prepare EMGLLF / EMGrank wrappers, simplify folder generateTestData
[valse.git] / R / initSmallEM.R
CommitLineData
d1531659 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
39046da6
BA
10initSmallEM = function(k,X,Y,tau)
11{
e166ed4e
BA
12 n = nrow(Y)
13 m = ncol(Y)
14 p = ncol(X)
ae4fa2cb 15
ef67d338 16 Zinit1 = array(0, dim=c(n,20))
e166ed4e
BA
17 betaInit1 = array(0, dim=c(p,m,k,20))
18 sigmaInit1 = array(0, dim = c(m,m,k,20))
19 phiInit1 = array(0, dim = c(p,m,k,20))
20 rhoInit1 = array(0, dim = c(m,m,k,20))
ae4fa2cb 21 Gam = matrix(0, n, k)
e166ed4e
BA
22 piInit1 = matrix(0,20,k)
23 gamInit1 = array(0, dim=c(n,k,20))
24 LLFinit1 = list()
25
26 require(MASS) #Moore-Penrose generalized inverse of matrix
e166ed4e
BA
27 for(repet in 1:20)
28 {
4725af56
BG
29 distance_clus = dist(X)
30 tree_hier = hclust(distance_clus)
31 Zinit1[,repet] = cutree(tree_hier, k)
32
e166ed4e
BA
33 for(r in 1:k)
34 {
35 Z = Zinit1[,repet]
c3bc4705 36 Z_indice = seq_len(n)[Z == r] #renvoit les indices où Z==r
e166ed4e 37
ef67d338
BA
38 betaInit1[,,r,repet] = ginv(crossprod(X[Z_indice,])) %*%
39 crossprod(X[Z_indice,], Y[Z_indice,])
e166ed4e 40 sigmaInit1[,,r,repet] = diag(m)
4725af56 41 phiInit1[,,r,repet] = betaInit1[,,r,repet] #/ sigmaInit1[,,r,repet]
e166ed4e 42 rhoInit1[,,r,repet] = solve(sigmaInit1[,,r,repet])
c3bc4705 43 piInit1[repet,r] = mean(Z == r)
e166ed4e
BA
44 }
45
46 for(i in 1:n)
47 {
48 for(r in 1:k)
49 {
4725af56 50 dotProduct = tcrossprod(Y[i,]%*%rhoInit1[,,r,repet]-X[i,]%*%phiInit1[,,r,repet])
e166ed4e
BA
51 Gam[i,r] = piInit1[repet,r]*det(rhoInit1[,,r,repet])*exp(-0.5*dotProduct)
52 }
ae4fa2cb 53 sumGamI = sum(Gam[i,])
e166ed4e
BA
54 gamInit1[i,,repet]= Gam[i,] / sumGamI
55 }
56
57 miniInit = 10
58 maxiInit = 11
59
ef67d338
BA
60 new_EMG = .Call("EMGLLF_core",phiInit1[,,,repet],rhoInit1[,,,repet],piInit1[repet,],
61 gamInit1[,,repet],miniInit,maxiInit,1,0,X,Y,tau)
e166ed4e
BA
62 LLFEessai = new_EMG$LLF
63 LLFinit1[repet] = LLFEessai[length(LLFEessai)]
64 }
65
66 b = which.max(LLFinit1)
67 phiInit = phiInit1[,,,b]
68 rhoInit = rhoInit1[,,,b]
69 piInit = piInit1[b,]
70 gamInit = gamInit1[,,b]
71
72 return (list(phiInit=phiInit, rhoInit=rhoInit, piInit=piInit, gamInit=gamInit))
39046da6 73}