Generate threshold vs. performance(s) for 2-class classification.

Generates data on threshold vs. performance(s) for 2-class classification that can be used for plotting.

Usage

generateThreshVsPerfData(
  obj,
  measures,
  gridsize = 100L,
  aggregate = TRUE,
  task.id = NULL
)

Arguments

obj

(list of Prediction | list of ResampleResult | BenchmarkResult)
Single prediction object, list of them, single resample result, list of them, or a benchmark result. In case of a list probably produced by different learners you want to compare, then name the list with the names you want to see in the plots, probably learner shortnames or ids.

measures

(Measure | list of Measure)
Performance measure(s) to evaluate. Default is the default measure for the task, see here getDefaultMeasure.

gridsize

(integer(1))
Grid resolution for x-axis (threshold). Default is 100.

aggregate

(logical(1))
Whether to aggregate ResamplePredictions or to plot the performance of each iteration separately. Default is TRUE.

task.id

(character(1))
Selected task in BenchmarkResult to do plots for, ignored otherwise. Default is first task.

Value

(ThreshVsPerfData). A named list containing the measured performance across the threshold grid, the measures, and whether the performance estimates were aggregated (only applicable for (list of) ResampleResults).

See also

Other generate_plot_data: generateCalibrationData(), generateCritDifferencesData(), generateFeatureImportanceData(), generateFilterValuesData(), generateLearningCurveData(), generatePartialDependenceData(), plotFilterValues()

Other thresh_vs_perf: plotROCCurves(), plotThreshVsPerf()