-#' initialization of the EM algorithm
+#' initialization of the EM algorithm
#'
#' @param k number of components
#' @param X matrix of covariates (of size n*p)
#' @param Y matrix of responses (of size n*m)
+#' @param fast boolean to enable or not the C function call
#'
#' @return a list with phiInit, rhoInit, piInit, gamInit
-#' @export
-#' @importFrom methods new
+#'
#' @importFrom stats cutree dist hclust runif
+#' @export
initSmallEM <- function(k, X, Y, fast)
{
n <- nrow(X)
for (r in 1:k)
{
Z <- Zinit1[, repet]
- Z_indice <- seq_len(n)[Z == r] #renvoit les indices oรน Z==r
+ Z_indice <- seq_len(n)[Z == r] #renvoit les indices ou Z==r
if (length(Z_indice) == 1) {
- betaInit1[, , r, repet] <- MASS::ginv(crossprod(t(X[Z_indice, ]))) %*%
+ betaInit1[, , r, repet] <- MASS::ginv(crossprod(t(X[Z_indice, ]))) %*%
crossprod(t(X[Z_indice, ]), Y[Z_indice, ])
} else {
- betaInit1[, , r, repet] <- MASS::ginv(crossprod(X[Z_indice, ])) %*%
+ betaInit1[, , r, repet] <- MASS::ginv(crossprod(X[Z_indice, ])) %*%
crossprod(X[Z_indice, ], Y[Z_indice, ])
}
sigmaInit1[, , r, repet] <- diag(m)
{
dotProduct <- tcrossprod(Y[i, ] %*% rhoInit1[, , r, repet]
- X[i, ] %*% phiInit1[, , r, repet])
- Gam[i, r] <- piInit1[repet, r] *
- gdet(rhoInit1[, , r, repet]) * exp(-0.5 * dotProduct)
+ Gam[i, r] <- piInit1[repet, r] *
+ det(rhoInit1[, , r, repet]) * exp(-0.5 * dotProduct)
}
sumGamI <- sum(Gam[i, ])
+ # TODO: next line is a division by zero if dotProduct is big
gamInit1[i, , repet] <- Gam[i, ]/sumGamI
}
piInit <- piInit1[b, ]
gamInit <- gamInit1[, , b]
- return(list(phiInit = phiInit, rhoInit = rhoInit, piInit = piInit, gamInit = gamInit))
+ list(phiInit = phiInit, rhoInit = rhoInit, piInit = piInit, gamInit = gamInit)
}