Monday, April 9, 2012

R PMML Support: BetteR than EveR!

PMML, the Predictive Model Markup Language, has become the de-facto standard to represent not only predictive models, but also data pre- and post-processing. In so doing, it allows for the interchange of models among different tools and environments, avoiding proprietary issues and incompatibilities.

R PMML Package


The PMML Package exports a variety of predictive models form R to PMML. The PMML package itself was conceived at first as part of Togaware's data mining toolkit Rattle. Although it can easily be accessed through Rattle's GUI, it can also be accessed directly in R.

R Package
To download the PMML Package from CRAN, the R Archive, click HERE.

Extended PMML Support

Traditionally, the PMML Package offered support for the following data mining algorithms:
  • ksvm(kernlab): Support Vector Machines
  • nnet: Neural Networks
  • rpart: C&RT Decision Trees
  • lm & glm (stats): Linear and Binary Logistic Regression Models
  • arules: Association Rules
  • kmeans and hclust: Clustering Model
Recently, it has been expanded to support:
  • multinom (nnet): Multinomial Logistic Regression Models;
  • glm (stats): Generalized Linear Models for classification and regression with a wide variety of link functions
  • randomForest: Random Forest Models for classification and regression
  • coxph (survival): Cox Regression Models to calculate survival and stratified cumulative hazards
  • ada: Stochastic Boosting
  • naiveBayes (e1071): Naive Bayes Classifiers
  • svm (e1071): Support Vector Machines

Once exported in PMML, your R model can be readily deployed in the Zementis ADAPA Scoring Engine, where it can be put to work immediately.

No comments:

Post a Comment

Note: Only a member of this blog may post a comment.

Welcome to the World of Predictive Analytics!

© Predictive Analytics by Zementis, Inc. - All Rights Reserved.





Copyright © 2009 Zementis Incorporated. All rights reserved.

Privacy - Terms Of Use - Contact Us