1 #' valse
2 #'
3 #' Main function
4 #'
5 #' @param X matrix of covariates (of size n*p)
6 #' @param Y matrix of responses (of size n*m)
7 #' @param procedure among 'LassoMLE' or 'LassoRank'
8 #' @param selecMod method to select a model among 'DDSE', 'DJump', 'BIC' or 'AIC'
9 #' @param gamma integer for the power in the penaly, by default = 1
10 #' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
11 #' @param maxi integer, maximum number of iterations in the EM algorithm, by default = 100
12 #' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
13 #' @param kmin integer, minimum number of clusters, by default = 2
14 #' @param kmax integer, maximum number of clusters, by default = 10
15 #' @param rank.min integer, minimum rank in the low rank procedure, by default = 1
16 #' @param rank.max integer, maximum rank in the low rank procedure, by default = 5
17 #' @param ncores_outer Number of cores for the outer loop on k
18 #' @param ncores_inner Number of cores for the inner loop on lambda
19 #' @param thresh real, threshold to say a variable is relevant, by default = 1e-8
20 #' @param size_coll_mod (Maximum) size of a collection of models
21 #' @param fast TRUE to use compiled C code, FALSE for R code only
22 #' @param verbose TRUE to show some execution traces
23 #'
24 #' @return a list with estimators of parameters
25 #'
26 #' @examples
27 #' #TODO: a few examples
28 #' @export
29 valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mini = 10,
30 maxi = 50, eps = 1e-04, kmin = 2, kmax = 3, rank.min = 1, rank.max = 5, ncores_outer = 1,
31 ncores_inner = 1, thresh = 1e-08, size_coll_mod = 10, fast = TRUE, verbose = FALSE,
32 plot = TRUE)
33 {
34 p <- dim(X)[2]
35 m <- dim(Y)[2]
36 n <- dim(X)[1]
38 if (verbose)
39 print("main loop: over all k and all lambda")
41 if (ncores_outer > 1) {
42 cl <- parallel::makeCluster(ncores_outer, outfile = "")
43 parallel::clusterExport(cl = cl, envir = environment(), varlist = c("X",
44 "Y", "procedure", "selecMod", "gamma", "mini", "maxi", "eps", "kmin",
45 "kmax", "rank.min", "rank.max", "ncores_outer", "ncores_inner", "thresh",
46 "size_coll_mod", "verbose", "p", "m"))
47 }
49 # Compute models with k components
50 computeModels <- function(k)
51 {
52 if (ncores_outer > 1)
55 if (verbose)
56 print(paste("Parameters initialization for k =", k))
57 # smallEM initializes parameters by k-means and regression model in each
58 # component, doing this 20 times, and keeping the values maximizing the
59 # likelihood after 10 iterations of the EM algorithm.
60 P <- initSmallEM(k, X, Y, fast)
61 grid_lambda <- computeGridLambda(P\$phiInit, P\$rhoInit, P\$piInit, P\$gamInit,
62 X, Y, gamma, mini, maxi, eps, fast)
63 if (length(grid_lambda) > size_coll_mod)
64 grid_lambda <- grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)]
66 if (verbose)
67 print("Compute relevant parameters")
68 # select variables according to each regularization parameter from the grid:
69 # S\$selected corresponding to selected variables
70 S <- selectVariables(P\$phiInit, P\$rhoInit, P\$piInit, P\$gamInit, mini, maxi,
71 gamma, grid_lambda, X, Y, thresh, eps, ncores_inner, fast)
73 if (procedure == "LassoMLE") {
74 if (verbose)
75 print("run the procedure Lasso-MLE")
76 # compute parameter estimations, with the Maximum Likelihood Estimator,
77 # restricted on selected variables.
78 models <- constructionModelesLassoMLE(P\$phiInit, P\$rhoInit, P\$piInit,
79 P\$gamInit, mini, maxi, gamma, X, Y, eps, S, ncores_inner, fast, verbose)
80 } else {
81 if (verbose)
82 print("run the procedure Lasso-Rank")
83 # compute parameter estimations, with the Low Rank Estimator, restricted on
84 # selected variables.
85 models <- constructionModelesLassoRank(S, k, mini, maxi, X, Y, eps, rank.min,
86 rank.max, ncores_inner, fast, verbose)
87 }
88 # warning! Some models are NULL after running selectVariables
89 models <- models[sapply(models, function(cell) !is.null(cell))]
90 models
91 }
93 # List (index k) of lists (index lambda) of models
94 models_list <-
95 if (ncores_outer > 1) {
96 parLapply(cl, kmin:kmax, computeModels)
97 } else {
98 lapply(kmin:kmax, computeModels)
99 }
100 if (ncores_outer > 1)
101 parallel::stopCluster(cl)
103 if (!requireNamespace("capushe", quietly = TRUE))
104 {
105 warning("'capushe' not available: returning all models")
106 return(models_list)
107 }
109 # Get summary 'tableauRecap' from models
110 tableauRecap <- do.call(rbind, lapply(seq_along(models_list), function(i)
111 {
112 models <- models_list[[i]]
113 # For a collection of models (same k, several lambda):
114 LLH <- sapply(models, function(model) model\$llh[1])
115 k <- length(models[[1]]\$pi)
116 sumPen <- sapply(models, function(model) k * (dim(model\$rho)[1] + sum(model\$phi[,
117 , 1] != 0) + 1) - 1)
118 data.frame(model = paste(i, ".", seq_along(models), sep = ""), pen = sumPen/n,
119 complexity = sumPen, contrast = -LLH)
120 }))
121 tableauRecap <- tableauRecap[which(tableauRecap[, 4] != Inf), ]
123 modSel <- capushe::capushe(tableauRecap, n)
124 indModSel <- if (selecMod == "DDSE")
125 as.numeric(modSel@DDSE@model) else if (selecMod == "Djump")
126 as.numeric(modSel@Djump@model) else if (selecMod == "BIC")
127 modSel@BIC_capushe\$model else if (selecMod == "AIC")
128 modSel@AIC_capushe\$model
130 mod <- as.character(tableauRecap[indModSel, 1])
131 listMod <- as.integer(unlist(strsplit(mod, "[.]")))
132 modelSel <- models_list[[listMod[1]]][[listMod[2]]]
134 ## Affectations
135 Gam <- matrix(0, ncol = length(modelSel\$pi), nrow = n)
136 for (i in 1:n)
137 {
138 for (r in 1:length(modelSel\$pi))
139 {
140 sqNorm2 <- sum((Y[i, ] %*% modelSel\$rho[, , r] - X[i, ] %*% modelSel\$phi[, , r])^2)
141 Gam[i, r] <- modelSel\$pi[r] * exp(-0.5 * sqNorm2) * det(modelSel\$rho[, , r])
142 }
143 }
144 Gam <- Gam/rowSums(Gam)
145 modelSel\$affec <- apply(Gam, 1, which.max)
146 modelSel\$proba <- Gam
148 if (plot)
149 print(plot_valse(X, Y, modelSel, n))
151 return(modelSel)
152 }