Benchmark Multiple Learners on Multiple Tasks

Source: R/benchmark.R

Runs a benchmark of the cross-product of learners, tasks, and resampling strategies (possibly in parallel).

Resamplings which are not already instantiated will be instantiated automatically. Note that these auto-instantiated resamplings will not be synchronized per task, i.e. learners will see different splits of the same task.

To generate exhaustive designs and automatically instantiate resampling strategies per task, see expand_grid().

benchmark(design, ctrl = list())

Arguments

design	(data.frame()): Data frame (or data.table()) with three columns: "task", "learner", and "resampling". Each row defines a set of resampled experiments by providing a Task, Learner and Resampling strategy. The helper function expand_grid() can assist in generating an exhaustive design (see examples).
ctrl	(named list as returned by mlr_control()): Object to control experiment execution. See mlr_control().

Value

BenchmarkResult.

Examples

tasks = mlr_tasks$mget(c("iris", "sonar"))
learners = mlr_learners$mget(c("classif.featureless", "classif.rpart"))
resamplings = mlr_resamplings$mget("holdout")

design = expand_grid(tasks, learners, resamplings)
print(design)
#>             task                     learner          resampling
#> 1: <TaskClassif> <LearnerClassifFeatureless> <ResamplingHoldout>
#> 2: <TaskClassif>       <LearnerClassifRpart> <ResamplingHoldout>
#> 3: <TaskClassif> <LearnerClassifFeatureless> <ResamplingHoldout>
#> 4: <TaskClassif>       <LearnerClassifRpart> <ResamplingHoldout>

set.seed(123)
bmr = benchmark(design)

# performance for all conducted experiments
head(as.data.table(bmr))
#>                hash          task task_id                     learner
#> 1: e4be888f65b194c4 <TaskClassif>    iris <LearnerClassifFeatureless>
#> 2: bc09a032e797e992 <TaskClassif>    iris       <LearnerClassifRpart>
#> 3: f3ab4827f36b9492 <TaskClassif>   sonar <LearnerClassifFeatureless>
#> 4: 8c127813347dbd34 <TaskClassif>   sonar       <LearnerClassifRpart>
#>             learner_id          resampling resampling_id classif.mmce
#> 1: classif.featureless <ResamplingHoldout>       holdout    0.7400000
#> 2:       classif.rpart <ResamplingHoldout>       holdout    0.0600000
#> 3: classif.featureless <ResamplingHoldout>       holdout    0.4347826
#> 4:       classif.rpart <ResamplingHoldout>       holdout    0.2463768

# aggregated performance values
bmr$aggregated(objects = FALSE)
#>                hash resampling_id task_id          learner_id classif.mmce
#> 1: e4be888f65b194c4       holdout    iris classif.featureless    0.7400000
#> 2: bc09a032e797e992       holdout    iris       classif.rpart    0.0600000
#> 3: f3ab4827f36b9492       holdout   sonar classif.featureless    0.4347826
#> 4: 8c127813347dbd34       holdout   sonar       classif.rpart    0.2463768

# Overview of of resamplings that were conducted internally
rrs = bmr$resample_results
print(rrs)
#>                hash task_id          learner_id resampling_id N
#> 1: e4be888f65b194c4    iris classif.featureless       holdout 1
#> 2: bc09a032e797e992    iris       classif.rpart       holdout 1
#> 3: f3ab4827f36b9492   sonar classif.featureless       holdout 1
#> 4: 8c127813347dbd34   sonar       classif.rpart       holdout 1

# Extract first ResampleResult
rr = bmr$resample_result(hash = rrs$hash[1])
print(rr)
#> <ResampleResult> of learner 'iris' on task 'classif.featureless' with 1 iterations
#>       Measure Min. 1st Qu. Median Mean 3rd Qu. Max. Sd
#>  classif.mmce 0.74    0.74   0.74 0.74    0.74 0.74 NA

# Extract predictions of first experiment of this resampling
head(as.data.table(rr$experiment(1)$prediction))
#>    row_id   response  truth
#> 1:      2 versicolor setosa
#> 2:      3 versicolor setosa
#> 3:     12 versicolor setosa
#> 4:     15 versicolor setosa
#> 5:     18 versicolor setosa
#> 6:     19 versicolor setosa