%% 清空环境变量
warning off % 关闭报警信息
close all % 关闭开启的图窗
clear % 清空变量
clc % 清空命令行
%% 导入数据（时间序列的单列数据）
result = xlsread('data.xlsx');
%% 数据分析
num_samples = length(result); % 样本个数
kim = 15; % 延时步长（kim个历史数据作为自变量）
zim = 1; % 跨zim个时间点进行预测
%% 划分数据集
for i = 1: num_samples - kim - zim + 1
res(i, :) = [reshape(result(i: i + kim - 1), 1, kim), result(i + kim + zim - 1)];
end
%% 数据集分析
outdim = 1; % 最后一列为输出
num_size = 0.7; % 训练集占数据集比例
num_train_s = round(num_size * num_samples); % 训练集样本个数
f_ = size(res, 2) - outdim; % 输入特征维度
%% 划分训练集和测试集
P_train = res(1: num_train_s, 1: f_)';
T_train = res(1: num_train_s, f_ + 1: end)';
M = size(P_train, 2);
P_test = res(num_train_s + 1: end, 1: f_)';
T_test = res(num_train_s + 1: end, f_ + 1: end)';
N = size(P_test, 2);
%% 数据归一化
[P_train, ps_input] = mapminmax(P_train, 0, 1);
P_test = mapminmax('apply', P_test, ps_input);
[t_train, ps_output] = mapminmax(T_train, 0, 1);
t_test = mapminmax('apply', T_test, ps_output);
%% 数据平铺
P_train = double(reshape(P_train, f_ , 1, 1, M));
P_test = double(reshape(P_test , f_ , 1, 1, N));
t_train = t_train';
t_test = t_test' ;
%% 数据格式转换
for i = 1 : M
p_train{i, 1} = P_train(:, :, 1, i);
end
for i = 1 : N
p_test{i, 1} = P_test( :, :, 1, i);
end
%% 创建待优化函数
ObjFcn = @BOFunction;
%% 贝叶斯优化参数范围
optimVars = [
optimizableVariable('NumOfUnits', [10, 50], 'Type', 'integer')
optimizableVariable('InitialLearnRate', [1e-3, 1], 'Transform', 'log')
optimizableVariable('L2Regularization', [1e-10, 1e-2], 'Transform', 'log')];
%% 贝叶斯优化网络参数
BayesObject = bayesopt(ObjFcn, optimVars, ... % 优化函数，和参数范围
'MaxTime', Inf, ... % 优化时间（不限制）
'IsObjectiveDeterministic', false, ...
'MaxObjectiveEvaluations', 30, ... % 最大迭代次数
'Verbose', 1, ... % 显示优化过程
'UseParallel', false);
%% 得到最优参数
NumOfUnits = BayesObject.XAtMinEstimatedObjective.NumOfUnits; % 最佳隐藏层节点
InitialLearnRate = BayesObject.XAtMinEstimatedObjective.InitialLearnRate; % 最佳初始学习率
L2Regularization = BayesObject.XAtMinEstimatedObjective.L2Regularization; % 最佳L2正则化系数
%% 创建网络
layers = [ ...
sequenceInputLayer(f_) % 输入层
lstmLayer(NumOfUnits, 'OutputMode', 'last') % LSTM层
reluLayer % Relu激活层
dropoutLayer(0.2) % Dropout层
fullyConnectedLayer(1) % 全连接层
regressionLayer]; % 回归层
% 参数设置
options = trainingOptions('adam', ... % 优化算法Adam
'MaxEpochs', 800, ... % 最大训练次数
'GradientThreshold', 1, ... % 梯度阈值
'InitialLearnRate', InitialLearnRate, ... % 初始学习率
'LearnRateSchedule', 'piecewise', ... % 学习率调整
'LearnRateDropPeriod', 700, ... % 训练700次后开始调整学习率
'LearnRateDropFactor',0.2, ... % 学习率调整因子
'L2Regularization', L2Regularization, ... % 正则化参数
'ExecutionEnvironment', 'cpu',... % 训练环境
'Verbose', 0, ... % 关闭优化过程
'Plots', 'training-progress'); % 画出曲线
%% 训练
net = trainNetwork(p_train, t_train, layers, options);
%% 预测
t_sim1 = predict(net,p_train);
t_sim2 = predict(net,p_test);
%% 模型预测数据反归一化
T_sim1 = mapminmax('reverse', t_sim1', ps_output);
T_sim2 = mapminmax('reverse', t_sim2', ps_output);
%% 数据格式转换
T_sim1=double(T_sim1);
T_sim2=double(T_sim2);
%% 绘图
%% 测试集结果
% figure;
% plotregression(T_test,T_sim2,['回归图']);
% figure;
% ploterrhist(T_test-T_sim2,['误差直方图']);
%% 均方根误差 RMSE
error1 = sqrt(sum((T_sim1 - T_train).^2)./M);
error2 = sqrt(sum((T_test - T_sim2).^2)./N);
%%
%决定系数
R1 = 1 - norm(T_train - T_sim1)^2 / norm(T_train - mean(T_train))^2;
R2 = 1 - norm(T_test - T_sim2)^2 / norm(T_test - mean(T_test ))^2;
%%
%均方误差 MSE
mse1 = sum((T_sim1 - T_train).^2)./M;
mse2 = sum((T_sim2 - T_test).^2)./N;
%%
%RPD 剩余预测残差
SE1=std(T_sim1-T_train);
RPD1=std(T_train)/SE1;
SE=std(T_sim2-T_test);
RPD2=std(T_test)/SE;
%% 平均绝对误差MAE
MAE1 = mean(abs(T_train - T_sim1));
MAE2 = mean(abs(T_test - T_sim2));
%% 平均绝对百分比误差MAPE
MAPE1 = mean(abs((T_train - T_sim1)./T_train));
MAPE2 = mean(abs((T_test - T_sim2)./T_test));
%% 训练集绘图
figure
plot(T_sim1,'-','Color',[255 0 0]./255,'linewidth',1,'Markersize',5,'MarkerFaceColor',[250 0 0]./255)
hold on
plot(T_train,'-','Color',[150 150 150]./255,'linewidth',0.8,'Markersize',4,'MarkerFaceColor',[150 150 150]./255)
legend('BO-LSTM预测值','真实值')
xlabel('预测样本')
ylabel('预测结果')
string={'训练集预测结果对比';['(R^2 =' num2str(R1) ' RMSE= ' num2str(error1) ' MSE= ' num2str(mse1) ' RPD= ' num2str(RPD1) ')' ]};
title(string)
%% 训练集误差图
figure
bar((T_sim1 - T_train)./T_train)
legend('BO-LSTM模型训练集相对误差','Location','NorthEast','FontName','华文宋体')
title('BO-LSTM模型训练集相对误差','fontsize',12,'FontName','华文宋体')
ylabel('误差','fontsize',12,'FontName','华文宋体')
xlabel('样本','fontsize',12,'FontName','华文宋体')
xlim([1 M]);
%% 预测集绘图
figure
plot(T_sim2,'-','Color',[0 0 255]./255,'linewidth',1,'Markersize',5,'MarkerFaceColor',[0 0 255]./255)
hold on
plot(T_test,'-','Color',[0 0 0]./255,'linewidth',0.8,'Markersize',4,'MarkerFaceColor',[0 0 0]./255)
legend('BO-LSTM预测值','真实值')
xlabel('预测样本')
ylabel('预测结果')
string={'测试集预测结果对比';['(R^2 =' num2str(R2) ' RMSE= ' num2str(error2) ' MSE= ' num2str(mse2) ' RPD= ' num2str(RPD2) ')']};
title(string)
%% 测试集误差图
figure
bar((T_sim2 - T_test )./T_test)
legend('BO-LSTM模型测试集相对误差','Location','NorthEast','FontName','华文宋体')
title('BO-LSTM模型测试集相对误差','fontsize',12,'FontName','华文宋体')
ylabel('误差','fontsize',12,'FontName','华文宋体')
xlabel('样本','fontsize',12,'FontName','华文宋体')
xlim([1 N]);
%% 绘制线性拟合图
%% 训练集拟合效果图
figure
plot(T_train,T_sim1,'*r');
xlabel('真实值')
ylabel('预测值')
string = {'训练集效果图';['R^2_c=' num2str(R1) ' RMSEC=' num2str(error1) ]};
title(string)
hold on ;h=lsline;
set(h,'LineWidth',1,'LineStyle','-','Color',[1 0 1])
%% 预测集拟合效果图
figure
plot(T_test,T_sim2,'ob');
xlabel('真实值')
ylabel('预测值')
string1 = {'测试集效果图';['R^2_p=' num2str(R2) ' RMSEP=' num2str(error2) ]};
title(string1)
hold on ;h=lsline();
set(h,'LineWidth',1,'LineStyle','-','Color',[1 0 1])
%% 求平均
R3=(R1+R2)./2;
error3=(error1+error2)./2;
%% 总数据线性预测拟合图
tsim=[T_sim1,T_sim2]';
S=[T_train,T_test]';
figure
plot(S,tsim,'ob');
xlabel('真实值')
ylabel('预测值')
string1 = {'所有样本拟合预测图';['R^2_p=' num2str(R3) ' RMSEP=' num2str(error3) ]};
title(string1)
hold on ;h=lsline()
