本实验使用环境为Anaconda3 Jupyter，调用Sklearn包，请提前准备好。
1 .常规软件包importcsvimportnumpyasnpfromsklearn.preprocessingimportstandardscalerfromsklearn.model _ selectionionimporttrarin imeimportdatetimefromsklearn.metricsimportexplained _ variance _ scorefromsklearn.svmimportsvv port mean _ squared _ erred efromsklearn.metricsimportconfusion _ matrixfromsklearn.metricsimportconfusion _ matrixfromsklearn n n _ reportfrtfromskleararn 由于efromsklearnimportmetricsfromsklearn.metricsimportmean _ metrics是时间序列预测，因此必须反转目标集和特征集。
#时间time=[]#特征feature=[]#目标target=[] csv_file=CSV.reader(open ('南沙水质数据. CSV ' ) ) forcontentincsv _ file 3333=0: feature.append (content (1: )=0:time.append(content ) targets=[ ] foriintarget : targets.append (I [0] ) feature.reverse ) ) targets .
#str为datetimetime_rel=[]for i，jinenumerate(time ) : time _ rel.append (datetime.strp time ) j ) 0，' % y
3 .使用数据标准化StandardScaler ()方法将特征数据标准化。
#标准化转换scaler=standardscaler(#培训标准化对象scaler.fit(feature ) #转换数据集feature=scaler.transform ) feature )4.支持
feature_train、feature_test、target_train、target _ test=train _ test_split (feature、targets、test _ split ) test_split random_state=8) feature_test=feature[int(len ) feature(*0.9 ) : int (len ) feature ) ] target _ test label _ time=time_rel [ int (len (time _ rel ) 0.9 ) : int (len ) time _ rel ) ] model _ SVR=SVR
legend(['True','SVR'])fig = plt.gcf()fig.set_size_inches(18.5, 10.5)plt.title("SVR") # 标题plt.show()print("MSE:",mean_squared_error(target_test,predict_results))print("R2 = ",metrics.r2_score(target_test,predict_results)) # R2print("MAE = ",mean_absolute_error(target_test,predict_results)) # R2最终结果如下：
精度过低，需要使用优化算法进行优化，本文选择PSO。
对SVR参数的惩罚参数C、损失函数epsilon、核系数gamma进行调参，设置其范围为[0,10]、[0,5]、[0,100]，可以自行设置。一共20代，每代20人，可以自行设置。
class PSO: def __init__(self, parameters): """ particle swarm optimization parameter: a list type, like [NGEN, pop_size, var_num_min, var_num_max] """ # 初始化 self.NGEN = parameters[0] # 迭代的代数 self.pop_size = parameters[1] # 种群大小 self.var_num = len(parameters[2]) # 变量个数 self.bound = [] # 变量的约束范围 self.bound.append(parameters[2]) self.bound.append(parameters[3]) self.pop_x = np.zeros((self.pop_size, self.var_num)) # 所有粒子的位置 self.pop_v = np.zeros((self.pop_size, self.var_num)) # 所有粒子的速度 self.p_best = np.zeros((self.pop_size, self.var_num)) # 每个粒子最优的位置 self.g_best = np.zeros((1, self.var_num)) # 全局最优的位置 # 初始化第0代初始全局最优解 temp = -1 for i in range(self.pop_size): for j in range(self.var_num): self.pop_x[i][j] = random.uniform(self.bound[0][j], self.bound[1][j]) self.pop_v[i][j] = random.uniform(0, 1) self.p_best[i] = self.pop_x[i] # 储存最优的个体 fit = self.fitness(self.p_best[i]) if fit > temp: self.g_best = self.p_best[i] temp = fit def fitness(self, ind_var): X = feature_train y = target_train """ 个体适应值计算 """ x1 = ind_var[0] x2 = ind_var[1] x3 = ind_var[2] if x1==0:x1=0.001 if x2==0:x2=0.001 if x3==0:x3=0.001 clf = SVR(C=x1,epsilon=x2,gamma=x3) clf.fit(X, y) predictval=clf.predict(feature_test) print("R2 = ",metrics.r2_score(target_test,predictval)) # R2 return metrics.r2_score(target_test,predictval) def update_operator(self, pop_size): """ 更新算子：更新下一时刻的位置和速度 """ c1 = 2 # 学习因子，一般为2 c2 = 2 w = 0.4 # 自身权重因子 for i in range(pop_size): # 更新速度 self.pop_v[i] = w * self.pop_v[i] + c1 * random.uniform(0, 1) * ( self.p_best[i] - self.pop_x[i]) + c2 * random.uniform(0, 1) * (self.g_best - self.pop_x[i]) # 更新位置 self.pop_x[i] = self.pop_x[i] + self.pop_v[i] # 越界保护 for j in range(self.var_num): if self.pop_x[i][j] < self.bound[0][j]: self.pop_x[i][j] = self.bound[0][j] if self.pop_x[i][j] > self.bound[1][j]: self.pop_x[i][j] = self.bound[1][j] # 更新p_best和g_best if self.fitness(self.pop_x[i]) > self.fitness(self.p_best[i]): self.p_best[i] = self.pop_x[i] if self.fitness(self.pop_x[i]) > self.fitness(self.g_best): self.g_best = self.pop_x[i] def main(self): popobj = [] self.ng_best = np.zeros((1, self.var_num))[0] for gen in range(self.NGEN): self.update_operator(self.pop_size) popobj.append(self.fitness(self.g_best)) print('############ Generation {} ############'.format(str(gen + 1))) if self.fitness(self.g_best) > self.fitness(self.ng_best): self.ng_best = self.g_best.copy() print('最好的位置：{}'.format(self.ng_best)) print('最大的函数值：{}'.format(self.fitness(self.ng_best))) print("---- End of (successful) Searching ----") plt.figure() fig = plt.gcf() fig.set_size_inches(18.5, 10.5) plt.title("Figure1") plt.xlabel("iterators", size=14) plt.ylabel("fitness", size=14) t = [t for t in range(self.NGEN)] plt.plot(t, popobj, color='b', linewidth=2) plt.show()跑起来～
if __name__ == '__main__': NGEN = 20 popsize = 20 low = [0,0,0] up = [10,5,100] parameters = [NGEN, popsize, low, up] pso = PSO(parameters) pso.main()最优适应值变化如下：
结果如下：
其各项评价指标均变优