weka

Weka 3: Data Mining Software in Java

Weka is a collection of machine learning algorithms for data mining tasks. The algorithms can either be applied directly to a dataset or called from your own Java code. Weka contains tools for data pre-processing, classification, regression, clustering, association rules, and visualization. It is also well-suited for developing new machine learning schemes. Weka is open source software issued under the GNU General Public License.

---

The Weka mailing list

Please post Weka-related questions, comments, and bug reports to the Weka mailing list. There is also the searchable mailing list archive. Please do not email individual members of our research group about Weka problems.

---

Take a tour of Weka

• Click here for screenshots of the Explorer user interface in Weka.

• Click here for a presentation demonstrating all graphical user interfaces in Weka. (Powerpoint file)

Requirements

Java 1.4 is required to run Weka. Depending on your computing platform you may have to download and install it separately. It is available for free from Sun.

Downloading and installing Weka

There are different options for downloading and installing Weka 3.4 on your system:

• Windows

  Click here to download a self-extracting executable that includes Java VM 1.4
  (weka-3-4-3jre.exe; 22,263,015 bytes)

  Click here to download a self-extracting executable without the Java VM
  (weka-3-4-3.exe; 8,571,851 bytes)

  These executables will install Weka in your Program Menu. Download the second version if you already have Java 1.4 on your system.

• Mac OS X

  Sorry, the Mac installer is currently still at version 3.4.2. If you want the latest version, you can download the zip file from below instead.

  Click here to download a disk image
  (weka-3-4-2.dmg; 5,999,405 bytes)

  This disk image contains an installer for Weka. Note that Java 1.4 is included in the most recent versions of Mac OS X.

• Other platforms (Linux, etc.)

  Click here to download a zip archive containing Weka
  (weka-3-4-3.zip; 8,438,801 bytes)

  First unzip the zip file. This will create a new directory called weka-3-4. To run Weka, change into that directory and type

  java -jar weka.jar

  Note that Java needs to be installed on your system for this to work.

Older versions of Weka

Click here to download a jar archive containing Weka 3.0, the command-line-based version of Weka described in Chapter 8 of the data mining book by Ian H. Witten and Eibe Frank.
(weka-3-0-6.jar, 2,061,642 bytes).

All old versions of Weka are available from the Sourceforge website.

Documentation

Weka 3.4 has extensive help facilities built in. However, there is also:

• API documentation generated from the source code using Javadoc.

• A draft chapter of the data mining book that describes Weka 3.0. (The code for the MessageClassifier class from that chapter is available here).

• A page for trouble-shooting Weka.

• The archive of the Weka mailing list.

• A page documenting the ARFF data format used by Weka.

• An introduction to using Weka 3.3.5 from the command line.

• A user guide for the Explorer user interface (written for Weka 3.3.4).

• A description of the Bayes net package in Weka. (html)

• A tutorial for the Experimenter based on Weka 3.2.

• A page describing how to load your Access database into the Weka Explorer.

Citing Weka

If you want to refer to Weka in a publication, please cite the data mining book. The full citation is "Data Mining: Practical machine learning tools with Java implementations," by Ian H. Witten and Eibe Frank, Morgan Kaufmann, San Francisco, 2000.

Collections of datasets

Available separately:

• A jarfile containing 37 classification problems, originally obtained from the UCI repository (datasets-UCI.jar, 1,190,961 Bytes).
• A jarfile containing 37 regression problems, obtained from various sources (datasets-numeric.jar, 169,344 Bytes).
• A jarfile containing 6 agricultural datasets obtained from agricultural researchers in New Zealand (agridatasets.jar, 31,200 Bytes).
• A jarfile containing 30 regression datasets collected by Luis Torgo (regression-datasets.jar, 10,090,266 Bytes).

After expanding into a directory using your jar utility, these datasets may be used with Weka.

Weka-related Projects

• GRB Tool Shed - a tool to aid gamma ray burst research.
• Spectral clustering by Luigi Dragone.
• Kea - automatic keyphrase extraction.
• Word sense disambiguation by Ted Pedersen.
• WekaMetal - a meta-learning extension to Weka.
• maxdView visualisation tool for microarray data.
• LocBoost classification demo applet.
• YALE - Yet Another Learning Environment.
• Tertius: a system for rule discovery.
• MARFF - extension of ARFF for Multi-Relational Applications.
• Weka-Parallel - parallel processing for Weka.
• Automatic Knowledge Miner - online data mining reports.
• KDDML-MQL - support for KDD process.
• GATE - NLP workbench with Weka interface.
• TClass - classifying multivariate time series.
• Learning Vector Quanization - and more with Weka.
• Bayesian Network Classifiers - with bindings for Weka.
• Weka Visualization tools - using PMML, VisWiz, and ROCOn.
• Weka on Text - software for text mining.
• RSW - sequential classification with Weka.
• Cahit Arf - a data extraction utility for Weka.
• Judge - software for document classification and clustering.
• Milk - a workbench for multi-instance learning.
• Modified version of Weka, including time series mining and visualization tools.
• C4.5Rule-PANE and NeC4.5
• Proper - a propositionalization toolbox
• Grid Weka - grid computing with Weka.
• Balie* - BAseLine Information Extraction.

Development

We are following the Linux model of releases, where an even second digit of a release number indicates a "stable" release and an odd second digit indicates a "development" release (e.g. 3.0.x is a stable release, and 3.1.x is a developmental release). If you are using a developmental release, you might get to play with extra funky features, but it is entirely possible that these features come/go/transmogrify from one release to the next. If you require stability (e.g. if you are using Weka for teaching), use a stable release.

History

Book version (3.0)		Old GUI version (3.2)		New GUI version (3.4)
				3.4.3
				3.4.2
				3.4.1
				3.4
				3.3.6
				3.3.5
				3.3.4
				3.3.3
		3.2.3		3.3.2
3.0.6		3.2.2		3.3.1
3.0.5		3.2.1		3.3
3.0.4		3.2
3.0.3		3.1.9
3.0.2		3.1.8
3.0.1		3.1.7
3.0		3.1.6
Prerelease 6		3.1.5
Prerelease 5		3.1.4
Prerelease 4

Weka via CVS

If you want to check out the current state of Weka as it is currently being worked on, you can do so via anonymous CVS. Set the CVSROOT environment variable to:

:pserver:cvs_anon@cvs.scms.waikato.ac.nz:/usr/local/global-cvs/ml_cvs 

Then you can checkout the latest snapshot of Weka using:

cvs login cvs co weka cvs logout 

When you are asked for a password, just hit ENTER.

Miscellaneous code

• Simple message classifier application from Chapter 8 of the book.
• Function for reading arff files into the R statistical package (kindly provided by Dr Craig Struble).

Contributors (not up to date)

Abdelaziz Mahoui, Alexander K. Seewald, Ashraf M. Kibriya, Bernhard Pfahringer, Brent Martin, Eibe Frank, Gabi Schmidberger, Ian H. Witten, J. Lindgren, Janice Boughton, Jason Wells, Len Trigg, Lucio de Souza Coelho, Malcolm Ware, Mark Hall, Remco Bouckaert, Richard Kirkby, Shane Butler, Shane Legg, Stuart Inglis, Sylvain Roy, Tony Voyle, Xin Xu, Yong Wang, Zhihai Wang

Other Weka-related literature

Weka for kids.

---

If you have any comments about these pages then please contact: mlwebmaster@cs.waikato.ac.nz

---