From b9ac6a1be148908ac7a901376f6d5c95e7f1088f Mon Sep 17 00:00:00 2001 From: Yann Richet Date: Sat, 11 Jul 2026 15:42:13 +0200 Subject: [PATCH] release: prepare CRAN submission 1.1-0 - DESCRIPTION: bump to 1.1-0 (updates current CRAN 0.9-3), refresh Date. - NEWS.md: 1.1-0 changelog (NestedKriging, Vecchia VLL(m) objective, objective/ regmodel/noise argument changes, fixes). - cran-comments.md: submission notes (test environments, R CMD check results, installed-size NOTE justification, reverse-dependencies). - .Rbuildignore: exclude cran-comments.md from the built package. --- .Rbuildignore | 2 ++ DESCRIPTION | 4 ++-- NEWS.md | 28 ++++++++++++++++++++++++++++ cran-comments.md | 39 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 71 insertions(+), 2 deletions(-) create mode 100644 NEWS.md create mode 100644 cran-comments.md diff --git a/.Rbuildignore b/.Rbuildignore index 67e193c..4f4b5a9 100644 --- a/.Rbuildignore +++ b/.Rbuildignore @@ -32,3 +32,5 @@ ^src/.*\.dll$ ^compat$ + +^cran-comments\.md$ diff --git a/DESCRIPTION b/DESCRIPTION index 9ac9484..475d271 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,8 +1,8 @@ Package: rlibkriging Type: Package Title: Kriging Models using the 'libKriging' Library -Version: 1.0-0 -Date: 2026-05-12 +Version: 1.1-0 +Date: 2026-07-11 Authors@R: c(person(given = "Yann", family = "Richet", diff --git a/NEWS.md b/NEWS.md new file mode 100644 index 0000000..6107393 --- /dev/null +++ b/NEWS.md @@ -0,0 +1,28 @@ +# rlibkriging 1.1-0 + +## New features + +* New `NestedKriging` class: a divide-and-conquer Gaussian process for large + designs. The data are partitioned into groups, one `Kriging` submodel is + fitted per group with a common prior, and predictions are aggregated with the + optimal nested-kriging aggregation (`"NK"`, interpolating) or a + product-of-experts rule (`"PoE"`, `"gPoE"`, `"BCM"`, `"rBCM"`). + +* New Vecchia approximated log-likelihood objective for large designs: fit a + `Kriging` model with `objective = "VLL(m)"` (or `"VLL"`, default `m = 30`), + costing O(n m^3) per evaluation instead of O(n^3). + +## Changes + +* `Kriging()` / `fit()`: `objective` now also accepts `"VLL"` / `"VLL(m)"`, and + `regmodel` now accepts `"quadratic"`. + +* `Kriging()` / `fit()`: the `noise` argument has been moved to the **last** + position, for consistency with `WarpKriging` and the other language bindings. + Code that passes `noise` by name is unaffected; positional calls that relied + on `noise` being the 4th argument must be updated. + +## Fixes + +* Fix a possible deadlock when forking after threads were created. +* Numerous build and portability fixes (Windows, macOS deployment target). diff --git a/cran-comments.md b/cran-comments.md new file mode 100644 index 0000000..9258711 --- /dev/null +++ b/cran-comments.md @@ -0,0 +1,39 @@ +## Submission + +This is a feature update of rlibkriging (1.1-0), updating the current CRAN +version 0.9-3. (Version 1.0-0 was a GitHub-only release and was not submitted +to CRAN.) + +Main user-visible changes (see NEWS.md): + +* new `NestedKriging` class (divide-and-conquer GP for large designs); +* new Vecchia approximated log-likelihood fit objective `"VLL(m)"`; +* `objective` also accepts `"VLL"`/`"VLL(m)"` and `regmodel` accepts + `"quadratic"`; the `noise` argument of `Kriging()`/`fit()` moved to the last + position (named calls are unaffected). + +## Test environments + +Tested via GitHub Actions and R-hub on: + +* Ubuntu 22.04, R release, R-devel and R oldrel-1 +* macOS (Apple Silicon), R release, R-devel and R oldrel-1 +* Windows Server, R release, R-devel and R oldrel-1 + +using `R CMD check --as-cran`. + +## R CMD check results + +0 errors | 0 warnings | 1 note + +* checking installed package size ... NOTE + installed size is ~40Mb (sub-directories `lib`, `include`, `libs`). + + rlibkriging bundles the 'libKriging' C++ library together with its C++ + dependencies (Armadillo and lbfgsb) as source and static libraries; the size + comes entirely from these vendored components, as in the previous CRAN + release. There is no run-time download. + +## Reverse dependencies + +There are no reverse dependencies on CRAN.