Mining sequence data in R with the TraMineR package

TraMineR is a R-package for mining and visualizing sequences of categorical data.
Its primary aim is the knowledge discovery from event or state sequences describing life courses, although most of its features apply also to non temporal data such as text or DNA sequences for instance.
The name TraMineR is a contraction of Life Trajectory Miner for R. Indeed, as some may suspect, it was also inspired by the authors’ taste for Gewurztraminer wine.

This guide is essentially a tutorial that describes the features and usage of the TraMine Rpackage.
It may also serve, however, as an introduction to sequential data analysis. The presentation is illustrated with data from the social sciences. Illustrative data sets andRscripts (sequence of R-commands) are included in the TraMineR distribution package.
The functions and options used in the guide as well as their displayed output correspond tothe version indicated on the title page. Though the guide discusses the major functionalities of the package, it is not exhaustive. For a full list and description of available functions, see the Reference Manual of the current version that can be found on the CRAN (http://cran.r-project.org/web/packages/TraMineR/). Check also the ‘History’ tab on the package webpage (http://mephisto.unige.ch/traminer) for the latest added features.

For new comers to R, a short introduction to the R-environment is given in Appendix A in which the reader will learn where R can be obtained as well as its basic commands and principles. Chapter 3 shortly explains how to use the package and describes the illustrative data sets provided with it.