mutation: Mutation of Chromosomes in Genetic Algoritm

In slwu89/GA: Genetic Algorithm-based Variable Selection for Generalized Linear Models

Description

Mutation randomly determines if and where on the chromosome, or model, a mutation of one of the alleles, or covariates occurs. This is used in the genetic algorithm to introduce randomness not present in the genetic makeup of the population. Mutation is according to a Poisson process because in the usual case the number of alleles on the chromosome, C, is large and probability of mutation is small. The number of mutations is first sampled by rpois and then the mutations are scattered randomly across the chromosome.

Usage

mutation(new_pop, C, C_ix, mutation)

Arguments

new_pop	a nested list of chromosomes representing the child population. The the result of selection and crossover.
C	a value representing the population size. Should be of class integer, corresponding to the number of columns of input matrix x for initial regression.
C_ix	a sequence of integers from 1 to number of models considered for mutation (C).
mutation	a value indicating the rate at which mutation should occur. Input as rate parameter lambda, or rpois for generating indices of chromosome list where mutation occurs.

slwu89/GA documentation built on May 14, 2019, 5:20 p.m.