This package provides a set of tools for spatio-temporal imputation in R. It includes the implementation for then CUTOFF imputation method, a useful cross-validation function that can be used not only by the CUOTFF method but also by some other imputation functions to help choosing an optimal value for relevant parameters, such as the number of k-nearest neighbors for the KNN imputation method, or the number of components for the SVD imputation method. It also contains tools for simulating data with missing values with respect to some specific missing pattern, for example, block missing. Some useful visualisation functions for imputation purposes are also provided in the package.
|Author||Lingbing Feng, Gen Nowak, Alan. H. Welsh, Terry. J. O'Neill|
|Date of publication||2014-05-13 07:44:40|
|Maintainer||Lingbing Feng <email@example.com>|
complete.chunk: Complete Chunk Data A chunk of data with no missing values...
CosK: The Cosine Kernel
Cut: The simple version of CUTOFF
cutoff: The CUTOFF Spatio-temporal Imputation Method
date.month: Date month data Date information for the Murray-Darling Basin...
EpanK: The Epanechnikov Kernel
GaussK: The Gaussian Kernel
Grmse: RMSE give imputed data matrix and the true matrix
HeatStruct: Structure Heatmap with Missing Value Demonstration
hqmr.data: Murray-Darling Basin Rainfall Data
impCV: Cross-validation for spatio-temporal imputation
MissSimulation: Simulate a missing vector with block missing pattern.
nmissing: Count the number of missing values in a vector or data matrix
UnifK: The Uniform Kernel
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.