{"id":19863618,"url":"https://github.com/sandialabs/avatar","last_synced_at":"2026-02-17T19:01:37.046Z","repository":{"id":142395530,"uuid":"327137165","full_name":"sandialabs/avatar","owner":"sandialabs","description":"The Avatar Tools codes are an implementation of ensembles specifically for decision trees.","archived":false,"fork":false,"pushed_at":"2022-12-03T17:46:09.000Z","size":1057,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-29T21:33:52.267Z","etag":null,"topics":["scr-2451","snl-data-analysis"],"latest_commit_sha":null,"homepage":"","language":"C","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sandialabs.png","metadata":{"files":{"readme":"README.md","changelog":"ChangeLog","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":"support/Makefile.standalone","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-01-05T22:38:44.000Z","updated_at":"2024-08-01T14:29:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"ea290003-9cbb-4f2d-a5d0-685d7dbf6fee","html_url":"https://github.com/sandialabs/avatar","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sandialabs/avatar","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sandialabs%2Favatar","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sandialabs%2Favatar/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sandialabs%2Favatar/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sandialabs%2Favatar/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sandialabs","download_url":"https://codeload.github.com/sandialabs/avatar/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sandialabs%2Favatar/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29554377,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-17T18:16:07.221Z","status":"ssl_error","status_checked_at":"2026-02-17T18:16:04.782Z","response_time":100,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["scr-2451","snl-data-analysis"],"created_at":"2024-11-12T15:15:32.097Z","updated_at":"2026-02-17T19:01:37.040Z","avatar_url":"https://github.com/sandialabs.png","language":"C","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Avatar Tools\nVersion 1.1\n\nSupervised machine learning is the process of using past experience to\npredict the future. \"Ensembles\" are a machine-learning meta-method\nthat can be applied to most machine learning algorithms. Ensembles\ngenerally greatly improve accuracy, reduce or remove most of the\ndesign issues presented by machine learning, and are admirably suited\nto parallel and distributed computation.\n\nThe Avatar Tools codes are an implementation of ensembles specifically\nfor decision trees.\n\nSome features that distinguish Avatar Tools from other \"ensembles for\ndecision trees\" codes are:\n\n* Does the bookkeeping necessary for out of bag (OOB) validation.\n\n* Can use OOB validation to automatically determine optimal ensemble size.\n\n* Provides an MPI-based parallel implementation, for distributed\n  operation.\n\n* Provides convenient tools for cross-validation, to assess the\n  accuracy provided by a training set.\n\n* Handles both plain text and Exodus simulation data.\n\n\nThe Avatar Tools codes are intended for Unix machines, and are known\nto build and pass their tests on Linux, Mac OS X, and Solaris\nmachines.\n\nSee INSTALL for installation instructions,\n\nSee the files in support/ for sample data and a brief tutorial.\n\n## Citations\n\nPlease cite one or more of the following papers, if you wish to cite the Avatar Tools:\n\n```\n@INPROCEEDINGS{Chawla2,\n  author = {Nitesh Chawla and Thomas Moore and Kevin Bowyer and Lawrence Hall\n        and Clayton Springer and Philip Kegelmeyer},\n  title = {Bagging is a Small-Data-Set Phenomenon},\n  booktitle = {International Conference on Computer Vision and Pattern Recognition\n        (CVPR)},\n  year = {2001}\n}\n\n@ARTICLE{CaBoHaKe02,\n  author = {Nitesh V.~Chawla and Kevin W.~Bowyer and Lawrence O.~Hall and W.~Philip\n        Kegelmeyer},\n  title = {{SMOTE}: Synthetic Minority Over-sampling Technique},\n  journal = {Journal of Artificial Intelligence Research},\n  year = {2002},\n  volume = {16},\n  pages = {321-357},\n  url = {http://adsabs.harvard.edu/abs/2011arXiv1106.1813B},\n}\n\nARTICLE{ChHaBoKe04,\n  author = {Nitesh V.~Chawla and Lawrence O.~Hall and Kevin W.~Bowyer and W.~Philip\n        Kegelmeyer },\n  title = {Learning ensembles from bites: A scalable and accurate approach},\n  journal = {Journal of Machine Learning Research},\n  year = {2004},\n  volume = {5},\n  pages = {421--451}\n}\n\n@INPROCEEDINGS{Chawla4,\n  author = {Nitesh V.~Chawla and Lawrence O.~Hall and Kevin W.~Bowyer and Thomas\n        E.~Moore and W.~Philip Kegelmeyer},\n  title = {Distributed Pasting of Small Votes},\n  booktitle = {International Workshop on Multiple Classifier Systems},\n  year = {2002},\n  address = {Sardegna, Italy},\n  month = {June}\n}\n\nTECHREPORT{Hall2,\n  author = {L.O.~Hall and K.W.~Bowyer and N.~Chawla and T.~Moore and W.~Philip\n        Kegelmeyer},\n  title = {{AVATAR} --- Adaptive Visualization Aid for Touring and Recovery},\n  institution = {Sandia National Laboratories},\n  year = {2000},\n  type = {Sandia Report},\n  number = {SAND2000-8203},\n  month = {January}\n}\n\n@article {CiHoCh11,\n   author = {Cieslak, David and Hoens, T. and Chawla, Nitesh and Kegelmeyer, W.},\n   title = {Hellinger distance decision trees are robust and skew-insensitive},\n   journal = {Data Mining and Knowledge Discovery},\n   publisher = {Springer Netherlands},\n   issn = {1384-5810},\n   vol = {24}, \n   issue = 1,\n   pages = {136--158},\n   url = {http://dx.doi.org/10.1007/s10618-011-0222-1},\n   note = {10.1007/s10618-011-0222-1},\n   year = {2012}\n}\n```\n\n\n## Acknowledgments\n\nThe Avatar Tools come from a decade-long machine learning research\nprogram led by Philip Kegelmeyer at Sandia National Laboratories, with\ncontributions from collaborators at the University of South Florida\n(notably, Professor Larry Hall and students Robert Banfield and Larry\nShoemaker) and at Notre Dame (Computer Science Department Chair Kevin\nBower and Professor Nitesh Chawla.)\n\nEarly research implementations largely came from Robert Banfield and\nSteven Eschrich, at USF. The current production implementation is by\nKen Buch, a contractor with Limit Point Systems.\n\n\nIf you have questions, contact:\n\nPhilip Kegelmeyer, wpk@sandia.gov\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsandialabs%2Favatar","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsandialabs%2Favatar","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsandialabs%2Favatar/lists"}