KmmComponent

KmmComponent-class

This class defines a kernel component of a mixture Model. It inherits
from [<code><a href="/link/?package=MixAll&version=1.4.2" iclustercomponent'="" data-mini-rdoc="MixAll::"></a>'>IClusterComponent</code>].

Algorithms and methods for model-based clustering and classification.
It supports various types of data: continuous, categorical and counting
and can handle mixed data of these types. It can fit Gaussian (with diagonal
covariance structure), gamma, categorical and Poisson models. The algorithms
also support missing values. This package can be used as an independent alternative to the
(not free) 'mixtcomp' software available at <https://massiccc.lille.inria.fr/>.

Serge Iovleff

MixAll

Clustering and Classification using Model-Based Mixture Models

Parmeet Bathia

KmmComponent function

<dl class="dl-horizontal">
<dt><code>dim</code></dt><dd>Vector with the dimension of the kth cluster</dd></dl><dt><code>sigma2</code></dt><dd>Vector with the standard deviation in the kth cluster.</dd><dt><code>gram</code></dt><dd>Matrix storing the gram matrix if its computation is needed</dd><dt><code>kernelName</code></dt><dd>string with the name of the kernel to use. Possible values:
"Gaussian", "polynomial", "Laplace", "linear","rationalQuadratic", "Hamming".
Default is "Gaussian".</dd><dt><code>kernelParameters</code></dt><dd>vector with the parameters of the kernel.</dd><dt><code>kernelComputation</code></dt><dd>boolean value set as <code>TRUE</code> if Gram matrix is to be computed
<code>FALSE</code> othewise. Default is <code>TRUE</code>.</dd>

Slots

This class defines a kernel component of a mixture Model. It inherits
from [<code><a href='<a href='IClusterComponent'></a>'>IClusterComponent</a></code>].

KmmComponent: Definition of the [`'>KmmComponent`] class

Description

Arguments

Slots

See Also

Examples