Release v 1.0.2 to CRAN (#439)

[Merging despite problem with the new torch version found after CRAN release. Will have to deal with that to get vaeac up running.]

.Rbuildignore

@@ -6,7 +6,6 @@
 ^\.lintr$
 ^\.covrignore$
 ^LICENSE\.md$
-inst/compare_lundberg\.xgb\.obj
 ^\.github$
 ^CODE_OF_CONDUCT\.md$
 ^cran-comments\.md$
@@ -31,7 +30,7 @@ inst/compare_lundberg\.xgb\.obj
 ^vignettes/cache_vaeac/*$
 ^vignettes/cache_regression/*$
 ^vignettes/cache_asymmetric_causal/*$
-#^tests/testthat/_snaps/*$ # Uncomment when submitting to CRAN to reduce filesize
+^tests/testthat/_snaps/*$ # Uncomment when submitting to CRAN to reduce filesize
 ^inst/code_paper/*$
 ^inst/joss_paper/*$
 

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: shapr
-Version: 1.0.1.9000
+Version: 1.0.2.9000
 Title: Prediction Explanation with Dependence-Aware Shapley Values
 Description: Complex machine learning models are often hard to interpret. However, in 
   many situations it is crucial to understand and explain why a model made a specific 
@@ -30,7 +30,7 @@ RoxygenNote: 7.3.2
 Depends: R (>= 3.5.0)
 Imports: 
     stats,
-    data.table,
+    data.table (>= 1.15.0),
     Rcpp (>= 0.12.15),
     Matrix,
     future.apply,

NEWS.md

@@ -1,27 +1,38 @@
-# shapr (development version)
+# shapr 1.0.2
 
 * Fix CRAN NOTE which turned out to be bug related to returning NULL rather than integer(0) to identify (unconditional)
-asymmetric causal sampling [#435](https://github.com/NorskRegnesentral/shapr/pull/435)
+asymmetric causal sampling ([#435](https://github.com/NorskRegnesentral/shapr/pull/435))
+* [Py] Get 'shaprpy' up to speed with the latest 'shapr' version and return the internal list properly 
+([#436](https://github.com/NorskRegnesentral/shapr/pull/436))
+* Allow manual groups in `explain_forecast()` ([#433](https://github.com/NorskRegnesentral/shapr/pull/433))
+* Minor updates to readme and pkgdown site after CRAN release of shapr 1.0.1 
+([#437](https://github.com/NorskRegnesentral/shapr/pull/437), 
+[#438](https://github.com/NorskRegnesentral/shapr/pull/438))
+* Require data.table >= 1.15.0 to allow uniform usage of `by=.I`
+([#434](https://github.com/NorskRegnesentral/shapr/issues/434))
+* Minor doc edits ([#439](https://github.com/NorskRegnesentral/shapr/issues/439))
+
+
 
 # shapr 1.0.1 
 
-* Spelling checking and other minor clean up [#431](https://github.com/NorskRegnesentral/shapr/pull/431))
-* Add extra_computation_args and output_args to explain_forecast() [#428](https://github.com/NorskRegnesentral/shapr/pull/428))
-* Rename vaeac plotting functions [#428](https://github.com/NorskRegnesentral/shapr/pull/428))
-* Move explain() arguments `paired_shap_sampling` and `kernelSHAP_reweighting` into `extra_computation_args` [#428](https://github.com/NorskRegnesentral/shapr/pull/428))
-* Improved and unified the documentation [#427](https://github.com/NorskRegnesentral/shapr/pull/427))
-* Remove seed argument from the boostrap function as its better handled by the mother function [#427](https://github.com/NorskRegnesentral/shapr/pull/427))
-* Renamed various internal functions to be consistent with names in the rest of the package [#427](https://github.com/NorskRegnesentral/shapr/pull/427))
-* Remove MSEv from explain_forecast (as it was only supported for horizon=1). Should return in a more general manner in the future [#427](https://github.com/NorskRegnesentral/shapr/pull/427))
-* Improve efficiency of coalition sampling code and move to string sampling [#426](https://github.com/NorskRegnesentral/shapr/pull/426))
-* Bugfix `iterative = TRUE` for `explain_forecast()` which was not using coalitions from previous iterations [#426](https://github.com/NorskRegnesentral/shapr/pull/426))
-* Bugfix the handling and output with the `verbose` argument for `explain_forecast()` [#425](https://github.com/NorskRegnesentral/shapr/pull/425))
-* Improved flexibility of the beeswarm plot functionality [#424](https://github.com/NorskRegnesentral/shapr/pull/424))
-* Bugfix edge case where the `party` package returns a `constparty` object [#423](https://github.com/NorskRegnesentral/shapr/pull/423))
-* Bugfix error due to extra comma in rarely used warning [#422](https://github.com/NorskRegnesentral/shapr/pull/422))
-* Shined up the vignettes a bit [#421](https://github.com/NorskRegnesentral/shapr/pull/421))
-* Bugfix `keep_samp_for_vS` with iterative approach [#417](https://github.com/NorskRegnesentral/shapr/pull/417))
-* [Python] Brought the python code base up to speed with essentially all functionality in `explain()` in R [#416](https://github.com/NorskRegnesentral/shapr/pull/416))
+* Spelling checking and other minor clean up ([#431](https://github.com/NorskRegnesentral/shapr/pull/431))
+* Add extra_computation_args and output_args to explain_forecast() ([#428](https://github.com/NorskRegnesentral/shapr/pull/428))
+* Rename vaeac plotting functions ([#428](https://github.com/NorskRegnesentral/shapr/pull/428))
+* Move explain() arguments `paired_shap_sampling` and `kernelSHAP_reweighting` into `extra_computation_args` ([#428](https://github.com/NorskRegnesentral/shapr/pull/428))
+* Improved and unified the documentation ([#427](https://github.com/NorskRegnesentral/shapr/pull/427))
+* Remove seed argument from the boostrap function as its better handled by the mother function ([#427](https://github.com/NorskRegnesentral/shapr/pull/427))
+* Renamed various internal functions to be consistent with names in the rest of the package ([#427](https://github.com/NorskRegnesentral/shapr/pull/427))
+* Remove MSEv from explain_forecast (as it was only supported for horizon=1). Should return in a more general manner in the future ([#427](https://github.com/NorskRegnesentral/shapr/pull/427))
+* Improve efficiency of coalition sampling code and move to string sampling ([#426](https://github.com/NorskRegnesentral/shapr/pull/426))
+* Bugfix `iterative = TRUE` for `explain_forecast()` which was not using coalitions from previous iterations ([#426](https://github.com/NorskRegnesentral/shapr/pull/426))
+* Bugfix the handling and output with the `verbose` argument for `explain_forecast()` ([#425](https://github.com/NorskRegnesentral/shapr/pull/425))
+* Improved flexibility of the beeswarm plot functionality ([#424](https://github.com/NorskRegnesentral/shapr/pull/424))
+* Bugfix edge case where the `party` package returns a `constparty` object ([#423](https://github.com/NorskRegnesentral/shapr/pull/423))
+* Bugfix error due to extra comma in rarely used warning ([#422](https://github.com/NorskRegnesentral/shapr/pull/422))
+* Shined up the vignettes a bit ([#421](https://github.com/NorskRegnesentral/shapr/pull/421))
+* Bugfix `keep_samp_for_vS` with iterative approach ([#417](https://github.com/NorskRegnesentral/shapr/pull/417))
+* [Python] Brought the python code base up to speed with essentially all functionality in `explain()` in R ([#416](https://github.com/NorskRegnesentral/shapr/pull/416))
 * Please CRAN with dontrun on long running examples + skip_on_cran for the parallelized tests.
 
 # shapr 1.0.0 (GitHub only)

R/approach.R

@@ -2,7 +2,7 @@
 #'
 #' The different choices of `approach` take different (optional) parameters,
 #' which are forwarded from [explain()].
-#' See the \href{https://norskregnesentral.github.io/shapr/articles/general_usage.html}{general usage}
+#' See the \href{https://norskregnesentral.github.io/shapr/articles/general_usage.html}{general usage vignette}
 #' for more information about the different approaches.
 #'
 #' @param ... Arguments passed to specific classes. See below

R/explain.R

@@ -125,7 +125,7 @@
 #' then the function will use the previous object to continue the computation.
 #' This is useful if the computation is interrupted or you want higher accuracy than already obtained, and therefore
 #' want to continue the iterative estimation. See the
-#' \href{https://norskregnesentral.github.io/shapr/articles/general_usage.html}{general usage} for examples.
+#' \href{https://norskregnesentral.github.io/shapr/articles/general_usage.html}{general usage vignette} for examples.
 #'
 #' @param asymmetric Logical.
 #' Not applicable for (regular) non-causal or asymmetric explanations.
@@ -183,7 +183,7 @@
 #' @details The `shapr` package implements kernelSHAP estimation of dependence-aware Shapley values with
 #' eight different Monte Carlo-based approaches for estimating the conditional distributions of the data.
 #' These are all introduced in the
-#' \href{https://norskregnesentral.github.io/shapr/articles/general_usage.html}{general usage}.
+#' \href{https://norskregnesentral.github.io/shapr/articles/general_usage.html}{general usage vignette}.
 #' (From R: `vignette("general_usage", package = "shapr")`).
 #' Moreover,
 #'  \href{https://martinjullum.com/publication/aas-2021-explaining/aas-2021-explaining.pdf}{Aas et al. (2021)}

cran-comments.md

@@ -1,14 +1,14 @@
-# shapr 1.0.1 (Major release)
+# shapr 1.0.2 (Patch release)
 
-* **By CRAN request** after initial submission: 
-  * Fixed spelling in DESCRIPTION
-  * Reduced tarball size mainly by (temporary) removing snapshot files from the build as they are not run on CRAN.
+* (Resubmission of exactly the same package as submitted Jan 22nd. During check 
+there seemed to be installation issues with the dials and rsample package (unrelated to my package).
+Unfortunately my emails commenting on this seems to have not reached the CRAN team, which unfortunately removed shapr 1.0.1.
+on CRAN. See below for original patch release comments.)
 
-* Complete rewrite of the package compared to the previous CRAN release. We moved from two main user functions 
-`shapr()` and `explain()` to a single function `explain()` that includes both.
-Thus, this change breaks essentially all existing code that uses the previous version of the package.
-* A comprehensive list of changes and new functionality can be found in the NEWS.md file.
-* We deem the package fully mature at this stage, and therefore release it as a stable, major version.
+* Fix test error in prepare_data_gaussian_cpp seen on clang-UBSAN gcc-UBSAN compliers in CRAN checks. 
+Turned out to be an actual bug for an edge case.
+* Other minor fixes to GH repo, pkgdown site, python wrapper ++ unrelated to the actual shapr CRAN package.
+See NEWS.md for details.
 
 ## Test environments
 
@@ -19,17 +19,18 @@ The win-builder and R-hub tests are run without snapshots tests (to replicate CR
 * GHA (ubuntu-latest), R-version: devel, release, oldrel-1, oldrel-2
 * GHA (windows-latest), R-version: release
 * GHA (macOS-latest), R-version: release
-* win-builder, R-versions: devel, release, oldrelease 
+* devtools-win-builder, R-versions: devel, release, oldrelease 
+* devools-mac-builder, R-versions: release 
 * R-hub (ubuntu-latest): R-version: devel
-* R-hub (macos-13): R-version: devel
-* R-hub (macos-latest): R-version: devel
 * R-hub (windows-latest): R-version: devel
+* R-hub (clang-asan): R-version: devel
+
 
 ## R CMD check results
 
 There were no ERRORs, WARNINGs
 
-There were 1 NOTE
+There were in total 2 NOTES
 
 ### NOTE (multiple platforms):
 
@@ -41,13 +42,21 @@ There were 1 NOTE
 
 > The package is growing in size, uses more complied code, and the documentation is comprehensive.
 
+### NOTE (win-builder):
+
+* checking CRAN incoming feasibility ... [20s] NOTE
+Maintainer: 'Martin Jullum <[email protected]>'
+
+Days since last update: 6
+
+> Correct. I was required to fix the issue by the CRAN team.
 
 ## Downstream dependencies
 There is 2 downstream dependency (`PPtreeregViz`, `SEMdeep`) of `shapr`. 
 In addition, the package `shapviz` provides additional plotting functionality without stating an explicit dependency 
 (I believe shapr actually should have be listed under Suggests?)
 
-The 3 packages fails on R CMD checks, but I have submitted PRs to fix all issues.
+The 2 packages fails on R CMD checks, but I have submitted PRs to fix them.
 
 ### PPtreeregViz
 
@@ -61,7 +70,5 @@ There has been no reaction from the maintainer.
 
 ### shapviz
 
-* Nov 15th 2024 I submitted a PR fixing the issue: https://github.com/ModelOriented/shapviz/pull/162
-The PR was merged to the GitHub version of `shapviz` on Nov 16th 2024. 
-The CRAN version has naturally not been updated yet.
-I will notify the maintainer of `shapvix` when the new version of `shapr` is released on CRAN.
+*Passes the checks
+