Plots a bar chart from the ranks of algorithms. Alternatively,
tiles can be plotted for every rank-task combination, see pos
for details. In all plot variants the ranks of the learning algorithms are displayed on
the x-axis. Areas are always colored according to the learner.id
.
plotBMRRanksAsBarChart(bmr, measure = NULL, ties.method = "average",
aggregation = "default", pos = "stack", order.lrns = NULL,
order.tsks = NULL, pretty.names = TRUE)
(BenchmarkResult) Benchmark result.
(Measure) Performance measure. Default is the first measure used in the benchmark experiment.
(character(1)
)
See rank for details.
(character(1)
)
“mean” or “default”. See getBMRAggrPerformances
for details on “default”.
(character(1)
)
Optionally set how the bars are positioned in ggplot2.
Ranks are plotted on the x-axis.
“tile” plots a heat map with task
as the y-axis.
Allows identification of the performance in a special task.
“stack” plots a stacked bar plot.
Allows for comparison of learners within and and across ranks.
“dodge” plots a bar plot with bars next to each other instead
of stacked bars.
(character(n.learners)
)
Character vector with learner.ids
in new order.
(character(n.tasks)
)
Character vector with task.ids
in new order.
(logical(1)
)
Whether to use the short name of the learner instead of its ID in labels. Defaults to TRUE
.
ggplot2 plot object.
Other plot: plotBMRBoxplots
,
plotBMRSummary
,
plotCalibration
,
plotCritDifferences
,
plotLearningCurve
,
plotPartialDependence
,
plotROCCurves
, plotResiduals
,
plotThreshVsPerf
Other benchmark: BenchmarkResult
,
batchmark
, benchmark
,
convertBMRToRankMatrix
,
friedmanPostHocTestBMR
,
friedmanTestBMR
,
generateCritDifferencesData
,
getBMRAggrPerformances
,
getBMRFeatSelResults
,
getBMRFilteredFeatures
,
getBMRLearnerIds
,
getBMRLearnerShortNames
,
getBMRLearners
,
getBMRMeasureIds
,
getBMRMeasures
, getBMRModels
,
getBMRPerformances
,
getBMRPredictions
,
getBMRTaskDescs
,
getBMRTaskIds
,
getBMRTuneResults
,
plotBMRBoxplots
,
plotBMRSummary
,
plotCritDifferences
,
reduceBatchmarkResults
# NOT RUN {
# see benchmark
# }
Run the code above in your browser using DataLab