{"id":17285519,"url":"https://github.com/pmadruga/ds-jobindex","last_synced_at":"2026-02-19T02:01:02.548Z","repository":{"id":37219967,"uuid":"281091133","full_name":"pmadruga/ds-jobindex","owner":"pmadruga","description":"Machine learning techniques (NLP) applied to the jobindex.dk dataset","archived":false,"fork":false,"pushed_at":"2023-02-16T02:05:13.000Z","size":1613,"stargazers_count":2,"open_issues_count":14,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-10-20T04:13:05.319Z","etag":null,"topics":["bert","deep-learning","machine-learning","natural-language-processing","nlp","python","pytorch","tfidf-vectorizer","transformers"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pmadruga.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"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":"2020-07-20T10:54:08.000Z","updated_at":"2025-08-13T10:31:39.000Z","dependencies_parsed_at":"2025-04-06T09:40:44.672Z","dependency_job_id":null,"html_url":"https://github.com/pmadruga/ds-jobindex","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pmadruga/ds-jobindex","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmadruga%2Fds-jobindex","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmadruga%2Fds-jobindex/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmadruga%2Fds-jobindex/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmadruga%2Fds-jobindex/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pmadruga","download_url":"https://codeload.github.com/pmadruga/ds-jobindex/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmadruga%2Fds-jobindex/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29600841,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-19T00:59:38.239Z","status":"online","status_checked_at":"2026-02-19T02:00:07.702Z","response_time":117,"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"}},"keywords":["bert","deep-learning","machine-learning","natural-language-processing","nlp","python","pytorch","tfidf-vectorizer","transformers"],"created_at":"2024-10-15T09:56:46.857Z","updated_at":"2026-02-19T02:01:02.524Z","avatar_url":"https://github.com/pmadruga.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Learning based search engine - Jobindex.DK case\n\n## Abstract\nAfter scrapping the data from jobindex.dk - Denmark's biggest job portal - of 4.2 million jobs, a set of different Natural Language Processing techniques and Machine Learning models were applied to the data. Specifically, [TFIDF](https://en.wikipedia.org/wiki/Tf%E2%80%93idf) and [BERT](https://github.com/google-research/bert) models were applied on top of a direct search (no AI).\n\nThe goal was to improve search results on a non-English data set, which was achieved, especially with [BERT](https://github.com/google-research/bert).\n\n## Structure\n\nThe search engine is structured into two parts:\n\n1. Python script: preprocessing of text, generation of embeddings, distance calculation and file exporting.\n2. Jupyter notebook: Determine BERT distances and present results.\n\n## Run\n\nTo generate a preprocessed dataset:\n\n```\npython src --process '/data/interim/jobindex_cropped_bigger.csv'\n```\n\nTo get recommendations (a preprocessed dataset has to be generated beforehand), run the `search_engine_results.ipynb` notebook.\n\n## Scripts\n\nTo lint code, run: \n```\n./scripts/lint-code.sh\n```\n\nTo start notebooks, run:\n```\n./scripts/start_notebooks.sh\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpmadruga%2Fds-jobindex","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpmadruga%2Fds-jobindex","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpmadruga%2Fds-jobindex/lists"}