哈里斯鹰优化算法的python

哈里斯鹰优化算法（Harris Hawks Optimization, HHO）是一种基于自然界中哈里斯鹰捕猎行为的元启发式优化算法。该算法通过模拟哈里斯鹰的协作捕猎策略来寻找问题的最优解。以下是哈里斯鹰优化算法的Python实现示例：

import numpy as np

class HHO:
    def __init__(self, objective_function, bounds, n_hawks, max_iter):
        self.objective_function = objective_function
        self.bounds = bounds
        self.n_hawks = n_hawks
        self.max_iter = max_iter
        self.dim = len(bounds)
        self.population = np.random.uniform(low=[b[0] for b in bounds],
                                            high=[b[1] for b in bounds],
                                            size=(self.n_hawks, self.dim))
        self.fitness = np.array([self.objective_function(individual) for individual in self.population])
        self.best_index = np.argmin(self.fitness)
        self.best_solution = self.population[self.best_index]
        self.best_fitness = self.fitness[self.best_index]

    def optimize(self):
        for iteration in range(self.max_iter):
            for i in range(self.n_hawks):
                E1 = 2 * (1 - (iteration / self.max_iter))
                E0 = -1 + np.random.random() * 2
                J = 2 * (1 - np.random.random())

                if np.abs(E0) >= 1:
                    # Exploration on the population
                    q = np.random.random()
                    rand_hawk_index = np.random.randint(0, self.n_hawks)
                    X_rand = self.population[rand_hawk_index]

                    if q < 0.5:
                        self.population[i] = X_rand - np.random.random() * np.abs(X_rand - 2 * np.random.random() * self.population[i])
                    else:
                        self.population[i] = (self.best_solution - self.population.mean(0)) - np.random.random() * (self.bounds[:, 0] + np.random.random() * (self.bounds[:, 1] - self.bounds[:, 0]))
                else:
                    # Exploitation by team work
                    if np.random.random() >= 0.5:
                        Y = self.best_solution - E1 * np.abs(self.best_solution - 2 * np.random.random() * self.population[i])
                    else:
                        X_rand = self.population[np.random.randint(0, self.n_hawks)]
                        Y = X_rand - E1 * np.abs(X_rand - 2 * np.random.random() * self.population[i])

                    self.population[i] = Y

            self.fitness = np.array([self.objective_function(individual) for individual in self.population])
            current_best_index = np.argmin(self.fitness)
            if self.fitness[current_best_index] < self.best_fitness:
                self.best_solution = self.population[current_best_index]
                self.best_fitness = self.fitness[current_best_index]

            print(f"Iteration {iteration+1}, Best Fitness: {self.best_fitness}")

        return self.best_solution, self.best_fitness

# Example usage
if __name__ == "__main__":
    def objective_function(x):
        return np.sum(x**2)

    bounds = [(-10, 10), (-10, 10)]
    n_hawks = 10
    max_iter = 50

    hho = HHO(objective_function, bounds, n_hawks, max_iter)
    best_solution, best_fitness = hho.optimize()
    print(f"Best Solution: {best_solution}, Best Fitness: {best_fitness}")