The TDMR framework has the aim to facilitate the training, tuning and
evaluation of data mining models. It puts special emphasis on tuning these data
mining models as well as simultaneously tuning certain preprocessing options.
TDMR is especially designed to work with R-package SPOT as the preferred
tuner, but it offers also the possibility to use other tuners, e.g., R-package cma_es, latin
hypercube design (LHD) or direct-search optimizers (like BFGS or Powell) for
comparison.
For a more comprehensive description see
·
TDMR-docu.html and
PDF-versions
·
TDMR-docu.pdf
and
of these documents can be downloaded from the TDM
website http://gociop.de/research-projects/tuned-data-mining/.
For changes in package TDMR see changes.html.