{"id":168630,"name":null,"description":"A library for squeakily cleaning and filtering language datasets.","url":"https://github.com/carperai/squeakily","last_synced_at":"2025-09-09T20:46:31.030Z","repository":{"id":62814476,"uuid":"562608408","full_name":"CarperAI/squeakily","owner":"CarperAI","description":"A library for squeakily cleaning and filtering language datasets.","archived":false,"fork":false,"pushed_at":"2023-07-10T16:30:58.000Z","size":1349,"stargazers_count":47,"open_issues_count":4,"forks_count":10,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-09-05T02:49:19.361Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://carperai.github.io/squeakily/","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/CarperAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":"2022-11-06T21:17:40.000Z","updated_at":"2025-06-03T07:45:12.000Z","dependencies_parsed_at":"2024-11-10T17:47:41.894Z","dependency_job_id":null,"html_url":"https://github.com/CarperAI/squeakily","commit_stats":{"total_commits":33,"total_committers":5,"mean_commits":6.6,"dds":0.4242424242424242,"last_synced_commit":"ba81f6e11fab424794d46cbf06d398ea2ad4a7f1"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CarperAI/squeakily","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CarperAI","download_url":"https://codeload.github.com/CarperAI/squeakily/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274359002,"owners_count":25270682,"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":"CarperAI","name":"CarperAI","uuid":"104362400","kind":"organization","description":"","email":null,"website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/104362400?v=4","repositories_count":15,"last_synced_at":"2023-03-06T21:38:24.806Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/CarperAI","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-16T22:02:52.593Z","updated_at":"2023-03-06T21:38:24.824Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CarperAI","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CarperAI/repositories"},"packages":[{"id":5395170,"name":"squeakily","ecosystem":"pypi","description":"A library for squeakily cleaning and filtering language datasets.","homepage":"https://github.com/CarperAI/squeakily","licenses":"Apache Software License 2.0","normalized_licenses":["Apache-2.0"],"repository_url":"https://github.com/CarperAI/squeakily","keywords_array":["nbdev","jupyter","notebook","python"],"namespace":null,"versions_count":2,"first_release_published_at":"2022-11-07T02:51:25.000Z","latest_release_published_at":"2022-11-30T04:03:25.000Z","latest_release_number":"0.0.2","last_synced_at":"2025-09-05T02:46:04.267Z","created_at":"2022-11-07T04:38:08.387Z","updated_at":"2025-09-05T19:29:25.340Z","registry_url":"https://pypi.org/project/squeakily/","install_command":"pip install squeakily --index-url https://pypi.org/simple","documentation_url":"https://squeakily.readthedocs.io/","metadata":{"funding":null,"documentation":null,"classifiers":["Development Status :: 4 - Beta","Intended Audience :: Developers","License :: OSI Approved :: Apache Software License","Natural Language :: English","Programming Language :: Python :: 3.10","Programming Language :: Python :: 3.7","Programming Language :: Python :: 3.8","Programming Language :: Python :: 3.9"],"normalized_name":"squeakily","project_status":null},"repo_metadata":{"id":62814476,"uuid":"562608408","full_name":"CarperAI/squeakily","owner":"CarperAI","description":"A library for squeakily cleaning and filtering language datasets.","archived":false,"fork":false,"pushed_at":"2023-07-10T16:30:58.000Z","size":1349,"stargazers_count":47,"open_issues_count":4,"forks_count":10,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-09-05T02:49:19.361Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://carperai.github.io/squeakily/","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/CarperAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":"2022-11-06T21:17:40.000Z","updated_at":"2025-06-03T07:45:12.000Z","dependencies_parsed_at":"2024-11-10T17:47:41.894Z","dependency_job_id":null,"html_url":"https://github.com/CarperAI/squeakily","commit_stats":{"total_commits":33,"total_committers":5,"mean_commits":6.6,"dds":0.4242424242424242,"last_synced_commit":"ba81f6e11fab424794d46cbf06d398ea2ad4a7f1"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CarperAI/squeakily","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CarperAI","download_url":"https://codeload.github.com/CarperAI/squeakily/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273728155,"owners_count":25157136,"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":"2025-09-05T02:00:09.113Z","response_time":402,"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_record":{"login":"CarperAI","name":"CarperAI","uuid":"104362400","kind":"organization","description":"","email":null,"website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/104362400?v=4","repositories_count":15,"last_synced_at":"2023-03-06T21:38:24.806Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/CarperAI","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-16T22:02:52.593Z","updated_at":"2023-03-06T21:38:24.824Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CarperAI","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CarperAI/repositories"},"tags":[]},"repo_metadata_updated_at":"2025-09-05T19:29:25.339Z","dependent_packages_count":0,"downloads":13,"downloads_period":"last-month","dependent_repos_count":1,"rankings":{"downloads":44.12921386276626,"dependent_repos_count":21.835841835996224,"dependent_packages_count":9.840959837582574,"stargazers_count":10.167040850010714,"forks_count":11.438627364716233,"docker_downloads_count":null,"average":19.4823367502144},"purl":"pkg:pypi/squeakily","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/pypi/squeakily","docker_dependents_count":null,"docker_downloads_count":null,"usage_url":"https://repos.ecosyste.ms/usage/pypi/squeakily","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/pypi/squeakily/dependencies","status":null,"funding_links":[],"critical":null,"issue_metadata":{"last_synced_at":"2025-08-17T21:46:59.570Z","issues_count":4,"pull_requests_count":8,"avg_time_to_close_issue":702096.5,"avg_time_to_close_pull_request":190798.66666666666,"issues_closed_count":2,"pull_requests_closed_count":6,"pull_request_authors_count":4,"issue_authors_count":1,"avg_comments_per_issue":0.0,"avg_comments_per_pull_request":0.875,"merged_pull_requests_count":6,"bot_issues_count":0,"bot_pull_requests_count":0,"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,"issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/issues","maintainers":[{"login":"ncoop57","count":7,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/ncoop57"}],"active_maintainers":[]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/squeakily/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/squeakily/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/squeakily/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/squeakily/related_packages","maintainers":[{"uuid":"coop57","login":"coop57","name":null,"email":null,"url":null,"packages_count":17,"html_url":"https://pypi.org/user/coop57/","role":null,"created_at":"2023-02-06T22:41:36.780Z","updated_at":"2023-02-06T22:41:36.780Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers/coop57/packages"}],"registry":{"name":"pypi.org","url":"https://pypi.org","ecosystem":"pypi","default":true,"packages_count":726702,"maintainers_count":308881,"namespaces_count":0,"keywords_count":238369,"github":"pypi","metadata":{"funded_packages_count":50594},"icon_url":"https://github.com/pypi.png","created_at":"2022-04-04T15:19:23.364Z","updated_at":"2025-09-09T06:31:19.922Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages","maintainers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers","namespaces_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/namespaces"}}],"commits":{"id":693365,"full_name":"CarperAI/squeakily","default_branch":"main","committers":[{"name":"ncoop57","email":"nacooper01@wm.edu","count":19},{"name":"ncoop57","email":"nacooper01@email.wm.edu","count":5},{"name":"nathan","email":"nathan@ip-172-31-38-94.ec2.internal","count":4},{"name":"Erfan Al-Hossami","email":"ealhossa@uncc.edu","count":4},{"name":"nathan","email":"nathan@cpu32-dy-m6i-8xlarge-1.hpc-1click-cpu.pcluster","count":1}],"total_commits":33,"total_committers":5,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":6.6,"dds":0.4242424242424242,"past_year_committers":null,"past_year_total_commits":null,"past_year_total_committers":null,"past_year_total_bot_commits":null,"past_year_total_bot_committers":null,"past_year_mean_commits":null,"past_year_dds":null,"last_synced_at":"2023-03-20T11:47:41.079Z","last_synced_commit":"ba81f6e11fab424794d46cbf06d398ea2ad4a7f1","created_at":"2023-03-09T11:32:01.046Z","updated_at":"2023-09-19T17:40:00.341Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:17:06.873Z","repositories_count":5504845,"commits_count":857199632,"contributors_count":31353449,"owners_count":914335,"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":"CarperAI/squeakily","html_url":"https://github.com/CarperAI/squeakily","last_synced_at":"2025-08-17T21:46:59.570Z","status":"error","issues_count":4,"pull_requests_count":8,"avg_time_to_close_issue":702096.5,"avg_time_to_close_pull_request":190798.66666666666,"issues_closed_count":2,"pull_requests_closed_count":6,"pull_request_authors_count":4,"issue_authors_count":1,"avg_comments_per_issue":0.0,"avg_comments_per_pull_request":0.875,"merged_pull_requests_count":6,"bot_issues_count":0,"bot_pull_requests_count":0,"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":"2023-05-15T05:23:21.672Z","updated_at":"2025-08-17T21:46:59.570Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarperAI%2Fsqueakily/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"COLLABORATOR":4},"pull_request_author_associations_count":{"CONTRIBUTOR":4,"COLLABORATOR":3,"NONE":1},"issue_authors":{"ncoop57":4},"pull_request_authors":{"ncoop57":3,"simugrad":2,"taisazero":2,"reshinthadithyan":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-07T00:00:10.533Z","repositories_count":10153511,"issues_count":32070773,"pull_requests_count":100067667,"authors_count":10723509,"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":"ncoop57","count":7,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/ncoop57"}],"active_maintainers":[]},"events":{"total":{"WatchEvent":2,"ForkEvent":1},"last_year":{"WatchEvent":2,"ForkEvent":1}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/deploy.yaml","sha":null,"kind":"manifest","created_at":"2023-02-15T03:50:35.249Z","updated_at":"2023-02-15T03:50:35.249Z","repository_link":"https://github.com/CarperAI/squeakily/blob/main/.github/workflows/deploy.yaml","dependencies":[{"id":7675725902,"package_name":"fastai/workflows/quarto-ghp","ecosystem":"actions","requirements":"master","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/test.yaml","sha":null,"kind":"manifest","created_at":"2023-02-15T03:50:36.403Z","updated_at":"2023-02-15T03:50:36.403Z","repository_link":"https://github.com/CarperAI/squeakily/blob/main/.github/workflows/test.yaml","dependencies":[{"id":7675725909,"package_name":"fastai/workflows/nbdev-ci","ecosystem":"actions","requirements":"master","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2024-11-10T17:35:22.595Z","updated_at":"2024-11-10T17:35:22.595Z","repository_link":"https://github.com/CarperAI/squeakily/blob/main/setup.py","dependencies":[]}],"score":8.249313746260636,"created_at":"2025-09-09T01:20:33.598Z","updated_at":"2025-10-07T08:39:35.759Z","avatar_url":"https://github.com/CarperAI.png","language":"Jupyter Notebook","category":null,"sub_category":null,"monthly_downloads":13,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":["transformer"],"project_url":"https://science.ecosyste.ms/api/v1/projects/168630","html_url":"https://science.ecosyste.ms/projects/168630"}