Skip to main content

k-Means (fast)

Synopsis​

This operator represents an implementation of

k-Means according to C. Elkan. This operator will create a cluster attribute if not present yet.

Description​

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. For more information, please see paper: - Using the Triangle Inequality to Accelerate k-Means - Proceedings of the Twentieth International Conference on Machine Learning (ICML-2003), Washington DC, 2003

Input​

example set​

This is an example set input port

Output​

cluster model​

clustered set​

Parameters​

add cluster attribute​

If enabled, a cluster id is generated as new special attribute directly in this operator, otherwise this operator does not add an id attribute. In the latter case you have to use the Apply Model operator to generate the cluster attribute.

add as label​

If true, the cluster id is stored in an attribute with the special role 'label' instead of 'cluster'.

remove unlabeled​

Delete the unlabeled examples.

k​

The number of clusters which should be detected.

determine good start values​

Determine the first k centroids using the K-Means++ heuristic described in "k-means++: The Advantages of Careful Seeding" by David Arthur and Sergei Vassilvitskii 2007

measure types​

The measure type

mixed measure​

Select measure

nominal measure​

Select measure

numerical measure​

Select measure

divergence​

Select divergence

kernel type​

The kernel type

kernel gamma​

The kernel parameter gamma.

kernel sigma1​

The kernel parameter sigma1.

kernel sigma2​

The kernel parameter sigma2.

kernel sigma3​

The kernel parameter sigma3.

kernel degree​

The kernel parameter degree.

kernel shift​

The kernel parameter shift.

kernel a​

The kernel parameter a.

kernel b​

The kernel parameter b.

max runs​

The maximal number of runs of k-Means with random initialization that are performed.

max optimization steps​

The maximal number of iterations performed for one run of k-Means.

use local random seed​

Indicates if a local random seed should be used.

local random seed​

Specifies the local random seed