I am working with the genalg library for R, and try to save all the generations when I run a binary generic algorithm. It does not seems like there is a built-in method for that in the library, so my attempt was to save each chromosome, x, coming through the evaluation function.
To test this method I have tried to insert print(x) in the evaluation function to be able to see all the evaluated chromosomes. However, the number of printed chromosomes does not always match what I am suspecting.
I thought that the number of printed chromosomes would be equal to the number of iterations times the population size, but it does not seems to be try all the time.
The problem is that I want to know from which generation (or iteration) each chromosome belongs, which I can't tell if the number of chromosomes are different from iter times popSize.
What is the reason for this, and how can I "fix" it. Or is there another way of saving each chromosome and from which iteration it belongs?
Below is an example, where I thought that the evaluation function would print 2x5 chromosomes, but only prints 8.
library(genalg)
library(ggplot2)
dataset <- data.frame(
item = c("pocketknife", "beans", "potatoes", "unions", "sleeping bag", "rope", "compass"),
survivalpoints = c(10, 20, 15, 2, 30, 10, 30),
weight = c(1, 5, 10, 1, 7, 5, 1))
weightlimit <- 20
evalFunc <- function(x) {
print(x)
current_solution_survivalpoints <- x %*% dataset$survivalpoints
current_solution_weight <- x %*% dataset$weight
if (current_solution_weight > weightlimit)
return(0) else return(-current_solution_survivalpoints
}
iter = 2
popSize = 5
set.seed(1)
GAmodel <- rbga.bin(size = 7, popSize = popSize, iters = iter, mutationChance = 0.1,elitism = T, evalFunc = evalFunc)
Looking at the function code, it seems like at each iteration (generation) a subset of chromosomes is chosen from the population (population = 5 chromosomes in your example) with a certain probability (0.1 in your case) and mutated. Evaluation function is called only for the mutated chromosomes at each generation (and of course for all the chromosomes in the first iteration to know their initial value).
Note that, this subset do not include elitists group, which in your example you have defined as 1 element big (you have erroneously passed elitism=TRUE and TRUE is implicitly converted to 1).
Anyway, to know the population at each generation, you can pass a monitor function through the monitorFun parameter e.g. :
# obj contains a lot of informations, try to print it
monitor <- function(obj) {
print(paste(" GENERATION :", obj$iter))
print("POPULATION:")
print(obj$population)
print("VALUES:")
print(obj$evaluations)
}
iter = 2
popSize = 5
set.seed(1)
GAmodel <- rbga.bin(size = 7, popSize = popSize,
iters = iter, mutationChance = 0.1,
elitism = 1, evalFunc = evalFunc, monitorFunc = monitor)