fitnessSplits.BigBang {galgo}R Documentation

Computes the fitness function from chromosomes for different splits

Description

Computes the fitness function from chromosomes for different splits.

Usage

## S3 method for class 'BigBang':
fitnessSplits(o,
        filter="none",
        subset=TRUE,
        fitnessFunc=o$data$modelSelectionFunc,
        maxCache=1e+06,
        chromosomes=NULL,
        use.cache=TRUE,
        ...)

Arguments

filter The BigBang object can save information about solutions that did not reach the goalFitness. filter=="solutions" ensures that only chromosomes that reach the goalFitness are considered. fitlter=="none" take all chromosomes. filter=="nosolutions" consider only no-solutions (for comparative purposes).
subset Second level of filter. subset can be a vector specifying which filtered chromosomes are used. It can be a logical vector or a numeric vector (indexes in order given by $bestChromosomes in BigBang object variable). If it is a numeric vector length one, a positive value means take those top chromosomes sorted by fitness, a negative value take those at bottom.
fitnessFunc The function that provides the fitness for every chromosome. If the fitness is ``split-sensitive'' it should returns only one value (like the common $galgo$fitnessFunc variable). If the fitness does the splitting process itself (like $data$modelSelectionFunc), the result should be a vector of a fitness value for every split. The default use $data$modelSelectionFunc.
maxCache The maximum number of values to be saved in the BigBang object (all variables starting with "fitnessSplits"). Useful for saving results between R sessions.
chromosomes The chromosomes to process. The default is using filter and subset to extract the chromosomes from the BigBang object.
use.cache Save/Restore values from previous computations with same parameters.

Value

A Matrix with chromosomes in rows and splits in columns. Each value is the result of the fitness function in a given chromosome on an split.

Author(s)

Victor Trevino. Francesco Falciani Group. University of Birmingham, U.K. http://www.bip.bham.ac.uk/bioinf

References

Goldberg, David E. 1989 Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Pub. Co. ISBN: 0201157675

See Also

For more information see BigBang. *plot().

Examples

   #bb is a BigBang object
   fs <- fitnessSplits(bb)
   fs
   fs <- fitnessSplits(bb, fitnessFunc=bb$galgo$fitnessFunc)
   fs
   fs <- fitnessSplits(bb, fitnessFunc=bb$data$modelSelectionFunc) # default
   fs
[Package galgo version 1.0-10 Index]