{"id":47895165,"url":"https://github.com/mehradi-github/ref-jupyter-datapreparation","last_synced_at":"2026-04-04T03:40:29.673Z","repository":{"id":322209291,"uuid":"1088555909","full_name":"mehradi-github/ref-jupyter-datapreparation","owner":"mehradi-github","description":"Data preparation on Heart Disease Dataset from UCI","archived":false,"fork":false,"pushed_at":"2025-11-03T06:40:23.000Z","size":5,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-11-03T08:22:35.903Z","etag":null,"topics":[],"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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mehradi-github.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-03T06:07:59.000Z","updated_at":"2025-11-03T06:38:07.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/mehradi-github/ref-jupyter-datapreparation","commit_stats":null,"previous_names":["mehradi-github/ref-jupyter-datapreparation"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/mehradi-github/ref-jupyter-datapreparation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mehradi-github%2Fref-jupyter-datapreparation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mehradi-github%2Fref-jupyter-datapreparation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mehradi-github%2Fref-jupyter-datapreparation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mehradi-github%2Fref-jupyter-datapreparation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mehradi-github","download_url":"https://codeload.github.com/mehradi-github/ref-jupyter-datapreparation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mehradi-github%2Fref-jupyter-datapreparation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31387023,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T01:22:39.193Z","status":"online","status_checked_at":"2026-04-04T02:00:07.569Z","response_time":60,"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":[],"created_at":"2026-04-04T03:40:28.811Z","updated_at":"2026-04-04T03:40:29.669Z","avatar_url":"https://github.com/mehradi-github.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Data Preparation for the UCI Heart Disease Dataset\n\nThis notebook walks through the step-by-step data preparation process for the \"processed.cleveland.data\" file from the UCI Machine Learning Repository.\n\n## **The main preparation tasks are**:\n\n1.  **Load Data:** Load the dataset from the web and assign the correct column names.\n2.  **Handle Missing Values:** The dataset uses `'?'` for missing data. We will replace these and impute them.\n3.  **Transform Target Variable:** Convert the multi-class target (0-4) to a binary target (0 vs. 1).\n4.  **Encode \u0026 Scale Features:** Use `ColumnTransformer` to properly one-hot encode categorical features and scale numerical features.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmehradi-github%2Fref-jupyter-datapreparation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmehradi-github%2Fref-jupyter-datapreparation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmehradi-github%2Fref-jupyter-datapreparation/lists"}