From: Benjamin Auder Date: Wed, 5 Apr 2017 22:17:56 +0000 (+0200) Subject: simplify EMGLLF_R a bit X-Git-Url: https://git.auder.net/variants/Chakart/pieces/doc/html/scripts/%3C?a=commitdiff_plain;h=cbfc356e52c566131516938ca0fb9aee5a442bf3;p=valse.git simplify EMGLLF_R a bit --- diff --git a/pkg/R/EMGLLF_R.R b/pkg/R/EMGLLF_R.R index 227d803..55101b0 100644 --- a/pkg/R/EMGLLF_R.R +++ b/pkg/R/EMGLLF_R.R @@ -1,42 +1,36 @@ EMGLLF_R = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,tau) { - #matrix dimensions + # Matrix dimensions n = dim(X)[1] p = dim(phiInit)[1] m = dim(phiInit)[2] k = dim(phiInit)[3] - - #init outputs + + # Outputs phi = phiInit rho = rhoInit pi = piInit - LLF = rep(0, maxi) + llh = -Inf S = array(0, dim=c(p,m,k)) - + + # Algorithm variables 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)))) + EPS = 1e-15 + + for (ite in 1:maxi) { + # Remember last pi,rho,phi values for exit condition in the end of loop Phi = phi Rho = rho Pi = pi - #calcul associé à Y et X - for(r in 1:k) + # Calcul associé à Y et X + for (r in 1:k) { for (mm in 1:m) Y2[,mm,r] = sqrt(gam[,r]) * Y[,mm] @@ -54,14 +48,13 @@ EMGLLF_R = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,ta ########## #Etape M # ########## - - #pour pi - for (r in 1:k) - b[r] = sum(abs(phi[,,r])) + + # Pour pi + b = sapply( 1:k, function(r) sum(abs(phi[,,r])) ) gam2 = colSums(gam) a = sum(gam %*% log(pi)) - #tant que les props sont negatives + # Tant que les props sont negatives kk = 0 pi2AllPositive = FALSE while (!pi2AllPositive) @@ -71,7 +64,7 @@ EMGLLF_R = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,ta kk = kk+1 } - #t(m) la plus grande valeur dans la grille O.1^k tel que ce soit décroissante ou constante + # 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) ) { @@ -86,13 +79,11 @@ EMGLLF_R = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,ta { for (mm in 1:m) { + ps = 0 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]) + ps = ps + Y2[i,mm,r] * sum(X2[i,,r] * phi[,mm,r]) + nY2 = sum(Y2[,mm,r]^2) + rho[mm,mm,r] = (ps+sqrt(ps^2+4*nY2*gam2[r])) / (2*nY2) } } @@ -117,40 +108,37 @@ EMGLLF_R = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,ta #Etape E # ########## - sumLogLLF2 = 0 + sumLogLLH2 = 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; + # Update gam[,] + sumLLH1 = 0 + sumGamI = 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) + gam[i,r] = pi[r] * exp(-0.5*sum( (Y[i,]%*%rho[,,r]-X[i,]%*%phi[,,r])^2 )) + * det(rho[,,r]) + sumLLH1 = sumLLH1 + gam[i,r] / (2*base::pi)^(m/2) + sumGamI = sumGamI + gam[i,r] } - sumLogLLF2 = sumLogLLF2 + log(sumLLF1) - sumGamI = sum(Gam[i,]) - if(sumGamI > EPS) - gam[i,] = Gam[i,] / sumGamI - else - gam[i,] = rep(0,k) + sumLogLLH2 = sumLogLLH2 + log(sumLLH1) + if(sumGamI > EPS) #else: gam[i,] is already ~=0 + gam[i,] = gam[i,] / sumGamI } 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])) ) + last_llh = llh + llh = -sumLogLLH2/n + lambda*sumPen + dist = ifelse( ite == 1, llh, (llh-last_llh) / (1+abs(llh)) ) 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 + if (ite>=mini && (dist>= tau || dist2 >= sqrt(tau))) + break } affec = apply(gam, 1, which.max) - return(list("phi"=phi, "rho"=rho, "pi"=pi, "LLF"=LLF, "S"=S, "affec" = affec )) + list( "phi"=phi, "rho"=rho, "pi"=pi, "llh"=llh, "S"=S, "affec"=affec ) }