I construct a benchmark with 4 graph learners on 1 dataset. The learner_id of the result of the benchmark is so long because I have some preprocessings. How can I set the learner id so that it wouldn't too long. Here's my code:
# step 1 the task
all_plays <- readRDS("../000files/all_plays.rds")
pbp_task <- as_task_classif(all_plays, target="play_type")
split_task <- partition(pbp_task, ratio=0.75)
task_train <- pbp_task$clone()$filter(split_task$train)
task_test <- pbp_task$clone()$filter(split_task$test)
# step 2 the preprocess
pbp_prep <- po("select",
selector = selector_invert(
selector_name(c("half_seconds_remaining","yards_gained","game_id")))
) %>>%
po("colapply",
affect_columns = selector_name(c("posteam","defteam")),
applicator = as.factor) %>>%
po("filter",
filter = mlr3filters::flt("find_correlation"), filter.cutoff=0.3) %>>%
po("scale", scale = F) %>>%
po("removeconstants")
# step 3 learners
rf_glr <- as_learner(pbp_prep %>>% lrn("classif.ranger", predict_type="prob"))
log_glr <-as_learner(pbp_prep %>>% lrn("classif.log_reg", predict_type="prob"))
tree_glr <- as_learner(pbp_prep %>>% lrn("classif.rpart", predict_type="prob"))
kknn_glr <- as_learner(pbp_prep %>>% lrn("classif.kknn", predict_type="prob"))
# step 4 benckmark grid
set.seed(0520)
cv <- rsmp("cv",folds=10)
design <- benchmark_grid(
tasks = task_train,
learners = list(rf_glr,log_glr,tree_glr,kknn_glr),
resampling = cv
)
# step 5 benchmark
bmr <- benchmark(design,store_models = T)
bmr
# learner_id toooo long...
<BenchmarkResult> of 40 rows with 4 resampling runs
nr task_id learner_id resampling_id
1 all_plays select.colapply.find_correlation.scale.removeconstants.randomForest cv
2 all_plays select.colapply.find_correlation.scale.removeconstants.logistic cv
3 all_plays select.colapply.find_correlation.scale.removeconstants.decisionTree cv
4 all_plays select.colapply.find_correlation.scale.removeconstants.kknn cv
iters warnings errors
10 0 0
10 0 0
10 0 0
10 0 0
The learner_id is too long in this result and it's also bad for autoplot(bmr). How can I set the learner_id to make it short?
Thank you very much.
You can do:
library(mlr3verse)
#> Loading required package: mlr3
learner = as_learner(po("pca") %>>% po("learner", lrn("regr.rpart")))
learner$id = "my_id"
print(learner)
#> <GraphLearner:my_id>
#> * Model: -
#> * Parameters: regr.rpart.xval=0
#> * Packages: mlr3, mlr3pipelines, rpart
#> * Predict Types: [response], se, distr
#> * Feature Types: logical, integer, numeric, character, factor, ordered,
#> POSIXct
#> * Properties: featureless, hotstart_backward, hotstart_forward,
#> importance, loglik, missings, oob_error, selected_features, weights
Created on 2022-07-22 by the reprex package (v2.0.1)