Author:Mark Hall <mhall{[at]}>
Changes:Fixed a bug affecting the correlation job in the case where a class attribute was set in the data and the user had not opted to keep it as part of the correlation analysis. Fixed a bug in the randomized data chunk job that affected the case when the user had opted to set the number of instances per chunk and the class attribute was numeric. Added a new feature where the correlation job now writes (to the output directory) a text file containing the names of the attributes that are represented in the correlation matrix.
Depends:weka (>=3.7.10), distributedWekaBase (>=1.0.4)
Description:Provides loaders and savers for HDFS, plus Hadoop jobs and tasks that wrap the tasks provided in distributedWekaBase. Includes libraries for Apache Hadoop 1.1.2.
License:GPL 2
Maintainer:Mark Hall <mhall{[at]}>