Package: spBPS 0.0-4

spBPS: Bayesian Predictive Stacking for Scalable Geospatial Transfer Learning

Provides functions for Bayesian Predictive Stacking within the Bayesian transfer learning framework for geospatial artificial systems, as introduced in "Bayesian Transfer Learning for Artificially Intelligent Geospatial Systems: A Predictive Stacking Approach" (Presicce and Banerjee, 2024) <doi:10.48550/arXiv.2410.09504>. This methodology enables efficient Bayesian geostatistical modeling, utilizing predictive stacking to improve inference across spatial datasets. The core functions leverage 'C++' for high-performance computation, making the framework well-suited for large-scale spatial data analysis in parallel and distributed computing environments. Designed for scalability, it allows seamless application in computationally demanding scenarios.

Authors:Luca Presicce [aut, cre], Sudipto Banerjee [aut]

spBPS_0.0-4.tar.gz
spBPS_0.0-4.zip(r-4.5)spBPS_0.0-4.zip(r-4.4)spBPS_0.0-4.zip(r-4.3)
spBPS_0.0-4.tgz(r-4.4-x86_64)spBPS_0.0-4.tgz(r-4.4-arm64)spBPS_0.0-4.tgz(r-4.3-x86_64)spBPS_0.0-4.tgz(r-4.3-arm64)
spBPS_0.0-4.tar.gz(r-4.5-noble)spBPS_0.0-4.tar.gz(r-4.4-noble)
spBPS_0.0-4.tgz(r-4.4-emscripten)spBPS_0.0-4.tgz(r-4.3-emscripten)
spBPS.pdf |spBPS.html
spBPS/json (API)

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

Peer review:

Bug tracker:https://github.com/lucapresicce/spbps/issues

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
  • openmp– GCC OpenMP (GOMP) support library

On CRAN:

4.40 score 10 scripts 13 downloads 15 exports 16 dependencies

Last updated 5 days agofrom:389cd729ed. Checks:OK: 1 NOTE: 8. Indexed: yes.

TargetResultDate
Doc / VignettesOKOct 27 2024
R-4.5-win-x86_64NOTEOct 27 2024
R-4.5-linux-x86_64NOTEOct 27 2024
R-4.4-win-x86_64NOTEOct 27 2024
R-4.4-mac-x86_64NOTEOct 27 2024
R-4.4-mac-aarch64NOTEOct 27 2024
R-4.3-win-x86_64NOTEOct 27 2024
R-4.3-mac-x86_64NOTEOct 27 2024
R-4.3-mac-aarch64NOTEOct 27 2024

Exports:arma_distbayesMvLMconjugateBPS_combineBPS_postBPS_post_MvTBPS_predBPS_pred_MvTBPS_PseudoBMABPS_weightsBPS_weights_MvTconv_optexpand_grid_cppforceSymmetry_cpppred_bayesMvLMconjugatesubset_data

Dependencies:bitbit64clarabelCVXRECOSolveRgmplatticeMatrixmniwosqpR6RcppRcppArmadilloRcppEigenRmpfrscs

Double Bayesian Predictive Stacking for (univariate) Spatial Analysis - Tutotial

Rendered fromtutorial.Rmdusingknitr::rmarkdownon Oct 27 2024.

Last update: 2024-10-24
Started: 2024-10-18

Readme and manuals

Help Manual

Help pageTopics
Compute the Euclidean distance matrixarma_dist
Gibbs sampler for Conjugate Bayesian Multivariate Linear ModelsbayesMvLMconjugate
Combine subset models wiht BPSBPS_combine
Perform the BPS sampling from posterior and posterior predictive given a set of stacking weightsBPS_post
Perform the BPS sampling from posterior and posterior predictive given a set of stacking weightsBPS_post_MvT
Compute the BPS posterior samples given a set of stacking weightsBPS_postdraws
Compute the BPS posterior samples given a set of stacking weightsBPS_postdraws_MvT
Compute the BPS spatial prediction given a set of stacking weightsBPS_pred
Compute the BPS spatial prediction given a set of stacking weightsBPS_pred_MvT
Combine subset models wiht Pseudo-BMABPS_PseudoBMA
Compute the BPS weights by convex optimizationBPS_weights
Compute the BPS weights by convex optimizationBPS_weights_MvT
Solver for Bayesian Predictive Stacking of Predictive densities convex optimization problemconv_opt
Compute the BPS weights by convex optimizationCVXR_opt
Evaluate the density of a set of unobserved response with respect to the conditional posterior predictived_pred_cpp
Evaluate the density of a set of unobserved response with respect to the conditional posterior predictived_pred_cpp_MvT
Compute the KCV of the density evaluations for fixed values of the hyperparametersdens_kcv
Compute the KCV of the density evaluations for fixed values of the hyperparametersdens_kcv_MvT
Compute the LOOCV of the density evaluations for fixed values of the hyperparametersdens_loocv
Compute the LOOCV of the density evaluations for fixed values of the hyperparametersdens_loocv_MvT
Build a grid from two vector (i.e. equivalent to 'expand.grid()' in 'R')expand_grid_cpp
Compute the parameters for the posteriors distribution of beta and Sigma (i.e. updated parameters)fit_cpp
Compute the parameters for the posteriors distribution of beta and Sigma (i.e. updated parameters)fit_cpp_MvT
Function to subset data for meta-analysisforceSymmetry_cpp
Return the CV predictive density evaluations for all the model combinationsmodels_dens
Return the CV predictive density evaluations for all the model combinationsmodels_dens_MvT
Sample R draws from the posterior distributionspost_draws
Sample R draws from the posterior distributionspost_draws_MvT
Predictive sampler for Conjugate Bayesian Multivariate Linear Modelspred_bayesMvLMconjugate
Draw from the conditional posterior predictive for a set of unobserved covariatesr_pred_cond
Draw from the conditional posterior predictive for a set of unobserved covariatesr_pred_cond_MvT
Draw from the joint posterior predictive for a set of unobserved covariatesr_pred_joint
Draw from the joint posterior predictive for a set of unobserved covariatesr_pred_joint_MvT
Draw from the marginals posterior predictive for a set of unobserved covariatesr_pred_marg
Draw from the joint posterior predictive for a set of unobserved covariatesr_pred_marg_MvT
Function to sample integers (index)sample_index
Perform prediction for BPS accelerated models - loop over prediction setspPredict_BPS
Function to subset data for meta-analysissubset_data