X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=R%2FinitSmallEM.R;h=7a35bc3693e9a60f5230c268ec1cc972db5c229d;hb=b4476024967cdd601bf82ff4108f5c2beb855e9e;hp=8f3c86b59baa01acab04c7042c6518c16339418c;hpb=493a35bfea6d1210c94ced8fbfe3e572f0389ea5;p=valse.git

diff --git a/R/initSmallEM.R b/R/initSmallEM.R
index 8f3c86b..7a35bc3 100644
--- a/R/initSmallEM.R
+++ b/R/initSmallEM.R
@@ -1,80 +1,74 @@
-library(MASS) #generalized inverse of matrix Monroe-Penrose
+#' initialization of the EM algorithm
+#'
+#' @param k number of components
+#' @param X matrix of covariates (of size n*p)
+#' @param Y matrix of responses (of size n*m)
+#' @param tau threshold to stop EM algorithm
+#'
+#' @return a list with phiInit, rhoInit, piInit, gamInit
+#' @export
+initSmallEM = function(k,X,Y,tau)
+{
+	n = nrow(Y)
+	m = ncol(Y)
+	p = ncol(X)
+  
+	Zinit1 = array(0, dim=c(n,20)) #doute sur la taille
+	betaInit1 = array(0, dim=c(p,m,k,20))
+	sigmaInit1 = array(0, dim = c(m,m,k,20))
+	phiInit1 = array(0, dim = c(p,m,k,20))
+	rhoInit1 = array(0, dim = c(m,m,k,20))
+	Gam = matrix(0, n, k)
+	piInit1 = matrix(0,20,k)
+	gamInit1 = array(0, dim=c(n,k,20))
+	LLFinit1 = list()
 
-vec_bin = function(X,r){
-  Z = c()
-  indice = c()
-  j=1
-  for(i in 1:length(X)){
-    if(X[i] == r){
-      Z[i] = 1
-      indice[j] = i
-      j=j+1
-    }
-    else{
-      Z[i] = 0
-    }
-  }
-  return(list(Z,indice))
-}
+	require(MASS) #Moore-Penrose generalized inverse of matrix
+	require(mclust) # K-means with selection of K
+	for(repet in 1:20)
+	{
+		clusters = Mclust(X,k) #default distance : euclidean  #Mclust(matrix(c(X,Y)),k)
+		Zinit1[,repet] = clusters$classification
+		
+		for(r in 1:k)
+		{
+			Z = Zinit1[,repet]
+			Z_bin = vec_bin(Z,r)
+			Z_vec = Z_bin$vec #vecteur 0 et 1 aux endroits o? Z==r
+			Z_indice = Z_bin$indice #renvoit les indices o? Z==r
+			
+			betaInit1[,,r,repet] = ginv(t(X[Z_indice,])%*%X[Z_indice,])%*%t(X[Z_indice,])%*%Y[Z_indice,]
+			sigmaInit1[,,r,repet] = diag(m)
+			phiInit1[,,r,repet] = betaInit1[,,r,repet]#/sigmaInit1[,,r,repet]
+			rhoInit1[,,r,repet] = solve(sigmaInit1[,,r,repet])
+			piInit1[repet,r] = sum(Z_vec)/n
+		}
+		
+		for(i in 1:n)
+		{
+			for(r in 1:k)
+			{
+				dotProduct = 3 #(Y[i,]%*%rhoInit1[,,r,repet]-X[i,]%*%phiInit1[,,r,repet]) %*% (Y[i,]%*%rhoInit1[,,r,repet]-X[i,]%*%phiInit1[,,r,repet])
+				Gam[i,r] = piInit1[repet,r]*det(rhoInit1[,,r,repet])*exp(-0.5*dotProduct)
+			}
+			sumGamI = sum(Gam[i,])
+			gamInit1[i,,repet]= Gam[i,] / sumGamI
+		}
+		
+		miniInit = 10
+		maxiInit = 11
+		
+		new_EMG = .Call("EMGLLF_core",phiInit1[,,,repet],rhoInit1[,,,repet],piInit1[repet,],
+										gamInit1[,,repet],miniInit,maxiInit,1,0,X,Y,tau)
+		LLFEessai = new_EMG$LLF
+		LLFinit1[repet] = LLFEessai[length(LLFEessai)]
+	}
 
-initSmallEM = function(k,X,Y,tau){
-  n = nrow(Y)
-  m = ncol(Y)
-  p = ncol(X)
+	b = which.max(LLFinit1)
+	phiInit = phiInit1[,,,b]
+	rhoInit = rhoInit1[,,,b]
+	piInit = piInit1[b,]
+	gamInit = gamInit1[,,b]
 
-  betaInit1 = array(0, dim=c(p,m,k,20))
-  sigmaInit1 = array(0, dim = c(m,m,k,20))
-  phiInit1 = array(0, dim = c(p,m,k,20))
-  rhoInit1 = array(0, dim = c(m,m,k,20))
-  piInit1 = matrix(0,20,k)
-  gamInit1 = array(0, dim=c(n,k,20))
-  LLFinit1 = list()
-  
-  
-  for(repet in 1:20){
-    clusters = hclust(dist(y)) #default distance : euclidean
-    clusterCut = cutree(clusters,k)
-    Zinit1[,repet] = clusterCut #retourne les indices (à quel cluster indiv_i appartient) d'un clustering hierarchique (nb de cluster = k)
-    
-    for(r in 1:k){
-      Z = Zinit1[,repet]
-      Z_bin = vec_bin(Z,r)
-      Z_vec = Z_bin[[1]] #vecteur 0 et 1 aux endroits où Z==r
-      Z_indice = Z_bin[[2]] #renvoit les indices où Z==r
-      
-      betaInit1[,,r,repet] = ginv(t(x[Z_indice,])%*%x[Z_indice,])%*%t(x[Z_indice,])%*%y[Z_indice,]
-      sigmaInit1[,,r,repet] = diag(m)
-      phiInit1[,,r,repet] = betaInit1[,,r,repet]/sigmaInit1[,,r,repet]
-      rhoInit1[,,r,repet] = solve(sigmaInit1[,,r,repet])
-      piInit1[repet,r] = sum(Z_vec)/n
-    }
-    
-    for(i in 1:n){
-      for(r in 1:k){
-        dotProduct = (y[i,]%*%rhoInit1[,,r,repet]-x[i,]%*%phiInit1[,,r,repet]) %*% (y[i,]%*%rhoInit1[,,r,repet]-x[i,]%*%phiInit1[,,r,repet])
-        Gam[i,r] = piInit1[repet,r]*det(rhoInit1[,,r,repet])*exp(-0.5*dotProduct)
-      }
-      sumGamI = sum(gam[i,])
-      gamInit1[i,,repet]= Gam[i,] / sumGamI
-    }
-    
-    miniInit = 10
-    maxiInit = 11
-    
-    new_EMG = EMGLLF(phiInit1[,,,repet],rhoInit1[,,,repet],piInit1[repet,],gamInit1[,,repet],miniInit,maxiInit,1,0,x,y,tau)
-    ##.C("EMGLLF", phiInit = phiInit, rhoInit = rhoInit, ...)
-    LLFEessai = new_EMG[[4]]
-    LLFinit1[[repet]] = LLFEessai[[length(LLFEessai)]]
-  }
-  
-  b = which.max(LLFinit1)
-  
-  phiInit = phiInit1[,,,b]
-  rhoInit = rhoInit1[,,,b]
-  piInit = piInit1[b,]
-  gamInit = gamInit1[,,b]
-  
-  return(list(phiInit, rhoInit, piInit, gamInit))
+	return (list(phiInit=phiInit, rhoInit=rhoInit, piInit=piInit, gamInit=gamInit))
 }
-
-