387d55329652f5c13a583f4cd710a2cb7fc9c613
[valse.git] / pkg / R / main.R
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 grid_lambda, a vector with regularization parameters if known, by default numeric(0)
21 #' @param size_coll_mod (Maximum) size of a collection of models
22 #' @param fast TRUE to use compiled C code, FALSE for R code only
23 #' @param verbose TRUE to show some execution traces
24 #'
25 #' @return a list with estimators of parameters
26 #'
27 #' @examples
28 #' #TODO: a few examples
29 #' @export
30 valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mini = 10,
31 maxi = 50, eps = 1e-04, kmin = 2, kmax = 3, rank.min = 1, rank.max = 5, ncores_outer = 1,
32 ncores_inner = 1, thresh = 1e-08, grid_lambda = numeric(0), size_coll_mod = 10,
33 fast = TRUE, verbose = FALSE, plot = TRUE)
34 {
35 n <- nrow(X)
36 p <- ncol(X)
37 m <- ncol(Y)
38
39 if (verbose)
40 print("main loop: over all k and all lambda")
41
42 if (ncores_outer > 1) {
43 cl <- parallel::makeCluster(ncores_outer, outfile = "")
44 parallel::clusterExport(cl = cl, envir = environment(), varlist = c("X",
45 "Y", "procedure", "selecMod", "gamma", "mini", "maxi", "eps", "kmin",
46 "kmax", "rank.min", "rank.max", "ncores_outer", "ncores_inner", "thresh",
47 "size_coll_mod", "verbose", "p", "m"))
48 }
49
50 # Compute models with k components
51 computeModels <- function(k)
52 {
53 if (ncores_outer > 1)
54 require("valse") #nodes start with an empty environment
55
56 if (verbose)
57 print(paste("Parameters initialization for k =", k))
58 # smallEM initializes parameters by k-means and regression model in each
59 # component, doing this 20 times, and keeping the values maximizing the
60 # likelihood after 10 iterations of the EM algorithm.
61 P <- initSmallEM(k, X, Y, fast)
62 if (length(grid_lambda) == 0)
63 {
64 grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit,
65 X, Y, gamma, mini, maxi, eps, fast)
66 }
67 if (length(grid_lambda) > size_coll_mod)
68 grid_lambda <- grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)]
69
70 if (verbose)
71 print("Compute relevant parameters")
72 # select variables according to each regularization parameter from the grid:
73 # S$selected corresponding to selected variables
74 S <- selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi,
75 gamma, grid_lambda, X, Y, thresh, eps, ncores_inner, fast)
76
77 if (procedure == "LassoMLE") {
78 if (verbose)
79 print("run the procedure Lasso-MLE")
80 # compute parameter estimations, with the Maximum Likelihood Estimator,
81 # restricted on selected variables.
82 models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit,
83 P$gamInit, mini, maxi, gamma, X, Y, eps, S, ncores_inner, fast, verbose)
84 } else {
85 if (verbose)
86 print("run the procedure Lasso-Rank")
87 # compute parameter estimations, with the Low Rank Estimator, restricted on
88 # selected variables.
89 models <- constructionModelesLassoRank(S, k, mini, maxi, X, Y, eps, rank.min,
90 rank.max, ncores_inner, fast, verbose)
91 }
92 # warning! Some models are NULL after running selectVariables
93 models <- models[sapply(models, function(cell) !is.null(cell))]
94 models
95 }
96
97 # List (index k) of lists (index lambda) of models
98 models_list <-
99 if (ncores_outer > 1) {
100 parLapply(cl, kmin:kmax, computeModels)
101 } else {
102 lapply(kmin:kmax, computeModels)
103 }
104 if (ncores_outer > 1)
105 parallel::stopCluster(cl)
106
107 if (!requireNamespace("capushe", quietly = TRUE))
108 {
109 warning("'capushe' not available: returning all models")
110 return(models_list)
111 }
112
113 # Get summary 'tableauRecap' from models
114 tableauRecap <- do.call(rbind, lapply(seq_along(models_list), function(i)
115 {
116 models <- models_list[[i]]
117 # For a collection of models (same k, several lambda):
118 LLH <- sapply(models, function(model) model$llh[1])
119 k <- length(models[[1]]$pi)
120 sumPen <- sapply(models, function(model) k * (dim(model$rho)[1] + sum(model$phi[,
121 , 1] != 0) + 1) - 1)
122 data.frame(model = paste(i, ".", seq_along(models), sep = ""), pen = sumPen/n,
123 complexity = sumPen, contrast = -LLH)
124 }))
125 tableauRecap <- tableauRecap[which(tableauRecap[, 4] != Inf), ]
126
127 if (verbose == TRUE)
128 print(tableauRecap)
129 modSel <- capushe::capushe(tableauRecap, n)
130 indModSel <- if (selecMod == "DDSE")
131 {
132 as.numeric(modSel@DDSE@model)
133 } else if (selecMod == "Djump")
134 {
135 as.numeric(modSel@Djump@model)
136 } else if (selecMod == "BIC")
137 {
138 modSel@BIC_capushe$model
139 } else if (selecMod == "AIC")
140 {
141 modSel@AIC_capushe$model
142 }
143
144 listMod <- as.integer(unlist(strsplit(as.character(indModSel), "[.]")))
145 modelSel <- models_list[[listMod[1]]][[listMod[2]]]
146 modelSel$tableau <- tableauRecap
147
148 if (plot)
149 print(plot_valse(X, Y, modelSel, n))
150
151 return(modelSel)
152 }