pmml.naiveBayes: Generate PMML for a Naive Bayes (naiveBayes) object

Description

Generate the Predictive Model Markup Language (PMML) representation of a naive bayes object from e1071. This object is the result of the model created using the naiveBayes function of the package.

Usage

## S3 method for class 'naiveBayes':
pmml(model, model.name="naiveBayes_Model",
     app.name="Rattle/PMML",
     description="NaiveBayes Model",
     copyright = NULL,
     transforms = NULL,
     dataset = NULL,
     predictedField, ...)

Arguments

model

the naiveBayes object contained in an object of class e1071, as that contained in the object returned by the function naiveBayes.

model.name

a name to give to the model in the PMML.

app.name

the name of the application that generated the PMML.

description

a descriptive text for the header of the PMML.

the copyright notice for the model.

transforms

transforms to represent within the PMML.

dataset

the dataset name of the data used to construct the model. Required to get the field variable names

predictedField

Required; the name of the predicted field.

...

further arguments passed to or from other methods.

Details

The Predictive Model Markup Language is an XML based language which provides a way for applications to define statistical and data mining models and to share models between PMML compliant applications. More information about PMML and the Data Mining Group can be found at http://www.dmg.org.

The PMML representation of the NaiveBayes model implements the representation as defined by the Data Mining Group: intermediate probability values which are less than the threshold value are replaced by the threshold value. This is different from the prediction function of the e1071 in which only probability values of 0 and standard deviations of continuous variables of with the value 0 are replaced by the threshold value. The two values will therefore not match exactly for cases involving very small probability values. The generated PMML can be imported into any PMML consuming application, such as the Zementis ADAPA and UPPI scoring engines which allow for predictive models built in R to be deployed and executed on site, in the cloud (Amazon, IBM, and FICO), in-database (IBM Netezza, Pivotal, Sybase IQ, Teradata and Teradata Aster) or Hadoop (Datameer and Hive).

References

PMML home page: http://www.dmg.org

A. Guazzelli, W. Lin, T. Jena (2012), /emph{PMML in Action: Unleashing the Power of Open Standards for Data Mining and Predictive Analytics}. CreativeSpace (Second Edition - Available on Amazon.com - http://www.amazon.com/dp/1470003244.

A. Guazzelli, M. Zeller, W. Lin, G. Williams (2009), /emph{PMML: An Open Standard for Sharing Models}. The R journal, Volume 1/1, 60-65 A. Guazzelli, T. Jena, W. Lin, M. Zeller (2013). Extending the Naive Bayes Model Element in PMML: Adding Support for Continuous Input Variables. In Proceedings of the 19th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.

Examples

Run this code

# Build a simple Naive Bayes model

# Upload the required library
library(e1071)
library(pmml)
library(mlbench)

# download an example dataset
data(HouseVotes84)
house <- na.omit(HouseVotes84)

# Construct an example model defining a threshold value of 0.003
model<-naiveBayes(Class~V1+V2+V3,data=house,threshold=0.003)

# Output the PMML representation 
pmml(model,dataset=house,predictedField="Class")