subset.ranked.list: Extracts a subset of algorithms or tasks

In wiesenfa/challengeR: Analyzing assessment data of biomedical image analysis competitions and visualization of results

Extracts a subset of algorithms or tasks

Description

Extracts the top performing algorithms or a subset of tasks.

Usage

## S3 method for class 'ranked.list'
subset(x, top, tasks, ...)

Arguments

x	The ranked asssessment data set.
top	A positive integer specifying the amount of top performing algorithms to be retrieved.
tasks	A vector of strings containing the task identifiers that should remain in the subset.
...	Further arguments passed to or from other functions.

Value

An S3 object of class "ranked.list" to represent a ranked assessment data set.

Reports for subsets (top list) of algorithms

If ties are present in the ranking, the subset will consist of more than top algorithms. Line plots for ranking robustness can be used to check whether algorithms performing well in other ranking methods are excluded. Bootstrapping still takes entire uncertainty into account. Podium plots and ranking heatmaps neglect excluded algorithms. Only available for single-task challenges (for multi-task challenges not sensible because each task would contain a different set of algorithms).

Reports for subsets of tasks

You may want to recompute the consensus ranking after creating the subset. An error will be raised if a task identifier is not contained in the assessment data set to avoid subsequent errors.

Examples

## Not run: 
 # only show the top 3 algorithms according to the chosen ranking method
 subset(ranking, top = 3) %>% report(...)

## End(Not run)

## Not run: 
 # restrict report to tasks "task1" and "task2"
 subset(ranking, tasks=c("task1", "task2")) %>% report(...)

## End(Not run)

wiesenfa/challengeR documentation built on Aug. 25, 2023, 6:43 a.m.