Skip to content
Subspace Stream Clustering Algorithms and Evaluation Measures
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.


The subspspaceMOA package is a collections of algorithms and evaluation measures for Subspace Stream Clustering, i.e. Stream Clustering for high-dimensional data, wherein data points are only clustered in certain subspaces of the data space. It builds on the famous MOA package for data stream analysis and the opensubspace package.

Build Instructions

To build SubspaceMOA, you should have the Gradle build tool installed. Then you can use the command gradle fatJar to build a jar that contains the package and all of its dependencies. This jar can be found in the build/libs folder.

Otherwise, you can run gradle <task> to run any of a list of tasks. The most important tasks are jar, which creates a jar that does not contain the dependencies, test, which runs a battery of tests and rjar, which creates a minified version of the jar containing the package and all of its dependencies. This minified version is especially also used in the R package subspaceMOA.

To run the minify task, one should also have proguard installed and the Java Home folder should be located at /usr/lib/jvm/default-java.

R interface

The source code for the R interface to this package can be found here


Marwan Hassani, Yunsu Kim, Thomas Seidl (2013); Subspace MOA: Subspace Stream Clustering Evaluation Using the MOA Framework; The 18th International Conference on Database Systems for Advanced Applications (Best Demo Award Runner-Up)

You can’t perform that action at this time.