RapidMiner Extension: Fast k-Means

This operator represents an implementation of k-Means according to Charles Elkan. In contrast to the standard implementation of k-Means, this implementation is much faster in many cases, especially for data sets with many attributes and a high k value, but it also needs more additional memory.

You can find more details in the the following publication:

Using the Triangle Inequality to Accelerate k-Means.

You can download it from here:

fast_kmeans.zip

Just unzip the Fast_KMeans.zip and copy the Fast_KMeans.jar file into the lib/plugins/ folder within your RapidMiner installation. Then restart RapidMiner and the extension will be loaded automatically.

You can find the Fast k-Means Operator in the Operator tree in Modeling ⇒ Clustering and Segmentation . It is named k-Means (fast) and can be used in the same way as the usual k-Means Operator.