{"id":16130219,"url":"https://github.com/lambdacasserole/classr","last_synced_at":"2026-04-29T17:07:14.392Z","repository":{"id":75385725,"uuid":"581861870","full_name":"lambdacasserole/classr","owner":"lambdacasserole","description":"Train microclassifiers in the cloud for spam detection, sentiment analysis and more.","archived":false,"fork":false,"pushed_at":"2024-02-27T15:42:03.000Z","size":2124,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-12T20:19:34.895Z","etag":null,"topics":["classification","classification-model","machine-learning","mlaas","naive-bayes","naive-bayes-classifier","saas","t3-stack","vercel"],"latest_commit_sha":null,"homepage":"https://classr.dev","language":"HTML","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/lambdacasserole.png","metadata":{"files":{"readme":"README.md","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":"2022-12-24T16:18:20.000Z","updated_at":"2023-01-15T10:02:06.000Z","dependencies_parsed_at":"2024-11-01T09:26:43.238Z","dependency_job_id":"02d6be91-2d0a-42ca-9869-88b0c6c20c5a","html_url":"https://github.com/lambdacasserole/classr","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lambdacasserole%2Fclassr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lambdacasserole%2Fclassr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lambdacasserole%2Fclassr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lambdacasserole%2Fclassr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lambdacasserole","download_url":"https://codeload.github.com/lambdacasserole/classr/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247492546,"owners_count":20947545,"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":["classification","classification-model","machine-learning","mlaas","naive-bayes","naive-bayes-classifier","saas","t3-stack","vercel"],"created_at":"2024-10-09T22:15:00.985Z","updated_at":"2026-04-29T17:07:14.298Z","avatar_url":"https://github.com/lambdacasserole.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Classr\n\nTrain microclassifiers in the cloud for spam detection, sentiment analysis and more.\n\n![Classr logo](./public/logo-light.svg)\n\n## Overview\n\nClassr is a web app that allows users to create *microclassifiers*. A microclassifier is just a machine learning model (classifier) that is trained using a minimal (but still reasonable) amount of training data (4MB max).\n\n![Screenshot of app](./screenshot-app.png)\n\nClassr uses the [bayes](https://www.npmjs.com/package/bayes) package at its core with custom additions for calculation of precision/recall/F1 score etc. and generation and rendering of confusion matrices.\n\n## Why this project?\n\nI wanted to see what I couuld do working on something from scratch with the T3 stack while sharpening my frontend skills in the process.\n\nTurns out, it's a super cool stack that you should definitely try out if you haven't already!\n\n* [create-t3-app](https://create.t3.gg/)\n* [TypeScript](https://typescriptlang.org)\n* [Next.js](https://nextjs.org)\n* [NextAuth.js](https://next-auth.js.org)\n* [Prisma](https://prisma.io)\n* [Tailwind CSS](https://tailwindcss.com)\n* [tRPC](https://trpc.io)\n\n## Limitations\n\nClassr trains multinomial naive bayes classifiers behind the scenes on unigrams generated by splitting strings along space characters. Train/test split is 20/80 and Laplace smoothing is at 1.\n\n**Any ML engineer with tell you that this is a very simple classifier with a lot of caveats. Use appropriately, and wield responsibly.**\n\nClassr does not support any of the following features (yet!):\n\n* Training on n-grams.\n* Tokenization based on anything but splitting documents along spaces.\n* Stopword removal.\n* More advanced classifiers (SVMs, random forests etc.)\n\n## Deployment\n\nThis app is designed for deployment on [Vercel](https://create.t3.gg/en/deployment/vercel) but you might also be able to get it to work with [Docker](https://create.t3.gg/en/deployment/docker) (I haven't tried this myself yet).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flambdacasserole%2Fclassr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flambdacasserole%2Fclassr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flambdacasserole%2Fclassr/lists"}