kml (version 0.9.2)

kml-package: ~ Overview: K-means for Longitudinal data ~

Description

KmL is a new implematation of k-means for longitudinal data (or trajectories). Here is an overview of the package. For the description of the algorithm, see kml.

Overview

To clusterize data, KmL go through three steps, each of which is associated to some functions:

1. Data preparation
2. Building "optimal" clusterization.
3. Exporting results

1. Data preparation

KmL works on object of class ClusterizLongData (abreviated cld). Data preparation therfore simply consists in tranforming data into an object ClusterizLongData. This can be done via function clusterizLongData (cld in short) or as.clusterizLongData (as.cld in short). The formers let the user build some data from scratch, the latters convert a data.frame in ClusterizLongData. Instead of working on real data, one can also work on artificial data. Such data can be created with generateArtificialLongData (gald in short). The resulting data will be of class ArtificialLongData which is a subclass of ClusterizLongData.

2. Building "optimal" clusterization

Once an object of class ClusterizLongData has been created, the algorithm kml can be run. Starting with a ClusterizLongData, kml built a Clusterization. A object of class Clusterization is a partition of trajectories into subgroups that also contains some information like the percentage of trajectories contained in each group or the Calinski & Harabasz criterion. kml is a "hill-climbing" algorhithm. The specificity of this kind of algorithm is that it always converges towards a maximum, but one cannot know whether it is a local or a global maximum. It offers no guarantee of optimality. To maximize one's chances of getting a quality Clusterization, it is better to execute the hill climbing algorithm several times, then to choose the best solution. By default, kml executes the hill climbing algorithm 20 times and chooses the Clusterization maximising the determinant of the matrix between. Likewise, it is not possible to know beforehand the optimum number of clusters. On the other hand, afterwards, it is possible to calculate clues that will enable us to choose. kml uses the Calinski & Harabasz criterion. In the end, kml tests by default 2, 3, 4, 5 et 6 clusters, 20 times each.

3. Exporting results

When kml has constructed some Clusterization, the user can examine them one by one and choose to export some. This can be done via function choice. choice opens a graphic windows showing various information including the trajectories cluterized by a specific Clusterization. When some Clusterization has been selected (the user can select more than 1), it is possible to save them. The clusters are therefore exported towards the file nom-cluster.csv. Criteria are exported towards nom-criteres.csv. The graphs are exported according to their extention.

Author(s)

Christophe Genolini PSIGIAM: Paris Sud Innovation Group in Adolescent Mental Health INSERM U669 / Maison de Solenn / Paris Contact author :

English translation

Rapha�l Ricaud Laboratoire "Sport & Culture" / "Sports & Culture" Laboratory University of Paris 10 / Nanterre

Details

ll{ Package: kml Type: Package Version: 0.9.1 Date: 2009-01-01 License: GPL (>= 2) Lazyload: yes Depends: methods,clv URL: http://www.r-project.org URL: http://christophe.genolini.free.fr/kml }

References

Article submited Web site: http://christophe.genolini.free.fr/kml

See Also

Overview: kml-package Classes : ClusterizLongData, Clusterization, ArtificialLongData Methods : clusterizLongData, kml, generateArtificialLongData, choice, as.clusterizLongData Plot : plot: overview, plot(ClusterizLongData), plot(Calinski), plotSubGroups(ClusterizLongData), plotAll(ClusterizLongData)

Examples

### 1. Data Preparation
myCld <- as.clusterizLongData(generateArtificialLongData())

### 2. Building "optimal" clusterization (with only 3 redrawings)
kml(myCld,nbRedrawing=3,printCal=TRUE,printTraj=TRUE)

### 3. Exporting results
try(choice(myCld))