SpatPCA: Regularized Principal Component Analysis for Spatial Data

Description

SpatPCA is an R package designed for efficient regularized principal component analysis, providing the following features:

• Identify dominant spatial patterns (eigenfunctions) with both smooth and localized characteristics.
• Conduct spatial prediction (Kriging) at new locations.
• Adapt to regularly or irregularly spaced data, spanning 1D, 2D, and 3D datasets.
• Implement using the alternating direction method of multipliers (ADMM) algorithm.

Installation

You can install SpatPCA using either of the following methods:

Install from CRAN

install.packages("SpatPCA")

Install the Development Version from GitHub

remotes::install_github("egpivo/SpatPCA")

Compilation Requirements

To compile C++ code with the required RcppArmadillo package, follow these instructions based on your operating system:

For Windows users

Install Rtools

For Mac users

1. Install Xcode Command Line Tools
2. Install the gfortran library. You can achieve this by running the following commands in the terminal:

brew update
brew install gcc

For a detailed solution, refer to this link, or download and install the library gfortran to resolve the error ld: library not found for -lgfortran.

Usage

To use SpatPCA, first load the package:

library(SpatPCA)

Then, apply the spatpca function with the following syntax:

spatpca(position, realizations)

• Input: Realizations with the corresponding positions.
• Output: Return the most dominant eigenfunctions automatically.

For more details, refer to the Demo.

Development

To submit package checks to R-hub v2, source tools/run_rhub_checks.R and use

submission <- run_rhub_checks(confirmation = TRUE)
summarise_rhub_jobs(submission)

Adjust include_os, platforms, or email as needed. summarise_rhub_jobs() prints the submission id plus GitHub URLs where each builder’s logs appear.

Authors

• Wen-Ting Wang (GitHub)
• Hsin-Cheng Huang

Maintainer

Wen-Ting Wang (GitHub)

Reference

Wang, W.-T. and Huang, H.-C. (2017). Regularized principal component analysis for spatial data. Journal of Computational and Graphical Statistics, 26, 14-25.

License

GPL (>= 2)

Citation

• To cite package ‘SpatPCA’ in publications use:

  Wang W, Huang H (2023). SpatPCA: Regularized Principal Component Analysis for
  Spatial Data_. R package version 1.3.5,
  <https://CRAN.R-project.org/package=SpatPCA>.

• A BibTeX entry for LaTeX users is

  @Manual{,
    title = {SpatPCA: Regularized Principal Component Analysis for Spatial Data},
    author = {Wen-Ting Wang and Hsin-Cheng Huang},
    year = {2023},
    note = {R package version 1.3.5},
    url = {https://CRAN.R-project.org/package=SpatPCA},
  }