From: Benjamin Auder <benjamin.auder@somewhere>
Date: Tue, 4 Apr 2017 10:51:52 +0000 (+0200)
Subject: temporary fix: use R version of EMGLLF and EMGrank in package
X-Git-Url: https://git.auder.net/%7B%7B%20path%28%27fos_user_profile_show%27%29%20%7D%7D?a=commitdiff_plain;h=567a7c388285ef17ce1e49d295527937dbfadf66;p=valse.git

temporary fix: use R version of EMGLLF and EMGrank in package
---

diff --git a/pkg/R/A_NAMESPACE.R b/pkg/R/A_NAMESPACE.R
index a1c8ce3..dd06c9c 100644
--- a/pkg/R/A_NAMESPACE.R
+++ b/pkg/R/A_NAMESPACE.R
@@ -1,4 +1,6 @@
 #' @include generateXY.R
+#' @include EMGLLF_R.R
+#' @include EMGrank_R.R
 #' @include EMGLLF.R
 #' @include EMGrank.R
 #' @include initSmallEM.R
diff --git a/pkg/R/EMGLLF.R b/pkg/R/EMGLLF.R
index 7d9ee77..5484706 100644
--- a/pkg/R/EMGLLF.R
+++ b/pkg/R/EMGLLF.R
@@ -25,6 +25,9 @@
 EMGLLF <- function(phiInit, rhoInit, piInit, gamInit,
 	mini, maxi, gamma, lambda, X, Y, tau)
 {
+	#TEMPORARY: use R version
+	return (EMGLLF_R(phiInit, rhoInit, piInit, gamInit,mini, maxi, gamma, lambda, X, Y, tau))
+
 	n = nrow(X) #nombre d'echantillons
 	p = ncol(X) #nombre de covariables
 	m = ncol(Y) #taille de Y (multivarié)
diff --git a/pkg/R/EMGLLF_R.R b/pkg/R/EMGLLF_R.R
new file mode 100644
index 0000000..039e291
--- /dev/null
+++ b/pkg/R/EMGLLF_R.R
@@ -0,0 +1,156 @@
+EMGLLF_R = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,tau)
+{
+  #matrix dimensions
+  n = dim(X)[1]
+  p = dim(phiInit)[1]
+  m = dim(phiInit)[2]
+  k = dim(phiInit)[3]
+  
+  #init outputs
+  phi = phiInit
+  rho = rhoInit
+  pi = piInit
+  LLF = rep(0, maxi)
+  S = array(0, dim=c(p,m,k))
+  
+  gam = gamInit
+  Gram2 = array(0, dim=c(p,p,k))
+  ps2 = array(0, dim=c(p,m,k))
+  b = rep(0, k)
+  X2 = array(0, dim=c(n,p,k))
+  Y2 = array(0, dim=c(n,m,k))
+  dist = 0
+  dist2 = 0
+  ite = 1
+  pi2 = rep(0, k)
+  ps = matrix(0, m,k)
+  nY2 = matrix(0, m,k)
+  ps1 = array(0, dim=c(n,m,k))
+  Gam = matrix(0, n,k)
+  EPS = 1E-15
+  
+  while(ite <= mini || (ite<= maxi && (dist>= tau || dist2 >= sqrt(tau))))
+	{
+    Phi = phi
+    Rho = rho
+    Pi = pi
+
+    #calcul associé à Y et X
+    for(r in 1:k)
+		{
+      for (mm in 1:m)
+        Y2[,mm,r] = sqrt(gam[,r]) * Y[,mm]
+      for (i in 1:n)
+        X2[i,,r] = sqrt(gam[i,r]) * X[i,]
+      for (mm in 1:m)
+        ps2[,mm,r] = crossprod(X2[,,r],Y2[,mm,r])
+      for (j in 1:p)
+			{
+        for (s in 1:p)
+          Gram2[j,s,r] = crossprod(X2[,j,r], X2[,s,r])
+      }
+    }
+
+    ##########
+    #Etape M #
+    ##########
+    
+    #pour pi
+    for (r in 1:k)
+      b[r] = sum(abs(phi[,,r]))
+    gam2 = colSums(gam)
+    a = sum(gam %*% log(pi))
+
+    #tant que les props sont negatives
+    kk = 0
+    pi2AllPositive = FALSE
+    while (!pi2AllPositive)
+		{
+      pi2 = pi + 0.1^kk * ((1/n)*gam2 - pi)
+      pi2AllPositive = all(pi2 >= 0)
+      kk = kk+1
+    }
+
+    #t(m) la plus grande valeur dans la grille O.1^k tel que ce soit décroissante ou constante
+    while( kk < 1000 && -a/n + lambda * sum(pi^gamma * b) <
+			-sum(gam2 * log(pi2))/n + lambda * sum(pi2^gamma * b) )
+		{
+      pi2 = pi + 0.1^kk * (1/n*gam2 - pi)
+      kk = kk + 1
+    }
+    t = 0.1^kk
+    pi = (pi + t*(pi2-pi)) / sum(pi + t*(pi2-pi))
+
+    #Pour phi et rho
+    for (r in 1:k)
+		{
+      for (mm in 1:m)
+			{
+        for (i in 1:n)
+				{
+          ps1[i,mm,r] = Y2[i,mm,r] * sum(X2[i,,r] * phi[,mm,r])
+        }
+        ps[mm,r] = sum(ps1[,mm,r])
+        nY2[mm,r] = sum(Y2[,mm,r]^2)
+        rho[mm,mm,r] = (ps[mm,r]+sqrt(ps[mm,r]^2+4*nY2[mm,r]*gam2[r])) / (2*nY2[mm,r])
+			}
+    }
+
+    for (r in 1:k)
+		{
+      for (j in 1:p)
+			{
+        for (mm in 1:m)
+				{
+          S[j,mm,r] = -rho[mm,mm,r]*ps2[j,mm,r] + sum(phi[-j,mm,r] * Gram2[j,-j,r])
+					if (abs(S[j,mm,r]) <= n*lambda*(pi[r]^gamma))
+            phi[j,mm,r]=0
+          else if(S[j,mm,r] > n*lambda*(pi[r]^gamma))
+            phi[j,mm,r] = (n*lambda*(pi[r]^gamma)-S[j,mm,r]) / Gram2[j,j,r]
+          else
+            phi[j,mm,r] = -(n*lambda*(pi[r]^gamma)+S[j,mm,r]) / Gram2[j,j,r]
+        }
+      }
+    }
+
+    ##########
+    #Etape E #
+    ##########
+
+		sumLogLLF2 = 0
+    for (i in 1:n)
+		{
+      #precompute sq norms to numerically adjust their values
+      sqNorm2 = rep(0,k)
+      for (r in 1:k)
+        sqNorm2[r] = sum( (Y[i,]%*%rho[,,r]-X[i,]%*%phi[,,r])^2 )
+
+      #compute Gam[,]
+      sumLLF1 = 0.0;
+      for (r in 1:k)
+			{
+				Gam[i,r] = pi[r] * exp(-0.5*sqNorm2[r]) * det(rho[,,r])
+        sumLLF1 = sumLLF1 + Gam[i,r] / (2*base::pi)^(m/2)
+      }
+      sumLogLLF2 = sumLogLLF2 + log(sumLLF1)
+      sumGamI = sum(Gam[i,])
+      if(sumGamI > EPS)
+        gam[i,] = Gam[i,] / sumGamI
+      else
+        gam[i,] = rep(0,k)
+    }
+
+    sumPen = sum(pi^gamma * b)
+    LLF[ite] = -sumLogLLF2/n + lambda*sumPen
+    dist = ifelse( ite == 1, LLF[ite], (LLF[ite]-LLF[ite-1]) / (1+abs(LLF[ite])) )
+    Dist1 = max( (abs(phi-Phi)) / (1+abs(phi)) )
+    Dist2 = max( (abs(rho-Rho)) / (1+abs(rho)) )
+    Dist3 = max( (abs(pi-Pi)) / (1+abs(Pi)) )
+    dist2 = max(Dist1,Dist2,Dist3)
+
+    ite = ite+1
+  }
+  
+  affec = apply(gam, 1, which.max)
+  return(list("phi"=phi, "rho"=rho, "pi"=pi, "LLF"=LLF, "S"=S, "affec" = affec ))
+}
diff --git a/pkg/R/EMGrank.R b/pkg/R/EMGrank.R
index e44ff7a..3216870 100644
--- a/pkg/R/EMGrank.R
+++ b/pkg/R/EMGrank.R
@@ -19,6 +19,9 @@
 #' @export
 EMGrank <- function(Pi, Rho, mini, maxi, X, Y, tau, rank)
 {
+	#TEMPORARY: use R version
+	return (EMGrank_R(Pi, Rho, mini, maxi, X, Y, tau, rank))
+
 	n = nrow(X) #nombre d'echantillons
 	p = ncol(X) #nombre de covariables
 	m = ncol(Y) #taille de Y (multivarié)
diff --git a/pkg/R/EMGrank_R.R b/pkg/R/EMGrank_R.R
new file mode 100644
index 0000000..c4576e4
--- /dev/null
+++ b/pkg/R/EMGrank_R.R
@@ -0,0 +1,85 @@
+#helper to always have matrices as arg (TODO: put this elsewhere? improve?)
+# --> Yes, we should use by-columns storage everywhere... [later!]
+matricize <- function(X)
+{
+	if (!is.matrix(X))
+		return (t(as.matrix(X)))
+	return (X)
+}
+
+require(MASS)
+EMGrank_R = function(Pi, Rho, mini, maxi, X, Y, tau, rank)
+{
+  #matrix dimensions
+  n = dim(X)[1]
+  p = dim(X)[2]
+  m = dim(Rho)[2]
+  k = dim(Rho)[3]
+  
+  #init outputs
+  phi = array(0, dim=c(p,m,k))
+  Z = rep(1, n)
+  LLF = 0
+  
+  #local variables
+  Phi = array(0, dim=c(p,m,k))
+  deltaPhi = c()
+  sumDeltaPhi = 0.
+  deltaPhiBufferSize = 20
+  
+  #main loop
+  ite = 1
+  while (ite<=mini || (ite<=maxi && sumDeltaPhi>tau))
+	{
+    #M step: Mise à jour de Beta (et donc phi)
+    for(r in 1:k)
+		{
+      Z_indice = seq_len(n)[Z==r] #indices où Z == r
+      if (length(Z_indice) == 0)
+        next
+      #U,S,V = SVD of (t(Xr)Xr)^{-1} * t(Xr) * Yr
+      s = svd( ginv(crossprod(matricize(X[Z_indice,]))) %*%
+				crossprod(matricize(X[Z_indice,]),matricize(Y[Z_indice,])) )
+      S = s$d
+      #Set m-rank(r) singular values to zero, and recompose
+      #best rank(r) approximation of the initial product
+      if(rank[r] < length(S))
+        S[(rank[r]+1):length(S)] = 0
+      phi[,,r] = s$u %*% diag(S) %*% t(s$v) %*% Rho[,,r]
+    }
+
+		#Etape E et calcul de LLF
+		sumLogLLF2 = 0
+		for(i in seq_len(n))
+		{
+			sumLLF1 = 0
+			maxLogGamIR = -Inf
+			for (r in seq_len(k))
+			{
+				dotProduct = tcrossprod(Y[i,]%*%Rho[,,r]-X[i,]%*%phi[,,r])
+				logGamIR = log(Pi[r]) + log(det(Rho[,,r])) - 0.5*dotProduct
+				#Z[i] = index of max (gam[i,])
+				if(logGamIR > maxLogGamIR)
+				{
+					Z[i] = r
+					maxLogGamIR = logGamIR
+				}
+				sumLLF1 = sumLLF1 + exp(logGamIR) / (2*pi)^(m/2)
+			}
+			sumLogLLF2 = sumLogLLF2 + log(sumLLF1)
+		}
+  
+		LLF = -1/n * sumLogLLF2
+
+		#update distance parameter to check algorithm convergence (delta(phi, Phi))
+		deltaPhi = c( deltaPhi, max( (abs(phi-Phi)) / (1+abs(phi)) ) ) #TODO: explain?
+		if (length(deltaPhi) > deltaPhiBufferSize)
+		  deltaPhi = deltaPhi[2:length(deltaPhi)]
+		sumDeltaPhi = sum(abs(deltaPhi))
+
+		#update other local variables
+		Phi = phi
+		ite = ite+1
+  }
+  return(list("phi"=phi, "LLF"=LLF))
+}