X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2Fmain.R;h=13df89fddad635010a1ab0128fd7c23e54df5efe;hp=fecf51979584ffcb2cbe964839d7cda737ce4fc0;hb=fb3557f39487d9631ffde30f20b70938d2a6ab0c;hpb=a3cbbaea1cc3c107e5ca62ed1ffe7b9499de0a91 diff --git a/pkg/R/main.R b/pkg/R/main.R index fecf519..13df89f 100644 --- a/pkg/R/main.R +++ b/pkg/R/main.R @@ -1,4 +1,4 @@ -#' valse +#' runValse #' #' Main function #' @@ -17,72 +17,90 @@ #' @param ncores_outer Number of cores for the outer loop on k #' @param ncores_inner Number of cores for the inner loop on lambda #' @param thresh real, threshold to say a variable is relevant, by default = 1e-8 +#' @param grid_lambda, a vector with regularization parameters if known, by default numeric(0) #' @param size_coll_mod (Maximum) size of a collection of models #' @param fast TRUE to use compiled C code, FALSE for R code only #' @param verbose TRUE to show some execution traces +#' @param plot TRUE to plot the selected models after run #' -#' @return a list with estimators of parameters +#' @return +#' The selected model if enough data are available to estimate it, +#' or a list of models otherwise. #' #' @examples -#' #TODO: a few examples +#' n = 50; m = 10; p = 5 +#' beta = array(0, dim=c(p,m,2)) +#' beta[,,1] = 1 +#' beta[,,2] = 2 +#' data = generateXY(n, c(0.4,0.6), rep(0,p), beta, diag(0.5, p), diag(0.5, m)) +#' X = data$X +#' Y = data$Y +#' res = runValse(X, Y) +#' X <- matrix(runif(100), nrow=50) +#' Y <- matrix(runif(100), nrow=50) +#' res = runValse(X, Y) +#' #' @export -valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mini = 10, - maxi = 50, eps = 1e-04, kmin = 2, kmax = 3, rank.min = 1, rank.max = 5, ncores_outer = 1, - ncores_inner = 1, thresh = 1e-08, size_coll_mod = 10, fast = TRUE, verbose = FALSE, - plot = TRUE) +runValse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mini = 10, + maxi = 50, eps = 1e-04, kmin = 2, kmax = 3, rank.min = 1, rank.max = 5, ncores_outer = 1, + ncores_inner = 1, thresh = 1e-08, grid_lambda = numeric(0), size_coll_mod = 10, + fast = TRUE, verbose = FALSE, plot = TRUE) { - p <- dim(X)[2] - m <- dim(Y)[2] - n <- dim(X)[1] + n <- nrow(X) + p <- ncol(X) + m <- ncol(Y) - if (verbose) + if (verbose) print("main loop: over all k and all lambda") if (ncores_outer > 1) { cl <- parallel::makeCluster(ncores_outer, outfile = "") - parallel::clusterExport(cl = cl, envir = environment(), varlist = c("X", - "Y", "procedure", "selecMod", "gamma", "mini", "maxi", "eps", "kmin", - "kmax", "rank.min", "rank.max", "ncores_outer", "ncores_inner", "thresh", + parallel::clusterExport(cl = cl, envir = environment(), varlist = c("X", + "Y", "procedure", "selecMod", "gamma", "mini", "maxi", "eps", "kmin", + "kmax", "rank.min", "rank.max", "ncores_outer", "ncores_inner", "thresh", "size_coll_mod", "verbose", "p", "m")) } # Compute models with k components computeModels <- function(k) { - if (ncores_outer > 1) - require("valse") #nodes start with an empty environment + if (ncores_outer > 1) + require("valse") #nodes start with an empty environment - if (verbose) + if (verbose) print(paste("Parameters initialization for k =", k)) # smallEM initializes parameters by k-means and regression model in each # component, doing this 20 times, and keeping the values maximizing the # likelihood after 10 iterations of the EM algorithm. P <- initSmallEM(k, X, Y, fast) - grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, - X, Y, gamma, mini, maxi, eps, fast) - if (length(grid_lambda) > size_coll_mod) + if (length(grid_lambda) == 0) + { + grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, + X, Y, gamma, mini, maxi, eps, fast) + } + if (length(grid_lambda) > size_coll_mod) grid_lambda <- grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)] - if (verbose) + if (verbose) print("Compute relevant parameters") # select variables according to each regularization parameter from the grid: # S$selected corresponding to selected variables - S <- selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, + S <- selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, gamma, grid_lambda, X, Y, thresh, eps, ncores_inner, fast) if (procedure == "LassoMLE") { - if (verbose) + if (verbose) print("run the procedure Lasso-MLE") # compute parameter estimations, with the Maximum Likelihood Estimator, # restricted on selected variables. - models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, + models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, gamma, X, Y, eps, S, ncores_inner, fast, verbose) } else { - if (verbose) + if (verbose) print("run the procedure Lasso-Rank") # compute parameter estimations, with the Low Rank Estimator, restricted on # selected variables. - models <- constructionModelesLassoRank(S, k, mini, maxi, X, Y, eps, rank.min, + models <- constructionModelesLassoRank(S, k, mini, maxi, X, Y, eps, rank.min, rank.max, ncores_inner, fast, verbose) } # warning! Some models are NULL after running selectVariables @@ -97,7 +115,7 @@ valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mi } else { lapply(kmin:kmax, computeModels) } - if (ncores_outer > 1) + if (ncores_outer > 1) parallel::stopCluster(cl) if (!requireNamespace("capushe", quietly = TRUE)) @@ -113,40 +131,37 @@ valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mi # For a collection of models (same k, several lambda): LLH <- sapply(models, function(model) model$llh[1]) k <- length(models[[1]]$pi) - sumPen <- sapply(models, function(model) k * (dim(model$rho)[1] + sum(model$phi[, + sumPen <- sapply(models, function(model) k * (dim(model$rho)[1] + sum(model$phi[, , 1] != 0) + 1) - 1) - data.frame(model = paste(i, ".", seq_along(models), sep = ""), pen = sumPen/n, + data.frame(model = paste(i, ".", seq_along(models), sep = ""), pen = sumPen/n, complexity = sumPen, contrast = -LLH) })) tableauRecap <- tableauRecap[which(tableauRecap[, 4] != Inf), ] + if (verbose) + print(tableauRecap) - modSel <- capushe::capushe(tableauRecap, n) - indModSel <- if (selecMod == "DDSE") - as.numeric(modSel@DDSE@model) else if (selecMod == "Djump") - as.numeric(modSel@Djump@model) else if (selecMod == "BIC") - modSel@BIC_capushe$model else if (selecMod == "AIC") - modSel@AIC_capushe$model - - mod <- as.character(tableauRecap[indModSel, 1]) - listMod <- as.integer(unlist(strsplit(mod, "[.]"))) - modelSel <- models_list[[listMod[1]]][[listMod[2]]] - - ## Affectations - Gam <- matrix(0, ncol = length(modelSel$pi), nrow = n) - for (i in 1:n) - { - for (r in 1:length(modelSel$pi)) + if (nrow(tableauRecap) > 10) { + modSel <- capushe::capushe(tableauRecap, n) + indModSel <- if (selecMod == "DDSE") { - sqNorm2 <- sum((Y[i, ] %*% modelSel$rho[, , r] - X[i, ] %*% modelSel$phi[, , r])^2) - Gam[i, r] <- modelSel$pi[r] * exp(-0.5 * sqNorm2) * det(modelSel$rho[, , r]) + as.numeric(modSel@DDSE@model) + } else if (selecMod == "Djump") + { + as.numeric(modSel@Djump@model) + } else if (selecMod == "BIC") + { + modSel@BIC_capushe$model + } else if (selecMod == "AIC") + { + modSel@AIC_capushe$model } - } - Gam <- Gam/rowSums(Gam) - modelSel$affec <- apply(Gam, 1, which.max) - modelSel$proba <- Gam - - if (plot) - print(plot_valse(X, Y, modelSel, n)) + listMod <- as.integer(unlist(strsplit(as.character(indModSel), "[.]"))) + modelSel <- models_list[[listMod[1]]][[listMod[2]]] + modelSel$models <- tableauRecap - return(modelSel) + if (plot) + print(plot_valse(X, Y, modelSel)) + return(modelSel) + } + tableauRecap }