ML之回归预测:利用九大类机器学习算法对无人驾驶系统参数(2018年的data,18+2)进行回归预测+评估九种模型性能

简介: ML之回归预测:利用九大类机器学习算法对无人驾驶系统参数(2018年的data,18+2)进行回归预测+评估九种模型性能

输出记录


1、第一次输出错误记录


数据的初步查验:输出回归目标值的差异

The max target value is PeakNonedb    89

dtype: int64

The min target value is PeakNonedb    56

dtype: int64

The average target value is PeakNonedb    63.392157

dtype: float64


LiR LiR:The value of default measurement of LiR is 0.5231458055883893

LiR:R-squared value of DecisionTreeRegressor: 0.5231458055883893

LiR:The mean squared error of DecisionTreeRegressor: 25.294980943838745

LiR:The mean absoluate error of DecisionTreeRegressor: 3.608855227697136

LiR:测试141~153行数据,

[[ 747.01164105]

[1534.72506527]

[2569.73860794]

[3646.40436281]

[1579.9293663 ]

[2860.34593738]

[3736.26316737]

[3506.55843101]

[3519.97015753]

[3565.68403454]

[3666.57047459]

[3700.74687407]]

kNN

kNNR_uni:The value of default measurement of kNNR_uni is 0.5866024699259604

kNNR_uni:R-squared value of DecisionTreeRegressor: 0.5866024699259604

kNNR_uni:The mean squared error of DecisionTreeRegressor: 21.928888888888892

kNNR_uni:The mean absoluate error of DecisionTreeRegressor: 3.2111111111111117

kNNR_uni:测试141~153行数据,

[[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]

[0.64097829]]

kNNR_dis:The value of default measurement of kNNR_dis is 0.6601811947182363

kNNR_dis:R-squared value of DecisionTreeRegressor: 0.6601811947182363

kNNR_dis:The mean squared error of DecisionTreeRegressor: 18.02586682616158

kNNR_dis:The mean absoluate error of DecisionTreeRegressor: 2.847311210973169

kNNR_dis:测试141~153行数据,

[[0.64115297]

[0.64098617]

[0.64095601]

[0.64095674]

[0.64098432]

[0.64095655]

[0.64095685]

[0.64095705]

[0.64095705]

[0.64095715]

[0.6409569 ]

[0.64095699]]

SVM

linear_SVR:The value of default measurement of linear_SVR is 0.22831988148305604

linear_SVR:R-squared value of DecisionTreeRegressor: 0.22831988148305604

linear_SVR:The mean squared error of DecisionTreeRegressor: 40.93417678062064

linear_SVR:The mean absoluate error of DecisionTreeRegressor: 4.02480324908603

linear_SVR:测试141~153行数据,

[177.03008956 325.6232456  539.28353027 735.51485927 323.06294283

568.35867934 732.77017607 736.16626099 743.3919392  747.74854384

743.58244066 757.04564832]


poly_SVR:The value of default measurement of poly_SVR is 0.5579245050116022

poly_SVR:R-squared value of DecisionTreeRegressor: 0.5579245050116022

poly_SVR:The mean squared error of DecisionTreeRegressor: 23.45012658485137

poly_SVR:The mean absoluate error of DecisionTreeRegressor: 3.1855299673953557

poly_SVR:测试141~153行数据,

[-1.03092264e+06 -7.08914443e+06 -4.71673473e+07 -1.43965988e+08

-7.08197015e+06 -4.62519130e+07 -1.43821606e+08 -1.34024997e+08

-1.33032109e+08 -1.32825434e+08 -1.32921612e+08 -1.33055776e+08]


rbf_SVR:The value of default measurement of rbf_SVR is 0.48978384736121017

rbf_SVR:R-squared value of DecisionTreeRegressor: 0.48978384736121017

rbf_SVR:The mean squared error of DecisionTreeRegressor: 27.064683522730615

rbf_SVR:The mean absoluate error of DecisionTreeRegressor: 3.248361364253994

rbf_SVR:测试141~153行数据,

[0.38231553 0.38231553 0.38231553 0.38231553 0.38231553 0.38231553

0.38231553 0.38231553 0.38231553 0.38231553 0.38231553 0.38231553]

DT DTR:The value of default measurement of DTR is 0.2302209550962223

DTR:R-squared value of DecisionTreeRegressor: 0.2302209550962223

DTR:The mean squared error of DecisionTreeRegressor: 40.833333333333336

DTR:The mean absoluate error of DecisionTreeRegressor: 4.111111111111111

DTR:测试141~153行数据,

[3.89129343 3.89129343 3.89129343 3.89129343 3.89129343 3.89129343

3.89129343 3.89129343 3.89129343 3.89129343 3.89129343 3.89129343]

RF RFR:The value of default measurement of RFR is 0.6240708685469911

RFR:R-squared value of DecisionTreeRegressor: 0.6240708685469911

RFR:The mean squared error of DecisionTreeRegressor: 19.941358024691358

RFR:The mean absoluate error of DecisionTreeRegressor: 2.9907407407407405

RFR:测试141~153行数据

[2.89029058 3.09049115 3.09049115 3.09049115 3.09049115 3.09049115

3.09049115 2.90206708 3.10226765 3.10226765 3.09049115 3.09049115]

ETR ETR:The value of default measurement of ETR is 0.7190149388336945

ETR:R-squared value of DecisionTreeRegressor: 0.7190149388336945

ETR:The mean squared error of DecisionTreeRegressor: 14.904999999999989

ETR:The mean absoluate error of DecisionTreeRegressor: 2.6666666666666656

ETR:测试141~153行数据

[2.51344245 2.54877196 2.54877196 2.54877196 2.54877196 2.54877196

2.54877196 2.33679488 2.54877196 2.54877196 2.54877196 2.54877196]

GB/GD

SGDR:The value of default measurement of SGDR is 0.4691791802079268

SGDR:R-squared value of DecisionTreeRegressor: 0.4691791802079268

SGDR:The mean squared error of DecisionTreeRegressor: 28.157668902967323

SGDR:The mean absoluate error of DecisionTreeRegressor: 3.693309750338626

SGDR:测试141~153行数据

[125.22055498 181.45266125 288.54749558 392.31320313 184.45855476

292.27252144 396.6089051  407.38658412 406.82100285 407.48230658

408.14902864 407.91771216]


GBR:The value of default measurement of GBR is 0.6340219593738237

GBR:R-squared value of DecisionTreeRegressor: 0.6340219593738237

GBR:The mean squared error of DecisionTreeRegressor: 19.413497190530663

GBR:The mean absoluate error of DecisionTreeRegressor: 2.792040256427659

GBR:测试141~153行数据

[2.79877177 3.34564311 3.34564311 3.41538604 3.48125832 3.40431433

3.41538604 2.88403709 3.41983671 3.41983671 3.41983671 3.41983671]

LGB [LightGBM] [Warning] feature_fraction is set=0.6, colsample_bytree=1.0 will be ignored. Current value: feature_fraction=0.6

[LightGBM] [Warning] min_data_in_leaf is set=18, min_child_samples=20 will be ignored. Current value: min_data_in_leaf=18

[LightGBM] [Warning] min_sum_hessian_in_leaf is set=0.001, min_child_weight=0.001 will be ignored. Current value: min_sum_hessian_in_leaf=0.001

[LightGBM] [Warning] bagging_fraction is set=0.7, subsample=1.0 will be ignored. Current value: bagging_fraction=0.7

LGB:The value of default measurement of LGB is 0.7257085935738725

LGB:R-squared value of DecisionTreeRegressor: 0.6340219593738237

LGB:The mean squared error of DecisionTreeRegressor: 19.413497190530663

LGB:The mean absoluate error of DecisionTreeRegressor: 2.792040256427659

LGB:测试141~153行数据

[2.35312797 2.34599463 2.34599463 2.34599463 2.34599463 2.34599463

2.34599463 2.34599463 2.34599463 2.34599463 2.34599463 2.34599463]

2、第二次输出评估模型性能记录


LiR LiR:The value of default measurement of LiR is 0.5231458055883893

LiR:R-squared value of DecisionTreeRegressor: 0.5231458055883893

LiR:The mean squared error of DecisionTreeRegressor: 25.294980943838745

LiR:The mean absoluate error of DecisionTreeRegressor: 3.608855227697136

kNN

kNNR_uni:The value of default measurement of kNNR_uni is 0.5866024699259604

kNNR_uni:R-squared value of DecisionTreeRegressor: 0.5866024699259604

kNNR_uni:The mean squared error of DecisionTreeRegressor: 21.928888888888892

kNNR_uni:The mean absoluate error of DecisionTreeRegressor: 3.2111111111111117


kNNR_dis:The value of default measurement of kNNR_dis is 0.6601811947182363

kNNR_dis:R-squared value of DecisionTreeRegressor: 0.6601811947182363

kNNR_dis:The mean squared error of DecisionTreeRegressor: 18.02586682616158

kNNR_dis:The mean absoluate error of DecisionTreeRegressor: 2.847311210973169

SVM

linear_SVR:The value of default measurement of linear_SVR is 0.22831988148305604

linear_SVR:R-squared value of DecisionTreeRegressor: 0.22831988148305604

linear_SVR:The mean squared error of DecisionTreeRegressor: 40.93417678062064

linear_SVR:The mean absoluate error of DecisionTreeRegressor: 4.02480324908603


poly_SVR:The value of default measurement of poly_SVR is 0.5579245050116022

poly_SVR:R-squared value of DecisionTreeRegressor: 0.5579245050116022

poly_SVR:The mean squared error of DecisionTreeRegressor: 23.45012658485137

poly_SVR:The mean absoluate error of DecisionTreeRegressor: 3.1855299673953557


rbf_SVR:The value of default measurement of rbf_SVR is 0.48978384736121017

rbf_SVR:R-squared value of DecisionTreeRegressor: 0.48978384736121017

rbf_SVR:The mean squared error of DecisionTreeRegressor: 27.064683522730615

rbf_SVR:The mean absoluate error of DecisionTreeRegressor: 3.248361364253994

DT DTR:The value of default measurement of DTR is -0.3190975606208273

DTR:R-squared value of DecisionTreeRegressor: -0.3190975606208273

DTR:The mean squared error of DecisionTreeRegressor: 69.97222222222223

DTR:The mean absoluate error of DecisionTreeRegressor: 5.027777777777778

RF RFR:The value of default measurement of RFR is 0.6920860546642035

RFR:R-squared value of DecisionTreeRegressor: 0.6920860546642035

RFR:The mean squared error of DecisionTreeRegressor: 16.333456790123456

RFR:The mean absoluate error of DecisionTreeRegressor: 2.861111111111111

ETR ETR:The value of default measurement of ETR is 0.6602917945510349

ETR:R-squared value of DecisionTreeRegressor: 0.6602917945510349

ETR:The mean squared error of DecisionTreeRegressor: 18.019999999999996

ETR:The mean absoluate error of DecisionTreeRegressor: 3.0055555555555555

GB/GD

SGDR:The value of default measurement of SGDR is 0.46348293353800685

SGDR:R-squared value of DecisionTreeRegressor: 0.46348293353800685

SGDR:The mean squared error of DecisionTreeRegressor: 28.459829296344633

SGDR:The mean absoluate error of DecisionTreeRegressor: 3.706383834628725


GBR:The value of default measurement of GBR is 0.6242967693280365

GBR:R-squared value of DecisionTreeRegressor: 0.6242967693280366

GBR:The mean squared error of DecisionTreeRegressor: 19.92937499923262

GBR:The mean absoluate error of DecisionTreeRegressor: 2.8923697398449524

LGB

[LightGBM] [Warning] feature_fraction is set=0.6, colsample_bytree=1.0 will be ignored. Current value: feature_fraction=0.6

[LightGBM] [Warning] min_data_in_leaf is set=18, min_child_samples=20 will be ignored. Current value: min_data_in_leaf=18

[LightGBM] [Warning] min_sum_hessian_in_leaf is set=0.001, min_child_weight=0.001 will be ignored. Current value: min_sum_hessian_in_leaf=0.001

[LightGBM] [Warning] bagging_fraction is set=0.7, subsample=1.0 will be ignored. Current value: bagging_fraction=0.7


LGB:The value of default measurement of LGB is 0.7257085935738725

LGB:R-squared value of DecisionTreeRegressor: 0.7257085935738725

LGB:The mean squared error of DecisionTreeRegressor: 14.54993157220446

LGB:The mean absoluate error of DecisionTreeRegressor: 2.9797938407355122



相关文章
|
人工智能 自然语言处理 IDE
模型微调不再被代码难住!PAI和Qwen3-Coder加速AI开发新体验
通义千问 AI 编程大模型 Qwen3-Coder 正式开源,阿里云人工智能平台 PAI 支持云上一键部署 Qwen3-Coder 模型,并可在交互式建模环境中使用 Qwen3-Coder 模型。
1737 109
|
人工智能 自然语言处理 运维
【新模型速递】PAI-Model Gallery云上一键部署Kimi K2模型
月之暗面发布开源模型Kimi K2,采用MoE架构,参数达1T,激活参数32B,具备强代码能力及Agent任务处理优势。在编程、工具调用、数学推理测试中表现优异。阿里云PAI-Model Gallery已支持云端部署,提供企业级方案。
772 0
【新模型速递】PAI-Model Gallery云上一键部署Kimi K2模型
|
算法 机器人
基于SOA海鸥优化算法的PID控制器最优控制参数计算matlab仿真
本课题研究基于海鸥优化算法(SOA)优化PID控制器参数的方法,通过MATLAB仿真对比传统PID控制效果。利用SOA算法优化PID的kp、ki、kd参数,以积分绝对误差(IAE)为适应度函数,提升系统响应速度与稳定性。仿真结果表明,SOA优化的PID控制器在阶跃响应和误差控制方面均优于传统方法,具有更快的收敛速度和更强的全局寻优能力,适用于复杂系统的参数整定。
|
算法 Python
粒子群算法对pi控制器进行参数优化,随时优化pi参数以控制直流无刷电机转速(Simulink仿真实现)
粒子群算法对pi控制器进行参数优化,随时优化pi参数以控制直流无刷电机转速(Simulink仿真实现)
458 9
|
机器学习/深度学习 人工智能 算法
【基于TTNRBO优化DBN回归预测】基于瞬态三角牛顿-拉夫逊优化算法(TTNRBO)优化深度信念网络(DBN)数据回归预测研究(Matlab代码实现)
【基于TTNRBO优化DBN回归预测】基于瞬态三角牛顿-拉夫逊优化算法(TTNRBO)优化深度信念网络(DBN)数据回归预测研究(Matlab代码实现)
478 0
|
人工智能 自然语言处理 运维
【新模型速递】PAI-Model Gallery云上一键部署gpt-oss系列模型
阿里云 PAI-Model Gallery 已同步接入 gpt-oss 系列模型,提供企业级部署方案。
|
机器学习/深度学习 编解码 并行计算
【创新未发表!】基于BKA算法优化-BP、HO算法优化-BP、CP算法优化-BP、GOOSE算法优化-BP、NRBO算法优化-BP神经网络回归预测比较研究(Matlab代码)
【创新未发表!】基于BKA算法优化-BP、HO算法优化-BP、CP算法优化-BP、GOOSE算法优化-BP、NRBO算法优化-BP神经网络回归预测比较研究(Matlab代码)
620 0
|
机器学习/深度学习 数据采集 人工智能
【机器学习算法篇】K-近邻算法
K近邻(KNN)是一种基于“物以类聚”思想的监督学习算法,通过计算样本间距离,选取最近K个邻居投票决定类别。支持多种距离度量,如欧式、曼哈顿、余弦相似度等,适用于分类与回归任务。结合Scikit-learn可高效实现,需合理选择K值并进行数据预处理,常用于鸢尾花分类等经典案例。(238字)
|
机器学习/深度学习 算法 数据挖掘
K-means聚类算法是机器学习中常用的一种聚类方法,通过将数据集划分为K个簇来简化数据结构
K-means聚类算法是机器学习中常用的一种聚类方法,通过将数据集划分为K个簇来简化数据结构。本文介绍了K-means算法的基本原理,包括初始化、数据点分配与簇中心更新等步骤,以及如何在Python中实现该算法,最后讨论了其优缺点及应用场景。
1961 6
|
机器学习/深度学习 数据采集 人工智能
20分钟掌握机器学习算法指南
在短短20分钟内,从零开始理解主流机器学习算法的工作原理,掌握算法选择策略,并建立对神经网络的直观认识。本文用通俗易懂的语言和生动的比喻,帮助你告别算法选择的困惑,轻松踏入AI的大门。
1141 8

热门文章

最新文章