{"id":15519909,"url":"https://github.com/ceteri/intro_spark","last_synced_at":"2025-04-17T06:30:42.691Z","repository":{"id":32456312,"uuid":"36035720","full_name":"ceteri/intro_spark","owner":"ceteri","description":"Code examples supporting the \"Introduction to Apache Spark\" video published by O'Reilly Media","archived":true,"fork":false,"pushed_at":"2022-07-01T17:37:35.000Z","size":162,"stargazers_count":37,"open_issues_count":1,"forks_count":35,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-03-29T21:51:06.381Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://shop.oreilly.com/product/0636920036807.do","language":"Scala","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ceteri.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}},"created_at":"2015-05-21T20:26:33.000Z","updated_at":"2025-03-07T17:44:41.000Z","dependencies_parsed_at":"2022-06-26T22:33:44.414Z","dependency_job_id":null,"html_url":"https://github.com/ceteri/intro_spark","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/ceteri%2Fintro_spark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceteri%2Fintro_spark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceteri%2Fintro_spark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceteri%2Fintro_spark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ceteri","download_url":"https://codeload.github.com/ceteri/intro_spark/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249319594,"owners_count":21250578,"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":[],"created_at":"2024-10-02T10:23:32.950Z","updated_at":"2025-04-17T06:30:42.348Z","avatar_url":"https://github.com/ceteri.png","language":"Scala","funding_links":[],"categories":[],"sub_categories":[],"readme":"Introduction to Apache Spark\n============================\n\nThe material here supports the O'Reilly Media video by Paco Nathan:\n[Introduction to Apache Spark](http://shop.oreilly.com/product/0636920036807.do)\n\nPlease see the code examples in the `src` directory here, which are numbered\nin the sequence used in the video.\n\nThis material assumes that you have downloaded a pre-compiled version of\nApache Spark on your laptop from http://spark.apache.org/downloads.html\n\n\nOutline\n-------\n\n  * Pre-Flight Check\n  * Spark Deconstructed: Log Mining Example\n  * Word Count\n  * Join\n  * Coding Exercise\n  * Pi Approximation\n  * Spark Streaming example\n  * Network Word Count in Python\n  * Network Word Count in Python -- Stateful\n  * GraphX example\n  * build/run SimpleApp.java with Maven\n  * build/run SimpleApp.scala with SBT\n\n\nUpdates\n-------\n\nSee the `bikeshare` directory for the Spark 1.3 update, showing DataFrames,\nMLlib, and GraphX with examples based on Capital Bikeshare data.\n\n\n---\n\nThis work is licensed under the Creative Commons Attribution-ShareAlike 4.0\nInternational License. To view a copy of this license, visit \nhttp://creativecommons.org/licenses/by-sa/4.0/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fceteri%2Fintro_spark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fceteri%2Fintro_spark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fceteri%2Fintro_spark/lists"}