【GRU回归预测】基于matlab双向门控循环单元GRU数据预测（多输入单输出）【含Matlab源码 3248期】.zip

%% GRU多变量回归预测 海神之光 %% 加载数据与数据集划分 clc;clear;close all data = xlsread('data.xlsx', 'Sheet1', 'A3:M1250'); % 输入数据 input =data(:,1:12)'; output=data(:,13)'; nwhole =size(data,1); % 打乱数据集 % temp=randperm(nwhole); % 不打乱数据集 temp=1:nwhole; train_ratio=0.9; ntrain=round(nwhole*train_ratio); ntest =nwhole-ntrain; % 准备输入和输出训练数据 input_train =input(:,temp(1:ntrain)); output_train=output(:,temp(1:ntrain)); % 准备测试数据 input_test =input(:, temp(ntrain+1:ntrain+ntest)); output_test=output(:,temp(ntrain+1:ntrain+ntest)); %% 数据归一化 method=@mapminmax; [inputn_train,inputps]=method(input_train); inputn_test=method('apply',input_test,inputps); [outputn_train,outputps]=method(output_train); outputn_test=method('apply',output_test,outputps); % 创建元胞或向量，长度为训练集大小； XrTrain = cell(size(inputn_train,2),1); YrTrain = zeros(size(outputn_train,2),1); for i=1:size(inputn_train,2) XrTrain{i,1} = inputn_train(:,i); YrTrain(i,1) = outputn_train(:,i); end % 创建元胞或向量，长度为测试集大小； XrTest = cell(size(inputn_test,2),1); YrTest = zeros(size(outputn_test,2),1); for i=1:size(input_test,2) XrTest{i,1} = inputn_test(:,i); YrTest(i,1) = outputn_test(:,i); end %% 创建混合GRU网络架构 % 输入特征维度 numFeatures = size(inputn_train,1); % 输出特征维度 numResponses = 1; FiltZise = 10; % 创建"-GRU"模型 layers = [... % 输入特征 sequenceInputLayer([numFeatures 1 1],'Name','input') sequenceFoldingLayer('Name','fold') % 特征提取 % convolution2dLayer([FiltZise 1],32,'Padding','same','WeightsInitializer','he','Name','conv','DilationFactor',1); % batchNormalizationLayer('Name','bn') % eluLayer('Name','elu') % averagePooling2dLayer(1,'Stride',FiltZise,'Name','pool1') % 展开层 sequenceUnfoldingLayer('Name','unfold') % 平滑层 flattenLayer('Name','flatten') % GRU特征学习 gruLayer(128,'Name','BiGRU1','RecurrentWeightsInitializer','He','InputWeightsInitializer','He') % GRU输出 gruLayer(32,'OutputMode',"last",'Name','bil4','RecurrentWeightsInitializer','He','InputWeightsInitializer','He') % GRU特征学习 gruLayer(128,'Name','BiGRU2','RecurrentWeightsInitializer','He','InputWeightsInitializer','He') % GRU输出 gruLayer(32,'OutputMode',"last",'Name','bil2','RecurrentWeightsInitializer','He','InputWeightsInitializer','He') dropoutLayer(0.25,'Name','drop3') % 全连接层 fullyConnectedLayer(numResponses,'Name','fc') regressionLayer('Name','output') ]; layers = layerGraph(layers); layers = connectLayers(layers,'fold/miniBatchSize','unfold/miniBatchSize'); %%GRU训练选项 % 批处理样本 MiniBatchSize =24; % 最大迭代次数 MaxEpochs = 60; % 学习率 learningrate = 0.005; % 一些参数调整 if gpuDeviceCount>0 mydevice = 'gpu'; else mydevice = 'cpu'; end options = trainingOptions( 'adam', ... 'MaxEpochs',100, ... 'GradientThreshold',1, ... 'InitialLearnRate',learningrate, ... 'LearnRateSchedule','piecewise', ... 'LearnRateDropPeriod',20, ... 'LearnRateDropFactor',0.8, ... 'L2Regularization',1e-3,... 'Verbose',false, ... 'ExecutionEnvironment',mydevice,... 'Plots','training-progress'); %% 训练混合网络 % rng(0); % 训练 net = trainNetwork(XrTrain,YrTrain,layers,options); % 预测 YPredtrain = predict(net,XrTrain,"ExecutionEnvironment",mydevice,"MiniBatchSize",numFeatures); % 结果 YPredtrain =double(YPredtrain'); % 反归一化 GRUoutput_train=method('reverse',YPredtrain,outputps); GRUoutput_train=double(GRUoutput_train); % 预测 YPredtest = predict(net,XrTest,"ExecutionEnvironment",mydevice,"MiniBatchSize",numFeatures); % 结果 YPredtest =double(YPredtest'); % 反归一化 GRUoutput_test=method('reverse',YPredtest,outputps); GRUoutput_test=double(GRUoutput_test); %% 测试集误差评价 GRUerror_test=GRUoutput_test'-output_test'; GRUpererror_test=GRUerror_test./output_test'; % RMSE RMSEtest = sqrt(sumsqr(GRUerror_test)/length(output_test)); % MAPE MAPEtest = mean(abs(GRUpererror_test)); disp("——————BiGRU网络模型测试数据——————————") disp(" 预测值 真实值 误差 ") disp([GRUoutput_test' output_test' GRUerror_test]) %-------------------------------------------------------------------------- disp('BiGRU测试平均绝对误差百分比MAPE'); disp(MAPEtest) disp('BiGRU测试均方根误差RMSE') disp(RMSEtest) %-------------------------------------------------------------------------- %% 数据可视化 figure() plot(GRUoutput_test,'ro-','linewidth',2) hold on plot(output_test,'bs-','linewidth',2) legend( '测试数据','实际数据','Location','NorthWest','FontName','黑体'); title('BiGRU模型测试结果及真实值','fontsize',12,'FontName','黑体') xlabel('样本','fontsize',12,'FontName','黑体'); ylabel('数值','fontsize',12,'FontName','黑体'); xlim([1 ntest]); %------------------------------------------------------------------------------------- figure() plot(GRUerror_test,'ro-','Color',[1 0 0]./255,'linewidth',2) legend('BiGRU模型测试误差','Location','NorthEast','FontName','黑体') title('BiGRU模型测试误差','fontsize',12,'FontName','黑体') ylabel('误差','fontsize',12,'FontName','黑体') xlabel('样本','fontsize',12,'FontName','黑体') xlim([1 ntest]); %------------------------------------------------------------------------------------- figure() plot(GRUpererror_test,'bs-','Color',[128 110 255]./255,'linewidth',2) legend('BiGRU模型测试相对误差','Location','NorthEast','FontName','黑体') title('BiGRU模型测试相对误差','fontsize',12,'FontName','黑体') ylabel('误差','fontsize',12,'FontName','黑体') xlabel('样本','fontsize',12,'FontName','黑体') xlim([1 ntest]);