{"id":18308605,"url":"https://github.com/hyzhak/decision-tree","last_synced_at":"2025-04-09T11:29:11.745Z","repository":{"id":143505408,"uuid":"87162821","full_name":"hyzhak/decision-tree","owner":"hyzhak","description":"Machine Learning: Decision Tree ","archived":false,"fork":false,"pushed_at":"2017-05-30T21:02:22.000Z","size":177,"stargazers_count":1,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-02-15T05:27:47.722Z","etag":null,"topics":["classification","data-science","decision-tree","machine-learning","regression"],"latest_commit_sha":null,"homepage":null,"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/hyzhak.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":"2017-04-04T08:16:31.000Z","updated_at":"2024-09-27T09:06:07.000Z","dependencies_parsed_at":"2024-01-21T01:00:32.361Z","dependency_job_id":null,"html_url":"https://github.com/hyzhak/decision-tree","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/hyzhak%2Fdecision-tree","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hyzhak%2Fdecision-tree/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hyzhak%2Fdecision-tree/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hyzhak%2Fdecision-tree/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hyzhak","download_url":"https://codeload.github.com/hyzhak/decision-tree/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248030531,"owners_count":21036206,"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","data-science","decision-tree","machine-learning","regression"],"created_at":"2024-11-05T16:08:32.393Z","updated_at":"2025-04-09T11:29:11.739Z","avatar_url":"https://github.com/hyzhak.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Decision Tree\nMachine Learning: Decision Tree. Function Approximation.\n\n## Assumptions\nGrow tree just big enough to fit correct labeled data.\nSo short decision tree is more preferable than long.\n\u003e Occam's razor: prefer the simplest hypothesis that fit the data\n\n## Properties\n- can approximate any discrete function\n- we should should choose first parameter which reduce maximum of entropy (ID3)\n\n```\nI(X,Y) = H(X) - H(X|Y)\n\nwhere:\nH(X) = - sum(P(X=i) * log2(P(X=i))) for i in [1, n]\nH(X|Y=v) = -sum(P(X=i|Y=v) * log2(P(X=i|Y=v)) for i in [1, n]\nH(X|Y) = sum(P(Y=v) * H(X|Y=v)) for v in Y\n```\n\nWe shouldn't use error rate criteria (what we care about) because \nwe can get stuck in local minimal\n- C4.5\n\n\n## Reduced-Error Pruning (Overfitting)\n\nSplit data into training and validation set\nCreate tree that classifies training set correctly\nDo until further pruning is harmful:\n1. Evaluate impact on validation set of pruning each possible node (plus those below it)\n2. Greedily remove the one that most improves validation set accuracy\n\n* produces smallest version of most accurate subtree\n\n## Related\n\n1. [No Free Lunch Theorem](https://en.wikipedia.org/wiki/No_free_lunch_theorem) *we can't really get a program to guess\na right function until it has seen all of examples*.\n2. Kearns-Mansour’96 [On the Boosting Ability of Top-Down Decision Tree Learning Algorithms](https://www.cis.upenn.edu/~mkearns/papers/topdown.pdf)\n\n# Link\n\n1. [10-601, Spring 2015 by Tom Mitchell and Maria-Florina Balcan](http://www.cs.cmu.edu/~ninamf/courses/601sp15/lectures.shtml)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhyzhak%2Fdecision-tree","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhyzhak%2Fdecision-tree","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhyzhak%2Fdecision-tree/lists"}