{"id":36285,"name":"mlentory-etl-pipeline","description":"This repository aims at exploring APIs from different ML-related platforms so we can harvest and harmonize data from them","url":"https://github.com/zbmed-semtec/mlentory-etl-pipeline","last_synced_at":"2025-09-05T07:04:31.116Z","repository":{"id":235501190,"uuid":"713601385","full_name":"zbmed-semtec/mlentory-etl-pipeline","owner":"zbmed-semtec","description":"This repository aims at exploring APIs from different ML-related platforms so we can harvest and harmonize data from them","archived":false,"fork":false,"pushed_at":"2025-09-03T08:35:35.000Z","size":13656,"stargazers_count":9,"open_issues_count":8,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-09-03T10:23:03.984Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zbmed-semtec.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-11-02T21:21:06.000Z","updated_at":"2025-09-03T08:35:40.000Z","dependencies_parsed_at":"2024-07-22T08:03:11.697Z","dependency_job_id":"4fb93adb-5881-43d7-b6bc-5297fbe93a78","html_url":"https://github.com/zbmed-semtec/mlentory-etl-pipeline","commit_stats":null,"previous_names":["zbmed-semtec/mlentory-etl-pipeline"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zbmed-semtec/mlentory-etl-pipeline","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zbmed-semtec%2Fmlentory-etl-pipeline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zbmed-semtec%2Fmlentory-etl-pipeline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zbmed-semtec%2Fmlentory-etl-pipeline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zbmed-semtec%2Fmlentory-etl-pipeline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zbmed-semtec","download_url":"https://codeload.github.com/zbmed-semtec/mlentory-etl-pipeline/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zbmed-semtec%2Fmlentory-etl-pipeline/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273723196,"owners_count":25156304,"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":"zbmed-semtec","name":"zbmed-semtec","uuid":"80634266","kind":"organization","description":"","email":null,"website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/80634266?v=4","repositories_count":12,"last_synced_at":"2023-05-28T14:10:14.224Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/zbmed-semtec","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-02-21T01:44:20.726Z","updated_at":"2023-05-28T14:10:14.230Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zbmed-semtec","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zbmed-semtec/repositories"},"packages":[],"commits":{"id":8673118,"full_name":"zbmed-semtec/mlentory-etl-pipeline","default_branch":"master","committers":null,"total_commits":null,"total_committers":null,"total_bot_commits":null,"total_bot_committers":null,"mean_commits":null,"dds":null,"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":null,"last_synced_commit":null,"created_at":"2025-02-09T05:47:24.992Z","updated_at":"2025-02-09T05:47:24.992Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/zbmed-semtec%2Fmlentory-etl-pipeline/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.343Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"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":"zbmed-semtec/mlentory-etl-pipeline","html_url":"https://github.com/zbmed-semtec/mlentory-etl-pipeline","last_synced_at":"2025-09-03T23:09:52.640Z","status":null,"issues_count":31,"pull_requests_count":73,"avg_time_to_close_issue":3021131.5,"avg_time_to_close_pull_request":677994.5322580645,"issues_closed_count":18,"pull_requests_closed_count":62,"pull_request_authors_count":6,"issue_authors_count":3,"avg_comments_per_issue":0.3548387096774194,"avg_comments_per_pull_request":0.2602739726027397,"merged_pull_requests_count":56,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":31,"past_year_pull_requests_count":67,"past_year_avg_time_to_close_issue":3021131.5,"past_year_avg_time_to_close_pull_request":583125.7678571428,"past_year_issues_closed_count":18,"past_year_pull_requests_closed_count":56,"past_year_pull_request_authors_count":6,"past_year_issue_authors_count":3,"past_year_avg_comments_per_issue":0.3548387096774194,"past_year_avg_comments_per_pull_request":0.2537313432835821,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":50,"created_at":"2025-02-09T05:47:25.703Z","updated_at":"2025-09-03T23:09:52.642Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/zbmed-semtec%2Fmlentory-etl-pipeline","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/zbmed-semtec%2Fmlentory-etl-pipeline/issues","issue_labels_count":{"bug":1},"pull_request_labels_count":{"enhancement":1,"bug":1},"issue_author_associations_count":{"COLLABORATOR":26,"CONTRIBUTOR":5},"pull_request_author_associations_count":{"COLLABORATOR":65,"CONTRIBUTOR":6,"NONE":2},"issue_authors":{"bit2424":26,"ljgarcia":4,"rohitharavinder":1},"pull_request_authors":{"bit2424":51,"ShriSuha":11,"Two-Kay":4,"rohitharavinder":3,"Dhwanisolanki12":2,"thijssnelleman":2},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10081478,"issues_count":31331220,"pull_requests_count":96240505,"authors_count":10693617,"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":{"bug":1},"past_year_pull_request_labels_count":{"enhancement":1,"bug":1},"past_year_issue_author_associations_count":{"COLLABORATOR":26,"CONTRIBUTOR":5},"past_year_pull_request_author_associations_count":{"COLLABORATOR":59,"CONTRIBUTOR":6,"NONE":2},"past_year_issue_authors":{"bit2424":26,"ljgarcia":4,"rohitharavinder":1},"past_year_pull_request_authors":{"bit2424":45,"ShriSuha":11,"Two-Kay":4,"rohitharavinder":3,"thijssnelleman":2,"Dhwanisolanki12":2},"maintainers":[{"login":"bit2424","count":77,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/bit2424"},{"login":"ShriSuha","count":10,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/ShriSuha"},{"login":"Two-Kay","count":4,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Two-Kay"}],"active_maintainers":[{"login":"bit2424","count":71,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/bit2424"},{"login":"ShriSuha","count":10,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/ShriSuha"},{"login":"Two-Kay","count":4,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Two-Kay"}]},"events":{"total":{"IssuesEvent":48,"WatchEvent":7,"DeleteEvent":4,"MemberEvent":3,"IssueCommentEvent":19,"PushEvent":150,"PullRequestReviewEvent":16,"PullRequestEvent":65,"ForkEvent":1,"CreateEvent":27},"last_year":{"IssuesEvent":48,"WatchEvent":7,"DeleteEvent":4,"MemberEvent":3,"IssueCommentEvent":19,"PushEvent":150,"PullRequestReviewEvent":16,"PullRequestEvent":65,"ForkEvent":1,"CreateEvent":27}},"keywords":[],"dependencies":[{"ecosystem":"docker","filepath":"code/transform/Dockerfile","sha":null,"kind":"manifest","created_at":"2024-07-16T19:12:50.376Z","updated_at":"2024-07-16T19:12:50.376Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/code/transform/Dockerfile","dependencies":[{"id":19144925954,"package_name":"python","ecosystem":"docker","requirements":"3.11","direct":true,"kind":"build","optional":false}]},{"ecosystem":"docker","filepath":"tests/Dockerfile","sha":null,"kind":"manifest","created_at":"2024-07-16T19:12:50.682Z","updated_at":"2024-07-16T19:12:50.682Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/tests/Dockerfile","dependencies":[{"id":19144926792,"package_name":"python","ecosystem":"docker","requirements":"3.11","direct":true,"kind":"build","optional":false}]},{"ecosystem":"docker","filepath":"tests/docker-compose.yml","sha":null,"kind":"manifest","created_at":"2024-07-16T19:12:51.066Z","updated_at":"2024-07-16T19:12:51.066Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/tests/docker-compose.yml","dependencies":[]},{"ecosystem":"pypi","filepath":"code/extractors/hf_extractor/requirements.txt","sha":null,"kind":"manifest","created_at":"2024-07-16T19:12:51.241Z","updated_at":"2024-07-16T19:12:51.241Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/code/extractors/hf_extractor/requirements.txt","dependencies":[{"id":19144928217,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928218,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928219,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928220,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928221,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928222,"package_name":"mysql-connector-python","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"code/transform/requirements.txt","sha":null,"kind":"manifest","created_at":"2024-07-16T19:12:51.690Z","updated_at":"2024-07-16T19:12:51.690Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/code/transform/requirements.txt","dependencies":[{"id":19144928636,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928637,"package_name":"watchdog","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928638,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928639,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928640,"package_name":"matplotlib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928641,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928642,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928643,"package_name":"seaborn","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928644,"package_name":"demjson3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19144928645,"package_name":"rdflib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"tests/requirements.txt","sha":null,"kind":"manifest","created_at":"2024-07-16T19:12:52.072Z","updated_at":"2024-07-16T19:12:52.072Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/tests/requirements.txt","dependencies":[{"id":19144928663,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928664,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928665,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928666,"package_name":"watchdog","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928667,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928668,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928669,"package_name":"pytest","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928670,"package_name":"pytest-mock","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928671,"package_name":"demjson3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":19144928672,"package_name":"rdflib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false}]},{"ecosystem":"docker","filepath":"code/docker-compose.yml","sha":null,"kind":"manifest","created_at":"2024-06-10T12:03:09.067Z","updated_at":"2024-06-10T12:03:09.067Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/code/docker-compose.yml","dependencies":[]},{"ecosystem":"docker","filepath":"playground/docker-compose.yml","sha":null,"kind":"manifest","created_at":"2024-06-10T12:03:09.125Z","updated_at":"2024-06-10T12:03:09.125Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/playground/docker-compose.yml","dependencies":[{"id":18519684183,"package_name":"cambridgesemantics/anzograph","ecosystem":"docker","requirements":"latest","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"playground/requirements.txt","sha":null,"kind":"manifest","created_at":"2024-06-10T12:03:10.601Z","updated_at":"2024-06-10T12:03:10.601Z","repository_link":"https://github.com/zbmed-semtec/mlentory-etl-pipeline/blob/main/playground/requirements.txt","dependencies":[{"id":18519684560,"package_name":"rdflib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684561,"package_name":"sqlalchemy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684562,"package_name":"transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684563,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684564,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684565,"package_name":"matplotlib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684566,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684567,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684568,"package_name":"seaborn","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684569,"package_name":"jupyter","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684570,"package_name":"notebook","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":18519684571,"package_name":"mysql-connector-python","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:51:09.865Z","updated_at":"2025-10-07T08:15:00.771Z","avatar_url":"https://github.com/zbmed-semtec.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":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/36285","html_url":"https://science.ecosyste.ms/projects/36285","bibtex_url":"https://science.ecosyste.ms/projects/36285/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/36285/export.apalike"}