Package: BKTR 0.2.0.9000

BKTR: Bayesian Kernelized Tensor Regression

Facilitates scalable spatiotemporally varying coefficient modelling with Bayesian kernelized tensor regression. The important features of this package are: (a) Enabling local temporal and spatial modeling of the relationship between the response variable and covariates. (b) Implementing the model described by Lei et al. (2023) <doi:10.48550/arXiv.2109.00046>. (c) Using a Bayesian Markov Chain Monte Carlo (MCMC) algorithm to sample from the posterior distribution of the model parameters. (d) Employing a tensor decomposition to reduce the number of estimated parameters. (e) Accelerating tensor operations and enabling graphics processing unit (GPU) acceleration with the 'torch' package.

Authors:Julien Lanthier [aut, cre, cph], Mengying Lei [aut], Aurélie Labbe [aut], Lijun Sun [aut]

BKTR_0.2.0.9000.tar.gz
BKTR_0.2.0.9000.zip(r-4.5)BKTR_0.2.0.9000.zip(r-4.4)BKTR_0.2.0.9000.zip(r-4.3)
BKTR_0.2.0.9000.tgz(r-4.4-any)BKTR_0.2.0.9000.tgz(r-4.3-any)
BKTR_0.2.0.9000.tar.gz(r-4.5-noble)BKTR_0.2.0.9000.tar.gz(r-4.4-noble)
BKTR_0.2.0.9000.tgz(r-4.4-emscripten)BKTR_0.2.0.9000.tgz(r-4.3-emscripten)
BKTR.pdf |BKTR.html✨
BKTR/json (API)
NEWS

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

Peer review:

Bug tracker:https://github.com/julien-hec/bktr/issues

Datasets:

On CRAN:

24 exports 1 stars 1.09 score 63 dependencies 17 scripts 1.1k downloads

Last updated 1 months agofrom:8c225295c8. Checks:OK: 1 NOTE: 6. Indexed: yes.

TargetResultDate
Doc / VignettesOKSep 17 2024
R-4.5-winNOTESep 17 2024
R-4.5-linuxNOTESep 17 2024
R-4.4-winNOTESep 17 2024
R-4.4-macNOTESep 17 2024
R-4.3-winNOTESep 17 2024
R-4.3-macNOTESep 17 2024

Exports:BixiDataBKTRRegressorCompositionOpsKernelKernelAddComposedKernelComposedKernelMaternKernelMulComposedKernelParameterKernelPeriodicKernelRQKernelSEKernelWhiteNoiseplot_beta_distsplot_covariates_beta_distsplot_hyperparams_distsplot_hyperparams_traceplotplot_spatial_betasplot_temporal_betasplot_y_estimatesreshape_covariate_dfssimulate_spatiotemporal_dataTensorOperatorTSR

Dependencies:askpassbitbit64bitopscallrclicollectionscolorspacecorocpp11curldata.tabledescdigestdplyrellipsisfansifarvergenericsggmapggplot2gluegtablehttrisobandjpegjsonlitelabelinglatticelifecyclemagrittrMASSMatrixmgcvmimemunsellnlmeopensslpillarpkgconfigplyrpngprocessxpspurrrR6R6PRColorBrewerRcpprlangsafetensorsscalesstringistringrsystibbletidyrtidyselecttorchutf8vctrsviridisLitewithr

BKTR Package Presentation

Rendered fromBKTR_Presentation_Article.pdf.asisusingR.rsp::asison Sep 17 2024.

Last update: 2023-09-04
Started: 2023-09-04

Readme and manuals

Help Manual

Help pageTopics
Operator overloading for kernel multiplication*.Kernel
Operator overloading for kernel addition+.Kernel
Spatial Features of Montreal BIXI Stations in 2019bixi_spatial_features
Spatial Locations of Montreal BIXI Stations in 2019bixi_spatial_locations
Daily Departure from BIXI Stations in 2019bixi_station_departures
Temporal Features in Montreal applicable to BIXI for 2019bixi_temporal_features
Temporal indices for the 2019 BIXI seasonbixi_temporal_locations
BIXI Data ClassBixiData
R6 class encapsulating the BKTR regression elementsBKTRRegressor
Kernel Composition OperationsCompositionOps
Base R6 class for KernelsKernel
R6 class for Kernels Composed via AdditionKernelAddComposed
R6 class for Composed KernelsKernelComposed
R6 class for Matern KernelsKernelMatern
R6 class for Kernels Composed via MultiplicationKernelMulComposed
R6 class for kernel's hyperparameterKernelParameter
R6 class for Periodic KernelsKernelPeriodic
R6 class for Rational Quadratic KernelsKernelRQ
R6 class for Square Exponential KernelsKernelSE
R6 class for White Noise KernelsKernelWhiteNoise
Plot Beta Coefficients Distributionplot_beta_dists
Plot Beta Coefficients Distribution Regrouped by Covariatesplot_covariates_beta_dists
Plot Hyperparameters Distributionsplot_hyperparams_dists
Plot Hyperparameters Traceplotplot_hyperparams_traceplot
Plot Spatial Beta Coefficientsplot_spatial_betas
Plot Temporal Beta Coefficientsplot_temporal_betas
Plot Y Estimatesplot_y_estimates
Print the summary of a BKTRRegressor instanceprint.BKTRRegressor
Function used to transform covariates coming from two dataframes one for spatial and one for temporal into a single dataframe with the right shape for the BKTR Regressor. This is useful when the temporal covariates do not vary trough space and the spatial covariates do not vary trough time (Like in the BIXI example). The function also adds a column for the target variable at the beginning of the dataframe.reshape_covariate_dfs
Simulate Spatiotemporal Data Using Kernel Covariances.simulate_spatiotemporal_data
Summarize a BKTRRegressor instancesummary.BKTRRegressor
R6 singleton that contains the configuration for the tensor backendTensorOperator
Tensor Operator SingletonTSR