浣熊算法优化ELM实现回归预测(python)

import numpy as np import random import math import copy ''' 种群初始化函数 ''' def initial(pop, dim, ub, lb): X = np.zeros([pop, dim]) for i in range(pop): for j in range(dim): X[i, j] = random.random() * (ub[j] - lb[j]) + lb[j] return X, lb, ub '''边界检查函数''' def BorderCheck(X, ub, lb, pop, dim): for i in range(pop): for j in range(dim): if X[i, j] > ub[j]: X[i, j] = ub[j] elif X[i, j] < lb[j]: X[i, j] = lb[j] return X '''计算适应度函数''' def CaculateFitness(X, fun): pop = X.shape[0] fitness = np.zeros([pop, 1]) for i in range(pop): fitness[i], model = fun(X[i, :]) return fitness '''适应度排序''' def SortFitness(Fit): fitness = np.sort(Fit, axis=0) index = np.argsort(Fit, axis=0) return fitness, index '''根据适应度对位置进行排序''' def SortPosition(X, index): Xnew = np.zeros(X.shape) for i in range(X.shape[0]): Xnew[i, :] = X[index[i], :] return Xnew '''浣熊优化算法''' def COA(pop, dim, lb, ub, MaxIter, fun): X, lb, ub = initial(pop, dim, ub, lb) # 初始化种群 fitness = CaculateFitness(X, fun) # 计算适应度值 indexBest = np.argmin(fitness) GbestScore = copy.copy(fitness[indexBest]) GbestPositon = np.zeros([1, dim]) GbestPositon[0, :] = copy.copy(X[indexBest, :]) Curve = np.zeros([MaxIter, 1]) for t in range(MaxIter): print("第" + str(t) + "次迭代") # 阶段一： for i in range(int(pop / 2)): I = int(round(1 + np.random.random())) # {1,2}中的随机数 iguana = copy.copy(GbestPositon[0, :]) Xp = np.zeros([1, dim]) Xp[0, :] = X[i, :] + np.random.random() * (iguana - I * X[i, :]) for j in range(dim): if Xp[0, j] > ub[j]: Xp[0, j] = ub[j] if Xp[0, j] < lb[j]: Xp[0, j] = lb[j] fitNew, model = fun(Xp[0, :]) if fitNew < fitness[i]: X[i, :] = copy.copy(Xp[0, :]) fitness[i] = fitNew for i in range(int(pop / 2), pop): iguana = lb.T + np.random.random() * (ub.T - lb.T) iguana = iguana.reshape(dim) FHL, model = fun(iguana) I = int(round(1 + np.random.random())) # {1,2}中的随机数 Xp = np.zeros([1, dim]) if fitness[i] > FHL: Xp[0, :] = X[i, :] + np.random.random() * (iguana - I * X[i, :]) else: Xp[0, :] = X[i, :] + np.random.random() * (X[i, :] - iguana) for j in range(dim): if Xp[0, j] > ub[j]: Xp[0, j] = ub[j] if Xp[0, j] < lb[j]: Xp[0, j] = lb[j] fitTemp, model = fun(Xp[0, :]) if fitTemp < fitness[i]: fitness[i] = fitTemp X[i, :] = copy.copy(Xp[0, :]) # 阶段二： for i in range(pop): low = lb / (t + 1) high = ub / (t + 1) Xp2 = np.zeros([1, dim]) Xp2[0, :] = X[i, :] + (1 - 2 * np.random.random()) * (low.T + np.random.random() * (high.T - low.T)) for j in range(dim): if Xp2[0, j] > high[j]: Xp2[0, j] = high[j] if Xp2[0, j] < low[j]: Xp2[0, j] = low[j] fitTemp, model = fun(Xp2[0, :]) if fitTemp < fitness[i]: fitness[i] = fitTemp X[i, :] = copy.copy(Xp2[0, :]) X = BorderCheck(X, ub, lb, pop, dim) fitness = CaculateFitness(X, fun) indexBest = np.argmin(fitness) indexWorst = np.argmax(fitness) if fitness[indexBest] <= GbestScore: # 更新全局最优 GbestScore = copy.copy(fitness[indexBest]) GbestPositon[0, :] = copy.copy(X[indexBest, :]) Curve[t] = GbestScore return GbestScore, GbestPositon, Curve