From 08f4604c778da8af7e26b52b1d433a6be82c3139 Mon Sep 17 00:00:00 2001
From: Benjamin Auder <benjamin.auder@somewhere>
Date: Wed, 5 Apr 2017 14:00:16 +0200
Subject: [PATCH] 'update'

---
 CCC.R                               |  86 +++++++++++++++++
 pkg/DESCRIPTION                     |   1 -
 pkg/R/A_NAMESPACE.R                 |   1 -
 pkg/R/constructionModelesLassoMLE.R | 144 +++++++++++++---------------
 pkg/R/filterModels.R                |  36 -------
 pkg/R/main.R                        |  36 +++----
 6 files changed, 172 insertions(+), 132 deletions(-)
 create mode 100644 CCC.R
 delete mode 100644 pkg/R/filterModels.R

diff --git a/CCC.R b/CCC.R
new file mode 100644
index 0000000..9a17c08
--- /dev/null
+++ b/CCC.R
@@ -0,0 +1,86 @@
+#' 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 (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))
+		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, glambda, computeAtLambda)
+		else
+			lapply(glambda, computeAtLambda)
+
+	if (ncores > 1)
+		parallel::stopCluster(cl)
+
+	out
+}
diff --git a/pkg/DESCRIPTION b/pkg/DESCRIPTION
index b13ee14..0a1c30e 100644
--- a/pkg/DESCRIPTION
+++ b/pkg/DESCRIPTION
@@ -31,7 +31,6 @@ Collate:
     'plot.R'
     'main.R'
     'selectVariables.R'
-    'filterModels.R'
     'constructionModelesLassoRank.R'
     'constructionModelesLassoMLE.R'
     'computeGridLambda.R'
diff --git a/pkg/R/A_NAMESPACE.R b/pkg/R/A_NAMESPACE.R
index dd06c9c..359cf88 100644
--- a/pkg/R/A_NAMESPACE.R
+++ b/pkg/R/A_NAMESPACE.R
@@ -7,7 +7,6 @@
 #' @include computeGridLambda.R
 #' @include constructionModelesLassoMLE.R
 #' @include constructionModelesLassoRank.R
-#' @include filterModels.R
 #' @include selectVariables.R
 #' @include main.R
 #' @include plot.R
diff --git a/pkg/R/constructionModelesLassoMLE.R b/pkg/R/constructionModelesLassoMLE.R
index a49529c..e8013a2 100644
--- a/pkg/R/constructionModelesLassoMLE.R
+++ b/pkg/R/constructionModelesLassoMLE.R
@@ -8,82 +8,72 @@
 #'
 #' export
 constructionModelesLassoMLE = function(phiInit, rhoInit, piInit, gamInit, mini, maxi,
-                                       gamma, X, Y, thresh, tau, S, ncores=3, artefact = 1e3, verbose=FALSE)
+	gamma, X, Y, thresh, tau, S, ncores=3, artefact = 1e3, verbose=FALSE)
 {
-  if (ncores > 1)
-  {
-    cl = parallel::makeCluster(ncores)
-    parallel::clusterExport( cl, envir=environment(),
-                             varlist=c("phiInit","rhoInit","gamInit","mini","maxi","gamma","X","Y","thresh",
-                                       "tau","S","ncores","verbose") )
-  }
-  
-  # Individual model computation
-  computeAtLambda <- function(lambda)
-  {
-    if (ncores > 1)
-      require("valse") #// nodes start with an empty 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 = S[[lambda]]$selected
-    #		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)} else {
-      
-      # lambda == 0 because we compute the EMV: no penalization here
-      res_EM = 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$pi
-      phiLambda = array(0, dim = c(p,m,k))
-      for (j in seq_along(col.sel))
-        phiLambda[col.sel[j],,] = phiLambda2[j,,]
-      
-      dimension = 0
-      for (j in 1:p)
-      {
-        b = setdiff(1:m, sel.lambda[[j]])## je confonds un peu ligne et colonne : est-ce dans le bon sens ? 
-        ## moi pour la dimension, j'aurai juste mis length(unlist(sel.lambda)) mais je sais pas si c'est rapide
-        if (length(b) > 0)
-          phiLambda[j,b,] = 0.0
-        dimension = dimension + sum(sel.lambda[[j]]!=0)
-      }
-      
-      # Computation of the loglikelihood
-      densite = vector("double",n)
-      for (r in 1:k)
-      {
-        delta = (Y%*%rhoLambda[,,r] - (X[, col.sel]%*%phiLambda[col.sel,,r]))/artefact
-        print(max(delta))
-        densite = densite + piLambda[r] *
-          det(rhoLambda[,,r])/(sqrt(2*base::pi))^m * exp(-tcrossprod(delta)/2.0)
-      }
-      llhLambda = c( sum(artefact^2 * log(densite)), (dimension+m+1)*k-1 )
-      list("phi"= phiLambda, "rho"= rhoLambda, "pi"= piLambda, "llh" = llhLambda)
-    }
-  }
-  
-  # For each lambda, computation of the parameters
-  out =
-    if (ncores > 1)
-      parLapply(cl, 1:length(S), computeAtLambda)
-  else
-    lapply(1:length(S), computeAtLambda)
-  
-  if (ncores > 1)
-    parallel::stopCluster(cl)
-  
-  out
+	if (ncores > 1)
+	{
+		cl = parallel::makeCluster(ncores)
+		parallel::clusterExport( cl, envir=environment(),
+			varlist=c("phiInit","rhoInit","gamInit","mini","maxi","gamma","X","Y","thresh",
+			"tau","S","ncores","verbose") )
+	}
+
+	# Individual model computation
+	computeAtLambda <- function(lambda)
+	{
+		if (ncores > 1)
+			require("valse") #nodes start with an empty environment
+
+		if (verbose)
+			print(paste("Computations for lambda=",lambda))
+
+		n = dim(X)[1]
+		p = dim(phiInit)[1]
+		m = dim(phiInit)[2]
+		k = dim(phiInit)[3]
+
+		sel.lambda = S[[lambda]]$selected
+#		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$phi
+		rhoLambda = res$rho
+		piLambda = res$pi
+		phiLambda = array(0, dim = c(p,m,k))
+		for (j in seq_along(col.sel))
+			phiLambda[col.sel[j],,] = phiLambda2[j,,]
+		dimension = length(unlist(sel.lambda))
+
+		# Computation of the loglikelihood
+		densite = vector("double",n)
+		for (r in 1:k)
+		{
+			delta = (Y%*%rhoLambda[,,r] - (X[, col.sel]%*%phiLambda[col.sel,,r]))/artefact
+			print(max(delta))
+			densite = densite + piLambda[r] *
+				det(rhoLambda[,,r])/(sqrt(2*base::pi))^m * exp(-tcrossprod(delta)/2.0)
+		}
+		llhLambda = c( sum(artefact^2 * log(densite)), (dimension+m+1)*k-1 )
+		list("phi"= phiLambda, "rho"= rhoLambda, "pi"= piLambda, "llh" = llhLambda)
+	}
+
+	# For each lambda, computation of the parameters
+	out =
+		if (ncores > 1)
+			parLapply(cl, 1:length(S), computeAtLambda)
+	else
+		lapply(1:length(S), computeAtLambda)
+
+	if (ncores > 1)
+		parallel::stopCluster(cl)
+
+	out
 }
diff --git a/pkg/R/filterModels.R b/pkg/R/filterModels.R
deleted file mode 100644
index 2659ed4..0000000
--- a/pkg/R/filterModels.R
+++ /dev/null
@@ -1,36 +0,0 @@
-#' Among a collection of models, this function constructs a subcollection of models with
-#' models having strictly different dimensions, keeping the model which minimizes
-#' the likelihood if there were several with the same dimension
-#'
-#' @param LLF a matrix, the first column corresponds to likelihoods for several models
-#'				the second column corresponds to the dimensions of the corresponding models.
-#'
-#' @return a list with indices, a vector of indices selected models,
-#'				 and D1, a vector of corresponding dimensions
-#'
-#' @export
-filterModels = function(LLF)
-{
-	D = LLF[,2]
-	D1 = unique(D)
-
-	indices = rep(1, length(D1))
-	#select argmax MLE
-	if (length(D1)>2)
-	{
-		for (i in 1:length(D1))
-		{
-			A = c()
-			for (j in 1:length(D))
-			{
-				if(D[[j]]==D1[[i]])
-					a = c(a, LLF[j,1])
-			}
-			b = max(a)
-			#indices[i] : first indices of the binary vector where u_i ==1
-			indices[i] = which.max(LLF == b)
-		}
-	}
-
-	return (list(indices=indices,D1=D1))
-}
diff --git a/pkg/R/main.R b/pkg/R/main.R
index 2cd345d..bff2ec5 100644
--- a/pkg/R/main.R
+++ b/pkg/R/main.R
@@ -33,10 +33,10 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10,
 
 	if (ncores_outer > 1)
 	{
-		cl = parallel::makeCluster(ncores_outer)
+		cl = parallel::makeCluster(ncores_outer, outfile='')
 		parallel::clusterExport( cl=cl, envir=environment(), varlist=c("X","Y","procedure",
 			"selecMod","gamma","mini","maxi","eps","kmin","kmax","rang.min","rang.max",
-			"ncores_outer","ncores_inner","verbose","p","m","k","tableauRecap") )
+			"ncores_outer","ncores_inner","verbose","p","m") )
 	}
 
 	# Compute models with k components
@@ -53,7 +53,6 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10,
     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)>size_coll_mod)
       grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)]
 
@@ -70,8 +69,8 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10,
 				print('run the procedure Lasso-MLE')
       #compute parameter estimations, with the Maximum Likelihood
       #Estimator, restricted on selected variables.
-      models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini,
-				maxi, gamma, X, Y, thresh, eps, S, ncores_inner, artefact = 1e3, verbose)
+      models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit,
+				mini, maxi, gamma, X, Y, thresh, eps, S, ncores_inner, artefact = 1e3, verbose)
     }
 		else
 		{
@@ -82,6 +81,8 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10,
       models <- constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
 				rank.min, rank.max, ncores_inner, verbose)
     }
+		#attention certains modeles sont NULL après selectVariables
+		models = models[sapply(models, function(cell) !is.null(cell))]
     models
   }
 
@@ -100,18 +101,19 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10,
 		return (models_list)
 	}
 
-	# Get summary "tableauRecap" from models ; TODO: jusqu'à ligne 114 à mon avis là c'est faux :/
-	tableauRecap = sapply( models_list, function(models) {
-		llh = do.call(rbind, lapply(models, function(model) model$llh))
-    LLH = llh[-1,1]
-    D = llh[-1,2]
-		c(LLH, D, rep(k, length(LLH)), 1:length(LLH))
-	}) 
-	tableauRecap
-	if (verbose)
-		print('Model selection')
-  tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
-  tableauRecap = tableauRecap[!is.infinite(tableauRecap[,1]),]
+	# Get summary "tableauRecap" from models
+	tableauRecap = do.call( rbind, lapply( models_list, function(models) {
+		#Pour un groupe de modeles (même k, différents lambda):
+		llh = matrix(ncol = 2)
+		for (l in seq_along(models))
+			llh = rbind(llh, models[[l]]$llh)
+		LLH = llh[-1,1]
+		D = llh[-1,2]
+		k = length(models[[1]]$pi)
+		cbind(LLH, D, rep(k, length(models)), 1:length(models))
+	} ) )
+	tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
+  tableauRecap = tableauRecap[(tableauRecap[,1])!=Inf,]
   data = cbind(1:dim(tableauRecap)[1], tableauRecap[,2], tableauRecap[,2], tableauRecap[,1])
 
   modSel = capushe::capushe(data, n)
-- 
2.44.0