A 'data.frame' processor/conditioner that prepares real-world data for predictive modeling in a statistically sound manner. 'vtreat' prepares variables so that data has fewer exceptional cases, making it easier to safely use models in production. Common problems 'vtreat' defends against: 'Inf', 'NA', too many categorical levels, rare categorical levels, and new categorical levels (levels seen during application, but not during training). 'vtreat::prepare' should be used as you would use 'model.matrix'.
|Author||John Mount, Nina Zumel|
|Date of publication||2017-01-21 23:09:51|
|Maintainer||John Mount <firstname.lastname@example.org>|
buildEvalSets: Build set carve-up for out-of sample evaluation.
catScore: return significnace 1 variable logistic regression
designTreatmentsC: Build all treatments for a data frame to predict a...
designTreatmentsN: build all treatments for a data frame to predict a numeric...
designTreatmentsZ: Design variable treatments with no outcome variable.
format.vtreatment: Display treatment plan.
getSplitPlanAppLabels: read application labels off a split plan.
kWayCrossValidation: k-fold cross validation, a splitFunction in the sense of...
kWayStratifiedY: k-fold cross validation stratified on y, a splitFunction in...
linScore: Return in-sample linear stats and scaling.
makekWayCrossValidationGroupedByColumn: Build a k-fold cross validation splitter, respecting (never...
mkCrossFrameCExperiment: Run categorical cross-frame experiment.
mkCrossFrameNExperiment: Run numeric cross frame experiment.
oneWayHoldout: One way holdout, a splitFunction in the sense of...
prepare: Apply treatments and restrict to useful variables.
print.vtreatment: Print treatmentplan.
problemAppPlan: check if appPlan is a good carve-up of 1:nRows into nSplits...
vnames: New treated variable names from a treatmentplan$treatment...
vorig: Original variable name from a treatmentplan$treatment item.
vtreat-package: vtreat: a package for simple variable treatment