Imputation methods

Functions to impute missing data

hotdeck()

Hot-Deck Imputation

impPCA()

Iterative EM PCA imputation

irmi()

Iterative robust model-based imputation (IRMI)

kNN()

k-Nearest Neighbour Imputation

matchImpute()

Fast matching/imputation based on categorical variable

medianSamp()

Aggregation function for a ordinal variable

rangerImpute()

Random Forest Imputation

regressionImp()

Regression Imputation

sampleCat()

Random aggregation function for a factor variable

xgboostImpute()

Xgboost Imputation

initialise()

Initialization of missing values

maxCat()

Aggregation function for a factor variable

Plotting functions

Functions to visualize missing and imputed values. See the visualization vignette for an overview.

aggr() plot(<aggr>) print(<aggr>) summary(<aggr>) print(<summary.aggr>)

Aggregations for missing/imputed values

barMiss()

Barplot with information about missing/imputed values

histMiss()

Histogram with information about missing/imputed values

marginmatrix()

Marginplot Matrix

marginplot()

Scatterplot with additional information in the margins

matrixplot()

Matrix plot

mosaicMiss()

Mosaic plot with information about missing/imputed values

pairsVIM()

Scatterplot Matrices

parcoordMiss()

Parallel coordinate plot with information about missing/imputed values

pbox()

Parallel boxplots with information about missing/imputed values

scattJitt()

Bivariate jitter plot

scattMiss()

Scatterplot with information about missing/imputed values

scattmatrixMiss()

Scatterplot matrix with information about missing/imputed values

spineMiss()

Spineplot with information about missing/imputed values

colSequence() colSequenceRGB() colSequenceHCL()

HCL and RGB color sequences

rugNA()

Rug representation of missing/imputed values

alphablend()

Alphablending for colors

Maps

colormapMiss() colormapMissLegend()

Colored map with information about missing/imputed values

mapMiss()

Map with information about missing/imputed values

bgmap()

Backgound map

growdotMiss()

Growing dot map with information about missing/imputed values

Datasets

Datasets to showcase several functionalities of VIM.

Animals_na

Animals_na

SBS5242

Synthetic subset of the Austrian structural business statistics data

bcancer

Breast cancer Wisconsin data set

brittleness

Brittleness index data set

chorizonDL

C-horizon of the Kola data with missing values

colic

Colic horse data set

collisions

Subset of the collision data

diabetes

Indian Prime Diabetes Data

food

Food consumption

kola.background

Background map for the Kola project data

pulplignin

Pulp lignin content

sleep

Mammal sleep data

tao

Tropical Atmosphere Ocean (TAO) project data

testdata

Simulated data set for testing purpose

toydataMiss

Simulated toy data set for examples

wine

Wine tasting and price

Other

VIM-package VIM

Visualization and Imputation of Missing Values

countInf()

Count number of infinite or missing values

evaluation() nrmse() pfc() msecov() msecor()

Error performance measures

gowerD()

Computes the extended Gower distance of two data sets

prepare()

Transformation and standardization

gapMiss()

Missing value gap statistics

tableMiss()

create table with highlighted missings/imputations