Adjustments for CRAN upload
[valse.git] / pkg / R / constructionModelesLassoMLE.R
... / ...
CommitLineData
1#' constructionModelesLassoMLE
2#'
3#' Construct a collection of models with the Lasso-MLE procedure.
4#'
5#' @param phiInit an initialization for phi, get by initSmallEM.R
6#' @param rhoInit an initialization for rho, get by initSmallEM.R
7#' @param piInit an initialization for pi, get by initSmallEM.R
8#' @param gamInit an initialization for gam, get by initSmallEM.R
9#' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
10#' @param maxi integer, maximum number of iterations in the EM algorithm, by default = 100
11#' @param gamma integer for the power in the penaly, by default = 1
12#' @param X matrix of covariates (of size n*p)
13#' @param Y matrix of responses (of size n*m)
14#' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
15#' @param S output of selectVariables.R
16#' @param ncores Number of cores, by default = 3
17#' @param fast TRUE to use compiled C code, FALSE for R code only
18#' @param verbose TRUE to show some execution traces
19#'
20#' @return a list with several models, defined by phi (the regression parameter reparametrized),
21#' rho (the covariance parameter reparametrized), pi (the proportion parameter is the mixture model), llh
22#' (the value of the loglikelihood function for this estimator on the training dataset). The list is given
23#' for several levels of sparsity, given by several regularization parameters computed automatically.
24#'
25#' @export
26constructionModelesLassoMLE <- function(phiInit, rhoInit, piInit, gamInit, mini,
27 maxi, gamma, X, Y, eps, S, ncores, fast, verbose)
28{
29 if (ncores > 1)
30 {
31 cl <- parallel::makeCluster(ncores, outfile = "")
32 parallel::clusterExport(cl, envir = environment(), varlist = c("phiInit",
33 "rhoInit", "gamInit", "mini", "maxi", "gamma", "X", "Y", "eps", "S",
34 "ncores", "fast", "verbose"))
35 }
36
37 # Individual model computation
38 computeAtLambda <- function(lambda)
39 {
40 if (ncores > 1)
41 require("valse") #nodes start with an empty environment
42
43 if (verbose)
44 print(paste("Computations for lambda=", lambda))
45
46 n <- nrow(X)
47 p <- ncol(X)
48 m <- ncol(Y)
49 k <- length(piInit)
50 sel.lambda <- S[[lambda]]$selected
51 # col.sel = which(colSums(sel.lambda)!=0) #if boolean matrix
52 col.sel <- which(sapply(sel.lambda, length) > 0) #if list of selected vars
53 if (length(col.sel) == 0)
54 return(NULL)
55
56 # lambda == 0 because we compute the EMV: no penalization here
57 res <- EMGLLF(array(phiInit[col.sel, , ], dim=c(length(col.sel),m,k)),
58 rhoInit, piInit, gamInit, mini, maxi, gamma, 0,
59 as.matrix(X[, col.sel]), Y, eps, fast)
60
61 # Eval dimension from the result + selected
62 phiLambda2 <- res$phi
63 rhoLambda <- res$rho
64 piLambda <- res$pi
65 phiLambda <- array(0, dim = c(p, m, k))
66 for (j in seq_along(col.sel))
67 phiLambda[col.sel[j], sel.lambda[[j]], ] <- phiLambda2[j, sel.lambda[[j]], ]
68 dimension <- length(unlist(sel.lambda))
69
70 ## Affectations
71 Gam <- matrix(0, ncol = length(piLambda), nrow = n)
72 for (i in 1:n)
73 {
74 for (r in 1:length(piLambda))
75 {
76 sqNorm2 <- sum((Y[i, ] %*% rhoLambda[, , r] - X[i, ] %*% phiLambda[, , r])^2)
77 Gam[i, r] <- piLambda[r] * exp(-0.5 * sqNorm2) * det(rhoLambda[, , r])
78 }
79 }
80 Gam2 <- Gam/rowSums(Gam)
81 affec <- apply(Gam2, 1, which.max)
82 proba <- Gam2
83 LLH <- c(sum(log(apply(Gam,1,sum))), (dimension + m + 1) * k - 1)
84 # ## Computation of the loglikelihood
85 # # Precompute det(rhoLambda[,,r]) for r in 1...k
86 # detRho <- sapply(1:k, function(r) gdet(rhoLambda[, , r]))
87 # sumLogLLH <- 0
88 # for (i in 1:n)
89 # {
90 # # Update gam[,]; use log to avoid numerical problems
91 # logGam <- sapply(1:k, function(r) {
92 # log(piLambda[r]) + log(detRho[r]) - 0.5 *
93 # sum((Y[i, ] %*% rhoLambda[, , r] - X[i, ] %*% phiLambda[, , r])^2)
94 # })
95 #
96 # #logGam <- logGam - max(logGam) #adjust without changing proportions -> change the LLH
97 # gam <- exp(logGam)
98 # norm_fact <- sum(gam)
99 # sumLogLLH <- sumLogLLH + log(norm_fact) - m/2* log(2 * base::pi)
100 # }
101 #llhLambda <- c(-sumLogLLH/n, (dimension + m + 1) * k - 1)
102 list(phi = phiLambda, rho = rhoLambda, pi = piLambda, llh = LLH, affec = affec, proba = proba)
103 }
104
105 # For each lambda, computation of the parameters
106 out <-
107 if (ncores > 1) {
108 parallel::parLapply(cl, 1:length(S), computeAtLambda)
109 } else {
110 lapply(1:length(S), computeAtLambda)
111 }
112
113 if (ncores > 1)
114 parallel::stopCluster(cl)
115
116 out
117}