Hi everyone!

New versions of Weka are available for download from the Weka homepage:

* Weka 3.8.0 - stable version. It is available as ZIP, with Win32 installer, Win32 installer incl. JRE 1.8.0_77, Win64 installer, Win64 installer incl. 64 bit JRE 1.8.0_77 and Mac OS X application with Oracle 64 bit JRE 1.8.0_77.

* Weka 3.9.0 - development version. It is available as ZIP, with Win32 installer, Win32 installer incl. JRE 1.8.0_77, Win64 installer, Win64 installer incl. 64 bit JRE 1.8.0_77 and Mac OS X application with Oracle 64 bit JRE 1.8.0_77.

* Weka 3.6.14 - stable book version. It is available as ZIP, with Win32 installer, Win32 installer incl. JRE 1.8.0_77, Win64 installer, Win64 installer incl. 64 bit JRE 1.8.0_77 and Mac OS X application with Oracle 64 bit JRE 1.8.0_77).

Stable Weka 3.6 and 3.8 receive bug fixes only. The development version receives bug fixes and new features.

3.8.0 and 3.9.0 are the first second digit version increases since stable 3.6 was released in 2008! At this point there is no functional difference between 3.8.0 and 3.9.0 - 3.7 has been branched to create 3.8 and development of core Weka will continue in 3.9. We feel that the package management system is a nice mechanism for allowing stable Weka to be extended with new features, while at the same time maintaining a stable core.

NOTE 1: Users of Weka 3.6 will find that serialized models created in 3.6 cannot be used in 3.8. Unfortunately, there is no workaround for this. Models will need to be recreated in Weka 3.8. Similarly, developers using 3.6 will find that there are some small changes that they need to make to their code in order to compile against 3.8. A quick check of the javadoc for 3.8 will hopefully show what is necessary.

NOTE 2: We have changed the default look and feel in Weka 3.8 and 3.9 to "Nimbus". We feel that this looks reasonable under the three main OS's. Furthermore, it is more performant under Mac OS X than the default Aqua LAF - we found that the Explorer's list of attributes becomes very slow to update on datasets with a large number of attributes when using the Aqua LAF on OS X. From the GUIChooser you can alter the LAF by selecting "Settings" from the "Program" menu (a restart will be required if the LAF is changed).

NOTE 3: When upgrading to Weka 3.8.0/3.9.0, Users of Weka 3.7.x may notice some exceptions thrown in the console relating to the package manager. To make these go away simply delete the installedPackageCache.ser file in ~/wekafiles/packages and then restart Weka.


Weka homepage:
http://www.cs.waikato.ac.nz/~ml/weka/

Pentaho data mining community documentation:
http://wiki.pentaho.com/display/Pent...+Documentation

Packages for Weka>=3.7.2 can be browsed online at:
http://weka.sourceforge.net/packageMetaData/

The Pentaho Weka micro site at http://weka.pentaho.com/ will be updated to reflect the new releases soon.

Note: It might take a while before Sourceforge.net has propagated all the files to its mirrors.

What's new in 3.8.0/3.9.0 compared to Weka 3.7.13?

Some highlights
---------------

In core weka:

* JAMA-based linear algebra routines replaced with MTJ. Faster operation with the option to use native libraries for even more speed
* General efficiency improvements in core, filters and some classifiers
* GaussianProcesses now handles instance weights
* New Knowledge Flow implementation. Engine completely rewritten from scratch with a simplified API
* New Workbench GUI
* GUI package manager now has a search facility
* FixedDictionaryStringToWordVector filter allows the use of an external dictionary for vectorization. DictionarySaver converter can be used to create a dictionary file

In packages:

* Packages that were using JAMA are now using MTJ
* New netlibNativeOSX, netlibNativeWindows and netlibNativeLinux packages providing native reference implementations (and system-optimized implementation in the case of OSX) of BLAS, LAPACK and ARPACK linear algebra
* New elasticNet package, courtesy of Nikhil Kinshore
* New niftiLoader package for loading a directory with MIR data in NIfTI format into Weka
* New percentageErrorMetrics package - provides plugin evaluation metrics for root mean square percentage error and mean absolute percentage error
* New iterativeAbsoluteErrorRegression package - provides a meta learner that fits a regression model to minimize absolute error
* New largeScaleKernelLearning package - contains filters for large-scale kernel-based learning
* discriminantAnalysis package now contains an implementation for LDA and QDA
* New Knowledge Flow component implementations in various packages
* newKnowledgeFlowStepExamples package - contains code examples for new Knowledge Flow API discussion in the Weka Manual
* RPlugin updated to latest version of MLR
* scatterPlot3D and associationRulesVisualizer packages updated with latest Java 3D libraries
* Support for pluggable activation functions in the multiLayerPerceptrons package

As usual, for a complete list of changes refer to the changelogs.

Cheers,
The Weka Team