cv.kNNImpute: CV for kNNImpute

In jeffwong/imputation: imputation

Description

Cross Validation for kNNImpute Artificially erase some data and run kNNImpute multiple times, varying k from 1 to k.max. For each k, compute the RMSE on the subset of x for which data was artificially erased.

Usage

  cv.kNNImpute(x, k.max = 5, parallel = F)

Arguments

x	a data frame or matrix where each row represents a different record
k.max	the largest amount of neighbors to try kNN Impute
parallel	runs each run for k = 1 to k = k.max in parallel. Requires a parallel backend to be registered

Examples

x = matrix(rnorm(100),10,10)
  x.missing = x > 1
  x[x.missing] = NA
  cv.kNNImpute(x)

jeffwong/imputation documentation built on May 19, 2019, 4:02 a.m.