{"payload":{"pageCount":3,"repositories":[{"type":"Public","name":"aws-glue-test-data-generator","owner":"AWS-Big-Data-Projects","isFork":true,"description":"AWS Glue Configurable Test Data Generator","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":7,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-02T14:53:23.376Z"}},{"type":"Public","name":"saas-analytics-infrastructure-on-aws","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":3,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-22T23:22:28.553Z"}},{"type":"Public","name":"aws-glue-job-tracker","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":4,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-22T17:50:31.351Z"}},{"type":"Public","name":"host-openemr-on-aws-fargate","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":3,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-12T14:48:58.691Z"}},{"type":"Public template","name":"data-engineering-zoomcamp","owner":"AWS-Big-Data-Projects","isFork":true,"description":"Free Data Engineering course! ","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":5005,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-21T04:28:21.433Z"}},{"type":"Public","name":"dbt-glue","owner":"AWS-Big-Data-Projects","isFork":true,"description":"This repository contains de dbt-glue adapter","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":59,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-07T08:33:36.100Z"}},{"type":"Public","name":"ClickHouse","owner":"AWS-Big-Data-Projects","isFork":true,"description":"ClickHouse® is a free analytics DBMS for big data","allTopics":[],"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":6584,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-31T11:09:21.182Z"}},{"type":"Public","name":"emr-trino-autoscale","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":4,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-20T10:58:32.383Z"}},{"type":"Public","name":"HeartRate-Monitoring-using-AWS-IOT-and-AWS-KINESIS","owner":"AWS-Big-Data-Projects","isFork":false,"description":"you run a script to mimic multiple sensors publishing messages on an IoT MQTT topic, with one message published every second. The events get sent to AWS IoT, where an IoT rule is configured. The IoT rule captures all messages and sends them to Firehose. From there, Firehose writes the messages in batches to objects stored in S3. In S3, you set u…","allTopics":["aws-kinesis","aws-iot","amazon-athena","aws-quicksight"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":3,"starsCount":10,"forksCount":1,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-19T07:41:17.152Z"}},{"type":"Public","name":"amazon-kinesis-data-analytics-blueprints","owner":"AWS-Big-Data-Projects","isFork":true,"description":"Kinesis Data Analytics Blueprints are a curated collection of Apache Flink applications. Each blueprint will walk you through how to solve a practical problem related to stream processing using Apache Flink. These blueprints can be leveraged to create more complex applications to solve your business challenges in Apache Flink.","allTopics":[],"primaryLanguage":{"name":"TypeScript","color":"#3178c6"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":6,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-14T18:12:27.682Z"}},{"type":"Public","name":"nextflow","owner":"AWS-Big-Data-Projects","isFork":true,"description":"A DSL for data-driven computational pipelines","allTopics":[],"primaryLanguage":{"name":"Groovy","color":"#4298b8"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":604,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-11T13:22:41.262Z"}},{"type":"Public","name":"awesome-opensource-data-engineering","owner":"AWS-Big-Data-Projects","isFork":true,"description":"An Awesome List of Open-Source Data Engineering Projects","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":281,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-07T09:45:09.168Z"}},{"type":"Public","name":"data-science-on-aws","owner":"AWS-Big-Data-Projects","isFork":true,"description":"AI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1066,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-02-20T04:43:42.137Z"}},{"type":"Public","name":"spark-on-aws-lambda","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":34,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-02-19T17:54:55.447Z"}},{"type":"Public","name":"serverless-datalake","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":6,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-12-31T17:49:18.918Z"}},{"type":"Public","name":"msk-serverless-data-pipeline","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":3,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-11-10T14:51:16.974Z"}},{"type":"Public","name":"monitor-serverless-datalake","owner":"AWS-Big-Data-Projects","isFork":true,"description":"Alerting and notification in a serverless data lake during failures","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":3,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-11-04T19:30:57.242Z"}},{"type":"Public","name":"aws-glue-cdk-cicd","owner":"AWS-Big-Data-Projects","isFork":true,"description":"Build, Test and Deploy ETL solutions using AWS Glue and AWS CDK based CI/CD pipelines","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":19,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-10-04T13:52:16.167Z"}},{"type":"Public","name":"amazon-opensearch-batch-indexing-with-aws-lambda","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":2,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-10-03T07:07:37.304Z"}},{"type":"Public","name":"arvados","owner":"AWS-Big-Data-Projects","isFork":true,"description":"An open source platform for managing and analyzing biomedical big data","allTopics":[],"primaryLanguage":{"name":"Go","color":"#00ADD8"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":113,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-09-19T18:19:08.025Z"}},{"type":"Public","name":".github","owner":"AWS-Big-Data-Projects","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-09-19T12:57:25.031Z"}},{"type":"Public","name":"data-engineering","owner":"AWS-Big-Data-Projects","isFork":true,"description":"Construct a modern data stack and orchestration the workflows to create high quality data for analytics and ML applications.","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":27,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-09-12T12:30:16.120Z"}},{"type":"Public","name":"aws-emr-serverless-using-terraform","owner":"AWS-Big-Data-Projects","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"HCL","color":"#844FBA"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":12,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-09-09T17:40:54.935Z"}},{"type":"Public","name":"AWS_File_Trans_Lamda_S3_SNS","owner":"AWS-Big-Data-Projects","isFork":true,"description":"AWS Data Engineering Project using Lambda, S3 and SNS","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-08-29T12:24:55.195Z"}},{"type":"Public","name":"querypal","owner":"AWS-Big-Data-Projects","isFork":true,"description":"Web UI for Amazon Athena","allTopics":[],"primaryLanguage":{"name":"Vue","color":"#41b883"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":26,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-08-29T03:43:08.795Z"}},{"type":"Public","name":"aws-security-hub-glue-aggregator-terraform","owner":"AWS-Big-Data-Projects","isFork":true,"description":"These Terraform modules aggregate Security Hub findings to centralized account using Amazon Kinesis Firehose and AWS Glue","allTopics":[],"primaryLanguage":{"name":"HCL","color":"#844FBA"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":5,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-08-23T09:08:36.835Z"}},{"type":"Public","name":"bigdata-file-viewer","owner":"AWS-Big-Data-Projects","isFork":true,"description":"A cross-platform (Windows, MAC, Linux) desktop application to view common bigdata binary format like Parquet, ORC, AVRO, etc. Support local file system, HDFS, AWS S3, Azure Blob Storage ,etc. ","allTopics":[],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":54,"license":"GNU General Public License v2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-08-12T12:23:34.318Z"}},{"type":"Public","name":"Airline_Data_Analysis","owner":"AWS-Big-Data-Projects","isFork":false,"description":"Process to gather streaming data from Airline API using NiFi & batch data using AWS redshift using Sqoop and build a data pipeline to analyse the data using Apache Hive and Druid and compare the performances ,to discuss the hive optimization techniques and visualise the data using AWS Quicksight","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":11,"forksCount":1,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-07-20T03:52:43.528Z"}},{"type":"Public","name":"emr-studio-notebook-examples","owner":"AWS-Big-Data-Projects","isFork":true,"description":"This repository contains ready-to-use notebook examples for a wide variety of use cases in Amazon EMR Studio.","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":39,"license":"MIT No Attribution","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-07-18T17:31:57.988Z"}},{"type":"Public","name":"serverless-etl-cdk","owner":"AWS-Big-Data-Projects","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-07-18T10:36:25.576Z"}}],"repositoryCount":80,"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"}