{"id":23976196,"url":"https://github.com/claudiozeni/raffy","last_synced_at":"2026-06-12T06:31:41.023Z","repository":{"id":215970940,"uuid":"354012611","full_name":"ClaudioZeni/Raffy","owner":"ClaudioZeni","description":"Ridge-regression Atomistic Force Fields in PYthon","archived":false,"fork":false,"pushed_at":"2021-08-24T09:24:56.000Z","size":63878,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-24T17:16:48.751Z","etag":null,"topics":["force-fields","machine-learning","molecular-dynamics"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ClaudioZeni.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2021-04-02T12:27:44.000Z","updated_at":"2021-08-24T09:24:59.000Z","dependencies_parsed_at":"2024-01-07T18:53:05.224Z","dependency_job_id":null,"html_url":"https://github.com/ClaudioZeni/Raffy","commit_stats":null,"previous_names":["claudiozeni/raffy"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/ClaudioZeni/Raffy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ClaudioZeni%2FRaffy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ClaudioZeni%2FRaffy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ClaudioZeni%2FRaffy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ClaudioZeni%2FRaffy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ClaudioZeni","download_url":"https://codeload.github.com/ClaudioZeni/Raffy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ClaudioZeni%2FRaffy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34232789,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-12T02:00:06.859Z","response_time":109,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["force-fields","machine-learning","molecular-dynamics"],"created_at":"2025-01-07T06:58:08.204Z","updated_at":"2026-06-12T06:31:41.003Z","avatar_url":"https://github.com/ClaudioZeni.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Raffy\nRidge-regression Atomistic Force Fields in PYthon\n\n\n\nDOI : 10.5281/zenodo.5243000\n\nUse this package to train and validate force fields for single- and multi-element materials.\nThe force fields are trained using ridge regression on local atomic environment descritptors computed in the \"Atomic Cluster Expansion\" (ACE) framework.\nThe package can also be used to classify local atomic environments according to their ACE local descriptor.\n\n\n## Installation\nTo install the package, clone the repository and then pip install:\n\n    git clone https://github.com/ClaudioZeni/Raffy\n    cd Raffy\n    pip install .\n\nThe installation process should take 1 to 5 minutes on a standard laptop.\n\n\n## Examples\nThree notebooks are available in the examples folder.\nLinear Potential showcases the training and validation of a linear potential for Si.\nTrajectory Clustering demonstrates how to use the Raffy package to classify local atomic environments on a sample MD trajectory of a Au nanoparticle.\nHierarchical Clustering Tutorial guides the creation of a hierachical k-means clustering to differentiate local atomic environments in an Au nanoparticle.\n\n\n\n## Dependancies\nThe package uses [ASE](https://pypi.org/project/ase/) to handle .xyz files, [MIR-FLARE](https://github.com/mir-group/flare) to handle local atomic environments, [NUMPY](https://numpy.org/) and [SCIPY](https://www.scipy.org/) for fast computation, and [RAY](https://ray.io/) for multiprocessing.\n\nThe package has been tested on Ubuntu 20.04.\n\n\n## References\nIf you use RAFFY in your research, or any part of this repository, please cite the following paper:\n\n[1] Claudio Zeni, Kevin Rossi, Aldo Glielmo, and Stefano de Gironcoli, \"Compact atomic descriptors enable accurate predictions via linear models\", The Journal of Chemical Physics 154, 224112 (2021) https://doi.org/10.1063/5.0052961 \n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclaudiozeni%2Fraffy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fclaudiozeni%2Fraffy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclaudiozeni%2Fraffy/lists"}