apply.impute.mappings: Applies imputation mappings

In XanderHorn/lazy: Automated data pre-processing and machine learning

Description

Uses output from map.impute to impute NA values in a dataframe. Also creates tracking features to indicate which observations had NA values.

Usage

apply.impute.mappings(data, impute.mappings, impute.mode = "auto",
  na.threshold = 0.1, track.features = TRUE, progress = TRUE)

Arguments

data	[required | data.frame] Dataset containing features to impute
impute.mappings	[required | list] Output from function map.impute
impute.mode	[optional | character | default="auto"] Imputation mode, options are auto, encode and median.mode. Auto applies a combination bewteen encoding and median.mode imputation based on the na.threshold parameter
na.threshold	[optional | numeric | default=0.1] Threshold for auto impute.mode to apply encoding or median.mode imputation. All features containing Na values above the specified percentage threshold will be imputed using encoding
track.features	[optional | logical | default=TRUE] Creates tracking features that records which observations had NA values present
progress	[optional | logical | default=TRUE] Display a progress bar

Value

Data frame with imputed original features and tracking features

Author(s)

Xander Horn

Examples

imp <- map.impute(data = iris)
new_iris <- apply.impute.mappings(iris, imp)

XanderHorn/lazy documentation built on Jan. 16, 2021, 6:15 p.m.