{"id":13789004,"url":"https://github.com/DataCanvasIO/Cooka","last_synced_at":"2025-05-12T03:31:16.319Z","repository":{"id":40616798,"uuid":"306203809","full_name":"DataCanvasIO/Cooka","owner":"DataCanvasIO","description":"A lightweight and visual AutoML system","archived":false,"fork":false,"pushed_at":"2023-11-22T09:14:13.000Z","size":11779,"stargazers_count":39,"open_issues_count":8,"forks_count":107,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-08-03T21:03:10.724Z","etag":null,"topics":["automated-feature-engineering","automated-machine-learning","automl","data-science","deep-learning","hyperparameter-optimization","machine-learning","neural-network"],"latest_commit_sha":null,"homepage":"https://cooka.readthedocs.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DataCanvasIO.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}},"created_at":"2020-10-22T02:42:49.000Z","updated_at":"2024-02-09T04:00:28.000Z","dependencies_parsed_at":"2024-01-07T03:51:29.175Z","dependency_job_id":"0f76051e-48f9-45c4-ac0b-28d9319c0388","html_url":"https://github.com/DataCanvasIO/Cooka","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataCanvasIO%2FCooka","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataCanvasIO%2FCooka/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataCanvasIO%2FCooka/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataCanvasIO%2FCooka/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DataCanvasIO","download_url":"https://codeload.github.com/DataCanvasIO/Cooka/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225117110,"owners_count":17423340,"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":["automated-feature-engineering","automated-machine-learning","automl","data-science","deep-learning","hyperparameter-optimization","machine-learning","neural-network"],"created_at":"2024-08-03T21:00:57.426Z","updated_at":"2024-11-18T02:32:15.204Z","avatar_url":"https://github.com/DataCanvasIO.png","language":"Python","readme":"\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/DataCanvasIO/Cooka/main/docs/static/Cooka.png\" width=\"500\" \u003e\n\n[![Python Versions](https://img.shields.io/pypi/pyversions/cooka.svg)](https://pypi.org/project/hypergbm)\n[![Downloads](https://pepy.tech/badge/cooka)](https://pepy.tech/project/hypergbm)\n[![PyPI Version](https://img.shields.io/pypi/v/cooka.svg)](https://pypi.org/project/hypergbm)\n\n[Doc](https://cooka.readthedocs.io) | [简体中文](README_zh_CN.md)\n\nCooka is a lightweight and visualization toolkit to manage datasets and design model learning experiments through web UI.\nIt's using [DeepTables](https://github.com/DataCanvasIO/DeepTables) and [HyperGBM](https://github.com/DataCanvasIO/HyperGBM) as experiment engine to complete feature engineering, neural architecture search and hyperparameter tuning automatically.\n    \n![DataCanvas AutoML Toolkit](https://raw.githubusercontent.com/DataCanvasIO/Cooka/main/docs/static/DAT_latest.png)\n\n## Features overview \nThrough the web UI provided by cooka you can:\n\n- Add and analyze datasets\n- Design experiment\n- View experiment process and result\n- Using models\n- Export experiment to jupyter notebook \n\nScreen shots：\n\u003ctable style=\"border: none\"\u003e\n    \u003cth\u003e\u003cimg src=\"https://raw.githubusercontent.com/DataCanvasIO/Cooka/main/docs/static/cooka_home_page.png\" width=\"500\"/\u003e\u003c/th\u003e\n    \u003cth\u003e\u003cimg src=\"https://raw.githubusercontent.com/DataCanvasIO/Cooka/main/docs/static/cooka_train.gif\" width=\"500\"/\u003e\u003c/th\u003e\n\u003c/table\u003e\n\nThe machine learning algorithms supported are ：\n- XGBoost\n- LightGBM\n- Catboost\n\nThe neural networks supported are：\n- WideDeep\n- DeepFM\n- xDeepFM\n- AutoInt\n- DCN\n- FGCNN \n- FiBiNet\n- PNN\n- AFM\n- [...](https://deeptables.readthedocs.io/en/latest/models.html)\n\n\nThe search algorithms supported are：\n- Evolution\n- MCTS(Monte Carlo Tree Search)\n- [...](https://github.com/DataCanvasIO/HyperGBM)\n\nThe supported feature engineering provided by  [scikit-learn](https://scikit-learn.org) and [featuretools](https://github.com/alteryx/featuretools) are：\n\n- Scaler\n    - StandardScaler\n    - MinMaxScaler\n    - RobustScaler\n    - MaxAbsScaler\n    - Normalizer\n   \n- Encoder\n    - LabelEncoder\n    - OneHotEncoder\n    - OrdinalEncoder\n\n- Discretizer\n    - KBinsDiscretizer\n    - Binarizer\n\n- Dimension Reduction\n    - PCA\n\n- Feature derivation\n    - featuretools\n\n- Missing value filling\n    - SimpleImputer \n\nIt can also extend the search space to support more feature engineering methods and modeling algorithms.\n\n## Installation \n\n### Using pip\n\nThe python version should be \u003e= 3.6, for CentOS , install the system package:\n\n```shell script\npip install --upgrade pip\npip install cooka\n```\n\nStart the web server：\n```shell script\ncooka server\n```\n\nThen open `http://\u003cyour_ip:8000\u003e` with your browser to use cooka.\n\nBy default, the cooka configuration file is at `~/.config/cooka/cooka.py`,  to generate a template:\n```shell script\nmkdir -p ~/.config/cooka/\ncooka generate-config \u003e ~/.config/cooka/cooka.py\n```\n\n### Using Docker\n\nLaunch a Cooka docker container:\n\n```shell script\ndocker run -ti -p 8888:8888 -p 8000:8000 -p 9001:9001 -e COOKA_NOTEBOOK_PORTAL=http://\u003cyour_ip\u003e:8888 datacanvas/cooka:latest\n```\n\nOpen `http://\u003cyour_ip:8000\u003e` with your browser to visit cooka.\n\n## Citation\n\nIf you use Cooka in your research, please cite us as follows:\n\nHaifeng Wu, Jian Yang. Cooka: A lightweight and visual AutoML system. https://github.com/DataCanvasIO/Cooka, 2021. Version 0.1.x\n```\n@misc{cooka,\n  author={Haifeng Wu, Jian Yang},\n  title={{Cooka}: {A lightweight and visual AutoML system}},\n  howpublished={https://github.com/DataCanvasIO/Cooka},\n  note={Version 0.1.x},\n  year={2021}\n}\n```\n\n## DataCanvas\n\n![](https://raw.githubusercontent.com/DataCanvasIO/Cooka/main/docs/static/dc_logo_1.png)\n\nCooka is an open source project created by [DataCanvas](https://www.datacanvas.com/). \n","funding_links":[],"categories":["Tools and projects"],"sub_categories":["LLM"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDataCanvasIO%2FCooka","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FDataCanvasIO%2FCooka","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDataCanvasIO%2FCooka/lists"}