The SAS Enterprise Miner has something called a "Score Code Node." This node applies all of the previous code (i.e. creating new variables, imputing missing values, and running the model etc.) to a completely untouched data set. How do I do this in R other than just using a hold out sample (i.e. test data)?
Use the Rattle GUI, as noted in the paper:
The underlying R code, constructed and executed by Rattle, is recorded in the Log tab, together with instructive comments. This allows the user to review the actual R commands. The R code snippets can also be copied as text (or Exported to file) from the Log tab and pasted into the R console and executed. This allows Rattle to be deployed for basic tasks, yet still access the full power of R as needed (e.g., to fine-tune modelling options that are not exposed in the interface).
http://journal.r-project.org/archive/2009-2/RJournal_2009-2_Williams.pdf
http://rattle.togaware.com/
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With