data.frameprocessor/conditioner that prepares real-world data for predictive modeling in a statistically sound manner.
vtreatprepares variables so that data has fewer exceptional cases, making it easier to safely use models in production. Common problems
NA, too many categorical levels, rare categorical levels, and new categorical levels (levels seen during application, but not during training). Reference: “
vtreat: a data.frame Processor for Predictive Modeling”, Zumel, Mount, 2016.
Let’s hear it for cross-language data science!