【RF时序预测】基于随机森林算法的时间序列预测附matlab代码

%%  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('数据集.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%%  构造数据集for i = 1: num_samples - kim - zim + 1    res(i, :) = [reshape(result(i: i + kim - 1), 1, kim), result(i + kim + zim - 1)];end%%  划分训练集和测试集temp = 1: 1: 922;P_train = res(temp(1: 700), 1: 15)';T_train = res(temp(1: 700), 16)';M = size(P_train, 2);P_test = res(temp(701: end), 1: 15)';T_test = res(temp(701: end), 16)';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);%%  转置以适应模型p_train = p_train'; p_test = p_test';t_train = t_train'; t_test = t_test';%%  训练模型trees = 100;                                      % 决策树数目leaf  = 5;                                        % 最小叶子数OOBPrediction = 'on';                             % 打开误差图OOBPredictorImportance = 'on';                    % 计算特征重要性Method = 'regression';                            % 分类还是回归net = TreeBagger(trees, p_train, t_train, 'OOBPredictorImportance', OOBPredictorImportance,...      'Method', Method, 'OOBPrediction', OOBPrediction, 'minleaf', leaf);importance = net.OOBPermutedPredictorDeltaError;  % 重要性%%  仿真测试t_sim1 = predict(net, p_train);t_sim2 = predict(net, p_test );%%  数据反归一化T_sim1 = mapminmax('reverse', t_sim1, ps_output);T_sim2 = mapminmax('reverse', t_sim2, ps_output);%%  均方根误差error1 = sqrt(sum((T_sim1' - T_train).^2) ./ M);error2 = sqrt(sum((T_sim2' - T_test ).^2) ./ N);%%  绘图figureplot(1: M, T_train, 'r-', 1: M, T_sim1, 'b-', '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'; ['RMSE=' num2str(error1)]};title(string)xlim([1, M])gridfigureplot(1: N, T_test, 'r-', 1: N, T_sim2, 'b-', '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'; ['RMSE=' num2str(error2)]};title(string)xlim([1, N])grid%%  绘制误差曲线figureplot(1: trees, oobError(net), 'b-', 'LineWidth', 1)legend('误差曲线')xlabel('决策树数目')ylabel('误差')xlim([1, trees])grid%%  绘制特征重要性figurebar(importance)legend('重要性')xlabel('特征')ylabel('重要性')%%  相关指标计算% R2R1 = 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;disp(['训练集数据的R2为：', num2str(R1)])disp(['测试集数据的R2为：', num2str(R2)])% MAEmae1 = sum(abs(T_sim1' - T_train)) ./ M ;mae2 = sum(abs(T_sim2' - T_test )) ./ N ;disp(['训练集数据的MAE为：', num2str(mae1)])disp(['测试集数据的MAE为：', num2str(mae2)])% MBEmbe1 = sum(T_sim1' - T_train) ./ M ;mbe2 = sum(T_sim2' - T_test ) ./ N ;disp(['训练集数据的MBE为：', num2str(mbe1)])disp(['测试集数据的MBE为：', num2str(mbe2)])%%  绘制散点图sz = 25;c = 'b';figurescatter(T_train, T_sim1, sz, c)hold onplot(xlim, ylim, '--k')xlabel('训练集真实值');ylabel('训练集预测值');xlim([min(T_train) max(T_train)])ylim([min(T_sim1) max(T_sim1)])title('训练集预测值 vs. 训练集真实值')figurescatter(T_test, T_sim2, sz, c)hold onplot(xlim, ylim, '--k')xlabel('测试集真实值');ylabel('测试集预测值');xlim([min(T_test) max(T_test)])ylim([min(T_sim2) max(T_sim2)])title('测试集预测值 vs. 测试集真实值')