{"id":15627177,"url":"https://github.com/eggsyntax/py-user-knowledge","last_synced_at":"2026-03-03T04:02:51.520Z","repository":{"id":239045357,"uuid":"788039642","full_name":"eggsyntax/py-user-knowledge","owner":"eggsyntax","description":"Predicting demographics of users with GPT based on text they've written","archived":false,"fork":false,"pushed_at":"2024-05-09T18:10:32.000Z","size":13106,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-15T13:42:57.206Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/eggsyntax.png","metadata":{"files":{"readme":"README","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-04-17T16:59:40.000Z","updated_at":"2024-05-16T23:40:17.000Z","dependencies_parsed_at":null,"dependency_job_id":"2fede022-5372-4536-9117-4b34abd3378c","html_url":"https://github.com/eggsyntax/py-user-knowledge","commit_stats":null,"previous_names":["eggsyntax/py-user-knowledge"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eggsyntax%2Fpy-user-knowledge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eggsyntax%2Fpy-user-knowledge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eggsyntax%2Fpy-user-knowledge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eggsyntax%2Fpy-user-knowledge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eggsyntax","download_url":"https://codeload.github.com/eggsyntax/py-user-knowledge/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240124227,"owners_count":19751439,"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"}},"keywords":[],"created_at":"2024-10-03T10:15:34.989Z","updated_at":"2026-03-03T04:02:46.472Z","avatar_url":"https://github.com/eggsyntax.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Series of experiments testing how well LLMs (mainly GPT-3.5) can predict \ndemographics from text (mainly OKCupid profiles).\n\nTo run from the command line:\n- Make sure that OPENAI_API_KEY is defined in your environment\n- Install packages (untested as yet, please let me know if you encounter difficulties): `conda install --file conda_requirements.txt`\n- `python test-demographics.py`\n\nNOTE: this is HORRIBLE CODE. This was my experiment with letting GPT-4 generate \nmost of the individual functions, and then it's just patches on patches \nfrom there.\n\nIt suffers further from my initial naivete about typical ML conventions for \neg data representation, so I'm munging data back and forth in a bunch of places.\n\nIdeally I will rewrite it when I get time, but also when do I ever get time?\n\nCaveat emptor.\n\nNote that despite using temperature=0, the probability distribution predicted \nby GPT will vary somewhat between runs, so results will differ.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feggsyntax%2Fpy-user-knowledge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feggsyntax%2Fpy-user-knowledge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feggsyntax%2Fpy-user-knowledge/lists"}