% 环境准备
clc;
clear;
warning off;
data = xlsread('dataC.xlsx', 'Sheet1');
x=data(:,1:end-1);
y=data(:,end);
% 求因子维度
[r,c]=size(x);
% 求因子均值
aver=mean(x);
% 求因子标准差
stdcov=std(x);
% 求目标均值
y_aver=mean(y);
% 求目标方差
y_stdcov=std(y);
% 数据标准化
stdarr=(x-aver(ones(r,1),:))./stdcov(ones(r,1),:);
std_y=(y-y_aver(ones(r,1)))./y_stdcov(ones(r,1));
% 计算相关系数矩阵
covArr=cov(stdarr);
%% 相关系数矩阵进行主成分分析
[pc1,latent,explain]=pcacov(covArr);
d=repmat(sign(sum(pc1)),size(pc1,1),1);
pc=pc1.*d;
sumcontr=0;
i=1;
% 选取贡献率大于90%的主成分
er=90;
while sumcontr<er
sumcontr=sumcontr+explain(i);
i=i+1;
end
pcNum=i-1;
% 计算各个主成分
F=stdarr*pc(:,1:pcNum);
FF=[ones(r,1),F];
Fcoeff=regress(std_y,FF);
Recoeff=pc(:,1:pcNum)*Fcoeff(2:pcNum+1,:);
result(1)=Fcoeff(1);
result(2:c+1)=Recoeff;
y_p=Fcoeff(1)+stdarr*Recoeff;
y_p=y_p.*y_stdcov(ones(r,1))+y_aver(ones(r,1));
%% GRU
res = [F y];
%% 数据分析
num_size = 0.9; % 训练集占数据集比例
outdim = 1; % 最后一列为输出
num_samples = size(res, 1); % 样本个数
res = res(randperm(num_samples), :); % 打乱数据集（不希望打乱时，注释该行）
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 = categorical(T_train)';
t_test = categorical(T_test )';
%% 数据平铺
% 将数据平铺成1维数据只是一种处理方式
% 也可以平铺成2维数据，以及3维数据，需要修改对应模型结构
% 但是应该始终和输入层数据结构保持一致
P_train = double(reshape(P_train, 5, 1, 1, M));
P_test = double(reshape(P_test , 5, 1, 1, N));
%% 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
%% 创建网络
layers = [ ...
sequenceInputLayer(5) % 输入层
gruLayer(6, 'OutputMode', 'last') % GRU层
reluLayer % Relu激活层
fullyConnectedLayer(4) % 全连接层
softmaxLayer % 分类层
classificationLayer];
%% 参数设置
options = trainingOptions('adam', ... % Adam 梯度下降算法
'MiniBatchSize', 100, ... % 批大小
'MaxEpochs', 1000, ... % 最大迭代次数
'InitialLearnRate', 1e-2, ... % 初始学习率
'LearnRateSchedule', 'piecewise', ... % 学习率下降
'LearnRateDropFactor', 0.1, ... % 学习率下降因子
'LearnRateDropPeriod', 700, ... % 经过700次训练后 学习率为 0.01 * 0.1
'Shuffle', 'every-epoch', ... % 每次训练打乱数据集
'ValidationPatience', Inf, ... % 关闭验证
'Plots', 'training-progress', ... % 画出曲线
'Verbose', false);
%% 训练模型
net = trainNetwork(p_train, t_train, layers, options);
%% 仿真预测
t_sim1 = predict(net, p_train);
t_sim2 = predict(net, p_test );
%% 数据反归一化
T_sim1 = vec2ind(t_sim1');
T_sim2 = vec2ind(t_sim2');
%% 性能评价
error1 = sum((T_sim1 == T_train)) / M * 100 ;
error2 = sum((T_sim2 == T_test )) / N * 100 ;
%% 查看网络结构
analyzeNetwork(net)
%% 数据排序
[T_train, index_1] = sort(T_train);
[T_test , index_2] = sort(T_test );
T_sim1 = T_sim1(index_1);
T_sim2 = T_sim2(index_2);
%% 绘图
figure
percent_explained = 100*explain / sum(explain);
[H,ax] =pareto(percent_explained);
xlabel('主成分')
ylabel('贡献率(%)')
title('主成分贡献率')
figure
plot(1: M, T_train, 'r-*', 1: M, T_sim1, 'b-o', 'LineWidth', 1)
legend('真实值', '预测值')
xlabel('预测样本')
ylabel('预测结果')
string = {'训练集预测结果对比'; ['准确率=' num2str(error1) '%']};
title(string)
xlim([1, M])
grid
figure
plot(1: N, T_test, 'r-*', 1: N, T_sim2, 'b-o', 'LineWidth', 1)
legend('真实值', '预测值')
xlabel('预测样本')
ylabel('预测结果')
string = {'测试集预测结果对比'; ['准确率=' num2str(error2) '%']};
title(string)
xlim([1, N])
grid
%% 混淆矩阵
figure
cm = confusionchart(T_train, T_sim1);
cm.Title = 'Confusion Matrix for Train Data';
cm.ColumnSummary = 'column-normalized';
cm.RowSummary = 'row-normalized';
figure
cm = confusionchart(T_test, T_sim2);
cm.Title = 'Confusion Matrix for Test Data';
cm.ColumnSummary = 'column-normalized';
cm.RowSummary = 'row-normalized';
