遗传算法的C++代码实现教程

此例程总共包含3个文件：main.c（主函数）；GA.c（包含3个所用函数）；GA.h（头文件），3个文件截图如下：⑤GA前GA刊main用visualc++或者visualstutio创建工程，然后将上述3个文件包含进工程，编译运行即可。亲测可行！！！3个文件代码分别如下：1、main.c：#include<iostream>#include"GA.h”usingnamespacestd;2“$$$$$$$&/*******************************************************************GAdemo求函数y=x*sin（10*pai*x）+2.0的最大值编码：浮点数,1位初始群体数：50变异概率：0.8进化代数：100取值范围：[0,4]变异步长：0.004注：因为是单数浮点数编码，所以未使用基因重组函数e力力力力力$$$$$$$$$$$$$$$力力力力力力力力$$$$$$$$$$$$$$$$$力、&“$$$$$$$$$$$$$$力力力，**********************************************************************/intmain(){GenEnginegenEngine(50,0.8,0.8,1,100,0,4);genEngine.OnStartGenAlg();getchar();}2、GA.c：#include<vector>#include<stdio.h>#include<stdlib.h>#include<time.h>#include<iostream>#include"GA.h”usingnamespacestd;//srand((unsigned)time(NULL));doublerandom(){doublerandNum;randNum=rand()*1.0/RAND_MAX;returnrandNum;}GenAlg::GenAlg(){}voidGenAlg::init(intpopsize,doubleMutRate,doubleCrossRate,intGenLenght,doubleLeftPoint,doubleRightPoint){popSize=popsize;mutationRate=MutRate;crossoverRate=CrossRate;chromoLength=GenLenght;totalFitness=0;generation=0;//fittestGenome=0;bestFitness=0.0;worstFitness=99999999;averageFitness=0;maxPerturbation=0.004;leftPoint=LeftPoint;rightPoint=RightPoint;//清空种群容器，以初始化vecPop.clear();for(inti=0;i<popSize;i++){〃类的构造函数已经把适应性评分初始化为0vecPop.push_back(Genome());//把所有的基因编码初始化为函数区间内的随机数。for(intj=0;j<chromoLength;j++){vecPop[i].vecGenome.push_back(random()*(rightPoint-leftPoint)+leftPoint);}}}voidGenAlg::Reset(){totalFitness=0;//bestFitness=0;//worstFitness=9999;averageFitness=0;voidGenAlg::CalculateBestWorstAvTot(){for(inti=0;i<popSize;++i){〃累计适应性分数.totalFitness+=vecPop[i].fitness;if(vecPop[i].fitness>=bestFitness){bestFitness=vecPop[i].fitness;fittestGenome=vecPop[i];}if(vecPop[i].fitness<=worstFitness)worstFitness=vecPop[i].fitness;}averageFitness=totalFitness/popSize;}GenomeGenAlg::GetChromoRoulette(){〃产生一个0到人口总适应性评分总和之间的随机数.〃中m_dTotalFitness记录了整个种群的适应性分数总和)doubleSlice=(random())*totalFitness;〃这个基因将承载转盘所选出来的那个个体.GenomeTheChosenOne;//累计适应性分数的和.doubleFitnessSoFar=0;//遍历总人口里面的每一条染色体。for(inti=0;i<popSize;++i){〃累计适应性分数.FitnessSoFar+=vecPop[i].fitness;〃如果累计分数大于随机数，就选择此时的基因.if(FitnessSoFar>=Slice){TheChosenOne=vecPop[i];break;}}//返回转盘选出来的个体基因returnTheChosenOne;}voidGenAlg::Mutate(vector<double>&chromo){//遵循预定的突变概率，对基因进行突变for(inti=0;i<chromo.size();++i){〃如果发生突变的话if(random()<mutationRate)//使该权值增加或者减少一个很小的随机数值chromo[i]+=((random()-0.5)*maxPerturbation);〃限定范围if(chromo[i]<leftPoint){chromo[i]=rightPoint;}elseif(chromo[i]>rightPoint){chromo[i]=leftPoint;}〃以上代码非基因变异的一般性代码只是用来保证基因编码的可行性。}}}//此函数产生新的一代,见证着整个进化的全过程.〃以父代种群的基因组容器作为参数传进去，该函数将往该容器里放入新一代的基因组(当然是经过了优胜劣汰的)voidGenAlg::Epoch(vector<Genome>&vecNewPop){//用类的成员变量来储存父代的基因组(在此之前m_vecPop储存的是不带估值的所有基因组)vecPop=vecNewPop;//初始化相关变量Reset();〃为相关变量赋值CalculateBestWorstAvTot();//清空装载新种群的容器vecNewPop.clear();〃产生新一代的所有基因组while(vecNewPop.size()<popSize){〃转盘随机抽出两个基因Genomemum=GetChromoRoulette();Genomedad=GetChromoRoulette();〃创建两个子代基因组vector<double>baby1,baby2;〃先把他们分别设置成父方和母方的基因baby1=mum.vecGenome;baby2=dad.vecGenome;//使子代基因发生基因突变Mutate(baby1);Mutate(baby2);//把两个子代基因组放到新的基因组容器里面vecNewPop.push_back(Genome(baby1,0));vecNewPop.push_back(Genome(baby2,0));}//子代产生完毕〃如果你设置的人口总数非单数的话,就会出现报错if(vecNewPop.size()!=popSize){//MessageBox("你的人口数目不是单数”)；cout<<"error"<<endl;return;}}GenomeGenAlg::GetBestFitness(){returnfittestGenome;}doubleGenAlg::GetAverageFitness(){returnaverageFitness;}voidGenEngine::report(constint&genNum){cout<<"第"<<genNum<<"代”<<endl;cout<<"最佳适应度："<<bestFitness<<endl;cout<<"最佳适应度基因取值："<<bestSearch<<endl;cout<<"平均适应度："<<averageFitness<<endl<<endl;}voidGenEngine::OnStartGenAlg(){〃产生随机数srand((unsigned)time(NULL));//初始化遗传算法引擎genAlg.init(g_popsize,g_dMutationRate,g_dCrossoverRate,g_numGen,g_LeftPoint,g_RightPoint);//清空种群容器m_population.clear();〃种群容器装进经过随机初始化的种群m_population=genAlg.vecPop;vector<double>input;doubleoutput;input.push_back(0);for(intGeneration=0;Generation<=g_Generation;Generation++){〃里面是对每一条染色体进行操作for(inti=0;i<g_popsize;i++){input=m_population[i].vecGenome;〃为每一个个体做适应性评价，如之前说的，评价分数就是函数值。其//Function函数的作用是输入自变量返回函数值，读者可以参考其代码。output=(double)curve.function(input);m_population[i].fitness=output;}〃由父代种群进化出子代种群genAlg.Epoch(m_population);//if(genAlg.GetBestFitness().fitness>=bestFitness)bestSearch=genAlg.GetBestFitness().vecGenome[0];bestFitness=genAlg.GetBestFitness().fitness;averageFitness=genAlg.GetAverageFitness();//cout<<bestSearch<<endl;report(Generation+1);}//returnbestSearch;}3、GA.h：#include<vector>usingnamespacestd;constdoublepai=3.1415926;classGenome{public:friendclassGenAlg;friendclassGenEngine;Genome():fitness(0){}Genome(vector<double>vec,doublef):vecGenome(vec),fitness(f){}〃类的带参数初始化参数。private:vector<double>vecGenome;//dFitness用于存储对该基因的适应性评估。doublefitness;〃类的无参数初始化参数。};〃遗传算法classGenAlg{public:〃这个容器将储存每一个个体的染色体vector<Genome>vecPop;//人口（种群）数量intpopSize;〃每一条染色体的基因的总数目intchromoLength;//所有个体对应的适应性评分的总和doubletotalFitness;//在所有个体当中最适应的个体的适应性评分doublebestFitness;//所有个体的适应性评分的平均值doubleaverageFitness;//在所有个体当中最不适应的个体的适应性评分doubleworstFitness;〃最适应的个体在m_vecPop容器里面的索引号GenomefittestGenome;//基因突变的概率，一般介于0.05和0.3之间doublemutationRate;//基因交叉的概率一般设为0.7doublecrossoverRate;//代数的记数器intgeneration;〃最大变异步长doublemaxPerturbation;doubleleftPoint;doublerightPoint;〃构造函数GenAlg();//初始化变量voidReset();//初始化函数voidinit(intpopsize,doubleMutRate,doubleCrossRate,intGenLenght,doubleLeftPoint,doubleRightPoint);〃计算TotalFitness,BestFitness,WorstFitness,AverageFitness等变量voidCalculateBestWorstAvTot();〃轮盘赌选择函数GenomeGetChromoRoulette();//基因变异函数voidMutate(vector<double>&chromo);〃这函数产生新一代基因voidEpoch(vector<Genome>&vecNewPop);GenomeGetBestFitness();doubleGetAverageFitness();}；classCurve{public:doublefunction(constvector<double>&input){doublex=input[0];doubleoutput;output=x*sin(10*pai*x)+2.0;returnoutput;}private:};〃遗传运算引擎classGenEngine{public:GenEngine(constint&popsize,constdouble&