1

我对 mlr3 相当陌生，并且在获取调整后的超参数（来自每个交叉验证）以及使用 AutoTuner 方法（利用嵌套重采样）优化的超参数方面都遇到了问题。我的理解是，在 AutoTuner 上应用重采样功能后，我们应该能够从每次迭代中看到单独调整的超参数。

为了证明这一点 - 我使用网站 ( https://mlr3gallery.mlr-org.com/house-prices-in-king-county/ ) 上提供的 mlr3 示例，在 Linux 服务器和 Windows 机器上进行了测试。更具体地说，我正在查看 xgboost 参数调整部分 - 代码如下：

library(mlr3)
library(mlr3learners)
library(mlr3tuning)
library(paradox)

# load data
data("kc_housing", package = "mlr3data")

tsk = TaskRegr$new("sales", kc_housing[-1], target = "price")
set.seed(4411)
train.idx = sample(seq_len(tsk$nrow), 0.7 * tsk$nrow)
test.idx = setdiff(seq_len(tsk$nrow), train.idx)
task_train = tsk$clone()$filter(train.idx)
task_test  = tsk$clone()$filter(test.idx)

set.seed(444L)
lrn_xgb = lrn("regr.xgboost")

# Define the ParamSet
ps = paradox::ParamSet$new(
  params = list(
    ParamDbl$new(id = "eta", lower = 0.2, upper = .4),
    ParamDbl$new(id = "min_child_weight", lower = 1, upper = 20),
    ParamDbl$new(id = "subsample", lower = .7, upper = .8),
    ParamDbl$new(id = "colsample_bytree",  lower = .9, upper = 1),
    ParamDbl$new(id = "colsample_bylevel", lower = .5, upper = .7),
    ParamInt$new(id = "nrounds", lower = 1L, upper = 25)
  ))

# Define the cross validation
cv3 = rsmp("cv", folds = 3)
# Define the Terminator
terminator = term("evals", n_evals = 5)
at = AutoTuner$new(learner = lrn_xgb, 
                   resampling = rsmp("holdout"), 
                   measures = msr("regr.mse"), 
                   tune_ps = ps,
                   terminator = terminator, 
                   tuner = tnr("random_search"))

res = resample(task = task_train, at, cv3)
sapply(res$learners, function(x) x$param_set$values)

下面是 sapply 的输出

        [,1] [,2] [,3]
nrounds 1    1    1   
verbose 0    0    0

会话环境（适用于 Windows 机器）

> sessionInfo()
R version 3.6.3 (2020-02-29)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 18363)

Matrix products: default

locale:
[1] LC_COLLATE=English_Australia.1252  LC_CTYPE=English_Australia.1252   
[3] LC_MONETARY=English_Australia.1252 LC_NUMERIC=C                      
[5] LC_TIME=English_Australia.1252    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] paradox_0.1.0      mlr3tuning_0.1.2   mlr3learners_0.1.6 mlr3_0.1.8        

loaded via a namespace (and not attached):
 [1] lgr_0.3.3          lattice_0.20-38    mlr3misc_0.1.8     digest_0.6.20      crayon_1.3.4      
 [6] grid_3.6.3         R6_2.4.0           mlr3measures_0.1.2 backports_1.1.4    magrittr_1.5      
[11] stringi_1.4.3      uuid_0.1-4         data.table_1.12.6  rstudioapi_0.10    Matrix_1.2-18     
[16] checkmate_2.0.0    xgboost_0.90.0.2   tools_3.6.3        compiler_3.6.3
4

1 回答 1

3

目前，您需要store_models = TRUE在resample()调用过程中专门设置将调优结果存储在AutoTuner.

我们将来可能会简化这种行为，因为$tuning_result即使store_tuning_instance = TRUE在AutoTuner.

library(mlr3)
library(paradox)
library(mlr3tuning)
lgr::get_logger("mlr3")$set_threshold("warn")
task = tsk("iris")
learner = lrn("classif.rpart")
resampling = rsmp("holdout")
measures = msr("classif.ce")
param_set = ParamSet$new(
  params = list(ParamDbl$new("cp", lower = 0.001, upper = 0.1)))

terminator = term("evals", n_evals = 5)
tuner = tnr("grid_search")
at = AutoTuner$new(learner, resampling, measures, param_set, terminator, tuner)

at$train(task)
# tuning result exists
at$tuning_result
#> $tune_x
#> $tune_x$cp
#> [1] 0.067
#> 
#> 
#> $params
#> $params$xval
#> [1] 0
#> 
#> $params$cp
#> [1] 0.067
#> 
#> 
#> $perf
#> classif.ce 
#>       0.08

res = resample(task = task, at, rsmp("cv", folds = 3), store_models = TRUE)
lapply(res$learners, function(x) x$tuning_result)
#> [[1]]
#> [[1]]$tune_x
#> [[1]]$tune_x$cp
#> [1] 0.012
#> 
#> 
#> [[1]]$params
#> [[1]]$params$xval
#> [1] 0
#> 
#> [[1]]$params$cp
#> [1] 0.012
#> 
#> 
#> [[1]]$perf
#> classif.ce 
#> 0.09090909 
#> 
#> 
#> [[2]]
#> [[2]]$tune_x
#> [[2]]$tune_x$cp
#> [1] 0.078
#> 
#> 
#> [[2]]$params
#> [[2]]$params$xval
#> [1] 0
#> 
#> [[2]]$params$cp
#> [1] 0.078
#> 
#> 
#> [[2]]$perf
#> classif.ce 
#> 0.09090909 
#> 
#> 
#> [[3]]
#> [[3]]$tune_x
#> [[3]]$tune_x$cp
#> [1] 0.045
#> 
#> 
#> [[3]]$params
#> [[3]]$params$xval
#> [1] 0
#> 
#> [[3]]$params$cp
#> [1] 0.045
#> 
#> 
#> [[3]]$perf
#> classif.ce 
#> 0.06060606

由reprex 包（v0.3.0）于 2020-03-20 创建

于 2020-03-20T00:30:47.420 回答