⚠️There's a newer version (3.2) of this package. Take me there.

imputeTS: Time Series Missing Value Imputation

The imputeTS package specializes on (univariate) time series imputation. It offers several different imputation algorithm implementations. Beyond the imputation algorithms the package also provides plotting and printing functions of time series missing data statistics. Additionally three time series datasets for imputation experiments are included.

Installation

The imputeTS package can be found on CRAN. For installation execute in R:

 install.packages("imputeTS")

If you want to install the latest version from GitHub (can be unstable) run:

library(devtools)
install_github("SteffenMoritz/imputeTS")

Usage

  • Imputation

    To impute (fill all missing values) in a time series x, run the following command:

     na.interpolation(x)

    Output is the time series x with all NA's replaced by reasonable values.

    This is just one example for an imputation algorithm. In this case interpolation was the algorithm of choice for calculating the NA replacements. There are several other algorithms (see also under caption "Imputation Algorithms"). All imputation functions are named alike starting with na. followed by a algorithm label e.g. na.mean, na.kalman, ...

  • Plotting

    To plot missing data statistics for a time series x, run the following command:

     plotNA.distribution(x)

    This is also just one example for a plot. Overall there are four different types of missing data plots. (see also under caption "Missing Data Plots").

  • Printing

    To print statistics about the missing data in a time series x, run the following command:

     statsNA(x)
  • Datasets

    To load the 'heating' time series (with missing values) into a variable y and the 'heating' time series (without missing values) into a variable z, run:

     y <- tsHeating
     z <- tsHeatingComplete

    There are three datasets provided with the package, the 'tsHeating', the 'tsAirgap' and the 'tsNH4' time series. (see also under caption "Datasets").

Imputation Algorithms

Here is a table with available algorithms to choose from:

FunctionDescription
na.interpolationMissing Value Imputation by Interpolation
na.kalmanMissing Value Imputation by Kalman Smoothing
na.locfMissing Value Imputation by Last Observation Carried Forward
na.maMissing Value Imputation by Weighted Moving Average
na.meanMissing Value Imputation by Mean Value
na.randomMissing Value Imputation by Random Sample
na.removeRemove Missing Values
na.replaceReplace Missing Values by a Defined Value
na.seadecSeasonally Decomposed Missing Value Imputation
na.seasplitSeasonally Splitted Missing Value Imputation

This is a rather broad overview. The functions itself mostly offer more than just one algorithm. For example na.interpolation can be set to linear or spline interpolation.

More detailed information about the algortihms and their options can be found in the imputeTS reference manual.

Missing Data Plots

Here is a table with available plots to choose from:

FunctionDescription
plotNA.distributionVisualize Distribution of Missing Values
plotNA.distributionBarVisualize Distribution of Missing Values (Barplot)
plotNA.gapsizeVisualize Distribution of NA gapsizes
plotNA.imputationsVisualize Imputed Values

More detailed information about the plots can be found in the imputeTS reference manual.

Datasets

There are two datasets (each in two versions) available:

DatasetDescription
tsAirgapTime series of monthly airline passengers (with NAs)
tsAirgapCompleteTime series of monthly airline passengers (complete)
tsHeatingTime series of a heating systems supply temperature (with NAs)
tsHeatingCompleteTime series of a heating systems supply temperature (complete)
tsNH4Time series of NH4 concentration in a wastewater system (with NAs)
tsNH4CompleteTime series of NH4 concentration in a wastewater system (complete)

The tsAirgap, tsHeating and tsNH4 time series are with NAs. Their complete versions are without NAs. Except the missing values their versions are identical. The NAs for the time series were artifically inserted by simulating the missing data pattern observed in similar non-complete time series from the same domain. Having a complete and incomplete version of the same dataset is useful for conducting experiments of imputation functions.

More detailed information about the datasets can be found in the imputeTS reference manual.

Support

If you found a bug or have suggestions, feel free to get in contact via steffen.moritz10 at gmail.com

All feedback is welcome

Version

2.6

License

GPL-3

Copy Link

Version

Down Chevron

Install

install.packages('imputeTS')

Monthly Downloads

30,374

Version

2.6

License

GPL-3

Issues

Pull Requests

Stars

Forks

Maintainer

Last Published

March 20th, 2018

Functions in imputeTS (2.6)