Generate PMML for various models The Predictive Modelling Markup Language (PMML) is a language for representing models, in an application independent way. Such models can then be loaded into other applications supporting PMML, including ADAPA from Zementis, Teradata Warehouse Miner and IBM's DB2. The package provides a generic pmml function to generate pmml for an object. Using a S3 generic function the approriate method for the class of the supplied object is dispatched. The package currently supports the export of PMML for linear regression, generalized linear regression, multinomial logistic regression, SVMs, rpart classification trees, randomSurvivalForest, randomForest, and kmeans clusters. This package is part of the Rattle toolkit. Software Depends: XML Suggests: arules, nnet, rpart, randomSurvivalForest, randomForest, kernlab Graham Williams <Graham.Williams@togaware.com> Graham Williams, Michael Hahsler (arules), Zementis Inc, Hemant Ishwaran, Udaya B. Kogalur, Rajarshi Guha GPL (>= 2) 2012-04-03 application/tgz http://CRAN.R-project.org/package=pmml