Neeraj Bokde, [email protected], Marcus W. Beck, [email protected]
This is the development repository for the imputeTestbench package. This package provides a testbench for comparing imputation methods for missing data in univariate time series.
The development version of this package can be installed from GitHub:
install.packages('devtools')
library(devtools)
install_github('neerajdhanraj/imputeTestbench', ref = 'development')
The current release can be installed from CRAN:
install.packages('imputeTestbench')
The core function is impute_errors()
. See the help documentation for
more details.
library(imputeTestbench)
a <- impute_errors(data = nottem)
a
## $Parameter
## [1] "rmse"
##
## $MissingPercent
## [1] 10 20 30 40 50 60 70 80 90
##
## $na.approx
## [1] 0.9126667 1.3668795 1.8426935 2.6618272 3.7385688 5.3712847 6.5980827
## [8] 8.3407465 10.6986736
##
## $na.interp
## [1] 0.8216307 1.1131238 1.3823202 1.6205857 1.9014233 2.1002091 2.3966999
## [8] 2.7278460 10.6986736
##
## $na_interpolation
## [1] 0.9126667 1.3668795 1.8426935 2.6618272 3.7385688 5.3712847 6.5980827
## [8] 8.3407465 10.6986736
##
## $na.locf
## [1] 1.855190 2.695737 3.893174 5.240849 6.308034 7.714301 9.331696
## [8] 10.843248 11.918100
##
## $na_mean
## [1] 2.671651 3.911746 4.634842 5.311242 6.116699 6.695346 7.128735 7.659977
## [9] 8.498380
plot_errors(a, plotType = 'line')
Neeraj Bokde and Marcus W. Beck (2016). imputeTestbench: Test Bench for the comparison of imputation methods. R package version 3.0. http://www.neerajbokde.com/cran/imputetestbench
Please submit any bug reports (or suggestions) using the issues tab of the GitHub page.
This package is released in the public domain under the creative commons license CC0.