Package: MagmaClustR 1.2.1

Arthur Leroy

MagmaClustR:Clustering and Prediction using Multi-Task Gaussian Processes with Common Mean

An implementation for the multi-task Gaussian processes with common mean framework. Two main algorithms, called 'Magma' and 'MagmaClust', are available to perform predictions for supervised learning problems, in particular for time series or any functional/continuous data applications. The corresponding articles has been respectively proposed by Arthur Leroy, Pierre Latouche, Benjamin Guedj and Servane Gey (2022) <doi:10.1007/s10994-022-06172-1>, and Arthur Leroy, Pierre Latouche, Benjamin Guedj and Servane Gey (2023) <https://jmlr.org/papers/v24/20-1321.html>. Theses approaches leverage the learning of cluster-specific mean processes, which are common across similar tasks, to provide enhanced prediction performances (even far from data) at a linear computational cost (in the number of tasks). 'MagmaClust' is a generalisation of 'Magma' where the tasks are simultaneously clustered into groups, each being associated to a specific mean process. User-oriented functions in the package are decomposed into training, prediction and plotting functions. Some basic features (classic kernels, training, prediction) of standard Gaussian processes are also implemented.

Authors:Arthur Leroy [aut, cre], Pierre Latouche [aut], Pierre Pathé [ctb], Alexia Grenouillat [ctb], Hugo Lelievre [ctb]

MagmaClustR_1.2.1.tar.gz
MagmaClustR_1.2.1.tar.gz(r-4.5-noble)MagmaClustR_1.2.1.tar.gz(r-4.4-noble)
MagmaClustR_1.2.1.tgz(r-4.4-emscripten)MagmaClustR_1.2.1.tgz(r-4.3-emscripten)
MagmaClustR.pdf |MagmaClustR.html✨
MagmaClustR/json (API)
NEWS

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

Peer review:

Bug tracker:https://github.com/arthurleroy/magmaclustr/issues

Uses libs:
  • c++– GNU Standard C++ Library v3
Datasets:
  • swimmers - French swimmers performances data on 100m freestyle events
  • weight - Weight follow-up data of children in Singapore

31 exports 0.23 score 41 dependencies 267 downloads

Last updated 7 days agofrom:01bd847cdb

Exports:%>%data_allocate_clusterexpand_grid_inputshphyperposteriorhyperposterior_clustkern_to_covkern_to_invlist_kern_to_covlist_kern_to_invplot_gifplot_gpplot_magmaplot_magmaclustplot_samplespred_gifpred_gppred_magmapred_magmaclustproba_max_clusterregularise_dataregularize_datasample_gpsample_magmasample_magmaclustselect_nb_clustersimu_dbtrain_gptrain_gp_clusttrain_magmatrain_magmaclust

Dependencies:backportsbroomclicolorspacecpp11dplyrfansifarvergenericsggplot2gluegtableisobandlabelinglatticelifecyclemagrittrMASSMatrixmgcvmunsellmvtnormnlmepillarpkgconfigplyrpurrrR6RColorBrewerRcpprlangscalesstringistringrtibbletidyrtidyselectutf8vctrsviridisLitewithr

Readme and manuals

Help Manual

Help pageTopics
Allocate training data into the most probable clusterdata_allocate_cluster
Expand a grid of inputsexpand_grid_inputs
Generate random hyper-parametershp
Compute the hyper-posterior distribution in Magmahyperposterior
Compute the hyper-posterior distribution for each cluster in MagmaClusthyperposterior_clust
MagmaClustR : Clustering and Prediction using Multi-Task Gaussian ProcessesMagmaClustR-package MagmaClustR
Plot smoothed curves of raw dataplot_db
Create a GIF of Magma or GP predictionsplot_gif
Plot Magma or GP predictionsplot_gp plot_magma
Plot MagmaClust predictionsplot_magmaclust
Display realisations from a (mixture of) GP predictionplot_samples
Magma prediction for ploting GIFspred_gif
Gaussian Process predictionpred_gp
Magma predictionpred_magma
MagmaClust predictionpred_magmaclust
Indicates the most probable clusterproba_max_cluster
Regularise a grid of inputs in a datasetregularise_data regularize_data
Draw samples from a posterior GP/Magma distributionsample_gp sample_magma
Draw samples from a MagmaClust posterior distributionsample_magmaclust
Select the optimal number of clustersselect_nb_cluster
Simulate a dataset tailored for MagmaClustRsimu_db
French swimmers performances data on 100m freestyle eventsswimmers
Learning hyper-parameters of a Gaussian Processtrain_gp
Prediction in MagmaClust: learning new HPs and mixture probabilitiestrain_gp_clust
Training Magma with an EM algorithmtrain_magma
Training MagmaClust with a Variational EM algorithmtrain_magmaclust
Weight follow-up data of children in Singaporeweight