mlr (version 2.10)

getBMRFeatSelResults: Extract the feature selection results from a benchmark result.

Description

Returns a nested list of FeatSelResults. The first level of nesting is by data set, the second by learner, the third for the benchmark resampling iterations. If as.df is TRUE, a data frame with “task.id”, “learner.id”, the resample iteration and the selected features is returned. Note that if more than one feature is selected and a data frame is requested, there will be multiple rows for the same dataset-learner-iteration; one for each selected feature.

Usage

getBMRFeatSelResults(bmr, task.ids = NULL, learner.ids = NULL,
  as.df = FALSE)

Arguments

bmr
[BenchmarkResult] Benchmark result.
task.ids
[character(1)] Restrict result to certain tasks. Default is all.
learner.ids
[character(1)] Restrict result to certain learners. Default is all.
as.df
[character(1)] Return one data.frame as result - or a list of lists of objects?. Default is FALSE.

Value

[list | data.frame]. See above.

See Also

Other benchmark: BenchmarkResult, benchmark, convertBMRToRankMatrix, friedmanPostHocTestBMR, friedmanTestBMR, generateCritDifferencesData, getBMRAggrPerformances, getBMRFilteredFeatures, getBMRLearnerIds, getBMRLearnerShortNames, getBMRLearners, getBMRMeasureIds, getBMRMeasures, getBMRModels, getBMRPerformances, getBMRPredictions, getBMRTaskDescriptions, getBMRTaskIds, getBMRTuneResults, plotBMRBoxplots, plotBMRRanksAsBarChart, plotBMRSummary, plotCritDifferences