Package: GpGp 0.5.1

Joseph Guinness

GpGp: Fast Gaussian Process Computation Using Vecchia's Approximation

Functions for fitting and doing predictions with Gaussian process models using Vecchia's (1988) approximation. Package also includes functions for reordering input locations, finding ordered nearest neighbors (with help from 'FNN' package), grouping operations, and conditional simulations. Covariance functions for spatial and spatial-temporal data on Euclidean domains and spheres are provided. The original approximation is due to Vecchia (1988) <http://www.jstor.org/stable/2345768>, and the reordering and grouping methods are from Guinness (2018) <doi:10.1080/00401706.2018.1437476>. Model fitting employs a Fisher scoring algorithm described in Guinness (2019) <doi:10.48550/arXiv.1905.08374>.

Authors:Joseph Guinness [aut, cre], Matthias Katzfuss [aut], Youssef Fahmy [aut]

GpGp_0.5.1.tar.gz
GpGp_0.5.1.tar.gz(r-4.5-noble)GpGp_0.5.1.tar.gz(r-4.4-noble)
GpGp_0.5.1.tgz(r-4.4-emscripten)GpGp_0.5.1.tgz(r-4.3-emscripten)
GpGp.pdf |GpGp.html
GpGp/json (API)
NEWS

# Install 'GpGp' in R:
install.packages('GpGp', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
  • openmp– GCC OpenMP (GOMP) support library
Datasets:
  • argo2016 - Ocean temperatures from Argo profiling floats
  • jason3 - Windspeed measurements from Jason-3 Satellite

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

4.40 score 1 stars 6 packages 141 scripts 741 downloads 108 exports 4 dependencies

Last updated 2 months agofrom:c5832091cd. Checks:OK: 2. Indexed: no.

TargetResultDate
Doc / VignettesOKNov 16 2024
R-4.5-linux-x86_64OKNov 16 2024

Exports:cond_simcondition_numberd_exponential_anisotropic2Dd_exponential_anisotropic3Dd_exponential_anisotropic3D_altd_exponential_isotropicd_exponential_nonstat_vard_exponential_scaledimd_exponential_spacetimed_exponential_sphered_exponential_sphere_warpd_exponential_spheretimed_exponential_spheretime_warpd_matern_anisotropic2Dd_matern_anisotropic3Dd_matern_anisotropic3D_altd_matern_categoricald_matern_isotropicd_matern_nonstat_vard_matern_scaledimd_matern_spacetimed_matern_spacetime_categoricald_matern_spacetime_categorical_locald_matern_sphered_matern_sphere_warpd_matern_spheretimed_matern_spheretime_warpd_matern15_isotropicd_matern15_scaledimd_matern25_isotropicd_matern25_scaledimd_matern35_isotropicd_matern35_scaledimd_matern45_isotropicd_matern45_scaledimddpen_hiddpen_loddpen_loglodpen_hidpen_lodpen_logloexpitexponential_anisotropic2Dexponential_anisotropic3Dexponential_anisotropic3D_altexponential_isotropicexponential_nonstat_varexponential_scaledimexponential_spacetimeexponential_sphereexponential_sphere_warpexponential_spheretimeexponential_spheretime_warpfast_Gp_simfast_Gp_sim_Linvfind_ordered_nnfind_ordered_nn_brutefisher_scoringfit_modelget_linkfunget_penaltyget_start_parmsgroup_obsintexpitL_multL_t_multLinv_multLinv_t_multmatern_anisotropic2Dmatern_anisotropic3Dmatern_anisotropic3D_altmatern_categoricalmatern_isotropicmatern_nonstat_varmatern_scaledimmatern_spacetimematern_spacetime_categoricalmatern_spacetime_categorical_localmatern_spherematern_sphere_warpmatern_spheretimematern_spheretime_warpmatern15_isotropicmatern15_scaledimmatern25_isotropicmatern25_scaledimmatern35_isotropicmatern35_scaledimmatern45_isotropicmatern45_scaledimorder_coordinateorder_dist_to_pointorder_maxminorder_middleoutpen_hipen_lopen_loglopredictionssph_grad_xyzsummary.GpGp_fittest_likelihood_objectvecchia_grouped_meanzero_loglikvecchia_grouped_profbeta_loglikvecchia_grouped_profbeta_loglik_grad_infovecchia_Linvvecchia_meanzero_loglikvecchia_profbeta_loglikvecchia_profbeta_loglik_grad_info

Dependencies:BHFNNRcppRcppArmadillo

Readme and manuals

Help Manual

Help pageTopics
Ocean temperatures from Argo profiling floatsargo2016
Conditional Simulation using Vecchia's approximationcond_sim
compute condition number of matrixcondition_number
expit function and integral of expit functionexpit intexpit
Geometrically anisotropic exponential covariance function (two dimensions)d_exponential_anisotropic2D exponential_anisotropic2D
Geometrically anisotropic exponential covariance function (three dimensions)d_exponential_anisotropic3D exponential_anisotropic3D
Geometrically anisotropic exponential covariance function (three dimensions, alternate parameterization)d_exponential_anisotropic3D_alt exponential_anisotropic3D_alt
Isotropic exponential covariance functiond_exponential_isotropic d_matern15_isotropic d_matern25_isotropic exponential_isotropic
Isotropic exponential covariance function, nonstationary variancesd_exponential_nonstat_var exponential_nonstat_var
Exponential covariance function, different range parameter for each dimensiond_exponential_scaledim exponential_scaledim
Spatial-Temporal exponential covariance functiond_exponential_spacetime exponential_spacetime
Isotropic exponential covariance function on sphered_exponential_sphere exponential_sphere
Deformed exponential covariance function on sphered_exponential_sphere_warp exponential_sphere_warp
Exponential covariance function on sphere x timed_exponential_spheretime exponential_spheretime
Deformed exponential covariance function on sphered_exponential_spheretime_warp exponential_spheretime_warp
Approximate GP simulationfast_Gp_sim
Approximate GP simulation with specified Linversefast_Gp_sim_Linv
Find ordered nearest neighbors.find_ordered_nn
Naive brute force nearest neighbor finderfind_ordered_nn_brute
Fisher scoring algorithmfisher_scoring
Estimate mean and covariance parametersfit_model
get link function, whether locations are lonlat and space timeget_linkfun
get penalty functionget_penalty
get default starting values of covariance parametersget_start_parms
GpGp: Fast Gaussian Process Computing.GpGp-package GpGp
Automatic grouping (partitioning) of locationsgroup_obs
Windspeed measurements from Jason-3 Satellitejason3
Multiply approximate Cholesky by a vectorL_mult
Multiply transpose of approximate Cholesky by a vectorL_t_mult
Multiply approximate inverse Cholesky by a vectorLinv_mult
Multiply transpose of approximate inverse Cholesky by a vectorLinv_t_mult
Geometrically anisotropic Matern covariance function (two dimensions)d_matern_anisotropic2D matern_anisotropic2D
Geometrically anisotropic Matern covariance function (three dimensions)d_matern_anisotropic3D d_matern_anisotropic3D_alt matern_anisotropic3D
Geometrically anisotropic Matern covariance function (three dimensions, alternate parameterization)matern_anisotropic3D_alt
Isotropic Matern covariance function with random effects for categoriesd_matern_categorical matern_categorical
Isotropic Matern covariance functiond_matern_isotropic matern_isotropic
Isotropic Matern covariance function, nonstationary variancesd_matern_nonstat_var matern_nonstat_var
Matern covariance function, different range parameter for each dimensiond_matern_scaledim matern_scaledim
Spatial-Temporal Matern covariance functiond_matern_spacetime matern_spacetime
Space-Time Matern covariance function with random effects for categoriesd_matern_spacetime_categorical matern_spacetime_categorical
Space-Time Matern covariance function with local random effects for categoriesd_matern_spacetime_categorical_local matern_spacetime_categorical_local
Isotropic Matern covariance function on sphered_matern_sphere matern_sphere
Deformed Matern covariance function on sphered_matern_sphere_warp matern_sphere_warp
Matern covariance function on sphere x timed_matern_spheretime matern_spheretime
Deformed Matern covariance function on sphered_matern_spheretime_warp matern_spheretime_warp
Isotropic Matern covariance function, smoothness = 1.5matern15_isotropic
Matern covariance function, smoothess = 1.5, different range parameter for each dimensiond_matern15_scaledim matern15_scaledim
Isotropic Matern covariance function, smoothness = 2.5matern25_isotropic
Matern covariance function, smoothess = 2.5, different range parameter for each dimensiond_matern25_scaledim matern25_scaledim
Isotropic Matern covariance function, smoothness = 3.5d_matern35_isotropic d_matern45_isotropic matern35_isotropic
Matern covariance function, smoothess = 3.5, different range parameter for each dimensiond_matern35_scaledim d_matern45_scaledim matern35_scaledim
Isotropic Matern covariance function, smoothness = 4.5matern45_isotropic
Matern covariance function, smoothess = 3.5, different range parameter for each dimensionmatern45_scaledim
Sorted coordinate orderingorder_coordinate
Distance to specified point orderingorder_dist_to_point
Maximum minimum distance orderingorder_maxmin
Middle-out orderingorder_middleout
penalize large values of parameter: penalty, 1st deriative, 2nd derivativeddpen_hi dpen_hi pen_hi
penalize small values of parameter: penalty, 1st deriative, 2nd derivativeddpen_lo dpen_lo pen_lo
penalize small values of log parameter: penalty, 1st deriative, 2nd derivativeddpen_loglo dpen_loglo pen_loglo
Compute Gaussian process predictions using Vecchia's approximationspredictions
compute gradient of spherical harmonics functionssph_grad_xyz
Print summary of GpGp fitsummary.GpGp_fit
test likelihood object for NA or Inf valuestest_likelihood_object
Grouped Vecchia approximation to the Gaussian loglikelihood, zero meanvecchia_grouped_meanzero_loglik
Grouped Vecchia approximation, profiled regression coefficientsvecchia_grouped_profbeta_loglik
Grouped Vecchia loglikelihood, gradient, Fisher informationvecchia_grouped_profbeta_loglik_grad_info
Entries of inverse Cholesky approximationvecchia_Linv
Vecchia's approximation to the Gaussian loglikelihood, zero meanvecchia_meanzero_loglik
Vecchia's approximation to the Gaussian loglikelihood, with profiled regression coefficients.vecchia_profbeta_loglik
Vecchia's loglikelihood, gradient, and Fisher informationvecchia_profbeta_loglik_grad_info