Rename main function into runValse, remove testthat folder since nobody's gonna write...
[valse.git] / pkg / R / initSmallEM.R
CommitLineData
0ba1b11c 1#' initialization of the EM algorithm
3453829e
BA
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#'
7#' @return a list with phiInit, rhoInit, piInit, gamInit
859c30ec 8#'
3453829e
BA
9#' @importFrom methods new
10#' @importFrom stats cutree dist hclust runif
859c30ec 11#' @export
3453829e
BA
12initSmallEM <- function(k, X, Y, fast)
13{
14 n <- nrow(X)
15 p <- ncol(X)
16 m <- ncol(Y)
17 nIte <- 20
18 Zinit1 <- array(0, dim = c(n, nIte))
19 betaInit1 <- array(0, dim = c(p, m, k, nIte))
20 sigmaInit1 <- array(0, dim = c(m, m, k, nIte))
21 phiInit1 <- array(0, dim = c(p, m, k, nIte))
22 rhoInit1 <- array(0, dim = c(m, m, k, nIte))
23 Gam <- matrix(0, n, k)
24 piInit1 <- matrix(0, nIte, k)
25 gamInit1 <- array(0, dim = c(n, k, nIte))
26 LLFinit1 <- list()
27
28 # require(MASS) #Moore-Penrose generalized inverse of matrix
29 for (repet in 1:nIte)
30 {
31 distance_clus <- dist(cbind(X, Y))
32 tree_hier <- hclust(distance_clus)
33 Zinit1[, repet] <- cutree(tree_hier, k)
34
35 for (r in 1:k)
36 {
37 Z <- Zinit1[, repet]
6775f5b9 38 Z_indice <- seq_len(n)[Z == r] #renvoit les indices ou Z==r
3453829e 39 if (length(Z_indice) == 1) {
0ba1b11c 40 betaInit1[, , r, repet] <- MASS::ginv(crossprod(t(X[Z_indice, ]))) %*%
3453829e
BA
41 crossprod(t(X[Z_indice, ]), Y[Z_indice, ])
42 } else {
0ba1b11c 43 betaInit1[, , r, repet] <- MASS::ginv(crossprod(X[Z_indice, ])) %*%
3453829e
BA
44 crossprod(X[Z_indice, ], Y[Z_indice, ])
45 }
46 sigmaInit1[, , r, repet] <- diag(m)
47 phiInit1[, , r, repet] <- betaInit1[, , r, repet] #/ sigmaInit1[,,r,repet]
48 rhoInit1[, , r, repet] <- solve(sigmaInit1[, , r, repet])
49 piInit1[repet, r] <- mean(Z == r)
50 }
51
52 for (i in 1:n)
53 {
54 for (r in 1:k)
55 {
56 dotProduct <- tcrossprod(Y[i, ] %*% rhoInit1[, , r, repet]
57 - X[i, ] %*% phiInit1[, , r, repet])
0ba1b11c 58 Gam[i, r] <- piInit1[repet, r] *
3453829e
BA
59 det(rhoInit1[, , r, repet]) * exp(-0.5 * dotProduct)
60 }
61 sumGamI <- sum(Gam[i, ])
62 # TODO: next line is a division by zero if dotProduct is big
63 gamInit1[i, , repet] <- Gam[i, ]/sumGamI
64 }
65
66 miniInit <- 10
67 maxiInit <- 11
68
69 init_EMG <- EMGLLF(phiInit1[, , , repet], rhoInit1[, , , repet], piInit1[repet, ],
70 gamInit1[, , repet], miniInit, maxiInit, gamma = 1, lambda = 0, X, Y,
71 eps = 1e-04, fast)
72 LLFinit1[[repet]] <- init_EMG$llh
73 }
74 b <- which.min(LLFinit1)
75 phiInit <- phiInit1[, , , b]
76 rhoInit <- rhoInit1[, , , b]
77 piInit <- piInit1[b, ]
78 gamInit <- gamInit1[, , b]
79
80 return(list(phiInit = phiInit, rhoInit = rhoInit, piInit = piInit, gamInit = gamInit))
81}