{"id":23535521,"url":"https://github.com/tinyadapter/relddpm","last_synced_at":"2025-05-14T20:35:52.889Z","repository":{"id":269504906,"uuid":"907624333","full_name":"tinyAdapter/RelDDPM","owner":"tinyAdapter","description":null,"archived":false,"fork":false,"pushed_at":"2024-12-24T03:18:13.000Z","size":26413,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-24T04:17:30.768Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/tinyAdapter.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-12-24T02:44:46.000Z","updated_at":"2024-12-24T03:18:16.000Z","dependencies_parsed_at":"2024-12-24T04:27:32.161Z","dependency_job_id":null,"html_url":"https://github.com/tinyAdapter/RelDDPM","commit_stats":null,"previous_names":["tinyadapter/relddpm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tinyAdapter%2FRelDDPM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tinyAdapter%2FRelDDPM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tinyAdapter%2FRelDDPM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tinyAdapter%2FRelDDPM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tinyAdapter","download_url":"https://codeload.github.com/tinyAdapter/RelDDPM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239242108,"owners_count":19605954,"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":[],"created_at":"2024-12-26T01:18:07.682Z","updated_at":"2025-02-17T06:14:27.198Z","avatar_url":"https://github.com/tinyAdapter.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RelDDPM\n\n## Introduction\n\nThis is the source code of the paper **Controllable Tabular Data Synthesis Using Diffusion Models**\n\n## Quick Start\n\n### Environment Setup\n\nBefore running the code, please make sure your Python version is above **3.7**.\nWe recommend running the code under a virtual environment:\n\n```sh\nconda create -n relddpm_env python=3.8\nconda activate relddpm_env\n```\n\nThen install the necessary packages by :\n\n```sh\npip install -r requirements.txt\n```\n\nInstall PyTorch :\n\n```sh\npip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116\n```\n\n### Code Structure\n\n```sh\n|-- datasets\n    |-- minority_class_oversampling # datasets used in minority class oversampling task\n    |-- missing_tuple_completion # datasets used in missing tuple completion task\n|-- ddpm # the denoise diffusion probabilistic model package\n|-- lib_completion # the library used in missing tuple completion task \n|-- lib_oversampling # the library used in minority class oversampling task \n|-- data_utils.py # the class to preprocess the dataset\n|-- eval_utils.py # the class to evaluate\n|-- eval.py # code of the evaluation\n|-- main.py # main code\n```\n\n### Run\n\n#### Minority Class Oversampling\n\nRun the code to generate synthetic data for minority class oversampling with the following command:\n\n```sh\npython main.py --task-name=oversampling --dataset-name=[dataset] --device=[GPU id] --save-name=[output file]\npython eval.py --task-name=oversampling --dataset-name=[dataset] --device=[GPU id] --save-name=[output file]\n```\n\nThe parameter \"dataset\" should be \"default\", \"shoppers\" or \"weatherAUS\".\n\nFor example:\n\n```sh\npython main.py --task-name=oversampling --dataset-name=default --device=0 --save-name=default_output\npython eval.py --task-name=oversampling --dataset-name=default --device=0 --save-name=default_output\n```\n\n#### Missing Tuple Completion\n\nRun the code to generate synthetic data for missing tuple completion with the following command:\n\n```sh\npython main.py --task-name=completion --dataset-name=[dataset] --device=[GPU id] --save-name=[output file]\npython eval.py --task-name=completion --dataset-name=[dataset] --device=[GPU id] --save-name=[output file]\n```\n\nThe parameter \"dataset\" should be \"heart\", \"airbnb\" or \"imdb\".\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftinyadapter%2Frelddpm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftinyadapter%2Frelddpm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftinyadapter%2Frelddpm/lists"}