Clusters data using the OKM (Overlapping K-Means) clustering algorithm.

Provide functions for overlaps clustering, fuzzy clustering and interval-valued data manipulation. The package implement the following algorithms:
OKM (Overlapping Kmeans) from Cleuziou, G. (2007) <doi:10.1109/icpr.2008.4761079> ;
NEOKM (Non-exhaustive overlapping Kmeans) from Whang, J. J., Dhillon, I. S., and Gleich, D. F. (2015) <doi:10.1137/1.9781611974010.105> ;
Fuzzy Cmeans from Bezdek, J. C. (1981) <doi:10.1007/978-1-4757-0450-1> ;
Fuzzy I-Cmeans from de A.T. De Carvalho, F. (2005) <doi:10.1016/j.patrec.2006.08.014>.

Nicolas Hiot

COveR

Clustering with Overlaps

Guillaume Cleuziou

okm function

<dl><dt>x</dt>
<dd>A numeric data matrix or data frame containing the data to be
clustered.</dd>
<dt>centers</dt>
<dd>Either a positive integer indicating the number of clusters to
create or a matrix of pre-initialized cluster centers.</dd>
<dt>iter.max</dt>
<dd>Maximum number of iterations allowed for the clustering
algorithm (default is 10).</dd>
<dt>nstart</dt>
<dd>Number of random initializations to find the best result
(default is 1).</dd>
<dt>trace</dt>
<dd>Logical value indicating whether to display the progress of the
algorithm (default is `FALSE`).</dd>
<dt>method</dt>
<dd>A string specifying the distance metric to use; options are
'euclid' (Euclidean distance) or 'manhattan' (Manhattan distance)
(default is "euclid").</dd></dl>

Arguments

Clusters data using the OKM (Overlapping K-Means) clustering algorithm. — okm

<dl>

<dt>x</dt>
<dd>A numeric data matrix or data frame containing the data to be
clustered.</dd>


<dt>centers</dt>
<dd>Either a positive integer indicating the number of clusters to
create or a matrix of pre-initialized cluster centers.</dd>


<dt>iter.max</dt>
<dd>Maximum number of iterations allowed for the clustering
algorithm (default is 10).</dd>


<dt>nstart</dt>
<dd>Number of random initializations to find the best result
(default is 1).</dd>


<dt>trace</dt>
<dd>Logical value indicating whether to display the progress of the
algorithm (default is `FALSE`).</dd>


<dt>method</dt>
<dd>A string specifying the distance metric to use; options are
'euclid' (Euclidean distance) or 'manhattan' (Manhattan distance)
(default is "euclid").</dd>

</dl>

okm: Clusters data using the OKM (Overlapping K-Means) clustering algorithm.

Description

Usage

Value

Arguments

Examples