k)
+	{
+		if (ncores_k > 1)
+			require("valse") #nodes start with an empty environment
+
+		if (verbose)
+			print(paste("Parameters initialization for k =",k))
     #smallEM initializes parameters by k-means and regression model in each component,
     #doing this 20 times, and keeping the values maximizing the likelihood after 10
     #iterations of the EM algorithm.
-    init = initSmallEM(k, X, Y)
-    phiInit <- init$phiInit
-    rhoInit <- init$rhoInit
-    piInit	<- init$piInit
-    gamInit <- init$gamInit
-    grid_lambda <- computeGridLambda(phiInit, rhoInit, piInit, gamInit, X, Y, gamma, mini, maxi, eps)
-    
+    P = initSmallEM(k, X, Y)
+    grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, X, Y,
+			gamma, mini, maxi, eps)
+
+		# TODO: 100 = magic number
     if (length(grid_lambda)>100)
       grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = 100)]
-    print("Compute relevant parameters")
+
+		if (verbose)
+			print("Compute relevant parameters")
     #select variables according to each regularization parameter
     #from the grid: A1 corresponding to selected variables, and
     #A2 corresponding to unselected variables.
-    
-    params = selectiontotale(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,grid_lambda,X,Y,1e-8,eps)
-    #params2 = selectVariables(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,grid_lambda[seq(1,length(grid_lambda), by=3)],X,Y,1e-8,eps)
-    ## etrange : params et params 2 sont différents ...
-    selected <- params$selected
-    Rho <- params$Rho
-    Pi <- params$Pi
-    
+    S = selectVariables(P$phiInit,P$rhoInit,P$piInit,P$gamInit,mini,maxi,gamma,
+			grid_lambda,X,Y,1e-8,eps,ncores_lambda)
+
     if (procedure == 'LassoMLE')
 		{
-      print('run the procedure Lasso-MLE')
+      if (verbose)
+				print('run the procedure Lasso-MLE')
       #compute parameter estimations, with the Maximum Likelihood
       #Estimator, restricted on selected variables.
-      model[[k]] = constructionModelesLassoMLE(phiInit, rhoInit,piInit,gamInit,mini,maxi,gamma,X,Y,thresh,eps,selected)
+      model = constructionModelesLassoMLE(phiInit, rhoInit, piInit, gamInit, mini,
+				maxi, gamma, X, Y, thresh, eps, S$selected)
       llh = matrix(ncol = 2)
       for (l in seq_along(model[[k]]))
         llh = rbind(llh, model[[k]][[l]]$llh)
@@ -79,12 +83,13 @@ valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 1
     }
 		else
 		{
-      print('run the procedure Lasso-Rank')
+      if (verbose)
+				print('run the procedure Lasso-Rank')
       #compute parameter estimations, with the Low Rank
       #Estimator, restricted on selected variables.
-      model = constructionModelesLassoRank(Pi, Rho, mini, maxi, X, Y, eps,
-                                           A1, rank.min, rank.max)
-      
+      model = constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
+				rank.min, rank.max)
+
       ################################################
       ### Regarder la SUITE  
       phi = runProcedure2()$phi
@@ -98,13 +103,24 @@ valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 1
         Phi[, , 1:k,-(1:(dim(Phi2)[4]))] <<- phi
       }
     }
-    tableauRecap[(cpt+1):(cpt+length(model[[k]])), ] = matrix(c(LLH, D, rep(k, length(model[[k]])), 1:length(model[[k]])), ncol = 4)
-    cpt = cpt+length(model[[k]])
+    tableauRecap[[k]] = matrix(c(LLH, D, rep(k, length(model[[k]])), 1:length(model[[k]])), ncol = 4))
   }
-  print('Model selection')
+
+	model <-
+		if (ncores_k > 1)
+			parLapply(cl, kmin:kmax, computeModel)
+		else
+			lapply(kmin:kmax, computeModel)
+	if (ncores_k > 1)
+		parallel::stopCluster(cl)
+
+	if (verbose)
+		print('Model selection')
+	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])
+
 	require(capushe)
   modSel = capushe(data, n)
   indModSel <-
diff --git a/pkg/R/selectVariables.R b/pkg/R/selectVariables.R
index b4fc0ab..869e7bf 100644
--- 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)
 	{
@@ -54,7 +55,8 @@ selectVariables = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambd
 	out <-
 		if (ncores > 1)
 			parLapply(cl, glambda, computeCoefs)
-		else lapply(glambda, computeCoefs)
+		else
+			lapply(glambda, computeCoefs)
 	if (ncores > 1)
 		parallel::stopCluster(cl)
 
diff --git a/pkg/R/selectiontotale.R b/pkg/R/selectiontotale.R
deleted file mode 100644
index 2cdac38..0000000
--- a/pkg/R/selectiontotale.R
+++ /dev/null
@@ -1,56 +0,0 @@
-#Return a list of outputs, for each lambda in grid: selected,Rho,Pi
-selectiontotale = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda,X,Y,thresh,tau, parallel = FALSE){
-  if (parallel) {
-    require(parallel)
-    cl = parallel::makeCluster( parallel::detectCores() / 4) # <-- ça devrait être un argument
-    parallel::clusterExport(cl=cl,
-                            varlist=c("phiInit","rhoInit","gamInit","mini","maxi","glambda","X","Y","thresh","tau"),
-                            envir=environment())
-    #Pour chaque lambda de la grille, on calcule les coefficients
-    out = parLapply(cl,  1:length(glambda), function(lambdaIndex)
-    {
-      params = 
-        EMGLLF(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda[lambdaIndex],X,Y,tau)
-      
-      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$Pi)
-    })
-    parallel::stopCluster(cl)
-  }
-  else {
-    selectedVariables = list()
-    Rho = list()
-    Pi = list()
-    cpt = 1
-    #Pour chaque lambda de la grille, on calcule les coefficients
-    for (lambdaIndex in 1:length(glambda)){
-      print(lambdaIndex)
-      params = 
-        EMGLLF(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda[lambdaIndex],X,Y,tau)
-      p = dim(phiInit)[1]
-      m = dim(phiInit)[2]
-      #selectedVariables: list where element j contains vector of selected variables in [1,m]
-      if (sum(params$phi) != 0){
-        selectedVariables[[cpt]] = sapply(1:p, function(j) {
-          #from boolean matrix mxk of selected variables obtain the corresponding boolean m-vector,
-          #and finally return the corresponding indices
-          c(seq_len(m)[ apply( abs(params$phi[j,,]) > thresh, 1, any ) ], rep(0, m-length(seq_len(m)[ apply( abs(params$phi[j,,]) > thresh, 1, any ) ] ) ))
-        })
-        if (length(unique(selectedVariables)) == length(selectedVariables)){
-          Rho[[cpt]] = params$rho
-          Pi[[cpt]] = params$pi
-          cpt = cpt+1
-        }
-      }
-    }
-    list("selected"=selectedVariables,"Rho"=Rho,"Pi"=Pi)
-  }
-}
\ No newline at end of file
-- 
2.44.0