preformat: Preformatting for Training with Warm Starts

In Rborist: Extensible, Parallelizable Implementation of the Random Forest Algorithm

Preformatting for Training with Warm Starts

Description

Presorts and formats training frame into a form suitable for subsequent training by rfArb caller or rfTrain command. Wraps this form to spare unnecessary recomputation when iteratively retraining, for example, under parameter sweep.

Usage

## Default S3 method:
preformat(x,
                   verbose=FALSE,
                   ...)

Arguments

x	the design frame expressed as either a data.frame object with numeric and/or factor columns or as a numeric or factor-valued matrix.
verbose	indicates whether to output progress of preformatting.
...	unused.

Value

an object of class Deframe consisting of:

rleFrame	run-length encoded representation of class RLEFrame consisting of: rankedFramerun-length encoded representation of class RankedFrame consisting of: nRowThe number of observations encoded. runValThe run-length encoded values. runRowThe corresponding row indices. rleHeightThe number of encodings, per predictor. topIdxThe accumulated end index, per predictor. numRankedpacked representation of sorted numerical values of class NumRanked consisting of: numValdistinct numerical values. numHeightvalue offset per predictor. facRankedpacked representation of sorted factor values of class FacRanked consisting of: facValdistinct factor values, zero-based. facHeightvalue offset per predictor.
nRow	the number of training observations.
signature	an object of type Signature consisting of: predFormPredictor class names. levelPer-predictor levels, regardless whether realized. factorPer-predictor realized levels. colNamesPredictor names. rowNamesObservation names.

Author(s)

Mark Seligman at Suiji.

See Also

Rborist

Examples

  ## Not run: 
    data(iris)
    pt <- preformat(iris[,-5])

    ppTry <- seq(0.2, 0.5, by= 0.3/10)
    nIter <- length(ppTry)
    rsq <- numeric(nIter)
    for (i in 1:nIter) {
      rb <- Rborist(pt, iris[,5], predProb=ppTry[i])
      rsq[i] = rb$validiation$rsq
    }
  
## End(Not run)

Rborist documentation built on July 26, 2023, 5:32 p.m.