pkg/R/generateSampleInputs.R

   1 #' Generate a sample of (X,Y) of size n
   2 #' @param meanX matrix of group means for covariates (of size p)
   3 #' @param covX covariance for covariates (of size p*p)
   4 #' @param covY covariance for the response vector (of size m*m*K)
   5 #' @param pi     proportion for each cluster
   6 #' @param beta regression matrix, of size p*m*k
   7 #' @param n     sample size
   8 #'
   9 #' @return list with X and Y
  10 #' @export
  11 generateXY = function(meanX, covX, covY, pi, beta, n)
  12 {
  13     p = dim(covX)[1]
  14     m = dim(covY)[1]
  15     k = dim(covY)[3]
  16
  17     X = matrix(nrow=n,ncol=p)
  18     Y = matrix(nrow=n,ncol=m)
  19     class = matrix(nrow = n)
  20
  21     require(MASS) #simulate from a multivariate normal distribution
  22     for (i in 1:n)
  23     {
  24         class[i] = sample(1:k, 1, prob=pi)
  25         X[i,] = mvrnorm(1, meanX, covX)
  26         Y[i,] = mvrnorm(1, X[i,] %*% beta[,,class[i]], covY[,,class[i]])
  27     }
  28
  29     return (list(X=X,Y=Y, class = class))
  30 }
  31
  32 #' Generate a sample of (X,Y) of size n with default values
  33 #' @param n sample size
  34 #' @param p number of covariates
  35 #' @param m size of the response
  36 #' @param k number of clusters
  37 #' @return list with X and Y
  38 #' @export
  39 generateXYdefault = function(n, p, m, k)
  40 {
  41     meanX = rep(0, p)
  42     covX = diag(p)
  43     covY = array(dim=c(m,m,k))
  44     for(r in 1:k)
  45     {
  46         covY[,,r] = diag(m)
  47     }
  48     pi = rep(1./k,k)
  49     #initialize beta to a random number of non-zero random value
  50     beta = array(0, dim=c(p,m,k))
  51     for (j in 1:p)
  52     {
  53         nonZeroCount = sample(1:m, 1)
  54         beta[j,1:nonZeroCount,] = matrix(runif(nonZeroCount*k), ncol=k)
  55     }
  56
  57     sample_IO = generateXY(meanX, covX, covY, pi, beta, n)
  58     return (list(X=sample_IO$X,Y=sample_IO$Y))
  59 }
  60
  61 #' Initialize the parameters in a basic way (zero for the conditional mean, uniform for weights,
  62 #' identity for covariance matrices, and uniformly distributed for the clustering)
  63 #' @param n sample size
  64 #' @param p number of covariates
  65 #' @param m size of the response
  66 #' @param k number of clusters
  67 #' @return list with phiInit, rhoInit,piInit,gamInit
  68 #' @export
  69 basicInitParameters = function(n,p,m,k)
  70 {
  71     phiInit = array(0, dim=c(p,m,k))
  72
  73     piInit = (1./k)*rep(1,k)
  74
  75     rhoInit = array(dim=c(m,m,k))
  76     for (i in 1:k)
  77         rhoInit[,,i] = diag(m)
  78
  79     gamInit = 0.1 * matrix(1, nrow=n, ncol=k)
  80     R = sample(1:k, n, replace=TRUE)
  81     for (i in 1:n)
  82         gamInit[i,R[i]] = 0.9
  83     gamInit = gamInit/sum(gamInit[1,])
  84
  85     return (list("phiInit" = phiInit, "rhoInit" = rhoInit, "piInit" = piInit, "gamInit" = gamInit))
  86 }