python 遗传算法实现 PytLab/gaft

谁践踏了优雅 2022-01-31 19:09 222阅读 0赞

[PytLab/gaft][PytLab_gaft]  
测试环境：python3.5  
[python环境搭建][python]  
安装：

pip install gaft

根据自己需求，只需要修改16,36行处代码即可直接使用  
genetic. py

# github: https://github.com/PytLab/gaft
    # installation:
    # pip install gaft
    # date: 2019-05-17
    from gaft import GAEngine
    from gaft.components import BinaryIndividual
    from gaft.components import Population
    from gaft.operators import RouletteWheelSelection
    from gaft.operators import UniformCrossover
    from gaft.operators import FlipBitMutation
    from gaft.analysis.fitness_store import FitnessStore
    from gaft.plugin_interfaces.analysis import OnTheFlyAnalysis
    
    # Define population.
    # 变量范围：x in [-2, 2] y in [-2, 2]
    indv_template = BinaryIndividual(ranges=[(-2, 2), (-2, 2)], eps=0.001)
    population = Population(indv_template=indv_template, size=50)
    population.init()
    
    # Create genetic operators.
    selection = RouletteWheelSelection()
    crossover = UniformCrossover(pc=0.8, pe=0.5)
    mutation = FlipBitMutation(pm=0.1)
    
    # Create genetic algorithm engine.
    engine = GAEngine(population=population, selection=selection,
                      crossover=crossover, mutation=mutation,
                      analysis=[FitnessStore])
    
    
    # Define fitness function.
    @engine.fitness_register
    @engine.minimize        # 注释这一行为找最大值
    def fitness(indv):
        x, y = indv.solution    # 对应【16行】的变量顺序
        return x * x + y
    
    
    # 输出结果：如果不要直接注释掉
    @engine.analysis_register
    class ConsoleOutput(OnTheFlyAnalysis):
        master_only = True
        interval = 20       # 每隔多少次迭代 打印一条结果
    
        def register_step(self, g, population, engine):
            best_indv = population.best_indv(engine.fitness)
            msg = 'Generation: {}, best fitness: {:.3f}'.format(g, engine.fmax)
            engine.logger.info(msg)
    
    
    if '__main__' == __name__:
        engine.run(ng=100)      # 迭代100次后停止

结果输出保存在**best\_fit.py**中的best\_fit变量中  
速度已经是很快了，如果还需要通过并行提高速度，参见[MPI加速][MPI]

[PytLab_gaft]: https://github.com/PytLab/gaft
[python]: https://blog.csdn.net/smilife_/article/details/88916846
[MPI]: https://juejin.im/post/59f880dc6fb9a044fb070f9e