{"payload":{"pageCount":2,"repositories":[{"type":"Public","name":"flowman","owner":"dimajix","isFork":false,"description":"Flowman is an ETL framework powered by Apache Spark. With its declarative approach, Flowman simplifies the development of complex data pipelines.","allTopics":["flowman","scala","sql","big-data","spark","apache-spark","hadoop","etl","bigdata","data-engineering"],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":10,"issueCount":47,"starsCount":88,"forksCount":17,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-21T06:37:06.388Z"}},{"type":"Public","name":"pyspark-advanced","owner":"dimajix","isFork":false,"description":"Jupyter Notebooks for PySpark Advanced Workshop","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":4,"forksCount":6,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-05T14:17:31.203Z"}},{"type":"Public","name":"pyspark-datascience","owner":"dimajix","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-16T16:38:35.709Z"}},{"type":"Public","name":"terraform-emr-training","owner":"dimajix","isFork":false,"description":"Terraform script for launching multiple EMR clusters for training purposes.","allTopics":[],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":1,"starsCount":16,"forksCount":20,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-02T16:50:19.094Z"}},{"type":"Public","name":"flowman-maven","owner":"dimajix","isFork":false,"description":"Maven plugin for streamlining the development workflow with Flowman","allTopics":[],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":2,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-08-14T07:42:51.217Z"}},{"type":"Public","name":"flowman-tutorial","owner":"dimajix","isFork":false,"description":"Tutorial for Flowman","allTopics":[],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-21T12:02:16.005Z"}},{"type":"Public","name":"flowman-demo-weather","owner":"dimajix","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":3,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-29T06:24:52.905Z"}},{"type":"Public","name":"docker-jupyterhub","owner":"dimajix","isFork":false,"description":"Docker image with jupyterhub","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-19T08:29:24.947Z"}},{"type":"Public","name":"spark-training","owner":"dimajix","isFork":false,"description":"Repository used for Spark Trainings","allTopics":["python","scala","spark","hive","hadoop","pyspark","spark-streaming","sqoop","spark-ml","hadoop-training","spark-training"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":4,"issueCount":1,"starsCount":53,"forksCount":67,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-21T20:46:45.781Z"}},{"type":"Public","name":"docker-maven-npm","owner":"dimajix","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-07T16:33:13.689Z"}},{"type":"Public","name":"flowman-example","owner":"dimajix","isFork":false,"description":"Example project for Flowman","allTopics":[],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-09-15T06:58:20.833Z"}},{"type":"Public","name":"spark-data-engineering","owner":"dimajix","isFork":false,"description":"Training notebooks for Data Engineering with Spark","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-09-18T07:11:51.373Z"}},{"type":"Public","name":"weather-analysis","owner":"dimajix","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":7,"forksCount":5,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-12-24T07:37:32.975Z"}},{"type":"Public","name":"docker-spark","owner":"dimajix","isFork":false,"description":"Repository for building Docker containers for Spark","allTopics":["docker","spark","hadoop","cluster"],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-08-19T08:10:08.403Z"}},{"type":"Public","name":"pyspark-ml-taxis","owner":"dimajix","isFork":false,"description":"Jupyter Notebooks for PySpark Workshop using NYC Taxi Trip data","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-10-20T19:03:32.807Z"}},{"type":"Public","name":"docker-hadoop","owner":"dimajix","isFork":false,"description":"Repository for building Docker containers for Hadoop","allTopics":["docker","hadoop"],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-04-11T13:59:17.272Z"}},{"type":"Public archive","name":"docker-java","owner":"dimajix","isFork":false,"description":"Base image for Java based Docker images","allTopics":["java","docker"],"primaryLanguage":{"name":"Dockerfile","color":"#384d54"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-04-11T11:43:33.092Z"}},{"type":"Public archive","name":"docker-jupyter-anaconda","owner":"dimajix","isFork":false,"description":"Docker Jupyter image based on Anaconda distribution","allTopics":[],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":1,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2018-12-08T11:46:20.013Z"}},{"type":"Public","name":"docker-miniconda","owner":"dimajix","isFork":false,"description":"Miniconda base image","allTopics":["python","docker","anaconda"],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2018-12-08T11:39:41.176Z"}},{"type":"Public","name":"pyspark-ml-crashcourse","owner":"dimajix","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2018-09-27T16:03:43.611Z"}},{"type":"Public","name":"docker-jupyter-spark","owner":"dimajix","isFork":false,"description":"Docker image for Jupyter notebooks with PySpark","allTopics":["python","docker","spark","hadoop","jupyter","pyspark"],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":1,"starsCount":25,"forksCount":24,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2018-08-03T18:50:12.978Z"}},{"type":"Public","name":"docker-hive","owner":"dimajix","isFork":false,"description":"Docker container running the Hive Metastore","allTopics":["docker","hive","hadoop"],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":1,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2017-12-23T10:33:21.570Z"}},{"type":"Public","name":"docker-alluxio","owner":"dimajix","isFork":false,"description":"Docker image for Apache Alluxio","allTopics":["docker","alluxio"],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2017-12-23T10:19:52.892Z"}},{"type":"Public archive","name":"docker-presto","owner":"dimajix","isFork":false,"description":"Repository for building Docker containers for Presto","allTopics":["docker","presto","hadoop","prestodb"],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2017-08-15T05:34:53.293Z"}},{"type":"Public archive","name":"vagrant-druid","owner":"dimajix","isFork":false,"description":"","allTopics":["vagrant","cluster","virtual","vagrantfile"],"primaryLanguage":{"name":"Puppet","color":"#302B6D"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2016-12-16T07:45:28.240Z"}},{"type":"Public archive","name":"puppet-druid","owner":"dimajix","isFork":true,"description":"Puppet module that sets up and configures a full druid cluster","allTopics":[],"primaryLanguage":{"name":"Puppet","color":"#302B6D"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":7,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2016-12-16T07:44:56.261Z"}},{"type":"Public archive","name":"vagrant-cloudera","owner":"dimajix","isFork":false,"description":"A Vagrant setup to run a virtual Cloudera cluster","allTopics":["vagrant","cloudera","cluster","virtual","vagrantfile"],"primaryLanguage":{"name":"Puppet","color":"#302B6D"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2016-07-12T14:40:06.723Z"}},{"type":"Public archive","name":"vagrant-storm-cluster","owner":"dimajix","isFork":true,"description":"Vagrant files for storm cluster","allTopics":[],"primaryLanguage":{"name":"Puppet","color":"#302B6D"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2016-02-22T14:29:14.319Z"}},{"type":"Public","name":"hadoop-training","owner":"dimajix","isFork":false,"description":"Source Code for Hadoop Training","allTopics":["spark","hadoop","hadoop-training"],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2015-12-28T17:44:41.305Z"}},{"type":"Public archive","name":"puppet-spark","owner":"dimajix","isFork":false,"description":"Puppet module to manage Apache Spark","allTopics":[],"primaryLanguage":{"name":"Puppet","color":"#302B6D"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2015-11-17T16:23:47.682Z"}}],"repositoryCount":33,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}