0

我正在使用mlr3一系列软件包和超频带方法来调整机器学习模型。一切进展顺利，但我无法弄清楚如何预测使用超频带找到新数据的最佳配置。

是否可以直接使用存储在结果中的信息来执行此操作instance- 或者我是否需要提取最佳配置（即instance$result），然后使用这些参数拟合一个新模型，然后我可以用它来预测？

在下面的示例中（从 mlr3 书中借用）如何使用存储的信息instance来预测新数据？

library(paradox)
library(mlr3tuning)
#> Loading required package: mlr3
library(mlr3hyperband)
library(mlr3pipelines)
set.seed(123)

# extend "classif.rpart" with "subsampling" as preprocessing step
ll = po("subsample") %>>% lrn("classif.rpart")

# extend hyperparameters of "classif.rpart" with subsampling fraction as budget
search_space = ps(
  classif.rpart.cp = p_dbl(lower = 0.001, upper = 0.1),
  classif.rpart.minsplit = p_int(lower = 1, upper = 10),
  subsample.frac = p_dbl(lower = 0.1, upper = 1, tags = "budget")
)

instance = TuningInstanceSingleCrit$new(
  task = tsk("iris"),
  learner = ll,
  resampling = rsmp("holdout"),
  measure = msr("classif.ce"),
  terminator = trm("none"), # hyperband terminates itself
  search_space = search_space
)

tuner = tnr("hyperband", eta = 3)
tuner$optimize(instance)
#> INFO  [11:33:32.366] [bbotk] Starting to optimize 3 parameter(s) with '<TunerHyperband>' and '<TerminatorNone> [list()]' 
#> INFO  [11:33:32.407] [bbotk] Amount of brackets to be evaluated = 3,  
#> INFO  [11:33:32.413] [bbotk] Start evaluation of bracket 1 
#> INFO  [11:33:32.417] [bbotk] Training 9 configs with budget of 0.111111 for each 
#> INFO  [11:33:32.418] [bbotk] Evaluating 9 configuration(s) 
#> INFO  [11:33:32.561] [mlr3]  Running benchmark with 9 resampling iterations 
#> INFO  [11:33:32.635] [mlr3]  Applying learner 'subsample.classif.rpart' on task 'iris' (iter 1/1) 
#> INFO  [11:33:32.700] [mlr3]  Applying learner 'subsample.classif.rpart' on task 'iris' (iter 1/1) 


### OUTPUT DELETED FOR CLARITY ###
 
#> INFO  [11:33:34.564] [bbotk] Finished optimizing after 22 evaluation(s) 
#> INFO  [11:33:34.565] [bbotk] Result: 
#> INFO  [11:33:34.566] [bbotk]  classif.rpart.cp classif.rpart.minsplit subsample.frac learner_param_vals 
#> INFO  [11:33:34.566] [bbotk]        0.07348139                      5      0.1111111          <list[6]> 
#> INFO  [11:33:34.566] [bbotk]   x_domain classif.ce 
#> INFO  [11:33:34.566] [bbotk]  <list[3]>       0.02
#>    classif.rpart.cp classif.rpart.minsplit subsample.frac learner_param_vals
#> 1:       0.07348139                      5      0.1111111          <list[6]>
#>     x_domain classif.ce
#> 1: <list[3]>       0.02

instance$result
#>    classif.rpart.cp classif.rpart.minsplit subsample.frac learner_param_vals
#> 1:       0.07348139                      5      0.1111111          <list[6]>
#>     x_domain classif.ce
#> 1: <list[3]>       0.02

由reprex 包于 2021-04-07 创建(v1.0.0)

4

0 回答 0