{"id":146797,"name":null,"description":"Code used for sourcing and cleaning the BigScience ROOTS corpus","url":"https://github.com/bigscience-workshop/data-preparation","last_synced_at":"2025-09-09T14:40:44.043Z","repository":{"id":37410452,"uuid":"485318608","full_name":"bigscience-workshop/data-preparation","owner":"bigscience-workshop","description":"Code used for sourcing and cleaning the BigScience ROOTS corpus","archived":false,"fork":false,"pushed_at":"2023-03-20T17:05:44.000Z","size":953,"stargazers_count":312,"open_issues_count":9,"forks_count":41,"subscribers_count":24,"default_branch":"main","last_synced_at":"2025-05-26T06:11:36.013Z","etag":null,"topics":["dataset","large-language-models","multilingual"],"latest_commit_sha":null,"homepage":"https://bigscience.huggingface.co/","language":"Jupyter Notebook","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/bigscience-workshop.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-04-25T10:08:43.000Z","updated_at":"2025-05-13T03:10:19.000Z","dependencies_parsed_at":"2024-11-11T06:02:17.698Z","dependency_job_id":null,"html_url":"https://github.com/bigscience-workshop/data-preparation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bigscience-workshop/data-preparation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata-preparation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata-preparation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata-preparation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata-preparation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop","download_url":"https://codeload.github.com/bigscience-workshop/data-preparation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata-preparation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274314285,"owners_count":25262607,"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","status":"online","status_checked_at":"2025-09-09T02:00:10.223Z","response_time":80,"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"}},"owner":{"login":"bigscience-workshop","name":"BigScience Workshop","uuid":"82455566","kind":"organization","description":"Research workshop on large language models - The Summer of Language Models 21","email":"bigscience-contact@googlegroups.com","website":"https://bigscience.huggingface.co","location":null,"twitter":"BigScienceW","company":null,"icon_url":"https://avatars.githubusercontent.com/u/82455566?v=4","repositories_count":28,"last_synced_at":"2023-03-03T19:53:10.825Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/bigscience-workshop","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-14T05:10:07.455Z","updated_at":"2023-03-03T19:53:10.861Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop/repositories"},"packages":[],"commits":{"id":5057056,"full_name":"bigscience-workshop/data-preparation","default_branch":"main","committers":[{"name":"Hugo Laurençon","email":"44556846+HugoLaurencon","login":"HugoLaurencon","count":16},{"name":"SaulLu","email":"55560583+SaulLu","login":"SaulLu","count":9},{"name":"Thomas Wang","email":"24695242+thomasw21","login":"thomasw21","count":7},{"name":"Christopher Akiki","email":"christopher.akiki@protonmail.com","login":"cakiki","count":5},{"name":"Teven","email":"teven.lescao@gmail.com","login":"TevenLeScao","count":3},{"name":"dependabot[bot]","email":"49699333+dependabot[bot]","login":"dependabot[bot]","count":2},{"name":"TristanThrush","email":"tristan@huggingface.co","login":"TristanThrush","count":2},{"name":"Paulo Villegas","email":"paulo.vllgs@gmail.com","login":"paulovn","count":2},{"name":"Leandro von Werra","email":"lvwerra","login":"lvwerra","count":1},{"name":"Albert Villanova del Moral","email":"8515462+albertvillanova","login":"albertvillanova","count":1}],"total_commits":48,"total_committers":10,"total_bot_commits":2,"total_bot_committers":1,"mean_commits":4.8,"dds":0.6666666666666667,"past_year_committers":[],"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2025-05-23T16:53:43.732Z","last_synced_commit":"9d0588419073cc5bf0fb92b58f37f2a1016572c3","created_at":"2024-11-11T03:12:41.974Z","updated_at":"2025-05-23T16:54:02.163Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata-preparation/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:17:06.873Z","repositories_count":5524511,"commits_count":868166479,"contributors_count":31942272,"owners_count":917070,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"bigscience-workshop/data-preparation","html_url":"https://github.com/bigscience-workshop/data-preparation","last_synced_at":"2025-05-26T06:11:20.891Z","status":null,"issues_count":12,"pull_requests_count":33,"avg_time_to_close_issue":4801662.333333333,"avg_time_to_close_pull_request":229716.87878787878,"issues_closed_count":3,"pull_requests_closed_count":33,"pull_request_authors_count":10,"issue_authors_count":9,"avg_comments_per_issue":0.08333333333333333,"avg_comments_per_pull_request":0.7272727272727273,"merged_pull_requests_count":32,"bot_issues_count":0,"bot_pull_requests_count":2,"past_year_issues_count":0,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2024-11-11T03:12:43.881Z","updated_at":"2025-09-01T10:41:14.277Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata-preparation","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata-preparation/issues","issue_labels_count":{},"pull_request_labels_count":{"dependencies":2},"issue_author_associations_count":{"NONE":8,"COLLABORATOR":3,"MEMBER":1},"pull_request_author_associations_count":{"COLLABORATOR":16,"MEMBER":10,"CONTRIBUTOR":6},"issue_authors":{"longxudou":3,"HugoLaurencon":2,"chris-ha458":1,"thomasw21":1,"wang9702":1,"SaulLu":1,"dk-github-acc":1,"belle9217":1,"cll-mtk":1},"pull_request_authors":{"SaulLu":10,"thomasw21":7,"HugoLaurencon":4,"cakiki":2,"dependabot[bot]":2,"paulovn":2,"TristanThrush":2,"TevenLeScao":1,"lvwerra":1,"albertvillanova":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-01T00:00:07.725Z","repositories_count":9957585,"issues_count":29574116,"pull_requests_count":85773325,"authors_count":9463536,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[{"login":"SaulLu","count":11,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/SaulLu"},{"login":"thomasw21","count":8,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/thomasw21"},{"login":"HugoLaurencon","count":6,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/HugoLaurencon"},{"login":"cakiki","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/cakiki"},{"login":"lvwerra","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/lvwerra"},{"login":"TevenLeScao","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/TevenLeScao"},{"login":"albertvillanova","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/albertvillanova"}],"active_maintainers":[]},"events":{"total":{"WatchEvent":14,"ForkEvent":3},"last_year":{"WatchEvent":14,"ForkEvent":3}},"keywords":["dataset","large-language-models","multilingual"],"dependencies":[{"ecosystem":"pypi","filepath":"preprocessing/tokenizer/python_script/requirements.txt","sha":null,"kind":"manifest","created_at":"2022-08-08T20:15:35.782Z","updated_at":"2022-08-08T20:15:35.782Z","repository_link":"https://github.com/bigscience-workshop/data-preparation/blob/main/preprocessing/tokenizer/python_script/requirements.txt","dependencies":[{"id":692971987,"package_name":"datasets","ecosystem":"pypi","requirements":"\u003e=1.18.0","direct":true,"kind":"runtime","optional":false},{"id":692971988,"package_name":"pyarrow","ecosystem":"pypi","requirements":"\u003e=6.0.0","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"preprocessing/training/requirements.txt","sha":null,"kind":"manifest","created_at":"2022-08-08T20:15:36.469Z","updated_at":"2022-08-08T20:15:36.469Z","repository_link":"https://github.com/bigscience-workshop/data-preparation/blob/main/preprocessing/training/requirements.txt","dependencies":[{"id":692982448,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982449,"package_name":"openpyxl","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982450,"package_name":"python-dotenv","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982451,"package_name":"py7zr","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982452,"package_name":"rarfile","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982453,"package_name":"zstandard","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982454,"package_name":"stanza","ecosystem":"pypi","requirements":"==1.2.0","direct":true,"kind":"runtime","optional":false},{"id":692982455,"package_name":"stanza-batch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982456,"package_name":"nltk","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982457,"package_name":"indic-nlp-library","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692982458,"package_name":"underthesea","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"sourcing/cc_pseudo_crawl/python_scripts/extract_text/requirements.txt","sha":null,"kind":"manifest","created_at":"2022-08-08T20:15:37.137Z","updated_at":"2022-08-08T20:15:37.137Z","repository_link":"https://github.com/bigscience-workshop/data-preparation/blob/main/sourcing/cc_pseudo_crawl/python_scripts/extract_text/requirements.txt","dependencies":[{"id":692988764,"package_name":"git","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"sourcing/cc_pseudo_crawl/python_scripts/requirements.txt","sha":null,"kind":"manifest","created_at":"2022-08-08T20:15:37.216Z","updated_at":"2022-08-08T20:15:37.216Z","repository_link":"https://github.com/bigscience-workshop/data-preparation/blob/main/sourcing/cc_pseudo_crawl/python_scripts/requirements.txt","dependencies":[{"id":692991283,"package_name":"boto3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692991284,"package_name":"bs4","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692991286,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692991287,"package_name":"pyathena","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692991288,"package_name":"surt","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692991289,"package_name":"tldextract","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":692991290,"package_name":"warcio","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"preprocessing/training/01a_catalogue_cleaning_and_filtering/streamlit-app/base/backend/requirements.txt","sha":null,"kind":"manifest","created_at":"2023-01-24T11:45:53.512Z","updated_at":"2023-01-24T11:45:53.512Z","repository_link":"https://github.com/bigscience-workshop/data-preparation/blob/main/preprocessing/training/01a_catalogue_cleaning_and_filtering/streamlit-app/base/backend/requirements.txt","dependencies":[{"id":7137121635,"package_name":"datasets","ecosystem":"pypi","requirements":"==1.17.0","direct":true,"kind":"runtime","optional":false},{"id":7137121636,"package_name":"pandas","ecosystem":"pypi","requirements":"==1.3.5","direct":true,"kind":"runtime","optional":false},{"id":7137121637,"package_name":"streamlit","ecosystem":"pypi","requirements":"==1.11.1","direct":true,"kind":"runtime","optional":false},{"id":7137121638,"package_name":"streamlit_diff_viewer","ecosystem":"pypi","requirements":"==0.0.2","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"preprocessing/training/01a_catalogue_cleaning_and_filtering/streamlit-app/with_pii/backend/requirements.txt","sha":null,"kind":"manifest","created_at":"2023-01-24T11:45:53.534Z","updated_at":"2023-01-24T11:45:53.534Z","repository_link":"https://github.com/bigscience-workshop/data-preparation/blob/main/preprocessing/training/01a_catalogue_cleaning_and_filtering/streamlit-app/with_pii/backend/requirements.txt","dependencies":[{"id":7137121688,"package_name":"datasets","ecosystem":"pypi","requirements":"==1.17.0","direct":true,"kind":"runtime","optional":false},{"id":7137121689,"package_name":"pandas","ecosystem":"pypi","requirements":"==1.3.5","direct":true,"kind":"runtime","optional":false},{"id":7137121690,"package_name":"streamlit","ecosystem":"pypi","requirements":"==1.11.1","direct":true,"kind":"runtime","optional":false},{"id":7137121691,"package_name":"streamlit_diff_viewer","ecosystem":"pypi","requirements":"==0.0.2","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"preprocessing/training/02_pii/requirements.txt","sha":null,"kind":"manifest","created_at":"2023-01-24T11:45:53.543Z","updated_at":"2023-01-24T11:45:53.543Z","repository_link":"https://github.com/bigscience-workshop/data-preparation/blob/main/preprocessing/training/02_pii/requirements.txt","dependencies":[{"id":7137121704,"package_name":"regex","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121705,"package_name":"validators","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121706,"package_name":"tqdm","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121707,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121708,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"sourcing/Gathering Identified Datasets and Collections/requirements.txt","sha":null,"kind":"manifest","created_at":"2023-01-24T11:45:53.554Z","updated_at":"2023-01-24T11:45:53.554Z","repository_link":"https://github.com/bigscience-workshop/data-preparation/blob/main/sourcing/Gathering Identified Datasets and Collections/requirements.txt","dependencies":[{"id":7137121746,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121747,"package_name":"openpyxl","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121748,"package_name":"python-dotenv","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121749,"package_name":"py7zr","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121750,"package_name":"rarfile","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121751,"package_name":"zstandard","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121752,"package_name":"stanza","ecosystem":"pypi","requirements":"==1.2.0","direct":true,"kind":"runtime","optional":false},{"id":7137121753,"package_name":"stanza-batch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121754,"package_name":"nltk","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121755,"package_name":"indic-nlp-library","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7137121756,"package_name":"underthesea","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":8.07402621612406,"created_at":"2025-09-09T00:23:01.115Z","updated_at":"2025-10-07T08:36:45.112Z","avatar_url":"https://github.com/bigscience-workshop.png","language":"Jupyter Notebook","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":["transformer","cryptocurrency","vlm","speech-recognition","qwen","pytorch-transformers","pretrained-models","model-hub","glm","gemma"],"project_url":"https://science.ecosyste.ms/api/v1/projects/146797","html_url":"https://science.ecosyste.ms/projects/146797"}