ftest_plot_performances: Plot the evaluation of weight of each performance on...

In functClust: Functional Clustering of Redundant Components of a System

Description

Evaluate by cross-validation (leave-one-out) the effect induced by leaving out each performance on the result of a functional clustering.

Usage

ftest_plot_performances(fres, rtest,
                        main = "Title", opt.crit = "Jaccard", opt.perf = NULL)

Arguments

fres	an object resulting from a functional clustering obtained with the whole dataset using the function fclust.
rtest	a list of matrices, each containing the results for a clustering index. rtest is an object generated by the function ftest.
main	a string, that is used as the first, reference part of the title of each graph.
opt.crit	a list of strings, indicating the clustering indices to plot. The indices can be: "Czekanowski_Dice", "Folkes_Mallows", "Jaccard", "Kulczynski", "Precision", "Rand", "Recall", "Rogers_Tanimoto", "Russel_Rao", "Sokal_Sneath1" or "Sokal_Sneath2". For more informations, see the notice of R-package clusterCrit.
opt.perf	a list, that can include a list, that can include opt.comp = list("all.together", "performances.together", "sorted.leg"). This option list manages the plot of results obtained using the function ftest with opt.var = "performances". The item order in list is any. "all.together", "performances.together" plot (i) the general mean index; (ii) the mean indices for each removed performance on a same plot, when removing one after one each performance from the dataset. This allows to evaluate the raw robustness of functional clustering to perturbation of dataset, and the weight of each performance on functional clustering. "sorted.leg" plot the names of performances decreasingly sorted according to their weight on functional clustering. "all" plot all possible graphs. This option is equivalent to opt.comp = list("all.together", "performances.together", "sorted.leg").

Details

The trees obtained by leaving out each performance are compared to the reference tree obtained with all performances using different criteria : "Czekanowski_Dice", "Folkes_Mallows", "Jaccard", "Kulczynski", "Precision", "Rand", "Recall", "Rogers_Tanimoto", "Russel_Rao", "Sokal_Sneath1" and "Sokal_Sneath2" index. For more informations, see the notice of R-package clusterCrit.

Value

Nothing. It is a procedure.

References

Package "clusterCrit": Clustering Indices, by Bernard Desgraupes (University of Paris Ouest - Lab Modal'X)

functClust documentation built on Dec. 2, 2020, 5:06 p.m.