Cascading

2013年1月30日 (三) 05:20的最后版本

Cascading: For scale free data processing

Cascading is an API layered over Hadoop that aids in the development of complex processing routines for large data sets.

Cascading is used for processing log or event data, building indexes of unstructured data from web crawls or internal content, or applying data-mining or machine learning techniques.

http://www.cascading.org/