Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Use cl to calculate parallel #48

Merged
merged 2 commits into from
Jul 30, 2024
Merged

Use cl to calculate parallel #48

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a969d33
Replace `parallel` with `cl` (closes #40)
wleoncio Jul 30, 2024
69e1ba2
Increment version number to 0.0.0.9019
wleoncio Jul 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion DESCRIPTION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
Package: MADMMplasso
Title: Multi Variate Multi Response 'ADMM' with Interaction Effects
Version: 0.0.0.9018
Version: 0.0.0.9019
Authors@R:
c(
person(
Expand Down
12 changes: 6 additions & 6 deletions R/MADMMplasso.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,7 @@
#' @param my_print Should information form each ADMM iteration be printed along the way? This prints the dual and primal residuals
#' @param alph an overrelaxation parameter in \[1, 1.8\]. The implementation is borrowed from Stephen Boyd's \href{https://stanford.edu/~boyd/papers/admm/lasso/lasso.html}{MATLAB code}
#' @param tree The results from the hierarchical clustering of the response matrix. The easy way to obtain this is by using the function (tree_parms) which gives a default clustering. However, user decide on a specific structure and then input a tree that follows such structure.
#' @param parallel should parallel processing be used or not? If set to `TRUE`, pal should be set to `FALSE`.
#' @param pal Should the lapply function be applied for an alternative quicker optimization when there no parallel package available?
#' @param pal Should the lapply function be applied for an alternative to parallelization.
#' @param tol threshold for the non-zero coefficients
#' @param cl The number of CPUs to be used for parallel processing
#' @param legacy If \code{TRUE}, use the R version of the algorithm
Expand Down Expand Up @@ -49,10 +48,11 @@

#' @example inst/examples/MADMMplasso_example.R
#' @export
MADMMplasso <- function(X, Z, y, alpha, my_lambda = NULL, lambda_min = 0.001, max_it = 50000, e.abs = 1E-3, e.rel = 1E-3, maxgrid, nlambda, rho = 5, my_print = FALSE, alph = 1.8, tree, parallel = TRUE, pal = !parallel, gg = NULL, tol = 1E-4, cl = 4, legacy = FALSE) {
if (parallel && pal) {
stop("parallel and pal cannot be TRUE at the same time")
}
MADMMplasso <- function(X, Z, y, alpha, my_lambda = NULL, lambda_min = 0.001, max_it = 50000, e.abs = 1E-3, e.rel = 1E-3, maxgrid, nlambda, rho = 5, my_print = FALSE, alph = 1.8, tree, pal = cl == 1L, gg = NULL, tol = 1E-4, cl = detectCores() - 1L, legacy = FALSE) {
# Recalculating the number of CPUs
cl <- ifelse(pal, 1L, cl) # cl is irrelevant if pal = TRUE
parallel <- cl > 1L

N <- nrow(X)

p <- ncol(X)
Expand Down
4 changes: 2 additions & 2 deletions R/cv_MADMMplasso.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#' @return results containing the CV values
#' @example inst/examples/cv_MADMMplasso_example.R
#' @export
cv_MADMMplasso <- function(fit, nfolds, X, Z, y, alpha = 0.5, lambda = fit$Lambdas, max_it = 50000, e.abs = 1E-3, e.rel = 1E-3, nlambda, rho = 5, my_print = FALSE, alph = 1, foldid = NULL, parallel = TRUE, pal = FALSE, gg = c(7, 0.5), TT, tol = 1E-4, cl = 2, legacy = FALSE) {
cv_MADMMplasso <- function(fit, nfolds, X, Z, y, alpha = 0.5, lambda = fit$Lambdas, max_it = 50000, e.abs = 1E-3, e.rel = 1E-3, nlambda, rho = 5, my_print = FALSE, alph = 1, foldid = NULL, pal = cl == 1L, gg = c(7, 0.5), TT, tol = 1E-4, cl = detectCores() - 1L, legacy = FALSE) {
BIG <- 10e9
no <- nrow(X)
ggg <- vector("list", nfolds)
Expand All @@ -28,7 +28,7 @@ cv_MADMMplasso <- function(fit, nfolds, X, Z, y, alpha = 0.5, lambda = fit$Lambd
print(c("fold,", ii))
oo <- foldid == ii

ggg[[ii]] <- MADMMplasso(X = X[!oo, , drop = FALSE], Z = Z[!oo, , drop = FALSE], y = y[!oo, , drop = FALSE], alpha = alpha, my_lambda = lambda, lambda_min = 0.01, max_it = max_it, e.abs = e.abs, e.rel = e.rel, nlambda = length(lambda[, 1]), rho = rho, tree = TT, my_print = my_print, alph = alph, parallel = parallel, pal = pal, gg = gg, tol = tol, cl = cl, legacy)
ggg[[ii]] <- MADMMplasso(X = X[!oo, , drop = FALSE], Z = Z[!oo, , drop = FALSE], y = y[!oo, , drop = FALSE], alpha = alpha, my_lambda = lambda, lambda_min = 0.01, max_it = max_it, e.abs = e.abs, e.rel = e.rel, nlambda = length(lambda[, 1]), rho = rho, tree = TT, my_print = my_print, alph = alph, pal = pal, gg = gg, tol = tol, cl = cl, legacy)

cv_p <- predict.MADMMplasso(ggg[[ii]], X = X[oo, , drop = FALSE], Z = Z[oo, ], y = y[oo, ])
ggg[[ii]] <- 0
Expand Down
2 changes: 1 addition & 1 deletion inst/examples/MADMMplasso_example.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,6 @@ fit <- MADMMplasso(
X, Z, y,
alpha = alpha, my_lambda = matrix(rep(0.2, ncol(y)), 1),
lambda_min = 0.001, max_it = 5000, e.abs = e.abs, e.rel = e.rel, maxgrid = nlambda,
nlambda = nlambda, rho = 5, tree = TT, my_print = FALSE, alph = TRUE, parallel = FALSE,
nlambda = nlambda, rho = 5, tree = TT, my_print = FALSE, alph = TRUE,
pal = TRUE, gg = gg1, tol = tol, cl = 6
)
11 changes: 4 additions & 7 deletions man/MADMMplasso.Rd
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

9 changes: 3 additions & 6 deletions man/cv_MADMMplasso.Rd
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 2 additions & 2 deletions tests/testthat/test-MADMMplasso.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ fit_C <- MADMMplasso(
X, Z, y,
alpha = alpha, my_lambda = matrix(rep(0.2, ncol(y)), 1),
lambda_min = 0.001, max_it = 5000, e.abs = e.abs, e.rel = e.rel, maxgrid = nlambda,
nlambda = nlambda, rho = 5, tree = TT, my_print = FALSE, alph = 1, parallel = FALSE,
nlambda = nlambda, rho = 5, tree = TT, my_print = FALSE, alph = 1,
pal = TRUE, gg = gg1, tol = tol, cl = 6
)
set.seed(9356219)
Expand All @@ -94,7 +94,7 @@ fit_R <- suppressWarnings(
X, Z, y,
alpha = alpha, my_lambda = matrix(rep(0.2, ncol(y)), 1),
lambda_min = 0.001, max_it = 5000, e.abs = e.abs, e.rel = e.rel, maxgrid = nlambda,
nlambda = nlambda, rho = 5, tree = TT, my_print = FALSE, alph = 1, parallel = FALSE,
nlambda = nlambda, rho = 5, tree = TT, my_print = FALSE, alph = 1,
pal = TRUE, gg = gg1, tol = tol, cl = 6, legacy = TRUE
)
)
Expand Down
20 changes: 7 additions & 13 deletions tests/testthat/test-parallel.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,19 +81,19 @@ mad_wrap <- function(seed = 3398, ...) {
alpha = 0.2, my_lambda = matrix(rep(0.2, ncol(y)), 1),
lambda_min = 0.001, max_it = 5000, e.abs = 1e-4, e.rel = 1e-2, maxgrid = 1L,
nlambda = 1L, rho = 5, tree = TT, my_print = FALSE, alph = 1, gg = gg1,
tol = 1e-3, cl = 2, ...
tol = 1e-3, ...
)
)
}
fit_R <- mad_wrap(legacy = TRUE, parallel = FALSE, pal = FALSE)
fit_C <- mad_wrap(legacy = FALSE, parallel = FALSE, pal = FALSE)
fit_R_pal <- mad_wrap(legacy = TRUE, parallel = FALSE, pal = TRUE)
fit_C_pal <- mad_wrap(legacy = FALSE, parallel = FALSE, pal = TRUE)
fit_R <- mad_wrap(legacy = TRUE, cl = 1L, pal = FALSE)
fit_C <- mad_wrap(legacy = FALSE, cl = 1L, pal = FALSE)
fit_R_pal <- mad_wrap(legacy = TRUE, cl = 1L, pal = TRUE)
fit_C_pal <- mad_wrap(legacy = FALSE, cl = 1L, pal = TRUE)

# Restrict to *nix machines
if (.Platform$OS.type == "unix") {
fit_R_parallel <- mad_wrap(legacy = TRUE, parallel = TRUE, pal = FALSE)
fit_C_parallel <- mad_wrap(legacy = FALSE, parallel = TRUE, pal = FALSE)
fit_R_parallel <- mad_wrap(legacy = TRUE, cl = 2L, pal = FALSE)
fit_C_parallel <- mad_wrap(legacy = FALSE, cl = 2L, pal = FALSE)
}

test_that("results are identical after parallelization", {
Expand All @@ -106,9 +106,3 @@ test_that("results are identical after parallelization", {
expect_identical(fit_C_pal, fit_C_parallel)
}
})

test_that("parallel and pal cannot be both true", {
msg <- "parallel and pal cannot be TRUE at the same time"
expect_error(mad_wrap(legacy = TRUE, parallel = TRUE, pal = TRUE), msg)
expect_error(mad_wrap(legacy = FALSE, parallel = TRUE, pal = TRUE), msg)
})
Loading