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.

lightgbm: Regression

# nolint start
library(mlexperiments)
library(mllrnrs)

See https://github.com/kapsner/mllrnrs/blob/main/R/learner_lightgbm.R for implementation details.

Preprocessing

Import and Prepare Data

library(mlbench)
data("BostonHousing")
dataset <- BostonHousing |>
  data.table::as.data.table() |>
  na.omit()

feature_cols <- colnames(dataset)[1:13]
target_col <- "medv"

General Configurations

seed <- 123
if (isTRUE(as.logical(Sys.getenv("_R_CHECK_LIMIT_CORES_")))) {
  # on cran
  ncores <- 2L
} else {
  ncores <- ifelse(
    test = parallel::detectCores() > 4,
    yes = 4L,
    no = ifelse(
      test = parallel::detectCores() < 2L,
      yes = 1L,
      no = parallel::detectCores()
    )
  )
}
options("mlexperiments.bayesian.max_init" = 10L)
options("mlexperiments.optim.lgb.nrounds" = 100L)
options("mlexperiments.optim.lgb.early_stopping_rounds" = 10L)

Generate Training- and Test Data

data_split <- splitTools::partition(
  y = dataset[, get(target_col)],
  p = c(train = 0.7, test = 0.3),
  type = "stratified",
  seed = seed
)

train_x <- model.matrix(
  ~ -1 + .,
  dataset[data_split$train, .SD, .SDcols = feature_cols]
)
train_y <- dataset[data_split$train, get(target_col)]


test_x <- model.matrix(
  ~ -1 + .,
  dataset[data_split$test, .SD, .SDcols = feature_cols]
)
test_y <- dataset[data_split$test, get(target_col)]

Generate Training Data Folds

fold_list <- splitTools::create_folds(
  y = train_y,
  k = 3,
  type = "stratified",
  seed = seed
)

Experiments

Prepare Experiments

# required learner arguments, not optimized
learner_args <- list(
  max_depth = -1L,
  verbose = -1L,
  objective = "regression",
  metric = "l2"
)

# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
predict_args <- NULL
performance_metric <- metric("rmsle")
performance_metric_args <- NULL
return_models <- FALSE

# required for grid search and initialization of bayesian optimization
parameter_grid <- expand.grid(
  bagging_fraction = seq(0.6, 1, .2),
  feature_fraction = seq(0.6, 1, .2),
  min_data_in_leaf = seq(2, 10, 2),
  learning_rate = seq(0.1, 0.2, 0.1),
  num_leaves = seq(2, 20, 4)
)
# reduce to a maximum of 10 rows
if (nrow(parameter_grid) > 10) {
  set.seed(123)
  sample_rows <- sample(seq_len(nrow(parameter_grid)), 10, FALSE)
  parameter_grid <- kdry::mlh_subset(parameter_grid, sample_rows)
}

# required for bayesian optimization
parameter_bounds <- list(
  bagging_fraction = c(0.2, 1),
  feature_fraction = c(0.2, 1),
  min_data_in_leaf = c(2L, 12L),
  learning_rate = c(0.1, 0.2),
  num_leaves =  c(2L, 20L)
)
optim_args <- list(
  iters.n = ncores,
  kappa = 3.5,
  acq = "ucb"
)

Hyperparameter Tuning

tuner <- mlexperiments::MLTuneParameters$new(
  learner = mllrnrs::LearnerLightgbm$new(
    metric_optimization_higher_better = FALSE
  ),
  strategy = "grid",
  ncores = ncores,
  seed = seed
)

tuner$parameter_grid <- parameter_grid
tuner$learner_args <- learner_args
tuner$split_type <- "stratified"

tuner$set_data(
  x = train_x,
  y = train_y
)

tuner_results_grid <- tuner$execute(k = 3)
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> 
#> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%)
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> 
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> 
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> 
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> 
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704
#> 
#> Parameter settings [===============================================================================================] 10/10 (100%)                                                                                                                                  
#> [LightGBM] [Info] Start training from score 22.450000
#> [LightGBM] [Info] Start training from score 22.655319
#> [LightGBM] [Info] Start training from score 22.592704

head(tuner_results_grid)
#>    setting_id metric_optim_mean nrounds bagging_fraction feature_fraction min_data_in_leaf learning_rate num_leaves max_depth
#> 1:          1          13.59085      85              0.6              0.6                4           0.2         18        -1
#> 2:          2          13.75483      55              0.8              1.0               10           0.2          6        -1
#> 3:          3          21.08526      58              0.8              0.8                4           0.1          2        -1
#> 4:          4          13.31343      92              1.0              0.8                4           0.1         10        -1
#> 5:          5          13.86649      80              1.0              0.6                6           0.2         18        -1
#> 6:          6          14.58646     100              1.0              1.0                8           0.1         14        -1
#>    verbose  objective metric
#> 1:      -1 regression     l2
#> 2:      -1 regression     l2
#> 3:      -1 regression     l2
#> 4:      -1 regression     l2
#> 5:      -1 regression     l2
#> 6:      -1 regression     l2

Bayesian Optimization

tuner <- mlexperiments::MLTuneParameters$new(
  learner = mllrnrs::LearnerLightgbm$new(
    metric_optimization_higher_better = FALSE
  ),
  strategy = "bayesian",
  ncores = ncores,
  seed = seed
)

tuner$parameter_grid <- parameter_grid
tuner$parameter_bounds <- parameter_bounds

tuner$learner_args <- learner_args
tuner$optim_args <- optim_args

tuner$split_type <- "stratified"

tuner$set_data(
  x = train_x,
  y = train_y
)

tuner_results_bayesian <- tuner$execute(k = 3)
#> 
#> Registering parallel backend using 4 cores.

head(tuner_results_bayesian)
#>    Epoch setting_id bagging_fraction feature_fraction min_data_in_leaf learning_rate num_leaves gpUtility acqOptimum inBounds
#> 1:     0          1              0.6              0.6                4           0.2         18        NA      FALSE     TRUE
#> 2:     0          2              0.8              1.0               10           0.2          6        NA      FALSE     TRUE
#> 3:     0          3              0.8              0.8                4           0.1          2        NA      FALSE     TRUE
#> 4:     0          4              1.0              0.8                4           0.1         10        NA      FALSE     TRUE
#> 5:     0          5              1.0              0.6                6           0.2         18        NA      FALSE     TRUE
#> 6:     0          6              1.0              1.0                8           0.1         14        NA      FALSE     TRUE
#>    Elapsed     Score metric_optim_mean nrounds errorMessage max_depth verbose  objective metric
#> 1:   1.081 -13.59085          13.59085      85           NA        -1      -1 regression     l2
#> 2:   1.072 -13.75483          13.75483      55           NA        -1      -1 regression     l2
#> 3:   1.044 -21.08526          21.08526      58           NA        -1      -1 regression     l2
#> 4:   1.126 -13.31343          13.31343      92           NA        -1      -1 regression     l2
#> 5:   0.104 -13.86649          13.86649      80           NA        -1      -1 regression     l2
#> 6:   0.106 -14.58646          14.58646     100           NA        -1      -1 regression     l2

k-Fold Cross Validation

validator <- mlexperiments::MLCrossValidation$new(
  learner = mllrnrs::LearnerLightgbm$new(
    metric_optimization_higher_better = FALSE
  ),
  fold_list = fold_list,
  ncores = ncores,
  seed = seed
)

validator$learner_args <- tuner$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(
  x = train_x,
  y = train_y
)

validator_results <- validator$execute()
#> 
#> CV fold: Fold1
#> 
#> CV fold: Fold2
#> 
#> CV fold: Fold3

head(validator_results)
#>     fold performance bagging_fraction feature_fraction min_data_in_leaf learning_rate num_leaves nrounds max_depth verbose
#> 1: Fold1   0.1572748              0.6              0.8                2           0.2         10      34        -1      -1
#> 2: Fold2   0.1770563              0.6              0.8                2           0.2         10      34        -1      -1
#> 3: Fold3   0.1439331              0.6              0.8                2           0.2         10      34        -1      -1
#>     objective metric
#> 1: regression     l2
#> 2: regression     l2
#> 3: regression     l2

Nested Cross Validation

validator <- mlexperiments::MLNestedCV$new(
  learner = mllrnrs::LearnerLightgbm$new(
    metric_optimization_higher_better = FALSE
  ),
  strategy = "grid",
  fold_list = fold_list,
  k_tuning = 3L,
  ncores = ncores,
  seed = seed
)

validator$parameter_grid <- parameter_grid
validator$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(
  x = train_x,
  y = train_y
)

validator_results <- validator$execute()
#> 
#> CV fold: Fold1
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> 
#> 
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> 
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> 
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> 
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> 
#> Parameter settings [===============================================================================================] 10/10 (100%)                                                                                                                                  
#> [LightGBM] [Info] Start training from score 22.387821
#> [LightGBM] [Info] Start training from score 22.485257
#> [LightGBM] [Info] Start training from score 22.476923
#> 
#> CV fold: Fold2
#> CV progress [====================================================================>-----------------------------------] 2/3 ( 67%)
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> 
#> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%)
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> 
#> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%)
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> 
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> 
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> 
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> 
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> 
#> Parameter settings [===============================================================================================] 10/10 (100%)                                                                                                                                  
#> [LightGBM] [Info] Start training from score 22.517722
#> [LightGBM] [Info] Start training from score 22.641401
#> [LightGBM] [Info] Start training from score 22.809677
#> 
#> CV fold: Fold3
#> CV progress [========================================================================================================] 3/3 (100%)
#>                                                                                                                                   
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> [LightGBM] [Warning] No further splits with positive gain, best gain: -inf
#> 
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> 
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> [LightGBM] [Warning] No further splits with positive gain, best gain: -inf
#> 
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846
#> 
#> Parameter settings [===============================================================================================] 10/10 (100%)                                                                                                                                  
#> [LightGBM] [Info] Start training from score 22.496129
#> [LightGBM] [Info] Start training from score 22.728387
#> [LightGBM] [Info] Start training from score 22.553846

head(validator_results)
#>     fold performance nrounds bagging_fraction feature_fraction min_data_in_leaf learning_rate num_leaves max_depth verbose
#> 1: Fold1   0.1856914      99              0.8              0.8                4           0.1          2        -1      -1
#> 2: Fold2   0.1842789      37              0.8              0.6                8           0.1         14        -1      -1
#> 3: Fold3   0.1516625      17              0.6              0.6                4           0.2         18        -1      -1
#>     objective metric
#> 1: regression     l2
#> 2: regression     l2
#> 3: regression     l2

Inner Bayesian Optimization

validator <- mlexperiments::MLNestedCV$new(
  learner = mllrnrs::LearnerLightgbm$new(
    metric_optimization_higher_better = FALSE
  ),
  strategy = "bayesian",
  fold_list = fold_list,
  k_tuning = 3L,
  ncores = ncores,
  seed = seed
)

validator$parameter_grid <- parameter_grid
validator$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 <- TRUE

validator$set_data(
  x = train_x,
  y = train_y
)

validator_results <- validator$execute()
#> 
#> 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 bagging_fraction feature_fraction min_data_in_leaf learning_rate num_leaves nrounds max_depth verbose
#> 1: Fold1   0.1972673        1.0000000        0.2000000                7     0.1000000          2     100        -1      -1
#> 2: Fold2   0.1934754        0.5029800        0.4977050                7     0.1195995          4      52        -1      -1
#> 3: Fold3   0.1391255        0.8050493        0.5902201                2     0.1458152         20      44        -1      -1
#>     objective metric
#> 1: regression     l2
#> 2: regression     l2
#> 3: regression     l2

Holdout Test Dataset Performance

Predict Outcome in Holdout Test Dataset

preds_lightgbm <- mlexperiments::predictions(
  object = validator,
  newdata = test_x
)

Evaluate Performance on Holdout Test Dataset

perf_lightgbm <- mlexperiments::performance(
  object = validator,
  prediction_results = preds_lightgbm,
  y_ground_truth = test_y,
  type = "regression"
)
perf_lightgbm
#>    model performance       mse       msle      mae      mape     rmse     rmsle       rsq      sse
#> 1: Fold1   0.1593611 16.258140 0.02539596 2.700096 0.1230206 4.032138 0.1593611 0.7945966 2520.012
#> 2: Fold2   0.1720557 12.614833 0.02960318 2.629003 0.1329465 3.551737 0.1720557 0.8406257 1955.299
#> 3: Fold3   0.1424064  9.666178 0.02027958 2.226562 0.1101779 3.109048 0.1424064 0.8778787 1498.258

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.