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     print(X[i,])
  27     print(beta[,,class[i]])
  28     Y[i,] = mvrnorm(1, X[i,] %*% beta[,,class[i]], covY[,,class[i]])
  29   }
  30
  31   return (list(X=X,Y=Y, class = class))
  32 }
  33
  34 #' Generate a sample of (X,Y) of size n with default values
  35 #' @param n sample size
  36 #' @param p number of covariates
  37 #' @param m size of the response
  38 #' @param k number of clusters
  39 #' @return list with X and Y
  40 #' @export
  41 generateXYdefault = function(n, p, m, k)
  42 {
  43   meanX = rep(0, p)
  44   covX = diag(p)
  45   covY = array(dim=c(m,m,k))
  46   for(r in 1:k)
  47   {
  48     covY[,,r] = diag(m)
  49   }
  50   pi = rep(1./k,k)
  51   #initialize beta to a random number of non-zero random value
  52   beta = array(0, dim=c(p,m,k))
  53   for (j in 1:p)
  54   {
  55     nonZeroCount = sample(1:m, 1)
  56     beta[j,1:nonZeroCount,] = matrix(runif(nonZeroCount*k), ncol=k)
  57   }
  58
  59   sample_IO = generateXY(meanX, covX, covY, pi, beta, n)
  60   return (list(X=sample_IO$X,Y=sample_IO$Y))
  61 }
  62
  63 #' Initialize the parameters in a basic way (zero for the conditional mean, uniform for weights,
  64 #' identity for covariance matrices, and uniformly distributed for the clustering)
  65 #' @param n sample size
  66 #' @param p number of covariates
  67 #' @param m size of the response
  68 #' @param k number of clusters
  69 #' @return list with phiInit, rhoInit,piInit,gamInit
  70 #' @export
  71 basicInitParameters = function(n,p,m,k)
  72 {
  73   phiInit = array(0, dim=c(p,m,k))
  74
  75   piInit = (1./k)*rep(1,k)
  76
  77   rhoInit = array(dim=c(m,m,k))
  78   for (i in 1:k)
  79     rhoInit[,,i] = diag(m)
  80
  81   gamInit = 0.1 * matrix(1, nrow=n, ncol=k)
  82   R = sample(1:k, n, replace=TRUE)
  83   for (i in 1:n)
  84     gamInit[i,R[i]] = 0.9
  85   gamInit = gamInit/sum(gamInit[1,])
  86
  87   return (list("phiInit" = phiInit, "rhoInit" = rhoInit, "piInit" = piInit, "gamInit" = gamInit))
  88 }