Hi all,
A long time ago, we decided to move unresolved issues which we do not
see to be going into the next release to a special fix version called
"Backlog". We wanted to keep those issues open to give contributors a
chance to return and finish their work. A lot of stuff has been
accumulated there and work has stalled on that, mostly because people
did not come with updated patches or did not fix issues with their code.
I think the "backlog" approach has not proven to work, therefore I
suggest we simply close all those issues to not have them "pollute" our
jira. We can always reopen them if someone wants to restart working on them.
I went through the issues and compiled a list of things that we should
close. If there are issues that you want to pick up and fix, please
shout, otherwise I will close the tickets one week from now.
Here's the list:
MAHOUT-525 Implement LatentFactorLogLinear models
MAHOUT-627 Baum-Welch Algorithm on Map-Reduce for Parallel Hidden Markov
Model Training.
MAHOUT-668 Adding knn support to Mahout classifiers
MAHOUT-772 Refactor Matrix/Vector implementation with linear operators
MAHOUT-836 On donating my Robust PCA Java code to Mahout
MAHOUT-918 Implement SGD based classifiers using MapReduce
MAHOUT-928 Add the ARFF data loader/converter on DF
MAHOUT-943 Improbe the way to make the split point on DF.
MAHOUT-968 Classifier based on restricted boltzmann machines
MAHOUT-975 Bug in Gradient Machine - Computation of the gradient
MAHOUT-1153 Implement streaming random forests
MAHOUT-1177 GSOC 2013: Reform and simplify the clustering APIs
MAHOUT-1178 GSOC 2013: Improve Lucene support in Mahout
MAHOUT-1179 GSOC 2013: Refactor and improve the classification APIs
MAHOUT-1193 We may want a BlockSparseMatrix
MAHOUT-1204 Rewrite Benchmarks using Caliper
MAHOUT-1206 Add density-based clustering algorithms to mahout
MAHOUT-1257 performance improvement to LogLikehood
MAHOUT-716 Implement Boosting
MAHOUT-732 Implement ranking autoencoder on top of gradient machine
MAHOUT-880 Add some matrix method(like addition, subtraction, norm ...
etc) to DistributedRowMatrix
MAHOUT-932 RandomForest quits with ArrayIndexOutOfBoundsException while
running sample
MAHOUT-1004 Distributed User-based Collaborative Filtering
MAHOUT-1022 Process Mining Algorithm Example in Mahout
MAHOUT-953 ArffVectorIterable does not gracefully handle duplicate
attribute name
Best,
Sebastian
