Changes in version 1.7.32 (2026-02-22) CRAN Checks o Resolve the warning "comparison of floating-point type with enumeration type is deprecated" because C++20 deprecated implicit conversions between enumerations and floating-point types. Changes in version 1.7.31 (2025-12-16) CRAN Checks o Remove Makevars, since C++17 is now the default C++ standard in the mainstream compilers (including Clang and GCC), and Rcpp:::LdFlags() has not been needed anymore for quite a long time. Changes o Change License from GPL>=2 to GPL>=3. Changes in version 1.7.30 (2023-01-06) Bug Fixes o Replace sprintf with snprintf. Changes in version 1.7.27 (2022-03-13) CRAN Checks o Drop the dependency on rattle.data since it's not available. Documentation o Use the iris dataset in examples. o Remove dependencies on party and markdown. o Correct typos. Changes in version 1.7.22 (2021-10-10) Documentation o Replace JSS URLs with DOIs. Changes in version 1.7.21 (2021-04-28) Documentation o Correct invalid links in NEWS. Changes in version 1.7.20 (2021-04-24) Bug Fixes o Correct the uninitialized variable pos in src/c4_5_var_selector.cpp. CRAN Checks o Suggest markdown and rmarkdown as dependency (See Move the markdown package from Imports to Suggests #1864). Documentation o Add authors' ORCID identifiers. o Change http to https. Changes in version 1.7.17 (2017-09-25) Bug Fixes o Use rattle.data for datasets instead of rattle. Changes in version 1.7.13 (2017-04-17) CRAN Checks o Remove deprecated Make variables with prefix CXX1X (CHANGES IN R 3.4.0). Changes in version 1.7.10 (2017-03-28) Enhancements o Increase the responsiveness when user interrupt. o Add registration for native routines. Bug Fixes o Segment fault and memory not mapped when user interrupt. Documentation o Add description for installation from GitHub. o Add citation info. Changes in version 1.7.0 (2016-10-28) Changes o Change the output of predict.wsrf to be a list of predictions of different types. Bug Fixes o Fix bug introduced in version 1.6.25 when adding wsrf.default for separate inputs and response. Enhancements o Throw more informative error when variable (attribute) not found in newdata of predict.wsrf. o Add interrupt check in predict.wsrf. Changes in version 1.6.25 (2016-09-10) New Features o Add a new argument nodesize to change the minimum node size. o Add a method wsrf.default to deal with separate inputs (x) and response (y), besides wsrf.formula with formula. Changes o Drop support of Boost for multithreading. Enhancements o Speed up data loading in wsrf and predict. Misc o Add subject classifications for the content of the package. o Add badges in README. Changes in version 1.5.46 Bug Fixes o Fix undefined column error when column name is a non-syntactic name, such as names contain whitespace. o Fix failure to switch to the code for the right compiler version. Documentation o Add URL and BugReports into DESCRIPTION. Changes in version 1.5.29 (2015-10-10) Bug Fixes o Fix out-of-bound access bug triggered by passing test data without the column of target variable. Changes in version 1.5.24 (2015-07-07) Bug Fixes o Add missing imports to correct the NOTEs from the newly added check item of R-devel on 2015-06-29. o Correct the URLs of CRAN package pages to their canonical form in the documentation. Documentation o Add more examples in the manual. o Update documentation. o Change vignette from Rnw to Rmd. Changes in version 1.5.14 (2015-06-09) Bug Fixes o Negative information gain when splitting nodes leads to -nan when normalized by sqrt(). o No-matched predicted results when predict type is "prob" (Thank _Erich Studerus_ for reporting this bug). o Fix a bug when assessing variable importance: Vector out of range access. Misc o Update documentation: Make it clear that the internal algorithm used. o Move all predict functionality from R into C++ code. o Correct all compilation warnings on Windows, Linux, and OS X and errors from memtest. Changes in version 1.5.0 (2015-05-24) New Features o Add new function subset to get a sub-forest from a wsrf model. o Add new function combine to merge multiple wsrf models into bigger one. o Add confusion, oot.times, predicted, useweights, mtry in the wsrf model list. o Add clusterlogfile in the parameter list of function wsrf for debug. Changes o Function predict.wsrf returns NAs when there are missing values in newdata. o Remove function summary.wsrf, moving its functionality into print.wsrf, so that the default outputs of print.wsrf gives a summary of the model. o Tree structure printed by function print.wsrf is slightly different from previous version: Decisions from the same test node (internal node) have the same item number. o Function oobErrorRate is renamed into oob.error.rate and made as generic. Enhancements o Refactor code, making rooms for future modifications: Remove unused code; Redefine some classes. o Operate on R objects directly in C++ code instead of copied ones. o Improve time performance. Bug Fixes o Correct weighted random sampling. Misc o Replace srand() with R _RNG_ functions. Changes in version 1.4.0 (2014-05-30) New Features o Add new function wsrfParallelInfo for querying the underlying parallel implementation (parallel or not). Bug Fixes o The predict method requires a dummy outcome column to be in the new data (Thank _Max Kuhn_ for reporting this bug). Minor Changes o Adapt R's make variable CXX_STD to configure installation. o List packages used by vignettes code in DESCRIPTION. Documentation o Let R to build the vignettes so that it can be visible on wsrf. Changes in version 1.3.0 (2014-02-09) o added documents: • vignettes • README.Rd • NEWS.md o provided Windows support (no multi-threading functionality, but can run in distributed way) o bug fixed: when used in distributed environment, variable name info is missing, therefore, "Error: Training Set is empty" occurs.