Package: bigGP 0.1.8

bigGP: Distributed Gaussian Process Calculations

Distributes Gaussian process calculations across nodes in a distributed memory setting, using Rmpi. The bigGP class provides high-level methods for maximum likelihood with normal data, prediction, calculation of uncertainty (i.e., posterior covariance calculations), and simulation of realizations. In addition, bigGP provides an API for basic matrix calculations with distributed covariance matrices, including Cholesky decomposition, back/forwardsolve, crossproduct, and matrix multiplication.

Authors:Christopher Paciorek [aut, cre], Benjamin Lipshitz [aut], Prabhat [ctb], Cari Kaufman [ctb], Tina Zhuo [ctb], Rollin Thomas [ctb]

bigGP_0.1.8.tar.gz


bigGP_0.1.8.tar.gz(r-4.5-noble)bigGP_0.1.8.tar.gz(r-4.4-noble)
bigGP.pdf |bigGP.html✨
bigGP/json (API)
NEWS

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

Peer review:

Uses libs:
  • openblas– Optimized BLAS
  • openmpi– High performance message passing library
Datasets:

On CRAN:

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

2.02 score 21 scripts 168 downloads 56 exports 1 dependencies

Last updated 2 years agofrom:f63affd9d8. Checks:OK: 1 NOTE: 1. Indexed: yes.

TargetResultDate
Doc / VignettesOKOct 26 2024
R-4.5-linux-x86_64NOTEOct 26 2024

Exports:.bigGP.fillallocbigGP.exitbigGP.initbigGP.quitcalcIJcollectDiagonalcollectRectangularMatrixcollectTriangularMatrixcollectVectordistributedKrigeProblemdistributeVectorkrigeProblemlocalAssignlocalBacksolvelocalCalclocalCalcChollocalCollectDiagonallocalCollectDiagonalTestlocalCollectRectangularMatrixlocalCollectRectangularMatrixTestlocalCollectTriangularMatrixlocalCollectTriangularMatrixTestlocalCollectVectorlocalCollectVectorTestlocalConstructRnormMatrixlocalCrossProdMatSelflocalCrossProdMatSelfDiaglocalCrossProdMatVeclocalDistributeVectorlocalDistributeVectorTestlocalForwardsolvelocalGetRectangularMatrixIndiceslocalGetTriangularMatrixIndiceslocalGetVectorIndiceslocalKrigeProblemConstructCovlocalKrigeProblemConstructMeanlocalMultChollocalPulllocalPullTestlocalRmpullpushremoteBacksolveremoteCalcremoteCalcCholremoteConstructRnormMatrixremoteConstructRnormVectorremoteCrossProdMatSelfremoteCrossProdMatSelfDiagremoteCrossProdMatVecremoteForwardsolveremoteGetIndicesremoteLsremoteMultCholremoteRm

Dependencies:Rmpi

Readme and manuals

Help Manual

Help pageTopics
Create Object with its Own Memoryalloc
Package for Calculations with Big Gaussian ProcessesbigGP-package bigGP
Information about the number and identities of the processes.bigGP .bigGP.fill bigGP-meta
Exit bigGP EnvironmentbigGP.exit bigGP.quit
Initialize bigGP packagebigGP.init
Calculate Partition FactorcalcD
Calculate Slave Process IdentifierscalcIJ
Return the Diagonal of a Distributed Square Matrix to the Master ProcesscollectDiagonal
Return a Distributed Rectangular Matrix to the Master ProcesscollectRectangularMatrix
Return a Distributed Symmetric or Triangular Matrix to the Master ProcesscollectTriangularMatrix
Return a Distributed Vector to the Master ProcesscollectVector
ReferenceClass for Distributed Components of the krigeProblem ReferenceClassdistributedKrigeProblem distributedKrigeProblem-class
Distribute a Vector to the Slave ProcessesdistributeVector
Find Length of Subset of Vector or Matrix Stored on Slave ProcessgetDistributedRectangularMatrixLength getDistributedTriangularMatrixLength getDistributedVectorLength
Class '"krigeProblem"'calcH, krigeProblem-method calcLogDens, krigeProblem-method calcPostCov, krigeProblem-method initializeSlaveProblems, krigeProblem-method krigeProblem krigeProblem-class optimizeLogDens, krigeProblem-method predict, krigeProblem-method remoteConstructCov, krigeProblem-method remoteConstructMean, krigeProblem-method setParams, krigeProblem-method show, krigeProblem-method simulateRealizations, krigeProblem-method
Assign a New Name to an Object on Slave ProcesslocalAssign
Local Calculation FunctionslocalBacksolve localCalc localCalcChol localConstructRnormMatrix localCrossProdMatSelf localCrossProdMatSelfDiag localCrossProdMatVec localForwardsolve localMultChol
Local Distribution and Collection FunctionslocalCollectDiagonal localCollectDiagonalTest localCollectRectangularMatrix localCollectRectangularMatrixTest localCollectTriangularMatrix localCollectTriangularMatrixTest localCollectVector localCollectVectorTest localDistributeVector localDistributeVectorTest localPull localPullTest
Get Indices of Vector or Matrix Elements Stored on Slave ProcesslocalGetRectangularMatrixIndices localGetTriangularMatrixIndices localGetVectorIndices
Calculate Mean Vector or Covariance Matrix on Slave ProcesslocalKrigeProblemConstructCov localKrigeProblemConstructMean
Remove Objects on Slave ProcesslocalRm
Copy Object from Slave Processes to Masterpull
Copy Object from Master to Slave Processespush
Do Arbitrary Calculations on One or Two InputsremoteCalc
Calculate Distributed Cholesky DecompositionremoteCalcChol
Create Distributed Vector or Matrix of Random NormalsremoteConstructRnormMatrix remoteConstructRnormVector
Distributed Crossproduct of a Rectangular Matrix with ItselfremoteCrossProdMatSelf remoteCrossProdMatSelfDiag
Distributed Crossproduct of a Rectangular Matrix and a VectorremoteCrossProdMatVec
Solve a Distributed Triangular SystemremoteBacksolve remoteForwardsolve
Determine Indices of Vector or Matrix Elements Stored on all ProcessesremoteGetIndices
Remote List ObjectsremoteLs
Distributed Multiplication of Lower Triangular Matrix and a Vector or MatrixremoteMultChol
Remote Remove ObjectsremoteRm
SN2011fe Supernova DatasetSN2011fe SN2011fe_covfunc SN2011fe_crosscovfunc SN2011fe_initialParams SN2011fe_meanfunc SN2011fe_mle SN2011fe_mle_subset SN2011fe_newdata SN2011fe_newdata_subset SN2011fe_predcovfunc SN2011fe_predmeanfunc SN2011fe_subset