vtreat1.6.5 package

A Statistically Sound 'data.frame' Processor/Conditioner

kWayStratifiedY

k-fold cross validation stratified on y, a splitFunction in the sense ...

kWayStratifiedYReplace

k-fold cross validation stratified with replacement on y, a splitFunct...

makeCustomCoderCat

Make a categorical input custom coder.

makeCustomCoderNum

Make a numeric input custom coder.

makekWayCrossValidationGroupedByColumn

Build a k-fold cross validation splitter, respecting (never splitting)...

mkCrossFrameCExperiment

Run categorical cross-frame experiment.

mkCrossFrameMExperiment

Function to build multi-outcome vtreat cross frame and treatment plan.

mkCrossFrameNExperiment

Run a numeric cross frame experiment.

multinomial_parameters

vtreat multinomial parameters.

regression_parameters

vtreat regression parameters.

rqdatatable_prepare

Apply a treatment plan using rqdatatable.

unsupervised_parameters

vtreat unsupervised parameters.

UnsupervisedTreatment

Stateful object for designing and applying unsupervised treatments.

prepare.simple_plan

Prepare a simple treatment.

prepare.treatmentplan

Apply treatments and restrict to useful variables.

print.multinomial_plan

Print treatmentplan.

print.simple_plan

Print treatmentplan.

print.treatmentplan

Print treatmentplan.

print.vtreatment

Print treatmentplan.

center_scale

Center and scale a set of variables.

problemAppPlan

check if appPlan is a good carve-up of 1:nRows into nSplits groups

classification_parameters

vtreat classification parameters.

getSplitPlanAppLabels

read application labels off a split plan.

kWayCrossValidation

k-fold cross validation, a splitFunction in the sense of vtreat::build...

apply_transform

Transform second argument by first.

as_rquery_plan

Convert vtreatment plans into a sequence of rquery operations.

BinomialOutcomeTreatment

Stateful object for designing and applying binomial outcome treatments...

buildEvalSets

Build set carve-up for out-of sample evaluation.

design_missingness_treatment

Design a simple treatment plan to indicate missingingness and perform ...

designTreatmentsC

Build all treatments for a data frame to predict a categorical outcome...

designTreatmentsN

build all treatments for a data frame to predict a numeric outcome

designTreatmentsZ

Design variable treatments with no outcome variable.

dot-wmean

Compute weighted mean

fit

Fit first arguemnt to data in second argument.

fit_prepare

Fit and prepare in a cross-validated manner.

fit_transform

Fit and transform in a cross-validated manner.

flatten_fn_list

Flatten a list of functions onto d.

format.vtreatment

Display treatment plan.

get_feature_names

Return feasible feature names.

get_score_frame

Return score frame from vps.

get_transform

Return underlying transform from vps.

MultinomialOutcomeTreatment

Stateful object for designing and applying multinomial outcome treatme...

novel_value_summary

Report new/novel appearances of character values.

NumericOutcomeTreatment

Stateful object for designing and applying numeric outcome treatments.

oneWayHoldout

One way holdout, a splitFunction in the sense of vtreat::buildEvalSets...

patch_columns_into_frame

Patch columns into data.frame.

pre_comp_xval

Pre-computed cross-plan (so same split happens each time).

prepare.multinomial_plan

Function to apply mkCrossFrameMExperiment treatemnts.

prepare

Apply treatments and restrict to useful variables.

rquery_prepare

Materialize a treated data frame remotely.

solve_piecewise

Solve as piecewise linear problem, numeric target.

solve_piecewisec

Solve as piecewise logit problem, categorical target.

spline_variable

Spline variable numeric target.

spline_variablec

Spline variable categorical target.

square_window

Build a square windows variable, numeric target.

square_windowc

Build a square windows variable, categorical target.

track_values

Track unique character values for variables.

value_variables_C

Value variables for prediction a categorical outcome.

value_variables_N

Value variables for prediction a numeric outcome.

variable_values

Return variable evaluations.

vnames

New treated variable names from a treatmentplan$treatment item.

vorig

Original variable name from a treatmentplan$treatment item.

vtreat-package

vtreat: A Statistically Sound 'data.frame' Processor/Conditioner

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). Reference: "'vtreat': a data.frame Processor for Predictive Modeling", Zumel, Mount, 2016, <DOI:10.5281/zenodo.1173313>.

  • Maintainer: John Mount
  • License: GPL-2 | GPL-3
  • Last published: 2024-06-12