README_CN.md

一个公平、可扩展的时间序列预测基准库和工具包

English | 简体中文

---

🎉 快速上手 | 💡 总体设计

📦 数据集 (Dataset) | 🛠️ 数据缩放 (Scaler) | 🧠 模型约定 (Model) | 📉 评估指标 (Metrics)

🏃‍♂️ 执行器 (Runner) | 📜 配置文件 (Config) | 📜 基线模型 (Baselines)

$\text{BasicTS}^{+}$ (Basic Time Series) 是一个面向时间序列预测的基准库和工具箱，现已支持时空预测、长序列预测等多种任务与数据集，涵盖统计模型、机器学习模型、深度学习模型等多类算法，为开发和评估时间序列预测模型提供了理想的工具。

如果你觉得这个项目对你有帮助，别忘了给个⭐Star支持一下，非常感谢！

BasicTS 一方面通过 统一且标准化的流程，为热门的深度学习模型提供了 公平且全面 的复现与对比平台。

另一方面，BasicTS 提供了用户 友好且易于扩展 的接口，帮助快速设计和评估新模型。用户只需定义模型结构，便可轻松完成基本操作。

你可以在快速上手找到详细的教程。另外，我们正在收集 ToDo 和 HowTo，如果您需要更多功能（例如：更多数据集或基准模型）或教程，欢迎提出 issue 或在此处留言。

Important

如果本项目对您有用，请考虑引用下面的论文:

@article{shao2023exploring,
   title={Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis},
   author={Shao, Zezhi and Wang, Fei and Xu, Yongjun and Wei, Wei and Yu, Chengqing and Zhang, Zhao and Yao, Di and Jin, Guangyin and Cao, Xin and Cong, Gao and others},
   journal={arXiv preprint arXiv:2310.06119},
   year={2023}
 }

🔥🔥🔥 该论文已被IEEE TKDE录用！你可以在这里查看论文。 🔥🔥🔥

✨ 主要功能亮点

公平的性能评估：

通过统一且全面的流程，用户能够公平且充分地对比不同模型在任意数据集上的性能表现。

使用 BasicTS 进行开发你可以：

最简代码实现

用户只需实现关键部分如模型架构、数据预处理和后处理，即可构建自己的深度学习项目。

基于配置文件控制一切

用户可以通过配置文件掌控流程中的所有细节，包括数据加载器的超参数、优化策略以及其他技巧（如课程学习）。

支持所有设备

BasicTS 支持 CPU、GPU 以及分布式 GPU 训练（单节点多 GPU 和多节点），依托 EasyTorch 作为后端。用户只需通过设置参数即可使用这些功能，无需修改代码。

保存训练日志

BasicTS 提供 `logging` 日志系统和 `Tensorboard` 支持，并统一封装接口，用户可以通过简便的接口调用来保存自定义的训练日志。

🚀 安装和快速上手

详细的安装步骤请参考 快速上手 教程。

📦 支持的模型

BasicTS 实现了丰富的基线模型，包括经典模型、时空预测模型和长序列预测模型等。

这些模型的代码实现可在 baselines 目录中找到。

下表中的代码链接（💻Code） 指向了相关论文的官方实现，感谢各位作者对代码的开源贡献！

时空预测

📊Baseline	📝Title	📄Paper	💻Code	🏛Venue	🎯Task
BigST	Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks	Link	Link	VLDB'24	STF
STDMAE	Spatio-Temporal-Decoupled Masked Pre-training for Traffic Forecasting	Link	Link	IJCAI'24	STF
STWave	When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks	Link	Link	ICDE'23	STF
STAEformer	Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting	Link	Link	CIKM'23	STF
MegaCRN	Spatio-Temporal Meta-Graph Learning for Traffic Forecasting	Link	Link	AAAI'23	STF
DGCRN	Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution	Link	Link	ACM TKDD'23	STF
STID	Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting	Link	Link	CIKM'22	STF
STEP	Pretraining Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting	Link	Link	SIGKDD'22	STF
D2STGNN	Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting	Link	Link	VLDB'22	STF
STNorm	Spatial and Temporal Normalization for Multi-variate Time Series Forecasting	Link	Link	SIGKDD'21	STF
STGODE	Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting	Link	Link	SIGKDD'21	STF
GTS	Discrete Graph Structure Learning for Forecasting Multiple Time Series	Link	Link	ICLR'21	STF
StemGNN	Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting	Link	Link	NeurIPS'20	STF
MTGNN	Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks	Link	Link	SIGKDD'20	STF
AGCRN	Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting	Link	Link	NeurIPS'20	STF
GWNet	Graph WaveNet for Deep Spatial-Temporal Graph Modeling	Link	Link	IJCAI'19	STF
STGCN	Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting	Link	Link	IJCAI'18	STF
DCRNN	Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting	Link	Link1, Link2	ICLR'18	STF

Long-Term Time Series Forecasting

📊Baseline	📝Title	📄Paper	💻Code	🏛Venue	🎯Task
GLAFF	Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective	Link	Link	NeurIPS'24	LTSF
CycleNet	CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns Forecasting	Link	Link	NeurIPS'24	LTSF
Fredformer	Fredformer: Frequency Debiased Transformer for Time Series Forecasting	Link	Link	KDD'24	LTSF
UMixer	An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting	Link	Link	AAAI'24	LTSF
TimeMixer	Decomposable Multiscale Mixing for Time Series Forecasting	Link	Link	ICLR'24	LTSF
Time-LLM	Time-LLM: Time Series Forecasting by Reprogramming Large Language Models	Link	Link	ICLR'24	LTSF
SparseTSF	Modeling LTSF with 1k Parameters	Link	Link	ICML'24	LTSF
iTrainsformer	Inverted Transformers Are Effective for Time Series Forecasting	Link	Link	ICLR'24	LTSF
Koopa	Learning Non-stationary Time Series Dynamics with Koopman Predictors	Link	Link	NeurIPS'24	LTSF
CrossGNN	CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement	Link	Link	NeurIPS'23	LTSF
NLinear	Are Transformers Effective for Time Series Forecasting?	Link	Link	AAAI'23	LTSF
Crossformer	Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting	Link	Link	ICLR'23	LTSF
DLinear	Are Transformers Effective for Time Series Forecasting?	Link	Link	AAAI'23	LTSF
DSformer	A Double Sampling Transformer for Multivariate Time Series Long-term Prediction	Link	Link	CIKM'23	LTSF
SegRNN	Segment Recurrent Neural Network for Long-Term Time Series Forecasting	Link	Link	arXiv	LTSF
MTS-Mixers	Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing	Link	Link	arXiv	LTSF
LightTS	Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP	Link	Link	arXiv	LTSF
ETSformer	Exponential Smoothing Transformers for Time-series Forecasting	Link	Link	arXiv	LTSF
NHiTS	Neural Hierarchical Interpolation for Time Series Forecasting	Link	Link	AAAI'23	LTSF
PatchTST	A Time Series is Worth 64 Words: Long-term Forecasting with Transformers	Link	Link	ICLR'23	LTSF
TiDE	Long-term Forecasting with TiDE: Time-series Dense Encoder	Link	Link	TMLR'23	LTSF
TimesNet	Temporal 2D-Variation Modeling for General Time Series Analysis	Link	Link	ICLR'23	LTSF
Triformer	Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting	Link	Link	IJCAI'22	LTSF
NSformer	Exploring the Stationarity in Time Series Forecasting	Link	Link	NeurIPS'22	LTSF
FiLM	Frequency improved Legendre Memory Model for LTSF	Link	Link	NeurIPS'22	LTSF
FEDformer	Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting	Link	Link	ICML'22	LTSF
Pyraformer	Low complexity pyramidal Attention For Long-range Time Series Modeling and Forecasting	Link	Link	ICLR'22	LTSF
HI	Historical Inertia: A Powerful Baseline for Long Sequence Time-series Forecasting	Link	None	CIKM'21	LTSF
Autoformer	Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting	Link	Link	NeurIPS'21	LTSF
Informer	Beyond Efficient Transformer for Long Sequence Time-Series Forecasting	Link	Link	AAAI'21	LTSF

其他方法

📊Baseline	📝Title	📄Paper	💻Code	🏛Venue	🎯Task
LightGBM	LightGBM: A Highly Efficient Gradient Boosting Decision Tree	Link	Link	NeurIPS'17	Machine Learning
NBeats	Neural basis expansion analysis for interpretable time series forecasting	Link	Link1, Link2	ICLR'19	Deep Time Series Forecasting
DeepAR	Probabilistic Forecasting with Autoregressive Recurrent Networks	Link	Link1, Link2, Link3	Int. J. Forecast'20	Probabilistic Time Series Forecasting
WaveNet	WaveNet: A Generative Model for Raw Audio.	Link	Link 1, Link 2	arXiv	Audio

📦 支持的数据集

BasicTS 支持多种类型的数据集，涵盖时空预测、长序列预测及大规模数据集。

时空预测

🏷️Name	🌐Domain	📏Length	📊Time Series Count	🔄Graph	⏱️Freq. (m)	🎯Task
METR-LA	Traffic Speed	34272	207	True	5	STF
PEMS-BAY	Traffic Speed	52116	325	True	5	STF
PEMS03	Traffic Flow	26208	358	True	5	STF
PEMS04	Traffic Flow	16992	307	True	5	STF
PEMS07	Traffic Flow	28224	883	True	5	STF
PEMS08	Traffic Flow	17856	170	True	5	STF

长序列预测

🏷️Name	🌐Domain	📏Length	📊Time Series Count	🔄Graph	⏱️Freq. (m)	🎯Task
BeijingAirQuality	Beijing Air Quality	36000	7	False	60	LTSF
ETTh1	Electricity Transformer Temperature	14400	7	False	60	LTSF
ETTh2	Electricity Transformer Temperature	14400	7	False	60	LTSF
ETTm1	Electricity Transformer Temperature	57600	7	False	15	LTSF
ETTm2	Electricity Transformer Temperature	57600	7	False	15	LTSF
Electricity	Electricity Consumption	26304	321	False	60	LTSF
ExchangeRate	Exchange Rate	7588	8	False	1440	LTSF
Illness	Ilness Data	966	7	False	10080	LTSF
Traffic	Road Occupancy Rates	17544	862	False	60	LTSF
Weather	Weather	52696	21	False	10	LTSF

大规模数据集

🏷️Name	🌐Domain	📏Length	📊Time Series Count	🔄Graph	⏱️Freq. (m)	🎯Task
CA	Traffic Flow	35040	8600	True	15	Large Scale
GBA	Traffic Flow	35040	2352	True	15	Large Scale
GLA	Traffic Flow	35040	3834	True	15	Large Scale
SD	Traffic Flow	35040	716	True	15	Large Scale

📉 主要结果

请参阅论文 多变量时间序列预测进展探索：全面基准评测和异质性分析。

贡献者 ✨

感谢这些优秀的贡献者们 (表情符号指南)：

S22 🚧 💻 🐛	blisky-li 💻	LMissher 💻 🐛	CNStark 🚇	Azusa 🐛	Yannick Wölker 🐛	hlhang9527 🐛
Chengqing Yu 💻	Reborn14 📖 💻	TensorPulse 🐛	superarthurlx 💻 🐛	Yisong Fu 💻	Xubin 📖	DU YIFAN 💻

此项目遵循 all-contributors 规范。欢迎任何形式的贡献！

Star History

🔗 致谢

BasicTS 是基于 EasyTorch 开发的，这是一个易于使用且功能强大的开源神经网络训练框架。