R: Plot a benchmark summary.

plotBMRSummary {mlr}

R Documentation

Plot a benchmark summary.

Description

Creates a scatter plot, where each line refers to a task. On that line the aggregated scores for all learners are plotted, for that task. Optionally, you can apply a rank transformation or just use one of ggplot2's transformations like ggplot2::scale_x_log10.

Usage

plotBMRSummary(bmr, measure = NULL, trafo = "none",
  order.tsks = NULL, pointsize = 4L, jitter = 0.05,
  pretty.names = TRUE)

Arguments

`bmr`	(BenchmarkResult) Benchmark result.
`measure`	(Measure) Performance measure. Default is the first measure used in the benchmark experiment.
`trafo`	(`character(1)`) Currently either “none” or “rank”, the latter performing a rank transformation (with average handling of ties) of the scores per task. NB: You can add always add ggplot2::scale_x_log10 to the result to put scores on a log scale. Default is “none”.
`order.tsks`	(`character(n.tasks)`) Character vector with `task.ids` in new order.
`pointsize`	(`numeric(1)`) Point size for ggplot2 ggplot2::geom_point for data points. Default is 4.
`jitter`	(`numeric(1)`) Small vertical jitter to deal with overplotting in case of equal scores. Default is 0.05.
`pretty.names`	(`logical(1)`) Whether to use the short name of the learner instead of its ID in labels. Defaults to `TRUE`.

Value

ggplot2 plot object.

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

Other plot: createSpatialResamplingPlots, plotBMRBoxplots, plotBMRRanksAsBarChart, plotCalibration, plotCritDifferences, plotLearningCurve, plotPartialDependence, plotROCCurves, plotResiduals, plotThreshVsPerf

Examples

# see benchmark