ParallellRunExperiment {rrepast} | R Documentation |
ParallellRunExperiment
Description
Run the model multiple times for different parameters given by design matrix function parameter.
Usage
ParallellRunExperiment(modeldir, datasource, maxtime, r = 1, design, FUN,
default = NULL)
Arguments
modeldir |
The installation directory of some repast model |
datasource |
The name of any model aggregate dataset |
maxtime |
The total simulated time |
r |
The number of experiment replications |
design |
The desing matrix holding parameter sampling |
FUN |
THe calibration function. |
default |
The alternative values for parameters which should be kept fixed |
Details
The FUN function must return zero for perfect fit and values greater than zero otherwise.
Value
A list with output and dataset
Examples
## Not run:
my.cost<- function(params, results) { # your best fit calculation, being 0 the best metric. }
d<- "/usr/models/your-model-directory"
f<- AddFactor(name="cyclePoint",min=40,max=90)
f<- AddFactor(factors=f, name="conjugationCost",min=1,max=80)
d<- AoE.LatinHypercube(factors=f)
v<- ParallellRunExperiment()
## End(Not run)
[Package rrepast version 0.8.0 Index]