{"id":13473489,"url":"https://github.com/weifantt/DEPTS","last_synced_at":"2025-03-26T19:34:11.758Z","repository":{"id":152731256,"uuid":"461863936","full_name":"weifantt/DEPTS","owner":"weifantt","description":null,"archived":false,"fork":false,"pushed_at":"2022-03-31T09:11:05.000Z","size":21,"stargazers_count":42,"open_issues_count":1,"forks_count":7,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-10-30T06:32:25.572Z","etag":null,"topics":["deep-learning","timeseries-forecasting"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/weifantt.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2022-02-21T13:01:42.000Z","updated_at":"2024-09-12T11:20:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"6e9bb77f-c890-4680-976e-732ffe4e17d0","html_url":"https://github.com/weifantt/DEPTS","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weifantt%2FDEPTS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weifantt%2FDEPTS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weifantt%2FDEPTS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weifantt%2FDEPTS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/weifantt","download_url":"https://codeload.github.com/weifantt/DEPTS/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245722832,"owners_count":20661831,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","timeseries-forecasting"],"created_at":"2024-07-31T16:01:04.145Z","updated_at":"2025-03-26T19:34:11.456Z","avatar_url":"https://github.com/weifantt.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# DEPTS\n\nSource code for the paper,\n[\"DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting\"](https://openreview.net/forum?id=AJAR-JgNw__),\nin ICLR22 Spotlight.\n\n## Overview\nDEPTS is a customized deep neural network architecture for periodic time series forecasting, which aims to solve the following two challenges:\n- To capture diversified periodic compositions\n- To model complicated periodic dependencies\n\n## Dataset\n\nYou can download the five benchmarks from [Google Drive](https://drive.google.com/file/d/1GYt2chsZLbmJkNG3lb-ytCrI3nuZKDxm/view?usp=sharing). All the datasets are well pre-processed. More details of datasets can be found in the [paper](https://openreview.net/forum?id=AJAR-JgNw__). After downloading the zip file, please unzip it to the root dir of DEPTS for experiments.\n\n## Usage\n\n### Setup\nPlease use `Python 3(.6)`  as well as the following packages:\n```text\ntorch \u003e= 1.6.0\ndataclasses\ndtaidistance\npandas\nnumpy\ntqdm\n```\n\n### Reproduce\nTo reproduce the results, you can see more details in `command.sh` and directly run:\n```text\nsh command.sh\n```\nNote that all the results reported in the paper are ensembled results of 30 models in order to get a robust evaluation and compare with [N-BEATS](https://arxiv.org/abs/1905.10437). You can also try to run the single model for evaluation if you find it challenging to run all the models.\n\n### Evaluation\n\nTo get the evaluation results, run\n```text\npython evaluation.py\n```\n\n\n\n## Citation\n\nIf you find our work interesting, you can cite the paper as\n\n```text\n@inproceedings{\nfan2022depts,\ntitle={{DEPTS}: Deep Expansion Learning for Periodic Time Series Forecasting},\nauthor={Wei Fan and Shun Zheng and Xiaohan Yi and Wei Cao and Yanjie Fu and Jiang Bian and Tie-Yan Liu},\nbooktitle={International Conference on Learning Representations},\nyear={2022},\nurl={https://openreview.net/forum?id=AJAR-JgNw__}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweifantt%2FDEPTS","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fweifantt%2FDEPTS","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweifantt%2FDEPTS/lists"}