{"posts":[{"template":"../@theme/templates/BlogPostPage","title":"Leveraging Query ReExecution for Smooth Hive 4 Migration","description":"An unsung hero in an enterprise-grade Hive deployment","author":{"id":"Hadoop","name":"Ryu Kobayashi, Shohei Okumiya","image":{}},"date":"2025-07-18T00:00:00.000Z","categories":[{"id":"hive","label":"Hive"},{"id":"open-source","label":"Open source"}],"image":{},"slug":"/blog/hive-query-reexecution","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Orchestrate dbt with Treasure Workflow Episode 2","description":"Practices sharing of how Data Team in Treasure Data leverages dbt Core (command line tools) with the Treasure Data ecosystem.","author":{"id":"Data","name":"Data Team (Ansel Lin, Satoshi Akama)","image":{}},"date":"2024-07-01T00:00:00.000Z","categories":[{"id":"workflow","label":"Workflow"}],"image":{},"slug":"/blog/orchestrate_dbt_2","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Upcoming Evolution of Treasure Data Query Engines","description":null,"author":{"id":"Toru","name":"Toru Takahashi","image":{}},"date":"2024-05-14T00:00:00.000Z","categories":[{"id":"hive","label":"Hive"}],"image":{},"slug":"/blog/query_engines_update2024","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Journey to Containers in Core Services Worker Platform","description":"Sharing our journey with container technology from Worker Platform that manages the fair scheduling of jobs and helps manage the state of individual jobs.","author":{"id":"Worker","name":"Worker Team (Johan Gustavsson, Kwangshin Oh, Ryo Wada, Takashi Kurihara, and You Yamagata)","image":{}},"date":"2024-03-30T00:00:00.000Z","categories":[{"id":"containers","label":"Containers"},{"id":"worker-platform","label":"Worker Platform"}],"image":{},"slug":"/blog/worker-journey-to-containers","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Automatic Customer Segmentation with Machine Learning","description":"Making Your Auto-Segmentation Model Work For You","author":{"id":"Yish","name":"Yish Lim","image":{}},"date":"2024-02-01T00:00:00.000Z","categories":[],"image":{},"social":"https://www.linkedin.com/in/yishuen-lim/","slug":"/blog/auto-segmentation","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Testing Distributed Components of Storage Engine","description":"Tackling challenges of testing of distributed components of Storage Engine with system tests","author":{"id":"SerhiiH","name":"Serhii Himadieiev","image":{}},"date":"2024-01-01T00:00:00.000Z","categories":[],"image":{},"slug":"/blog/distributed-system-testing","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Leveraging feedback is a skill!","description":"Tips for Engineers on how to interpret and incorporate feedback to further their career goals!","author":{"id":"Gary","name":"Gary Lucas","image":{}},"date":"2023-12-01T00:00:00.000Z","categories":[],"image":{},"slug":"/blog/how_to_receive_feedback","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Orchestrate dbt with Treasure Workflow","description":"A walkthrough of how to leverage dbt Core (command line tools) with the Treasure Data ecosystem.","author":{"id":"Ansel","name":"KuoHuei (Ansel) Lin","image":{}},"date":"2023-11-01T00:00:00.000Z","categories":[{"id":"workflow","label":"Workflow"}],"image":{},"slug":"/blog/orchestrate_dbt","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"The Zero Bug Policy","description":"Take back control of your bug backlog","author":{"id":"Tom","name":"Tom Walsh","image":{},"link":"https://github.com/twalsh92"},"date":"2023-10-01T00:00:00.000Z","image":{},"slug":"/blog/zero-bug-policy","excerpt":".","categories":[]},{"template":"../@theme/templates/BlogPostPage","title":"Integrating Kafka with Treasure Data","description":null,"author":{"id":"Biswadip","name":"Biswadip Paul","image":{}},"date":"2023-09-01T00:00:00.000Z","categories":[],"image":{},"slug":"/blog/apache_kafka_confluent_cloud","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Visual Studio Code extension for Treasure Data","description":"Boost Your Data Analysis Workflow with TD Query Tool for VS Code.","author":{"id":"Toru","name":"Toru Takahashi","image":{}},"date":"2023-08-01T00:00:00.000Z","categories":[{"id":"hive","label":"Hive"}],"image":{},"slug":"/blog/vscode-tdqt","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Hive Table scan optimization","description":"Hive highly parallelized table scans net 20-30% speed increase with PlazmaDB!","author":{"id":"Okumin","name":"Shohei Okumiya (@okumin)","image":{}},"date":"2023-7-01","categories":[{"id":"hive","label":"Hive"}],"image":{},"slug":"/blog/hive-table-scan-optimization","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Continuous Deployment of Treasure Workflow with Azure DevOps","description":"How to integrate Treasure Workflow with Azure DevOps","author":{"id":"Toru","name":"Toru Takahashi","image":{}},"date":"2023-06-16T00:00:00.000Z","image":{},"categories":[{"id":"workflow","label":"Workflow"}],"slug":"/blog/azure_devops","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"How to prepare simple test data for Hive and Presto","description":"This article show how to prepare simple data for Hive/Presto testing without using the actual table","author":{"id":"Kazuki Ito","name":"Kazuki Ito","image":{}},"date":"2023-06-01T00:00:00.000Z","categories":[{"id":"best-practice","label":"Best Practice"},{"id":"hive","label":"Hive"}],"image":{},"slug":"/blog/prepare_test_data_for_query","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Debugging unexpected _1 column's on data connector import","description":"Unexpected `_1` appended to column names","author":{"id":"Kohki","name":"Kohki","image":{}},"date":"2023-05-01T00:00:00.000Z","categories":[{"id":"best-practice","label":"Best Practice"},{"id":"debug","label":"Debug"}],"image":{},"slug":"/blog/column_1-dataconnector","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Embulk in TD, and in the future","description":"Updates to Embulk maintinance strategy.","author":{"id":"dmikurube","name":"Dai Mikurube","image":{}},"date":"2023-04-01T00:00:00.000Z","categories":[{"id":"embulk","label":"Embulk"},{"id":"open-source","label":"Open source"}],"image":{},"slug":"/blog/embulk-in-td","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Implementing the Hive Distributed Profiling System","description":"Use stack traces with Hive for scalable profiling.","author":{"id":"Okumin","name":"Shohei Okumiya (@okumin)","image":{}},"date":"2023-03-01T00:00:00.000Z","categories":[{"id":"hive","label":"Hive"}],"image":{},"slug":"/blog/hive-distributed-profiling","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"#TDTechTalk : 5 challenges in CDP","description":"The first TD in-person meet-up in three years.","author":{"id":"Taz","name":"TATSUNO \"Taz\" Yasuhiro","image":{}},"date":"2023-02-01T00:00:00.000Z","categories":[],"image":{},"carousel1":{"items":[{"avatar":"step0_1","isMd":true,"text":"Ramen"},{"avatar":"step0_2","isMd":true,"text":"Spicy Curry"},{"avatar":"step0_3","isMd":true,"text":"Unagi (BBQ grilled eel) over rice"}]},"slug":"/blog/tdtechtalk2022-tokyo","excerpt":"."},{"template":"../@theme/templates/BlogPostPage","title":"Fuzzy Matching","description":"Use statistics to match different unique ID's to same persona.","author":{"id":"Austin","name":"Austin","image":{}},"date":"2023-01-01T00:00:00.000Z","categories":[],"image":{},"slug":"/blog/fuzzy_matching","excerpt":"."}],"metadata":{"authors":[{"id":"Austin","name":"Austin","image":"austin.png"},{"id":"Debra","name":"Debra Eskinazi","image":"debra.png"},{"id":"Wayne","name":"Wayne Taylor","image":"wayne.png"},{"id":"Taz","name":"TATSUNO \"Taz\" Yasuhiro","image":"taz.jpg"},{"id":"dmikurube","name":"Dai Mikurube","image":"dmikurube.png"},{"id":"Kohki","name":"Kohki","image":"kohki.jpeg"},{"id":"Okumin","name":"Shohei Okumiya (@okumin)","image":"okumin.png"},{"id":"Toru","name":"Toru Takahashi","image":"toru.png"},{"id":"Tom","name":"Tom Walsh","image":"tom-walsh.jpeg","link":"https://github.com/twalsh92"},{"id":"Biswadip","name":"Biswadip Paul","image":"biswadip.png"},{"id":"Gary","name":"Gary Lucas","image":"default.png"},{"id":"Ansel","name":"KuoHuei (Ansel) Lin","image":"ansel.jpeg"},{"id":"SerhiiH","name":"Serhii Himadieiev","image":"serhii.jpeg"},{"id":"Yish","name":"Yish Lim","image":"yish.jpeg"},{"id":"Worker","name":"Worker Team (Johan Gustavsson, Kwangshin Oh, Ryo Wada, Takashi Kurihara, and You Yamagata)","image":"default.png"},{"id":"Data","name":"Data Team (Ansel Lin, Satoshi Akama)","image":"data_team.png"},{"id":"Hadoop","name":"Ryu Kobayashi, Shohei Okumiya","image":"ryu.jpeg"},{"id":"Kazuki Ito","name":"Kazuki Ito","image":"default.png"}],"categories":[{"id":"api","label":"API"},{"id":"company-update","label":"Company update"},{"id":"open-source","label":"Open source"},{"id":"hive","label":"Hive"},{"id":"embulk","label":"Embulk"},{"id":"best-practice","label":"Best Practice"},{"id":"debug","label":"Debug"},{"id":"workflow","label":"Workflow"},{"id":"containers","label":"Containers"},{"id":"worker-platform","label":"Worker Platform"}]}}