Package: soilVAE
Type: Package
Title: Supervised Variational Autoencoder Regression via 'reticulate'
Version: 0.1.10
Authors@R: c(
    person("Hugo", "Rodrigues", email = "rodrigues.machado.hugo@gmail.com", role = c("aut", "cre")),
    person("Alexandre M. J.-C.", "Wadoux", role = "cph",
           comment = "Copyright holder of the 'soilspec' package (MIT, 2020), from which the bundled 'datsoilspc' dataset is redistributed")
  )
Description: Supervised latent-variable regression for high-dimensional
        predictors such as soil reflectance spectra. The model uses an
        encoder-decoder neural network with a stochastic Gaussian
        latent representation regularized by a Kullback-Leibler term,
        and a supervised prediction head trained jointly with the
        reconstruction objective. The implementation interfaces R with
        a 'Python' deep-learning backend and provides utilities for
        training, tuning, and prediction.
License: MIT + file LICENSE
Encoding: UTF-8
RoxygenNote: 7.3.3
Imports: reticulate, stats
Suggests: knitr, rmarkdown, prospectr, pls
VignetteBuilder: knitr
SystemRequirements: Python (>= 3.9); TensorFlow (>= 2.13); Keras (>= 3)
URL: https://hugomachadorodrigues.github.io/soilVAE/,
        https://github.com/HugoMachadoRodrigues/soilVAE/
BugReports: https://github.com/HugoMachadoRodrigues/soilVAE/issues
NeedsCompilation: no
Packaged: 2026-10-29 12:21:14 UTC; root
Author: Hugo Rodrigues [aut, cre], Alexandre M. J.-C. Wadoux [cph]
        (Copyright holder of the 'soilspec' package (MIT, 2020), from
        which the bundled 'datsoilspc' dataset is redistributed)
Maintainer: Hugo Rodrigues <rodrigues.machado.hugo@gmail.com>
Depends: R (>= 3.5.0)
Config/pak/sysreqs: libpng-dev python3
Repository: https://hugomachadorodrigues.r-universe.dev
Date/Publication: 2026-08-22 17:50:02 UTC
RemoteUrl: https://github.com/cran/soilVAE
RemoteRef: HEAD
RemoteSha: c180889b56ef8e9abb0d6b28bbea7736413c0880