Package: registr 2.1.0

registr: Curve Registration for Exponential Family Functional Data

A method for performing joint registration and functional principal component analysis for curves (functional data) that are generated from exponential family distributions. This mainly implements the algorithms described in 'Wrobel et al. (2019)' <doi:10.1111/biom.12963> and further adapts them to potentially incomplete curves where (some) curves are not observed from the beginning and/or until the end of the common domain. Curve registration can be used to better understand patterns in functional data by separating curves into phase and amplitude variability. This software handles both binary and continuous functional data, and is especially applicable in accelerometry and wearable technology.

Authors:Julia Wrobel [aut, cre], Alexander Bauer [aut], Erin McDonnell [aut], Fabian Scheipl [ctb], Jeff Goldsmith [aut]

registr_2.1.0.tar.gz
registr_2.1.0.zip(r-4.5)registr_2.1.0.zip(r-4.4)registr_2.1.0.zip(r-4.3)
registr_2.1.0.tgz(r-4.4-x86_64)registr_2.1.0.tgz(r-4.4-arm64)registr_2.1.0.tgz(r-4.3-x86_64)registr_2.1.0.tgz(r-4.3-arm64)
registr_2.1.0.tar.gz(r-4.5-noble)registr_2.1.0.tar.gz(r-4.4-noble)
registr_2.1.0.tgz(r-4.4-emscripten)registr_2.1.0.tgz(r-4.3-emscripten)
registr.pdf |registr.html
registr/json (API)
NEWS

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

Peer review:

Bug tracker:https://github.com/julia-wrobel/registr/issues

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
Datasets:

On CRAN:

6.27 score 16 stars 29 scripts 182 downloads 1 mentions 12 exports 35 dependencies

Last updated 3 years agofrom:d9f392413a. Checks:OK: 1 NOTE: 8. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 02 2024
R-4.5-win-x86_64NOTENov 02 2024
R-4.5-linux-x86_64NOTENov 02 2024
R-4.4-win-x86_64NOTENov 02 2024
R-4.4-mac-x86_64NOTENov 02 2024
R-4.4-mac-aarch64NOTENov 02 2024
R-4.3-win-x86_64NOTENov 02 2024
R-4.3-mac-x86_64NOTENov 02 2024
R-4.3-mac-aarch64NOTENov 02 2024

Exports:bfpcabs_derivconstraintsdata_cleanfpca_gaussgfpca_twoSteploss_hloss_h_gradientregister_fpcaregistrsimulate_functional_datasimulate_unregistered_curves

Dependencies:bootclicpp11dplyrfansigamm4genericsgluelatticelifecyclelme4magrittrMASSMatrixmgcvminqanlmenloptrpbspillarpkgconfigpurrrR6RcppRcppArmadilloRcppEigenrlangstringistringrtibbletidyrtidyselectutf8vctrswithr

Registering Incomplete Curves

Rendered fromincomplete_curves.Rmdusingknitr::rmarkdownon Nov 02 2024.

Last update: 2021-07-02
Started: 2020-11-02

registr: a vignette

Rendered fromregistr.Rmdusingknitr::rmarkdownon Nov 02 2024.

Last update: 2022-01-10
Started: 2018-01-04

Readme and manuals

Help Manual

Help pageTopics
Simulate amplitude varianceamp_curve
Binary functional principal components analysisbfpca
Internal main preparation function for bfpcabfpca_argPreparation
Internal main optimization for bfpcabfpca_optimization
Nth derivative of spline basisbs_deriv
Coarsen an index vector to a given resolutioncoarsen_index
Define constraints for optimization of warping functionsconstraints
Covariance estimation after Hall et al. (2008)cov_hall
Crossproduct computation for highly irregular gridscrossprods_irregular
Crossproduct computation for mostly regular gridscrossprods_regular
Convert data to a 'refund' objectdata_clean
Estimate the derivative of the logit functionderiv.inv.logit
Determine the number of FPCs based on the share of explained variancedetermine_npc
Correct slightly improper parameter vectorsensure_proper_beta
Calculate expected score and score variance for the current subject.expectedScores
Estimate variational parameter for the current subject.expectedXi
Functional principal components analysis via variational EMfpca_gauss
Internal main preparation function for fpca_gaussfpca_gauss_argPreparation
Internal main optimization for fpca_gaussfpca_gauss_optimization
Generalized functional principal component analysisgfpca_twoStep
Generate subject-specific grid (t_star)grid_subj_create
Berkeley Growth Study data with simulated incompletenessgrowth_incomplete
Create initial parameters for (inverse) warping functionsinitial_params
Apply lambda transformation of variational parameter.lambdaF
Loss function for registration step optimizationloss_h
Gradient of loss function for registration steploss_h_gradient
Simulate mean curvemean_curve
Simulate meanmean_sim
NHANES activity datanhanes
Create two-parameter piecewise linear (inverse) warping functionspiecewise_linear2_hinv
Plot the results of a functional PCAplot.fpca
Simulate PC1psi1_sim
Simulate PC2psi2_sim
Register curves using constrained optimization and GFPCAregister_fpca
Register Exponential Family Functional Dataregistr
Internal function to register one curveregistr_oneCurve
Simulate functional datasimulate_functional_data
Simulate unregistered curvessimulate_unregistered_curves
Calculate quadratic form of spline basis functions for the current subject.squareTheta