python PSO算法

以下是使用Python实现PSO算法的示例代码：

import random

class Particle:
    def __init__(self, dim, minx, maxx):
        self.__pos = [random.uniform(minx, maxx) for i in range(dim)]
        self.__vel = [random.uniform(-1, 1) for i in range(dim)]
        self.__best_pos = self.__pos
        self.__fitness = float('inf')
        self.__best_fitness = float('inf')

    def update_fitness(self, fitness_func):
        self.__fitness = fitness_func(self.__pos)
        if self.__fitness < self.__best_fitness:
            self.__best_fitness = self.__fitness
            self.__best_pos = self.__pos

    def move(self):
        for i in range(len(self.__pos)):
            self.__pos[i] = self.__pos[i] + self.__vel[i]

    def set_pos(self, pos):
        self.__pos = pos

    def set_vel(self, vel):
        self.__vel = vel

    def get_pos(self):
        return self.__pos

    def get_vel(self):
        return self.__vel

    def get_best_pos(self):
        return self.__best_pos

    def get_fitness(self):
        return self.__fitness

    def get_best_fitness(self):
        return self.__best_fitness

class PSO:
    def __init__(self, dim, size, minx, maxx, fitness_func, max_iter=100, phi1=2.0, phi2=2.0, inertia_weight=0.7):
        self.__particles = [Particle(dim, minx, maxx) for i in range(size)]
        self.__fitness_func = fitness_func
        self.__max_iter = max_iter
        self.__phi1 = phi1
        self.__phi2 = phi2
        self.__inertia_weight = inertia_weight
        self.__best_fitness = float('inf')
        self.__best_pos = None

    def run(self):
        for i in range(self.__max_iter):
            for p in self.__particles:
                p.update_fitness(self.__fitness_func)
                if p.get_fitness() < self.__best_fitness:
                    self.__best_fitness = p.get_fitness()
                    self.__best_pos = p.get_pos()

            for p in self.__particles:
                new_vel = []
                for j in range(len(p.get_vel())):
                    r1 = random.uniform(0, 1)
                    r2 = random.uniform(0, 1)
                    cognitive_vel = self.__phi1 * r1 * (p.get_best_pos()[j] - p.get_pos()[j])
                    social_vel = self.__phi2 * r2 * (self.__best_pos[j] - p.get_pos()[j])
                    new_vel.append(self.__inertia_weight * p.get_vel()[j] + cognitive_vel + social_vel)
                p.set_vel(new_vel)
                p.move()

    def get_best_fitness(self):
        return self.__best_fitness

    def get_best_pos(self):
        return self.__best_pos

使用示例：

def sphere(x):
    return sum([xi ** 2 for xi in x])

pso = PSO(dim=10, size=50, minx=-10, maxx=10, fitness_func=sphere)
pso.run()
print("Best fitness: ", pso.get_best_fitness())
print("Best position: ", pso.get_best_pos())

该示例实现了一个简单的PSO算法，用于求解10维的Sphere函数的最小值。用户可以根据自己的需求修改fitness_func函数，来求解不同的优化问题。