长短期神经网络LSTM的博文分类，长短期神经网络微博博文分类（代码完整，数据齐全）

%% LSTM network %% import data clc clear close all %读取double格式数据 % [num0,ax,ay] = xlsread('emddata.xlsx'); % save maydata.mat num0 load maydata.mat numz = zeros(7,36); for hh = 1:7 num1 = num0(hh,:); num = []; for ii = 1:length(num1)-3 num = [num;num1(ii:ii+3)]; end n = 1:length(num); m=round(0.95*length(n)); input_train =num(n(1:m),1:3 );%训练数据输出数据 output_train = num(n(1:m),4);%训练数据输入数据 input_test = num(n(m),1:3);%测试数据输出数据 output_test = num(n(m+1:end),4);%测试数据输入数据 [inputn,inputps]=mapminmax(input_train',-1,1);%训练数据的输入数据的归一化 [outputn,outputps]=mapminmax(output_train',-1,1);%训练数据的输出数据的归一化de inputn_test=mapminmax('apply',input_test',inputps); %% Define Network Architecture % Define the network architecture. numFeatures = 3;%输入层维度 numResponses =1;%输出维度 % 200 hidden units numHiddenUnits = 50;%第一层维度 % a fully connected layer of size 50 & a dropout layer with dropout probability 0.5 layers = [ ... sequenceInputLayer(numFeatures)%输入层 lstmLayer(numHiddenUnits,'OutputMode','sequence')%第一层 fullyConnectedLayer(100)%链接层 dropoutLayer(0.06)%遗忘层 fullyConnectedLayer(numResponses)%链接层 regressionLayer];%回归层 % Specify the training options. % Train for 60 epochs with mini-batches of size 20 using the solver 'adam' maxEpochs = 60;%最大迭代次数 miniBatchSize =2;%最小批量 % the learning rate == 0.01 % set the gradient threshold to 1 % set 'Shuffle' to 'never' options = trainingOptions('adam', ... %解算器 'MaxEpochs',maxEpochs, ... %最大迭代次数 'MiniBatchSize',miniBatchSize, ... %最小批次 'InitialLearnRate',0.01, ... %初始学习率 'GradientThreshold',0.1, ... %梯度阈值 'Shuffle','every-epoch', ... %打乱顺序 'Plots','none',... %画图training-progress 'Verbose',0); %不输出训练过程 %% Train the Network net = trainNetwork(inputn,outputn,layers,options);%开始训练 % save maydata.mat %% Test the Network y_pred = predict(net,inputn_test,'MiniBatchSize',miniBatchSize)';%测试仿真输出 [y_pred1]=(mapminmax('reverse',y_pred',outputps)); % y_pred0 = predict(net,inputn,'MiniBatchSize',1)';%训练拟合值 % y_pred0=(mapminmax('reverse',y_pred0',outputps))'; % y_pred2=double(y_pred1'); yuce = zeros(1,length(n)-m); for cc = 1:length(n)-m inputn_test = [inputn_test(2:3) ;y_pred];%去掉第一个输入，加入刚预测得到值为最后一个输入 y_pred = predict(net,inputn_test,'MiniBatchSize',miniBatchSize)';%测试仿真输出 yuce(cc) = y_pred; end yucez=(mapminmax('reverse',yuce,outputps)); numz(hh,:)= yucez;%保存预测值 figure plot(output_test,'k-*') hold on plot(yucez,'r-o') hold off end