LkbGBMLHybrid {FKBL} | R Documentation |
This is the implementation of Hybrid, Pittsburgh-Michigan genetic method. This is a genetic algorithm, each individual represents a set of rules. With the given probability, the crossing operation for an individual is performed by, first selecting two different individuals, and then rule by rule with a 50% of probability, each one is swapped, i.e. every rule has 50
LkbGBMLHybrid(P, gene=50, cross=0.9, muta=0.8, crossM=0.9, mutaM=0.01, replaceH=2, train)
Takes the vector of partitions, the number of generations, the crossing and mutation probability in Hybrid method, crossing and mutation probability in the Michigan method, the number of individuals to replace, the train data.
P |
The vector of partitions. |
gene |
The number of generations. |
cross |
The cross probability up to 1. |
muta |
The mutation probability up to 1. |
crossM |
The cross probability for Michigan up to 1. |
mutaM |
The mutation probability for Michigan up to 1. |
replaceH |
The number of individuals to replace. |
train |
The train dataset. |
Returns a knowledge base with the partitions and the rules.
begin{itemize}
data(P) data(trainA) LkbGBMLHybrid(P,1000,0.9,0.8,0.9,0.01,2,trainA)