CNORfuzzy (version 1.14.0)

compileMultiRes: Compiles results from multiple runs and produces graph for choosing Post Refinement Threshold

Description

This function takes a list of objects returned by CNORwrapfuzzy (run using identical parameters, models, and data) and packages them together so they can be compared with plotMeanFuzzyFit and writeFuzzyNetwork. Because almost all training of cFL models are underdetermined problems, analyzing multiple runs together is essential.

Usage

compileMultiRes(allRes, tag=NULL, show=TRUE)

Arguments

allRes

list of objects returned by the CNORwrapFuzzy function.

tag

If provided, save the results in 3 files. Each file starts with the string "filename" that is provided. (_allRes.RData, _allFinalMSEs.RData and _allFinalNumParams.RData)

show

plot the MSE and mean number of parameters versus threshold. Can be switch off if show=FALSE

Examples

    data(ToyModel, package="CellNOptR")
    data(CNOlistToy,package="CellNOptR")
    paramsList = defaultParametersFuzzy(CNOlistToy, ToyModel)
    N = 10
    allRes = list()
    ## Not run: 
#         for (i in 1:N){
#             Res = CNORwrapFuzzy(CNOlistToy, ToyModel, paramsList)
#             allRes[[i]] = Res
#         }
# 
#         summary = compileMultiRes(allRes)
#         summary$allFinalMSEs
#         summary$allFinalNumParams
#     
#         # You can save the resuls in files using the tag argument
#         compileMultiRes(allRes, "output")
#     ## End(Not run)