work on constructionModeles + main (2 levels or //isation)
[valse.git] / pkg / R / selectVariables.R
CommitLineData
7064275b 1#' selectVariables
bb551124 2#'
7064275b 3#' It is a function which construct, for a given lambda, the sets of relevant variables.
e01c9b1f 4#'
5#' @param phiInit an initial estimator for phi (size: p*m*k)
6#' @param rhoInit an initial estimator for rho (size: m*m*k)
09ab3c16 7#' @param piInit an initial estimator for pi (size : k)
e01c9b1f 8#' @param gamInit an initial estimator for gamma
09ab3c16
BA
9#' @param mini minimum number of iterations in EM algorithm
10#' @param maxi maximum number of iterations in EM algorithm
11#' @param gamma power in the penalty
e01c9b1f 12#' @param glambda grid of regularization parameters
09ab3c16
BA
13#' @param X matrix of regressors
14#' @param Y matrix of responses
15#' @param thres threshold to consider a coefficient to be equal to 0
16#' @param tau threshold to say that EM algorithm has converged
4cc632c9 17#' @param ncores Number or cores for parallel execution (1 to disable)
e01c9b1f 18#'
7064275b 19#' @return a list of outputs, for each lambda in grid: selected,Rho,Pi
cad71b2c
BA
20#'
21#' @examples TODO
e01c9b1f 22#'
cad71b2c 23#' @export
bb551124
BA
24#'
25selectVariables = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda,
4cc632c9 26 X,Y,thresh,tau, ncores=3)
09ab3c16 27{
bb551124
BA
28 if (ncores > 1)
29 {
30 cl = parallel::makeCluster(ncores)
31 parallel::clusterExport(cl=cl,
32 varlist=c("phiInit","rhoInit","gamInit","mini","maxi","glambda","X","Y","thresh","tau"),
33 envir=environment())
34 }
35
36 # Calcul pour un lambda
37 computeCoefs <-function(lambda)
09ab3c16 38 {
bb551124
BA
39 params = EMGLLF(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,tau)
40
7064275b
BA
41 p = dim(phiInit)[1]
42 m = dim(phiInit)[2]
07848d25 43
7064275b 44 #selectedVariables: list where element j contains vector of selected variables in [1,m]
4e826748 45 selectedVariables = lapply(1:p, function(j) {
7064275b
BA
46 #from boolean matrix mxk of selected variables obtain the corresponding boolean m-vector,
47 #and finally return the corresponding indices
4e826748 48 seq_len(m)[ apply( abs(params$phi[j,,]) > thresh, 1, any ) ]
7064275b 49 })
09ab3c16 50
51485a7d 51 list("selected"=selectedVariables,"Rho"=params$rho,"Pi"=params$pi)
bb551124
BA
52 }
53
54 # Pour chaque lambda de la grille, on calcule les coefficients
55 out <-
4e826748
BA
56 if (ncores > 1)
57 parLapply(cl, glambda, computeCoefs)
4cc632c9
BA
58 else
59 lapply(glambda, computeCoefs)
4e826748
BA
60 if (ncores > 1)
61 parallel::stopCluster(cl)
62
63 # Suppression doublons
64 sha1_array <- lapply(out, digest::sha1)
65 out[ !duplicated(sha1_array) ]
66
5955cc25 67 out
09ab3c16 68}