Skip to content

machml/spatial-temporal-forecast

 
 

Repository files navigation

Spatial-Temporal-Forecast

Some baseline model of Spatial-Temporal Forecasting.

Models

  • T-GCN

PyTorch implementation of the spatio-temporal graph convolutional network proposed in T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction by Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, Haifeng Li.

  • STGCN

Pytorch version of stgcn proposed in Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting by Bing Yu, Haoteng Yin, Zhanxing Zhu. This version was implemented by FelixOpolka.

  • Graph Wavenet

Pytorch version of graph wavenet proposed in Graph WaveNet for Deep Spatial-Temporal Graph Modeling by Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang. This version was implemented by nnzhan. And there is a little refactoring on it.

Requirements

  • PyTorch
  • NumPy
  • Pytorch_geometric
  • Pytorch_lightning
  • TestTube

Example Dataset

  • METR-LA

The repository provides a usage example on the METR-LA dataset (original version to be found here).

  • NYC Sharing Bike

Origin source is citibikenyc. Example data is 201307-201402-citibike-tripdata.zip

Commands

python main.py -m gwnet -d metr
python main.py -m stgcn -d nyc-bike -t cheb -p pyg

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%