基于SCINet网络的时间序列建模和预测（Pytorch完整源码和数据）

# SCINet [](https://arxiv.org/pdf/2106.09305.pdf)  This is the original pytorch implementation for the following paper: [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://arxiv.org/pdf/2106.09305.pdf). Alse see the [Open Review verision](https://openreview.net/pdf?id=AyajSjTAzmg). If you find this repository useful for your research work, please consider citing it as follows: ``` @article{liu2022SCINet, title={SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction}, author={Liu, Minhao and Zeng, Ailing and Chen, Muxi and Xu, Zhijian and Lai, Qiuxia and Ma, Lingna and Xu, Qiang}, journal={Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022}, year={2022} } ``` ## Updates - [2022-09-15] SCINet has been accepted to NeurIPS 2022! - [2021-11-10] Added Reversible Instance Normalization RevIN[1] support! - [2021-09-17] SCINet v1.0 is released ## Features - [x] Support **11** popular time-series forecasting datasets, namely Electricity Transformer Temperature (ETTh1, ETTh2 and ETTm1) , Traffic, Solar-Energy, Electricity and Exchange Rate and PeMS (PEMS03, PEMS04, PEMS07 and PEMS08), ranging from power, energy, finance and traffic domains. [comment]: <> (![traffic]&#40;https://img.shields.io/badge/🚅-Traffic-yellow&#41;) [comment]: <> (![electric]&#40;https://img.shields.io/badge/%F0%9F%92%A1-Electricity-yellow&#41;) [comment]: <> (![Solar Energy]&#40;https://img.shields.io/badge/%F0%9F%94%86-Solar%20Energy-yellow&#41;) [comment]: <> (![finance]&#40;https://img.shields.io/badge/💵-Finance-yellow&#41;) - [x] Provide all training logs. - [x] Support RevIN to handle datasets with a large train-test sample distribution gap. To activate, simply add ```--RIN True``` to the command line. [**Read more**]&#40;./docs/RevIN.md&#41; ## To-do items - Integrate GNN-based spatial models into SCINet for better performance and higher efficiency on spatial-temporal time series. Our preliminary results show that this feature could result in considerable gains on the prediction accuracy of some datasets &#40;e.g., PEMSxx&#41;. - Generate probalistic forecasting results. Stay tuned! ## Used Datasets We conduct the experiments on **11** popular time-series datasets, namely **Electricity Transformer Temperature (ETTh1, ETTh2 and ETTm1) , PeMS (PEMS03, PEMS04, PEMS07 and PEMS08) and Traffic, Solar-Energy, Electricity and Exchange Rate**, ranging from **power, energy, finance and traffic domains**. ### Overall information of the 11 datasets | Datasets | Variants | Timesteps | Granularity | Start time | Task Type | | ------------- | -------- | --------- | ----------- | ---------- | ----------- | | ETTh1 | 7 | 17,420 | 1hour | 7/1/2016 | Multi-step | | ETTh2 | 7 | 17,420 | 1hour | 7/1/2016 | Multi-step | | ETTm1 | 7 | 69,680 | 15min | 7/1/2016 | Multi-step | | PEMS03 | 358 | 26,209 | 5min | 5/1/2012 | Multi-step | | PEMS04 | 307 | 16,992 | 5min | 7/1/2017 | Multi-step | | PEMS07 | 883 | 28,224 | 5min | 5/1/2017 | Multi-step | | PEMS08 | 170 | 17,856 | 5min | 3/1/2012 | Multi-step | | Traffic | 862 | 17,544 | 1hour | 1/1/2015 | Single-step | | Solar-Energy | 137 | 52,560 | 1hour | 1/1/2006 | Single-step | | Electricity | 321 | 26,304 | 1hour | 1/1/2012 | Single-step | | Exchange-Rate | 8 | 7,588 | 1hour | 1/1/1990 | Single-step | ## Get started ### Requirements Install the required package first: ``` cd SCINet conda create -n scinet python=3.8 conda activate scinet pip install -r requirements.txt ``` ### Dataset preparation All datasets can be downloaded [here](https://drive.google.com/drive/folders/1Gv1MXjLo5bLGep4bsqDyaNMI2oQC9GH2?usp=sharing). To prepare all dataset at one time, you can just run: ``` source prepare_data.sh ``` [](https://drive.google.com/drive/folders/1NU85EuopJNkptFroPtQVXMZE70zaBznZ) [](https://drive.google.com/drive/folders/17fwxGyQ3Qb0TLOalI-Y9wfgTPuXSYgiI) [](https://drive.google.com/drive/folders/12ffxwxVAGM_MQiYpIk9aBLQrb2xQupT-) The data directory structure is shown as follows. ``` ./ └── datasets/ ├── ETT-data │ ├── ETTh1.csv │ ├── ETTh2.csv │ └── ETTm1.csv ├── financial │ ├── electricity.txt │ ├── exchange_rate.txt │ ├── solar_AL.txt │ └── traffic.txt └── PEMS ├── PEMS03.npz ├── PEMS04.npz ├── PEMS07.npz └── PEMS08.npz ``` ### Run training code We follow the same settings of [StemGNN](https://github.com/microsoft/StemGNN) for PEMS 03, 04, 07, 08 datasets, [MTGNN](https://github.com/nnzhan/MTGNN) for Solar, electricity, traffic, financial datasets, [Informer](https://github.com/zhouhaoyi/Informer2020) for ETTH1, ETTH2, ETTM1 datasets. The detailed training commands are given as follows. #### For PEMS dataset (All datasets follow Input 12, Output 12): pems03 ``` python run_pems.py --dataset PEMS03 --hidden-size 0.0625 --dropout 0.25 --model_name pems03_h0.0625_dp0.25 --num_decoder_layer 2 ``` pems04 ``` python run_pems.py --dataset PEMS04 --hidden-size 0.0625 --dropout 0 --model_name pems04_h0.0625_dp0 ``` pems07 ``` python run_pems.py --dataset PEMS07 --hidden-size 0.03125 --dropout 0.25 --model_name pems07_h0.03125_dp0.25 ``` pems08 ``` python run_pems.py --dataset PEMS08 --hidden-size 1 --dropout 0.5 --model_name pems08_h1_dp0.5 ``` ##### PEMS Parameter highlights | Parameter Name | Description | Parameter in paper | Default | | -------------- | ----------------------- | ------------------ | ------- | | dataset | Name of dataset | N/A | PEMS08 | | horizon | Horizon | Horizon | 12 | | window_size | Look-back window | Look-back window | 12 | | hidden-size | hidden expansion | h | 1 | | levels | SCINet block levels | L | 2 | | stacks | The number of SCINet block| K | 1 | #### For Solar dataset: predict 3 ``` python run_financial.py --dataset_name solar_AL --window_size 160 --horizon 3 --hidden-size 1 --lastWeight 0.5 --stacks 2 --levels 4 --lradj 2 --lr 1e-4 --dropout 0.25 --batch_size 256 --model_name so_I160_o3_lr1e-4_bs256_dp0.25_h1_s2l4_w0.5 ``` predict 6 ``` python run_financial.py --dataset_name solar_AL --window_size 160 --horizon 6 --hidden-size 0.5 --lastWeight 0.5 --stacks 2 --levels 4 --lradj 2 --lr 1e-4 --dropout 0.25 --batch_size 256 --model_name so_I160_o6_lr1e-4_bs256_dp0.25_h0.5_s2l4_w0.5 ``` predict 12 ``` python run_financial.py --dataset_name solar_AL --window_size 160 --horizon 12 --hidden-size 2 --lastWeight 0.5 --stacks 2 --levels 4 --lradj 2 --lr 1e-4 --dropout 0.25 --batch_size 1024 --model_name so_I160_o12_lr1e-4_bs1024_dp0.25_h2_s2l4_w0.5 ``` predict 24 ``` python run_financial.py --dataset_name solar_AL --window_size 160 --horizon