# nolint start
library(mlexperiments)
The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
# nolint start
library(mlexperiments)
See https://github.com/kapsner/mlexperiments/blob/main/R/learner_knn.R for implementation details.
library(mlbench)
data("PimaIndiansDiabetes2")
<- PimaIndiansDiabetes2 |>
dataset ::as.data.table() |>
data.tablena.omit()
<- colnames(dataset)[1:8]
feature_cols <- "diabetes" target_col
<- 123
seed if (isTRUE(as.logical(Sys.getenv("_R_CHECK_LIMIT_CORES_")))) {
# on cran
<- 2L
ncores else {
} <- ifelse(
ncores test = parallel::detectCores() > 4,
yes = 4L,
no = ifelse(
test = parallel::detectCores() < 2L,
yes = 1L,
no = parallel::detectCores()
)
)
}options("mlexperiments.bayesian.max_init" = 10L)
<- splitTools::partition(
data_split y = dataset[, get(target_col)],
p = c(train = 0.7, test = 0.3),
type = "stratified",
seed = seed
)
<- model.matrix(
train_x ~ -1 + .,
$train, .SD, .SDcols = feature_cols]
dataset[data_split
)<- as.integer(dataset[data_split$train, get(target_col)]) - 1L
train_y
<- model.matrix(
test_x ~ -1 + .,
$test, .SD, .SDcols = feature_cols]
dataset[data_split
)<- as.integer(dataset[data_split$test, get(target_col)]) - 1L test_y
<- splitTools::create_folds(
fold_list y = train_y,
k = 3,
type = "stratified",
seed = seed
)
# required learner arguments, not optimized
<- list(
learner_args l = 2,
test = parse(text = "fold_test$x"),
use.all = FALSE
)
# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
<- list(type = "response")
predict_args <- metric("acc")
performance_metric <- NULL
performance_metric_args <- FALSE
return_models
# required for grid search and initialization of bayesian optimization
<- expand.grid(
parameter_grid k = seq(4, 68, 6)
)# reduce to a maximum of 10 rows
if (nrow(parameter_grid) > 10) {
set.seed(123)
<- sample(seq_len(nrow(parameter_grid)), 10, FALSE)
sample_rows <- kdry::mlh_subset(parameter_grid, sample_rows)
parameter_grid
}
# required for bayesian optimization
<- list(k = c(2L, 80L))
parameter_bounds <- list(
optim_args iters.n = ncores,
kappa = 3.5,
acq = "ucb"
)
<- mlexperiments::MLTuneParameters$new(
tuner learner = LearnerKnn$new(),
strategy = "grid",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner$learner_args <- learner_args
tuner$split_type <- "stratified"
tuner
$set_data(
tunerx = train_x,
y = train_y
)
<- tuner$execute(k = 3)
tuner_results_grid
head(tuner_results_grid)
#> setting_id metric_optim_mean k l use.all
#> 1: 1 0.2224638 16 2 FALSE
#> 2: 2 0.2628019 64 2 FALSE
#> 3: 3 0.2297907 10 2 FALSE
#> 4: 4 0.2371981 34 2 FALSE
#> 5: 5 0.2627214 58 2 FALSE
#> 6: 6 0.2444444 28 2 FALSE
<- mlexperiments::MLTuneParameters$new(
tuner learner = LearnerKnn$new(),
strategy = "bayesian",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner$parameter_bounds <- parameter_bounds
tuner
$learner_args <- learner_args
tuner$optim_args <- optim_args
tuner
$split_type <- "stratified"
tuner
$set_data(
tunerx = train_x,
y = train_y
)
<- tuner$execute(k = 3)
tuner_results_bayesian #> Registering parallel backend using 4 cores.
head(tuner_results_bayesian)
#> Epoch setting_id k gpUtility acqOptimum inBounds Elapsed Score metric_optim_mean errorMessage l use.all
#> 1: 0 1 16 NA FALSE TRUE 0.024 -0.2262480 0.2262480 NA 2 FALSE
#> 2: 0 2 64 NA FALSE TRUE 0.026 -0.2700483 0.2700483 NA 2 FALSE
#> 3: 0 3 10 NA FALSE TRUE 0.023 -0.2370370 0.2370370 NA 2 FALSE
#> 4: 0 4 34 NA FALSE TRUE 0.025 -0.2262480 0.2262480 NA 2 FALSE
#> 5: 0 5 58 NA FALSE TRUE 0.008 -0.2735910 0.2735910 NA 2 FALSE
#> 6: 0 6 28 NA FALSE TRUE 0.006 -0.2589372 0.2589372 NA 2 FALSE
<- mlexperiments::MLCrossValidation$new(
validator learner = LearnerKnn$new(),
fold_list = fold_list,
ncores = ncores,
seed = seed
)
$learner_args <- tuner$results$best.setting[-1]
validator
$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models
validator
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> CV fold: Fold1
#>
#> CV fold: Fold2
#>
#> CV fold: Fold3
head(validator_results)
#> fold performance k l use.all
#> 1: Fold1 0.7934783 16 2 FALSE
#> 2: Fold2 0.7391304 16 2 FALSE
#> 3: Fold3 0.8000000 16 2 FALSE
<- mlexperiments::MLNestedCV$new(
validator learner = LearnerKnn$new(),
strategy = "grid",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator
$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models
validator
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> CV fold: Fold1
#>
#> CV fold: Fold2
#>
#> CV fold: Fold3
#> CV progress [==========================================================================================================] 3/3 (100%)
head(validator_results)
#> fold performance k l use.all
#> 1: Fold1 0.7391304 22 2 FALSE
#> 2: Fold2 0.7391304 28 2 FALSE
#> 3: Fold3 0.7666667 34 2 FALSE
<- mlexperiments::MLNestedCV$new(
validator learner = LearnerKnn$new(),
strategy = "bayesian",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator
$parameter_bounds <- parameter_bounds
validator$optim_args <- optim_args
validator
$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models
validator
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> CV fold: Fold1
#>
#> Registering parallel backend using 4 cores.
#>
#> CV fold: Fold2
#> CV progress [======================================================================>-----------------------------------] 2/3 ( 67%)
#>
#> Registering parallel backend using 4 cores.
#>
#> CV fold: Fold3
#> CV progress [==========================================================================================================] 3/3 (100%)
#>
#> Registering parallel backend using 4 cores.
head(validator_results)
#> fold performance k l use.all
#> 1: Fold1 0.7391304 22 2 FALSE
#> 2: Fold2 0.7934783 10 2 FALSE
#> 3: Fold3 0.7888889 10 2 FALSE
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.