{"id":16597944,"url":"https://github.com/alexioannides/llm-regression","last_synced_at":"2025-10-20T08:07:54.667Z","repository":{"id":240592550,"uuid":"800182758","full_name":"AlexIoannides/llm-regression","owner":"AlexIoannides","description":"Exploring the classical regression capabilities of LLMs.","archived":false,"fork":false,"pushed_at":"2024-05-20T22:33:29.000Z","size":113,"stargazers_count":18,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-15T13:48:27.912Z","etag":null,"topics":["genai","llm","machine-learning","openai","regression"],"latest_commit_sha":null,"homepage":"","language":"Python","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/AlexIoannides.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":"2024-05-13T21:22:39.000Z","updated_at":"2025-03-14T02:05:02.000Z","dependencies_parsed_at":"2024-06-09T16:34:49.140Z","dependency_job_id":null,"html_url":"https://github.com/AlexIoannides/llm-regression","commit_stats":null,"previous_names":["alexioannides/llm-regression"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AlexIoannides/llm-regression","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexIoannides%2Fllm-regression","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexIoannides%2Fllm-regression/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexIoannides%2Fllm-regression/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexIoannides%2Fllm-regression/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AlexIoannides","download_url":"https://codeload.github.com/AlexIoannides/llm-regression/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexIoannides%2Fllm-regression/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":280050927,"owners_count":26263885,"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":"2025-10-20T02:00:06.978Z","response_time":62,"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":["genai","llm","machine-learning","openai","regression"],"created_at":"2024-10-12T00:07:08.565Z","updated_at":"2025-10-20T08:07:54.653Z","avatar_url":"https://github.com/AlexIoannides.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Regression using LLMs\n\nThe llm-regression package demonstrates how LLMs can be used to solve classical regression problems, and exposes these capabilities for you to experiment with. Example:\n\n```python\nfrom llm_regression import OpenAiRegressor\n\nllm_regressor = OpenAiRegressor(model=\"gpt-3.5-turbo\")\nllm_regressor.fit(X_train, y_train)\ny_pred = llm_regressor.predict(X_test)\n```\n\nThis work was motivated by the paper,\n\n[\"_From Words to Numbers: You LLM is Secretly a Capable Regressor_\", by Vacareanu et al. (2024)](https://arxiv.org/abs/2404.07544).\n\nWhich is well worth a read!\n\n## Installing\n\nYou can install the llm_regression package, together with the dependencies required to run the example notebooks, directly from this repo,\n\n```text\npip install -U pip\npip install \"llm-regression[examples] @ git+https://github.com/AlexIoannides/llm-regression.git\"\n```\n\n## Examples\n\nCheckout the [basic_demo notebook](https://github.com/AlexIoannides/llm-regression/tree/main/examples/basic_demo.ipynb).\n\n## Developer Setup\n\nIf you want to modify or extend the work in this repo, then the information in this section is for you.\n\n### Install Developer Tools\n\nInstall the package as an [editable dependency](https://setuptools.pypa.io/en/latest/userguide/development_mode.html), together with all the developer tools required to format code, check types and run tests:\n\n```text\npip install -e \".[dev]\"\n```\n\n### Developer Task Execution with Nox\n\nWe use [Nox](https://nox.thea.codes/en/stable/) for scripting developer tasks, such as formatting code, checking types and running tests. These tasks are defined in `noxfile.py`, a list of which can be returned on the command line,\n\n```text\n$ nox --list\n\nSessions defined in /Users/.../noxfile.py:\n\n* run_tests-3.12 -\u003e Run unit tests.\n- format_code-3.12 -\u003e Lint code and re-format where necessary.\n* check_code_formatting-3.12 -\u003e Check code for formatting errors.\n* check_types-3.12 -\u003e Run static type checking.\n- build_and_deploy-3.12 -\u003e Build wheel and deploy to PyPI.\n\nsessions marked with * are selected, sessions marked with - are skipped.\n```\n\nSingle tasks can be executed easily - e.g.,\n\n```text\n$ nox -s run_tests\n\nnox \u003e Running session run_tests-3.12\nnox \u003e Creating virtual environment (virtualenv) using python3.12 in .nox/run_tests-3-10\nnox \u003e python -m pip install '.[dev]'\nnox \u003e pytest \n======================================== test session starts ========================================\nplatform darwin -- Python 3.12.2, pytest-7.4.2, pluggy-1.3.0\nrootdir: /Users/.../llm_regression\nconfigfile: pyproject.toml\ntestpaths: tests\ncollected 1 item                                                                                                                                                         \n\ntests/test_hello_world.py                      [100%]\n\n========================================== 1 passed in 0.00s =========================================\nnox \u003e Session run_tests-3.12 was successful.\n```\n\n### CI/CD\n\nThis repo comes configured to run two [GitHub Actions](https://docs.github.com/en/actions) workflows:\n\n- **Test Python Package (CI)**, defined in `.github/workflows/python-package-ci.yml`\n- **Deploy Python Package (CD)**, defined in `.github/workflows/python-package-cd.yml`\n\nThe CI workflow has been configured to run whenever a pull request to the `main` branch is created. The CD workflow has been configured to run whenever a [release](https://docs.github.com/en/repositories/releasing-projects-on-github/managing-releases-in-a-repository) is created on GitHub.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexioannides%2Fllm-regression","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falexioannides%2Fllm-regression","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexioannides%2Fllm-regression/lists"}