{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2017-02-09T13:18:35.088507+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "keywords.tsv": { "checksum": "md5:0202530008708c280cc7e641f6754596", "ext": "tsv", "id": "9d7fc390-fbdb-4d46-8b0d-26221ced1156", "key": "keywords.tsv", "metadata": null, "mimetype": "text/tab-separated-values", "size": 47355505 } }, "order": [], "total_bytes": 47355505 }, "id": "285293", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/285293/access", "access_links": "https://zenodo.org/api/records/285293/access/links", "access_request": "https://zenodo.org/api/records/285293/access/request", "access_users": "https://zenodo.org/api/records/285293/access/users", "archive": "https://zenodo.org/api/records/285293/files-archive", "archive_media": "https://zenodo.org/api/records/285293/media-files-archive", "communities": "https://zenodo.org/api/records/285293/communities", "communities-suggestions": "https://zenodo.org/api/records/285293/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.285293", "draft": "https://zenodo.org/api/records/285293/draft", "files": "https://zenodo.org/api/records/285293/files", "latest": "https://zenodo.org/api/records/285293/versions/latest", "latest_html": "https://zenodo.org/records/285293/latest", "media_files": "https://zenodo.org/api/records/285293/media-files", "parent": "https://zenodo.org/api/records/768905", "parent_doi": "https://zenodo.org/doi/", "parent_html": "https://zenodo.org/records/768905", "requests": "https://zenodo.org/api/records/285293/requests", "reserve_doi": "https://zenodo.org/api/records/285293/draft/pids/doi", "self": "https://zenodo.org/api/records/285293", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.285293", "self_html": "https://zenodo.org/records/285293", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:285293/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:285293/sequence/default", "versions": "https://zenodo.org/api/records/285293/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "source{d}" } ], "person_or_org": { "family_name": "Markovtsev Vadim", "name": "Markovtsev Vadim", "type": "personal" } } ], "description": "
Origin
\n\n16,000,000 repositories on GitHub as of October 2016, classified with\u00a0github/linguist\u00a0and parsed with\u00a0Pygments. Token.Keyword tokens were filtered and MapReduce-d. Fuzzy duplicate repositories were discarded.
\n\nSome languages, e.g. Haskell, are parsed wrong, resulting in\u00a0many\u00a0keywords. Still they were not removed since we are not familiar with such languages.
\n\nFormat
\n\nTriples [language name]\\t[keyword]\\t[frequency]
\n\nTabs and new lines in keywords are escaped as \\t and \\n respectively.
", "publication_date": "2017-02-09", "publisher": "Zenodo", "related_identifiers": [ { "identifier": "https://data.world/vmarkovtsev/github-lng-keyword-frequencies", "relation_type": { "id": "isidenticalto", "title": { "de": "Ist identisch mit", "en": "Is identical to" } }, "scheme": "url" } ], "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "rights": [ { "description": { "en": "" }, "icon": "cc-by-nc-icon", "id": "cc-by-nc-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by-nc/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution Non Commercial 4.0 International" } } ], "subjects": [ { "subject": "source code" }, { "subject": "github" }, { "subject": "open source" }, { "subject": "programming" }, { "subject": "compilers" }, { "subject": "programming language" } ], "title": "Programming language keyword frequencies extracted from 16,000,000 public GitHub repositories (October 2016)" }, "parent": { "access": { "owned_by": { "user": 28463 } }, "communities": { "default": "bf9878bc-9048-4ff7-8033-6a6c36466dad", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2015-04-09T17:36:48+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "bf9878bc-9048-4ff7-8033-6a6c36466dad", "links": {}, "metadata": { "curation_policy": "Sanity check
\r\n", "description": "Data, code and papers about empirical knowledge in software engineering.", "page": "", "title": "Empirical Software Engineering" }, "revision_id": 0, "slug": "empirical-software-engineering", "updated": "2020-08-28T06:48:44.120149+00:00" } ], "ids": [ "bf9878bc-9048-4ff7-8033-6a6c36466dad" ] }, "id": "768905", "pids": { "doi": { "identifier": "", "provider": "legacy" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.285293", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:285293", "provider": "oai" } }, "revision_id": 7, "stats": { "all_versions": { "data_volume": 4498772975.0, "downloads": 95, "unique_downloads": 88, "unique_views": 495, "views": 518 }, "this_version": { "data_volume": 4451417470.0, "downloads": 94, "unique_downloads": 87, "unique_views": 492, "views": 513 } }, "status": "published", "updated": "2020-01-24T19:25:26.955145+00:00", "versions": { "index": 1, "is_latest": true } }