Learn R Programming

dief (version 1.2)

Metrics for Continuous Efficiency

Description

An implementation of the metrics dief@t and dief@k to measure the diefficiency (or continuous efficiency) of incremental approaches, see Acosta, M., Vidal, M. E., & Sure-Vetter, Y. (2017) . The metrics dief@t and dief@k allow for measuring the diefficiency during an elapsed time period t or while k answers are produced, respectively. dief@t and dief@k rely on the computation of the area under the curve of answer traces, and thus capturing the answer rate concentration over a time interval.

Copy Link

Version

Install

install.packages('dief')

Monthly Downloads

24

Version

1.2

License

MIT + file LICENSE

Issues

0

Pull Requests

2

Stars

6

Forks

4

Maintainer

Maribel Acosta

Last Published

February 28th, 2019

Functions in dief (1.2)

experiment1

Compares dief@t with other benchmark metrics as in <doi:10.1007/978-3-319-68204-4_1>
diefk2

Compute dief@k at a portion of the answer
dief

Tools for Computing Diefficiency Metrics
dieft

Compute metric dief@t
plotExperiment2

Generate radar plots that compare dief@k at different answer completeness in all tests as in <doi:10.1007/978-3-319-68204-4_1>
experiment2

Compares dief@k at different answer portions as in <doi:10.1007/978-3-319-68204-4_1>
plotExperiment2Test

Generate radar plots that compare dief@k at different answer completeness in a specific test as in <doi:10.1007/978-3-319-68204-4_1>
diefk

Compute metric dief@k
plotAnswerTrace

Plot the answer trace of approaches
metrics

Example of benchmarking performance with other metrics
traces

Example of answer traces
plotExperiment1

Generate radar plots that compare dief@t with other benchmark metrics in all tests as in <doi:10.1007/978-3-319-68204-4_1>
plotExperiment1Test

Generate radar plots that compare dief@t with other benchmark metrics in a specific test as in <doi:10.1007/978-3-319-68204-4_1>