utilisation de k-means au lieu de hierarchique dans initSmallEM - PB de dimensions...
[valse.git] / R / initSmallEM.R
1 #' initialization of the EM algorithm
2 #'
3 #' @param k number of components
4 #' @param X matrix of covariates (of size n*p)
5 #' @param Y matrix of responses (of size n*m)
6 #' @param tau threshold to stop EM algorithm
7 #'
8 #' @return a list with phiInit, rhoInit, piInit, gamInit
9 #' @export
10 initSmallEM = function(k,X,Y,tau)
11 {
12 n = nrow(Y)
13 m = ncol(Y)
14 p = ncol(X)
15
16 betaInit1 = array(0, dim=c(p,m,k,20))
17 sigmaInit1 = array(0, dim = c(m,m,k,20))
18 phiInit1 = array(0, dim = c(p,m,k,20))
19 rhoInit1 = array(0, dim = c(m,m,k,20))
20 piInit1 = matrix(0,20,k)
21 gamInit1 = array(0, dim=c(n,k,20))
22 LLFinit1 = list()
23
24 require(MASS) #Moore-Penrose generalized inverse of matrix
25 require(mclust) # K-means with selection of K
26 for(repet in 1:20)
27 {
28 clusters = Mclust(matrix(c(X,Y),nrow=n),k) #default distance : euclidean
29 Zinit1[,repet] = clusters$classification
30
31 for(r in 1:k)
32 {
33 Z = Zinit1[,repet]
34 Z_bin = vec_bin(Z,r)
35 Z_vec = Z_bin$Z #vecteur 0 et 1 aux endroits o? Z==r
36 Z_indice = Z_bin$indice #renvoit les indices o? Z==r
37
38 betaInit1[,,r,repet] =
39 ginv(t(x[Z_indice,])%*%x[Z_indice,])%*%t(x[Z_indice,])%*%y[Z_indice,]
40 sigmaInit1[,,r,repet] = diag(m)
41 phiInit1[,,r,repet] = betaInit1[,,r,repet]/sigmaInit1[,,r,repet]
42 rhoInit1[,,r,repet] = solve(sigmaInit1[,,r,repet])
43 piInit1[repet,r] = sum(Z_vec)/n
44 }
45
46 for(i in 1:n)
47 {
48 for(r in 1:k)
49 {
50 dotProduct = (y[i,]%*%rhoInit1[,,r,repet]-x[i,]%*%phiInit1[,,r,repet]) %*%
51 (y[i,]%*%rhoInit1[,,r,repet]-x[i,]%*%phiInit1[,,r,repet])
52 Gam[i,r] = piInit1[repet,r]*det(rhoInit1[,,r,repet])*exp(-0.5*dotProduct)
53 }
54 sumGamI = sum(gam[i,])
55 gamInit1[i,,repet]= Gam[i,] / sumGamI
56 }
57
58 miniInit = 10
59 maxiInit = 11
60
61 new_EMG = .Call("EMGLLF",phiInit1[,,,repet],rhoInit1[,,,repet],piInit1[repet,],
62 gamInit1[,,repet],miniInit,maxiInit,1,0,x,y,tau)
63 LLFEessai = new_EMG$LLF
64 LLFinit1[repet] = LLFEessai[length(LLFEessai)]
65 }
66
67 b = which.max(LLFinit1)
68 phiInit = phiInit1[,,,b]
69 rhoInit = rhoInit1[,,,b]
70 piInit = piInit1[b,]
71 gamInit = gamInit1[,,b]
72
73 return (list(phiInit=phiInit, rhoInit=rhoInit, piInit=piInit, gamInit=gamInit))
74 }