Package: GPopt
Type: Package
Title: 'Bayesian' Optimization using Gaussian Process Regression and
        Other Surrogates (R Interface to Python's 'GPopt')
Version: 0.10.2
Author: T. Moudiki
Maintainer: T. Moudiki <thierry.moudiki@gmail.com>
Description: An R interface to the Python package 'GPopt' for
        'Bayesian' Optimization using Gaussian Process Regression and
        Other Surrogates <https://github.com/Techtonique/GPopt>, for
        'Bayesian' optimization of black-box (and machine learning
        hyperparameter tuning) objective functions using Gaussian
        Process Regression and other surrogate models. Ported to R
        using 'reticulate' and 'uv', following the same technique
        described in
        <https://thierrymoudiki.github.io/blog/2025/12/17/r/python/new-nnetsauce-R-uv>.
        Every function in this package thinly wraps the corresponding
        Python object: attribute and method access with '$' in R
        mirrors attribute and method access with '.' in Python.
License: BSD_3_clause + file LICENSE
Encoding: UTF-8
RoxygenNote: 7.3.2
Imports: reticulate
SystemRequirements: Python (>= 3.9), the Python package GPopt
        (installed in a virtual environment, e.g. created with uv --
        see README.md)
URL: https://github.com/Techtonique/GPopt_r,
        https://github.com/Techtonique/GPopt
BugReports: https://github.com/Techtonique/GPopt_r/issues
Suggests: testthat (>= 3.0.0)
Config/testthat/edition: 3
Config/pak/sysreqs: libpng-dev python3
Repository: https://techtonique.r-universe.dev
Date/Publication: 2026-07-23 07:32:53 UTC
RemoteUrl: https://github.com/Techtonique/GPopt_r
RemoteRef: HEAD
RemoteSha: 381651db6c321500b464101e7536b9c91aa5e238
NeedsCompilation: no
Packaged: 2026-07-23 11:01:41 UTC; root