{"id":21678822,"url":"https://github.com/lucasbotang/coursera_big_data_for_data_engineers","last_synced_at":"2025-04-12T05:38:13.987Z","repository":{"id":162696067,"uuid":"147691951","full_name":"LucasBoTang/Coursera_Big_Data_for_Data_Engineers","owner":"LucasBoTang","description":"Assignments for Big Data for Data Engineers specialization on Coursera by Yandex.","archived":false,"fork":false,"pushed_at":"2019-01-18T21:38:02.000Z","size":485,"stargazers_count":8,"open_issues_count":0,"forks_count":17,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-04-12T05:38:00.742Z","etag":null,"topics":["hadoop","hive","spark","spark-sql"],"latest_commit_sha":null,"homepage":"","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/LucasBoTang.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}},"created_at":"2018-09-06T15:08:09.000Z","updated_at":"2022-08-20T16:01:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"d4b0a1ee-550a-437a-83f5-f2ab0145f75c","html_url":"https://github.com/LucasBoTang/Coursera_Big_Data_for_Data_Engineers","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/LucasBoTang%2FCoursera_Big_Data_for_Data_Engineers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LucasBoTang%2FCoursera_Big_Data_for_Data_Engineers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LucasBoTang%2FCoursera_Big_Data_for_Data_Engineers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LucasBoTang%2FCoursera_Big_Data_for_Data_Engineers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LucasBoTang","download_url":"https://codeload.github.com/LucasBoTang/Coursera_Big_Data_for_Data_Engineers/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248525168,"owners_count":21118616,"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":["hadoop","hive","spark","spark-sql"],"created_at":"2024-11-25T14:41:47.872Z","updated_at":"2025-04-12T05:38:13.979Z","avatar_url":"https://github.com/LucasBoTang.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Specialization: Big Data for Data Engineers\n\n## Big Data Essentials: HDFS, MapReduce and Spark RDD\n\nAssignments:\n- Hadoop Streaming Assignment 0: Word Count\n- Hadoop Streaming Assignment 1: Words Rating\n- Hadoop Streaming Assignment 2: Stop Words\n- Spark Assignment 1: Pairs\n- Spark Assignment 2: Reconstructing the path\n- Real-World Applications: TF-IDF\n\n## Big Data Analysis: Hive, Spark SQL, DataFrames and GraphFrames\n\nAssignments:\n- Hive Assignment 1. DDL: Create Tables\n- Hive Assignment 2. DML: Find Most Popular Tags\n- Spark Assignment 1: Counting number of the mutual friends\n- Spark Assignment 2: Graph based Music Recommender\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucasbotang%2Fcoursera_big_data_for_data_engineers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucasbotang%2Fcoursera_big_data_for_data_engineers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucasbotang%2Fcoursera_big_data_for_data_engineers/lists"}