Open
Description
The problem
I am getting an error message when implementing tidymodels functions for xgboost boosted tree model with GPU acceleration. Error reports problem with evals parameter in xgb.train
Reproducible example
Utilizing GPU-enabled xgboost version 2.1.3, accessed from Releases.
Package installation:
# Build and install xgboost with GPU support
wget https://github.com/dmlc/xgboost/releases/download/v2.1.3/xgboost_r_gpu_linux_2.1.3.tar.gz
Rscript -e "install.packages(c('data.table', 'jsonlite'))"
R CMD INSTALL ./xgboost_r_gpu_linux_2.1.3.tar.gz
Reprex with credit_data example data:
> library(xgboost); library(tibble); library(rsample); library(dplyr); library(purrr); library(parsnip); library(recipes); library(workflows); library(dials); library(tune); library(yardstick); library(tidymodels)
> data(credit_data, package = "modeldata")
> credit <- credit_data |> tibble::as_tibble()
> credit_split <- rsample::initial_split(
credit, prop = 0.8, strata = "Status"
)
> train <- rsample::training(credit_split)
test <- rsample::testing(credit_split)
> cv_split <- rsample::vfold_cv(
train, v = 5, repeats = 2, strata = "Status"
)
> scaler <- train |>
dplyr::count(Status) |>
dplyr::pull(n) |>
purrr::reduce(`/`)
> xg_spec <- parsnip::boost_tree(
mode = "classification",
trees = parsnip::tune(),
tree_depth = parsnip::tune(),
sample_size = parsnip::tune()
) |>
parsnip::set_engine(
"xgboost",
params = list(tree_method = "gpu_hist"),
scale_pos_weight = scaler
)
> rec_xg_flow <- recipes::recipe(Status ~ ., data = train) |>
recipes::step_unknown(
all_nominal_predictors(), new_level = "missing"
) |>
recipes::step_novel(all_nominal_predictors(), new_level = "Unseen") |>
recipes::step_other(all_nominal_predictors(), other = "Misc") |>
recipes::step_dummy(all_nominal_predictors(), one_hot = TRUE)
> xg_flow <- workflows::workflow(
preprocessor = rec_xg_flow, spec = xg_spec
)
> xg_trees <- dials::trees(range = c(10, 300))
xg_tree_depth <- dials::tree_depth(range = c(2, 8))
xg_sample_size <- dials::sample_prop(range = c(0.3, 1.0))
xg_params <- dials::parameters(xg_trees, xg_tree_depth, xg_sample_size)
> xg_tune <- tune::tune_grid(
xg_flow,
resamples = cv_split,
param_info = xg_params,
metrics = yardstick::metric_set(
yardstick::roc_auc, yardstick::accuracy
),
grid = 30,
control = tune::control_grid(allow_par = TRUE, save_pred = TRUE)
)
→ A | error: <text>:1:10: unexpected '<'
1: evals <- <
^
There were issues with some computations A: x300
Warning message:
All models failed. Run `show_notes(.Last.tune.result)` for more information.
> tune::show_notes(.Last.tune.result)
unique notes:
───────────────────────────
<text>:1:10: unexpected '<'
1: evals <- <
^Reprex derived from GPU Computing with R presentation (slides 61 - 75)
@sigmafelix @kyle-messier