{"id":45281,"name":"word2vecelastic","description":"Collect sentences from ElasticSearch, preprocess and train diachronic Word2Vec models","url":"https://github.com/centrefordigitalhumanities/word2vecelastic","last_synced_at":"2025-09-05T10:23:39.989Z","repository":{"id":182601376,"uuid":"171899269","full_name":"CentreForDigitalHumanities/Word2VecElastic","owner":"CentreForDigitalHumanities","description":"Collect sentences from ElasticSearch, preprocess and train diachronic Word2Vec models","archived":false,"fork":false,"pushed_at":"2025-07-14T15:04:03.000Z","size":122,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":5,"default_branch":"develop","last_synced_at":"2025-07-14T18:39:06.685Z","etag":null,"topics":["elasticsearch","embeddings","word2vec"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CentreForDigitalHumanities.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":"2019-02-21T15:43:30.000Z","updated_at":"2025-07-14T15:04:06.000Z","dependencies_parsed_at":"2024-03-14T12:25:52.344Z","dependency_job_id":"b8bf4593-d03c-49aa-ae3c-ec4bd1f019ad","html_url":"https://github.com/CentreForDigitalHumanities/Word2VecElastic","commit_stats":null,"previous_names":["uudigitalhumanitieslab/word2vecelastic","centrefordigitalhumanities/word2vecelastic"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/CentreForDigitalHumanities/Word2VecElastic","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FWord2VecElastic","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FWord2VecElastic/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FWord2VecElastic/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FWord2VecElastic/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CentreForDigitalHumanities","download_url":"https://codeload.github.com/CentreForDigitalHumanities/Word2VecElastic/tar.gz/refs/heads/develop","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FWord2VecElastic/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273743173,"owners_count":25159994,"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":"CentreForDigitalHumanities","name":"Centre for Digital Humanities","uuid":"87316747","kind":"organization","description":"Interdisciplinary centre for research and education in computational and data-driven methods in the humanities.","email":"cdh@uu.nl","website":"https://cdh.uu.nl/","location":"Netherlands","twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/87316747?v=4","repositories_count":39,"last_synced_at":"2024-04-24T06:02:37.702Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/CentreForDigitalHumanities","funding_links":[],"total_stars":20,"followers":12,"following":0,"created_at":"2022-11-08T06:06:11.908Z","updated_at":"2024-04-24T06:02:55.424Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CentreForDigitalHumanities","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CentreForDigitalHumanities/repositories"},"packages":[],"commits":{"id":7068206,"full_name":"CentreForDigitalHumanities/Word2VecElastic","default_branch":"develop","committers":[{"name":"BeritJanssen","email":"berit.janssen@gmail.com","login":"BeritJanssen","count":164},{"name":"lukavdplas","email":"lukavdplas@gmail.com","login":"lukavdplas","count":1}],"total_commits":165,"total_committers":2,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":82.5,"dds":0.0060606060606061,"past_year_committers":[{"name":"BeritJanssen","email":"berit.janssen@gmail.com","login":"BeritJanssen","count":16}],"past_year_total_commits":16,"past_year_total_committers":1,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":16.0,"past_year_dds":0.0,"last_synced_at":"2025-07-07T18:29:39.558Z","last_synced_commit":"9432cc149e73059b9283091b8226b20f04bc6723","created_at":"2024-11-30T06:07:23.054Z","updated_at":"2025-07-07T18:29:39.558Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FWord2VecElastic/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":"CentreForDigitalHumanities/Word2VecElastic","html_url":"https://github.com/CentreForDigitalHumanities/Word2VecElastic","last_synced_at":"2025-07-07T04:10:49.593Z","status":null,"issues_count":3,"pull_requests_count":4,"avg_time_to_close_issue":8252627.0,"avg_time_to_close_pull_request":5864522.0,"issues_closed_count":3,"pull_requests_closed_count":4,"pull_request_authors_count":1,"issue_authors_count":1,"avg_comments_per_issue":1.0,"avg_comments_per_pull_request":1.25,"merged_pull_requests_count":3,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":1,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":609052.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":1,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":1.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":1,"created_at":"2024-11-30T06:07:25.469Z","updated_at":"2025-08-31T00:14:18.958Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FWord2VecElastic","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FWord2VecElastic/issues","issue_labels_count":{"wontfix":1},"pull_request_labels_count":{},"issue_author_associations_count":{"CONTRIBUTOR":3},"pull_request_author_associations_count":{"CONTRIBUTOR":5},"issue_authors":{"lukavdplas":3},"pull_request_authors":{"BeritJanssen":5},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-01T00:00:07.725Z","repositories_count":9946380,"issues_count":29473096,"pull_requests_count":85381310,"authors_count":9367128,"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":{"CONTRIBUTOR":2},"past_year_issue_authors":{},"past_year_pull_request_authors":{"BeritJanssen":2},"maintainers":[],"active_maintainers":[]},"events":{"total":{"DeleteEvent":1,"IssueCommentEvent":1,"MemberEvent":1,"PushEvent":10,"PullRequestEvent":1,"CreateEvent":2},"last_year":{"DeleteEvent":1,"IssueCommentEvent":1,"MemberEvent":1,"PushEvent":10,"PullRequestEvent":1,"CreateEvent":2}},"keywords":["elasticsearch","embeddings","word2vec"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.in","sha":null,"kind":"manifest","created_at":"2023-10-04T14:32:09.589Z","updated_at":"2023-10-04T14:32:09.589Z","repository_link":"https://github.com/CentreForDigitalHumanities/Word2VecElastic/blob/develop/requirements.in","dependencies":[{"id":14104383025,"package_name":"elasticsearch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14104383026,"package_name":"gensim","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14104383027,"package_name":"pytest","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14104383028,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":14104383029,"package_name":"spacy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"lockfile","created_at":"2023-10-04T14:32:09.646Z","updated_at":"2023-10-04T14:32:09.646Z","repository_link":"https://github.com/CentreForDigitalHumanities/Word2VecElastic/blob/develop/requirements.txt","dependencies":[{"id":14104383037,"package_name":"attrs","ecosystem":"pypi","requirements":"==22.2.0","direct":false,"kind":"runtime","optional":false},{"id":14104383038,"package_name":"blis","ecosystem":"pypi","requirements":"==0.7.9","direct":false,"kind":"runtime","optional":false},{"id":14104383039,"package_name":"catalogue","ecosystem":"pypi","requirements":"==2.0.8","direct":false,"kind":"runtime","optional":false},{"id":14104383040,"package_name":"certifi","ecosystem":"pypi","requirements":"==2022.12.7","direct":false,"kind":"runtime","optional":false},{"id":14104383041,"package_name":"charset-normalizer","ecosystem":"pypi","requirements":"==2.1.1","direct":false,"kind":"runtime","optional":false},{"id":14104383042,"package_name":"click","ecosystem":"pypi","requirements":"==8.1.3","direct":false,"kind":"runtime","optional":false},{"id":14104383043,"package_name":"confection","ecosystem":"pypi","requirements":"==0.0.3","direct":false,"kind":"runtime","optional":false},{"id":14104383044,"package_name":"cymem","ecosystem":"pypi","requirements":"==2.0.7","direct":false,"kind":"runtime","optional":false},{"id":14104383045,"package_name":"elastic-transport","ecosystem":"pypi","requirements":"==8.4.0","direct":false,"kind":"runtime","optional":false},{"id":14104383046,"package_name":"elasticsearch","ecosystem":"pypi","requirements":"==8.6.1","direct":false,"kind":"runtime","optional":false},{"id":14104383047,"package_name":"exceptiongroup","ecosystem":"pypi","requirements":"==1.1.0","direct":false,"kind":"runtime","optional":false},{"id":14104383048,"package_name":"fst-pso","ecosystem":"pypi","requirements":"==1.8.1","direct":false,"kind":"runtime","optional":false},{"id":14104383050,"package_name":"fuzzytm","ecosystem":"pypi","requirements":"==2.0.5","direct":false,"kind":"runtime","optional":false},{"id":14104383052,"package_name":"gensim","ecosystem":"pypi","requirements":"==4.3.0","direct":false,"kind":"runtime","optional":false},{"id":14104383053,"package_name":"idna","ecosystem":"pypi","requirements":"==3.4","direct":false,"kind":"runtime","optional":false},{"id":14104383054,"package_name":"iniconfig","ecosystem":"pypi","requirements":"==1.1.1","direct":false,"kind":"runtime","optional":false},{"id":14104383055,"package_name":"jinja2","ecosystem":"pypi","requirements":"==3.1.2","direct":false,"kind":"runtime","optional":false},{"id":14104383056,"package_name":"joblib","ecosystem":"pypi","requirements":"==1.2.0","direct":false,"kind":"runtime","optional":false},{"id":14104383057,"package_name":"langcodes","ecosystem":"pypi","requirements":"==3.3.0","direct":false,"kind":"runtime","optional":false},{"id":14104383058,"package_name":"markupsafe","ecosystem":"pypi","requirements":"==2.1.1","direct":false,"kind":"runtime","optional":false},{"id":14104383059,"package_name":"miniful","ecosystem":"pypi","requirements":"==0.0.6","direct":false,"kind":"runtime","optional":false},{"id":14104383060,"package_name":"murmurhash","ecosystem":"pypi","requirements":"==1.0.9","direct":false,"kind":"runtime","optional":false},{"id":14104383061,"package_name":"numpy","ecosystem":"pypi","requirements":"==1.24.1","direct":false,"kind":"runtime","optional":false},{"id":14104383062,"package_name":"packaging","ecosystem":"pypi","requirements":"==22.0","direct":false,"kind":"runtime","optional":false},{"id":14104383063,"package_name":"pandas","ecosystem":"pypi","requirements":"==1.5.2","direct":false,"kind":"runtime","optional":false},{"id":14104383064,"package_name":"pathy","ecosystem":"pypi","requirements":"==0.10.1","direct":false,"kind":"runtime","optional":false},{"id":14104383065,"package_name":"pluggy","ecosystem":"pypi","requirements":"==1.0.0","direct":false,"kind":"runtime","optional":false},{"id":14104383066,"package_name":"preshed","ecosystem":"pypi","requirements":"==3.0.8","direct":false,"kind":"runtime","optional":false},{"id":14104383067,"package_name":"pydantic","ecosystem":"pypi","requirements":"==1.10.4","direct":false,"kind":"runtime","optional":false},{"id":14104383068,"package_name":"pyfume","ecosystem":"pypi","requirements":"==0.2.25","direct":false,"kind":"runtime","optional":false},{"id":14104383073,"package_name":"pytest","ecosystem":"pypi","requirements":"==7.2.0","direct":false,"kind":"runtime","optional":false},{"id":14104383074,"package_name":"python-dateutil","ecosystem":"pypi","requirements":"==2.8.2","direct":false,"kind":"runtime","optional":false},{"id":14104383075,"package_name":"pytz","ecosystem":"pypi","requirements":"==2022.7","direct":false,"kind":"runtime","optional":false},{"id":14104383076,"package_name":"requests","ecosystem":"pypi","requirements":"==2.28.1","direct":false,"kind":"runtime","optional":false},{"id":14104383077,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"==1.2.0","direct":false,"kind":"runtime","optional":false},{"id":14104383078,"package_name":"scipy","ecosystem":"pypi","requirements":"==1.10.0","direct":false,"kind":"runtime","optional":false},{"id":14104383079,"package_name":"simpful","ecosystem":"pypi","requirements":"==2.9.0","direct":false,"kind":"runtime","optional":false},{"id":14104383080,"package_name":"six","ecosystem":"pypi","requirements":"==1.16.0","direct":false,"kind":"runtime","optional":false},{"id":14104383081,"package_name":"smart-open","ecosystem":"pypi","requirements":"==6.3.0","direct":false,"kind":"runtime","optional":false},{"id":14104383082,"package_name":"spacy","ecosystem":"pypi","requirements":"==3.4.4","direct":false,"kind":"runtime","optional":false},{"id":14104383083,"package_name":"spacy-legacy","ecosystem":"pypi","requirements":"==3.0.11","direct":false,"kind":"runtime","optional":false},{"id":14104383084,"package_name":"spacy-loggers","ecosystem":"pypi","requirements":"==1.0.4","direct":false,"kind":"runtime","optional":false},{"id":14104383085,"package_name":"srsly","ecosystem":"pypi","requirements":"==2.4.5","direct":false,"kind":"runtime","optional":false},{"id":14104383086,"package_name":"thinc","ecosystem":"pypi","requirements":"==8.1.6","direct":false,"kind":"runtime","optional":false},{"id":14104383087,"package_name":"threadpoolctl","ecosystem":"pypi","requirements":"==3.1.0","direct":false,"kind":"runtime","optional":false},{"id":14104383088,"package_name":"tomli","ecosystem":"pypi","requirements":"==2.0.1","direct":false,"kind":"runtime","optional":false},{"id":14104383089,"package_name":"tqdm","ecosystem":"pypi","requirements":"==4.64.1","direct":false,"kind":"runtime","optional":false},{"id":14104383090,"package_name":"typer","ecosystem":"pypi","requirements":"==0.7.0","direct":false,"kind":"runtime","optional":false},{"id":14104383091,"package_name":"typing-extensions","ecosystem":"pypi","requirements":"==4.4.0","direct":false,"kind":"runtime","optional":false},{"id":14104383092,"package_name":"urllib3","ecosystem":"pypi","requirements":"==1.26.13","direct":false,"kind":"runtime","optional":false},{"id":14104383093,"package_name":"wasabi","ecosystem":"pypi","requirements":"==0.10.1","direct":false,"kind":"runtime","optional":false}]}],"score":0.6931471805599453,"created_at":"2025-09-04T15:51:20.666Z","updated_at":"2025-10-07T08:18:09.435Z","avatar_url":"https://github.com/CentreForDigitalHumanities.png","language":"Python","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/45281","html_url":"https://science.ecosyste.ms/projects/45281","bibtex_url":"https://science.ecosyste.ms/projects/45281/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/45281/export.apalike"}