Commit | Line | Data |
---|---|---|
ef67d338 BA |
1 | #' Generate a sample of (X,Y) of size n |
2 | #' @param meanX matrix of group means for covariates (of size p*K) | |
3 | #' @param covX covariance for covariates (of size p*p*K) | |
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 | |
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(covX)[3] | |
16 | ||
17 | X = matrix(nrow=n,ncol=p) | |
18 | Y = matrix(nrow=n,ncol=m) | |
19 | ||
20 | require(MASS) #simulate from a multivariate normal distribution | |
21 | for (i in 1:n) | |
22 | { | |
23 | class = sample(1:k, 1, prob=pi) | |
24 | X[i,] = mvrnorm(1, meanX[,class], covX[,,class]) | |
25 | Y[i,] = mvrnorm(1, X[i,] %*% beta[,,class], covY[,,class]) | |
26 | } | |
27 | ||
28 | return (list(X=X,Y=Y)) | |
29 | } | |
30 | ||
31 | #' Generate a sample of (X,Y) of size n with default values | |
32 | #' @param n sample size | |
33 | #' @param p number of covariates | |
34 | #' @param m size of the response | |
35 | #' @param k number of clusters | |
36 | #' @return list with X and Y | |
37 | #' @export | |
38 | generateXYdefault = function(n, p, m, k) | |
39 | { | |
40 | rangeX = 100 | |
41 | meanX = rangeX * matrix(1 - 2*runif(p*k), ncol=k) | |
42 | covX = array(dim=c(p,p,k)) | |
43 | covY = array(dim=c(m,m,k)) | |
44 | for(r in 1:k) | |
45 | { | |
46 | covX[,,r] = diag(p) | |
47 | covY[,,r] = diag(m) | |
48 | } | |
49 | pi = rep(1./k,k) | |
50 | #initialize beta to a random number of non-zero random value | |
51 | beta = array(0, dim=c(p,m,k)) | |
52 | for (j in 1:p) | |
53 | { | |
54 | nonZeroCount = sample(1:m, 1) | |
55 | beta[j,1:nonZeroCount,] = matrix(runif(nonZeroCount*k), ncol=k) | |
56 | } | |
57 | ||
58 | sample_IO = generateXY(meanX, covX, covY, pi, beta, n) | |
59 | return (list(X=sample_IO$X,Y=sample_IO$Y)) | |
60 | } | |
61 | ||
62 | #' Initialize the parameters in a basic way (zero for the conditional mean, uniform for weights, | |
63 | #' identity for covariance matrices, and uniformly distributed for the clustering) | |
64 | #' @param n sample size | |
65 | #' @param p number of covariates | |
66 | #' @param m size of the response | |
67 | #' @param k number of clusters | |
68 | #' @return list with phiInit, rhoInit,piInit,gamInit | |
69 | #' @export | |
70 | basicInitParameters = function(n,p,m,k) | |
71 | { | |
72 | phiInit = array(0, dim=c(p,m,k)) | |
73 | ||
74 | piInit = (1./k)*rep(1,k) | |
75 | ||
76 | rhoInit = array(dim=c(m,m,k)) | |
77 | for (i in 1:k) | |
78 | rhoInit[,,i] = diag(m) | |
79 | ||
80 | gamInit = 0.1 * matrix(1, nrow=n, ncol=k) | |
81 | R = sample(1:k, n, replace=TRUE) | |
82 | for (i in 1:n) | |
83 | gamInit[i,R[i]] = 0.9 | |
84 | gamInit = gamInit/sum(gamInit[1,]) | |
85 | ||
86 | return (list("phiInit" = phiInit, "rhoInit" = rhoInit, "piInit" = piInit, "gamInit" = gamInit)) | |
87 | } |