First commit
[valse.git] / pkg / R / constructionModelesLassoRank.R
CommitLineData
3453829e
BA
1#' constructionModelesLassoRank
2#'
3#' Construct a collection of models with the Lasso-Rank procedure.
4#'
5#' @param S output of selectVariables.R
6#' @param k number of components
7#' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
8#' @param maxi integer, maximum number of iterations in the EM algorithm, by default = 100
9#' @param X matrix of covariates (of size n*p)
10#' @param Y matrix of responses (of size n*m)
11#' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
12#' @param rank.min integer, minimum rank in the low rank procedure, by default = 1
13#' @param rank.max integer, maximum rank in the low rank procedure, by default = 5
14#' @param ncores Number of cores, by default = 3
15#' @param fast TRUE to use compiled C code, FALSE for R code only
16#' @param verbose TRUE to show some execution traces
17#'
18#' @return a list with several models, defined by phi, rho, pi, llh
19#'
20#' @export
21constructionModelesLassoRank <- function(S, k, mini, maxi, X, Y, eps, rank.min, rank.max,
22 ncores, fast, verbose)
23{
24 n <- nrow(X)
25 p <- ncol(X)
26 m <- ncol(Y)
27 L <- length(S)
28
29 # Possible interesting ranks
30 deltaRank <- rank.max - rank.min + 1
31 Size <- deltaRank^k
32 RankLambda <- matrix(0, nrow = Size * L, ncol = k + 1)
33 for (r in 1:k)
34 {
35 # On veut le tableau de toutes les combinaisons de rangs possibles, et des
36 # lambdas Dans la première colonne : on répète (rank.max-rank.min)^(k-1) chaque
37 # chiffre : ça remplit la colonne Dans la deuxieme : on répète
38 # (rank.max-rank.min)^(k-2) chaque chiffre, et on fait ça (rank.max-rank.min)^2
39 # fois ... Dans la dernière, on répète chaque chiffre une fois, et on fait ça
40 # (rank.min-rank.max)^(k-1) fois.
41 RankLambda[, r] <- rep(rank.min + rep(0:(deltaRank - 1), deltaRank^(r - 1),
42 each = deltaRank^(k - r)), each = L)
43 }
44 RankLambda[, k + 1] <- rep(1:L, times = Size)
45
46 if (ncores > 1)
47 {
48 cl <- parallel::makeCluster(ncores, outfile = "")
49 parallel::clusterExport(cl, envir = environment(), varlist = c("A1", "Size",
50 "Pi", "Rho", "mini", "maxi", "X", "Y", "eps", "Rank", "m", "phi", "ncores",
51 "verbose"))
52 }
53
54 computeAtLambda <- function(index)
55 {
56 lambdaIndex <- RankLambda[index, k + 1]
57 rankIndex <- RankLambda[index, 1:k]
58 if (ncores > 1)
59 require("valse") #workers start with an empty environment
60
61 # 'relevant' will be the set of relevant columns
62 selected <- S[[lambdaIndex]]$selected
63 relevant <- c()
64 for (j in 1:p)
65 {
66 if (length(selected[[j]]) > 0)
67 relevant <- c(relevant, j)
68 }
69 if (max(rankIndex) < length(relevant))
70 {
71 phi <- array(0, dim = c(p, m, k))
72 if (length(relevant) > 0)
73 {
74 res <- EMGrank(S[[lambdaIndex]]$Pi, S[[lambdaIndex]]$Rho, mini, maxi,
75 X[, relevant], Y, eps, rankIndex, fast)
76 llh <- c(res$LLF, sum(rankIndex * (length(relevant) - rankIndex + m)))
77 phi[relevant, , ] <- res$phi
78 }
79 list(llh = llh, phi = phi, pi = S[[lambdaIndex]]$Pi, rho = S[[lambdaIndex]]$Rho)
80 }
81 }
82
83 # For each lambda in the grid we compute the estimators
84 out <-
85 if (ncores > 1) {
86 parLapply(cl, seq_len(length(S) * Size), computeAtLambda)
87 } else {
88 lapply(seq_len(length(S) * Size), computeAtLambda)
89 }
90
91 if (ncores > 1)
92 parallel::stopCluster(cl)
93
94 out
95}