{"id":29544740,"url":"https://github.com/tauses/engagemachinelearning","last_synced_at":"2026-05-16T22:31:43.738Z","repository":{"id":301742167,"uuid":"981768909","full_name":"Tauses/EngageMachineLearning","owner":"Tauses","description":"Submitted as part of my Machine Learning exam.","archived":false,"fork":false,"pushed_at":"2025-06-28T14:18:37.000Z","size":33762,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-07-14T03:30:13.865Z","etag":null,"topics":["finetuned-model","llama2","llm","machinelearning"],"latest_commit_sha":null,"homepage":"","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/Tauses.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,"zenodo":null}},"created_at":"2025-05-11T20:53:02.000Z","updated_at":"2025-06-28T18:02:16.000Z","dependencies_parsed_at":"2025-06-28T15:30:33.049Z","dependency_job_id":"761599fe-6d7d-44bc-acbb-4aad2b24ac9a","html_url":"https://github.com/Tauses/EngageMachineLearning","commit_stats":null,"previous_names":["tauses/engagemachinelearning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Tauses/EngageMachineLearning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tauses%2FEngageMachineLearning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tauses%2FEngageMachineLearning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tauses%2FEngageMachineLearning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tauses%2FEngageMachineLearning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Tauses","download_url":"https://codeload.github.com/Tauses/EngageMachineLearning/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tauses%2FEngageMachineLearning/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265625563,"owners_count":23800623,"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":["finetuned-model","llama2","llm","machinelearning"],"created_at":"2025-07-17T16:00:57.172Z","updated_at":"2026-05-16T22:31:43.699Z","avatar_url":"https://github.com/Tauses.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1\u003eGaming Chatbot \u0026 Player Profiler\u003c/h1\u003e\n\nA compact Python toolkit for analysing gamers behavioural data and chatting with them through locally‑run Llama 2 models. The project demonstrates end‑to‑end ML: clustering, classification, sentiment analysis and an interactive recommendation bot. Using the K-means and RandomForest pipeline for optimal prediction capabilities.\n\n\u003ch2\u003eKey Features\u003c/h2\u003e\n\u003col\u003e\n  \u003cli\u003eData profiling \u0026mdash; K-Means clustering (\u003ccode\u003eTrainProfiler.py\u003c/code\u003e) categorizes players into six intuitive segments.\u003c/li\u003e\n\n  \u003cli\u003eEngagement prediction \u0026mdash; Random-Forest classifier (\u003ccode\u003eRFTrainBot.py\u003c/code\u003e) forecasts each player's engagement level.\u003c/li\u003e\n\n  \u003cli\u003e\u003cstrong\u003eThree chatbots\u003c/strong\u003e\n    \u003col\u003e\n      \u003cli\u003e\u003cstrong\u003eHeavy\u003c/strong\u003e \u0026mdash; fully automated ML + Llama; uses regex to extract user features (\u003ccode\u003eChatbot_Heavy_Model.py\u003c/code\u003e).\u003c/li\u003e\n      \u003cli\u003e\u003cstrong\u003eLight\u003c/strong\u003e \u0026mdash; semi-automated, keyword-triggered ML for user-feature extraction (\u003ccode\u003eChatbot_Lighter_Model.py\u003c/code\u003e).\u003c/li\u003e\n      \u003cli\u003e\u003cstrong\u003eStupid\u003c/strong\u003e \u0026mdash; rule-based fallback with canned responses (\u003ccode\u003eChatbot_Stupid.py\u003c/code\u003e).\u003c/li\u003e\n    \u003c/ol\u003e\n  \u003c/li\u003e\n\n  \u003cli\u003eSentiment and keyword tracking with NLTK.\u003c/li\u003e\n\n  \u003cli\u003eLocal Llama 2 inference via \u003cem\u003ellama-cpp-python\u003c/em\u003e (no external API keys required).\u003c/li\u003e\n\u003c/ol\u003e\n\n\u003ch2\u003eREQUIREMENTS\u003c/h2\u003e\nIn order to run the light and heavy model, you must first install Visual Studio BuildTools for desktop. \nhttps://visualstudio.microsoft.com/visual-cpp-build-tools/\nUnder \"Workloads\" after installing the BuildTools Choose \"Desktop Development with C++\" and wait for it to install the packages.\n\nNow you should be able to run it.\n\n\u003ch2\u003eCustomising the Models\u003c/h2\u003e\nWish to try my models?\n\nYou can try editing the \u003cstrong\u003en_clusters\u003c/strong\u003e in TrainProfiler.py.\nThere's quite a few other settings to mess around with aswell. Watch out for the context window, the max is 4096, setting it higher results in crashing the program.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftauses%2Fengagemachinelearning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftauses%2Fengagemachinelearning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftauses%2Fengagemachinelearning/lists"}