Clusterization-class {kml}R Documentation

~ Class: Clusterization ~

Description

An object of class Clusterization is a partition of trajectories in subgroups. The object also contains a certain number of information like the percentage of trajectories that each group contains or the Calinski criterion.

Objects from the Class

Objects are not intend to be created by users. Clusterization are created by kml and directly added to a "ClusterizLongData" object.

Slots

id
[character]: single identifier for each individual.
nbClusters
[numeric]: number of groups
.
clusters
[factor]: vector containing the affectation groups of each individual. The groups are in capital letters, from A to LETTERS[nbClusters]. Please note that a group might be empty. The groups are sort in reverse order (A is the biggest group, Bis the next,...
percentEachCluster
[numeric]: percentage of trajectories contained in each group.
varBetween
[matrix]: Matrix of variance between
traceBetween
[numeric]: Trace of the matrix variance between
varWithin
[matrix]: Matrix of variance within
traceWithin
[numeric]: Trace of the matrix of variance within
detWithin
[numeric]: Determinant of the matrix of variance within
calinskiCriterion
[numeric]: Calinski criterion (formula : traceBetween/traceWithin*(g-1)/(n-g) with g=number of groups and n=number of individual.)
convergenceTime:
[numeric] number of iteration necessary to kml to find the Clusterization

validation rules

A class Clusterization object must follow some rules to be valid:

Details

The partitioning of an ensemble of trajectories is given by the couple (id,clusters). id must correspond to id of an object of class ClusterizLongData ; the vector clusters then sets the group that each individual belongs to.

See Also

kml-package

Examples

showClass("Clusterization")

[Package kml version 0.9.0 Index]