{"id":27711,"name":"pycurator","description":"Simplifying large-scale metadata curation","url":"https://github.com/michaelbaluja/pycurator","last_synced_at":"2025-09-05T03:42:20.941Z","repository":{"id":43271088,"uuid":"375076255","full_name":"michaelbaluja/PyCurator","owner":"michaelbaluja","description":"Simplifying large-scale metadata curation","archived":false,"fork":false,"pushed_at":"2022-09-03T23:43:21.000Z","size":4466,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-13T16:54:02.042Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://pycurator.readthedocs.io/en/latest/","language":"Python","has_issues":true,"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/michaelbaluja.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-06-08T16:29:44.000Z","updated_at":"2024-05-29T13:36:48.000Z","dependencies_parsed_at":"2022-09-04T18:22:36.859Z","dependency_job_id":null,"html_url":"https://github.com/michaelbaluja/PyCurator","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/michaelbaluja/PyCurator","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/michaelbaluja","download_url":"https://codeload.github.com/michaelbaluja/PyCurator/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273708959,"owners_count":25153728,"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":{"login":"michaelbaluja","name":"Michael Baluja","uuid":"39929823","kind":"user","description":"Machine Learning and Data Science MS student, enjoyer, and user.","email":"","website":"michaelbaluja.com","location":"San Diego, CA","twitter":"mlbaluja","company":null,"icon_url":"https://avatars.githubusercontent.com/u/39929823?u=d11453d6d55c7f6a239ebe7a1c974064e933eb37\u0026v=4","repositories_count":4,"last_synced_at":"2023-03-06T21:13:58.672Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/michaelbaluja","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-16T21:41:55.932Z","updated_at":"2023-03-06T21:13:58.685Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/michaelbaluja","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/michaelbaluja/repositories"},"packages":[{"id":4354974,"name":"pycurator","ecosystem":"pypi","description":"Collect data from popular data repositories with ease.","homepage":"https://github.com/michaelbaluja/PyCurator","licenses":"BSD License","normalized_licenses":["BSD-3-Clause"],"repository_url":"https://github.com/michaelbaluja/PyCurator","keywords_array":["curation","API","data collection"],"namespace":null,"versions_count":5,"first_release_published_at":"2022-05-09T17:30:00.000Z","latest_release_published_at":"2022-09-02T00:00:24.000Z","latest_release_number":"0.1.2","last_synced_at":"2025-08-14T11:51:24.558Z","created_at":"2022-05-09T17:40:38.151Z","updated_at":"2025-08-14T11:51:24.558Z","registry_url":"https://pypi.org/project/pycurator/","install_command":"pip install pycurator --index-url https://pypi.org/simple","documentation_url":"https://pycurator.readthedocs.io/","metadata":{"funding":null,"documentation":null,"classifiers":["Development Status :: 4 - Beta","Environment :: Console","Intended Audience :: Science/Research","License :: OSI Approved :: BSD License","Operating System :: OS Independent","Programming Language :: Python :: 3.10","Topic :: Scientific/Engineering"],"normalized_name":"pycurator"},"repo_metadata":{"id":43271088,"uuid":"375076255","full_name":"michaelbaluja/PyCurator","owner":"michaelbaluja","description":"Simplifying large-scale metadata curation","archived":false,"fork":false,"pushed_at":"2022-09-03T23:43:21.000Z","size":4466,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-04T21:05:16.585Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://pycurator.readthedocs.io/en/latest/","language":"Python","has_issues":true,"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/michaelbaluja.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-06-08T16:29:44.000Z","updated_at":"2024-05-29T13:36:48.000Z","dependencies_parsed_at":"2022-09-04T18:22:36.859Z","dependency_job_id":null,"html_url":"https://github.com/michaelbaluja/PyCurator","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/michaelbaluja/PyCurator","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/michaelbaluja","download_url":"https://codeload.github.com/michaelbaluja/PyCurator/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265175332,"owners_count":23722646,"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"},"owner_record":{"login":"michaelbaluja","name":"Michael Baluja","uuid":"39929823","kind":"user","description":"Machine Learning and Data Science MS student, enjoyer, and user.","email":"","website":"michaelbaluja.com","location":"San Diego, CA","twitter":"mlbaluja","company":null,"icon_url":"https://avatars.githubusercontent.com/u/39929823?u=d11453d6d55c7f6a239ebe7a1c974064e933eb37\u0026v=4","repositories_count":4,"last_synced_at":"2023-03-06T21:13:58.672Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/michaelbaluja","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-16T21:41:55.932Z","updated_at":"2023-03-06T21:13:58.685Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/michaelbaluja","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/michaelbaluja/repositories"},"tags":[]},"repo_metadata_updated_at":"2025-07-13T16:51:47.026Z","dependent_packages_count":0,"downloads":12,"downloads_period":"last-month","dependent_repos_count":1,"rankings":{"downloads":34.2227950908319,"dependent_repos_count":21.744141596728245,"dependent_packages_count":9.985458443227419,"stargazers_count":20.32917320588501,"forks_count":22.640454726198044,"docker_downloads_count":null,"average":21.784404612574125},"purl":"pkg:pypi/pycurator","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/pypi/pycurator","docker_dependents_count":null,"docker_downloads_count":null,"usage_url":"https://repos.ecosyste.ms/usage/pypi/pycurator","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/pypi/pycurator/dependencies","status":null,"funding_links":[],"critical":null,"issue_metadata":{"last_synced_at":"2025-05-04T21:05:22.689Z","issues_count":5,"pull_requests_count":2,"avg_time_to_close_issue":600065.8,"avg_time_to_close_pull_request":326383.5,"issues_closed_count":5,"pull_requests_closed_count":2,"pull_request_authors_count":1,"issue_authors_count":3,"avg_comments_per_issue":1.0,"avg_comments_per_pull_request":1.0,"merged_pull_requests_count":1,"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/michaelbaluja%2FPyCurator/issues","maintainers":[{"login":"stephlabou","count":4,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/stephlabou"},{"login":"michaelbaluja","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/michaelbaluja"}],"active_maintainers":[]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/pycurator/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/pycurator/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/pycurator/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/pycurator/related_packages","maintainers":[{"uuid":"michaelbaluja","login":"michaelbaluja","name":null,"email":null,"url":null,"packages_count":1,"html_url":"https://pypi.org/user/michaelbaluja/","role":null,"created_at":"2023-02-25T22:13:37.161Z","updated_at":"2023-02-25T22:13:37.161Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers/michaelbaluja/packages"}],"registry":{"name":"pypi.org","url":"https://pypi.org","ecosystem":"pypi","default":true,"packages_count":724971,"maintainers_count":308293,"namespaces_count":0,"keywords_count":237984,"github":"pypi","metadata":{"funded_packages_count":50481},"icon_url":"https://github.com/pypi.png","created_at":"2022-04-04T15:19:23.364Z","updated_at":"2025-09-04T05:23:51.177Z","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":{"message":"Repository syncing started."},"issues_stats":{"full_name":"michaelbaluja/PyCurator","html_url":"https://github.com/michaelbaluja/PyCurator","last_synced_at":"2025-07-13T16:51:56.081Z","status":null,"issues_count":5,"pull_requests_count":2,"avg_time_to_close_issue":600065.8,"avg_time_to_close_pull_request":326383.5,"issues_closed_count":5,"pull_requests_closed_count":2,"pull_request_authors_count":1,"issue_authors_count":3,"avg_comments_per_issue":1.0,"avg_comments_per_pull_request":1.0,"merged_pull_requests_count":1,"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":"2023-05-15T03:33:00.609Z","updated_at":"2025-07-13T16:51:56.081Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/michaelbaluja%2FPyCurator/issues","issue_labels_count":{"bug":2,"enhancement":1},"pull_request_labels_count":{},"issue_author_associations_count":{"OWNER":2,"COLLABORATOR":2,"NONE":1},"pull_request_author_associations_count":{"COLLABORATOR":2},"issue_authors":{"michaelbaluja":2,"stephlabou":2,"jggautier":1},"pull_request_authors":{"stephlabou":2},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-03T00:00:08.273Z","repositories_count":10060029,"issues_count":31035129,"pull_requests_count":93957968,"authors_count":10685658,"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":"stephlabou","count":4,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/stephlabou"},{"login":"michaelbaluja","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/michaelbaluja"}],"active_maintainers":[]},"events":{"total":{},"last_year":{}},"keywords":[],"dependencies":[{"ecosystem":"conda","filepath":"environment.yml","sha":null,"kind":"manifest","created_at":"2022-09-04T18:22:36.770Z","updated_at":"2022-09-04T18:22:36.770Z","repository_link":"https://github.com/michaelbaluja/PyCurator/blob/main/environment.yml","dependencies":[{"id":3812273267,"package_name":"kaggle","ecosystem":"conda","requirements":"\u003e=1.5.12","direct":true,"kind":"runtime","optional":false},{"id":3812273268,"package_name":"openml","ecosystem":"conda","requirements":"\u003e=0.12.2","direct":true,"kind":"runtime","optional":false},{"id":3812273269,"package_name":"openpyxl","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":3812273270,"package_name":"pandas","ecosystem":"conda","requirements":"\u003e=1.4.1","direct":true,"kind":"runtime","optional":false},{"id":3812273271,"package_name":"pytest","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":3812273272,"package_name":"python","ecosystem":"conda","requirements":"\u003e=3.10","direct":true,"kind":"runtime","optional":false},{"id":3812273273,"package_name":"requests","ecosystem":"conda","requirements":"\u003e=2.27.1","direct":true,"kind":"runtime","optional":false},{"id":3812273274,"package_name":"setuptools","ecosystem":"conda","requirements":"\u003e=57.4.0","direct":true,"kind":"runtime","optional":false},{"id":3812273275,"package_name":"sphinx","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"docs/doc_requires.txt","sha":null,"kind":"manifest","created_at":"2022-09-04T18:22:36.795Z","updated_at":"2022-09-04T18:22:36.795Z","repository_link":"https://github.com/michaelbaluja/PyCurator/blob/main/docs/doc_requires.txt","dependencies":[{"id":3812273289,"package_name":"sphinx-book-theme","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2022-09-04T18:22:36.837Z","updated_at":"2022-09-04T18:22:36.837Z","repository_link":"https://github.com/michaelbaluja/PyCurator/blob/main/requirements.txt","dependencies":[{"id":3812273328,"package_name":"kaggle","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":3812273329,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":3812273330,"package_name":"pytest","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":3812273331,"package_name":"requests","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":3812273332,"package_name":"appdirs","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:51:00.049Z","updated_at":"2025-10-07T08:12:16.799Z","avatar_url":"https://github.com/michaelbaluja.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":12,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/27711","html_url":"https://science.ecosyste.ms/projects/27711","bibtex_url":"https://science.ecosyste.ms/projects/27711/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/27711/export.apalike"}