pmm: Predictive Mean Matching

In missRanger: Fast Imputation of Missing Values

Predictive Mean Matching

Description

For each value in the prediction vector xtest, one of the closest k values in the prediction vector xtrain is randomly chosen and its observed value in ytrain is returned.

Usage

pmm(xtrain, xtest, ytrain, k = 1L, seed = NULL)

Arguments

xtrain	Vector with predicted values in the training data. Can be of type logical, numeric, character, or factor.
xtest	Vector as xtrain with predicted values in the test data. Missing values are not allowed.
ytrain	Vector of the observed values in the training data. Must be of same length as xtrain. Missing values in either of xtrain or ytrain will be dropped in a pairwise manner.
k	Number of nearest neighbours to sample from.
seed	Integer random seed.

Value

Vector of the same length as xtest with values from xtrain.

Examples

pmm(xtrain = c(0.2, 0.2, 0.8), xtest = 0.3, ytrain = c(0, 0, 1)) # 0
pmm(xtrain = c(TRUE, FALSE, TRUE), xtest = FALSE, ytrain = c(2, 0, 1)) # 0
pmm(xtrain = c(0.2, 0.8), xtest = 0.3, ytrain = c("A", "B"), k = 2) # "A" or "B"
pmm(xtrain = c("A", "A", "B"), xtest = "A", ytrain = c(2, 2, 4), k = 2) # 2
pmm(xtrain = factor(c("A", "B")), xtest = factor("C"), ytrain = 1:2) # 2

missRanger documentation built on Nov. 19, 2023, 5:14 p.m.