Pangool, Hadoop API made easy!
summary
Library that implements tuple-based MapReduce on top of Hadoop, available as a Maven artifact and documented on the project site. Claims: simpler API that covers common patterns (secondary sorting, joins, multiple inputs/outputs, Solr export) so developers write far less boilerplate. Implements a memory-free right-side join and schema-driven tuples. Benchmarks show only a small overhead compared with native Hadoop jobs, so it works at near-native speed while easing MapReduce development.
AI-written summary · about
related talks
34mBig Data, Small Code ... #bbuzz
10mMapReduce in 10 Minutes
36mIn-memory data pipeline and warehouse at scale
15mOptimizing Query Performance in Big Data Systems
07mComplementary Solutions with Hadoop
31mOne Data Pipeline to Rule Them All
34mOnline learning, Vowpal Wabbit and Hadoop #bbuzz
56mResistance is Futile: What You Need to Know about Big Data