Changes in version 1.6.5 (2024-06-12) - try to lower dependencies to avoid lme4 2024-06-17 removal threat Changes in version 1.6.4 (2023-08-19) - work around https://github.com/r-lib/roxygen2/issues/1491 Changes in version 1.6.3 (2021-06-11) - Fix some links. - Remove LazyData decl. Changes in version 1.6.2 (2020-10-17) - Move to tinytest Changes in version 1.6.1 (2020-08-12) - Documentation improvements. Changes in version 1.6.0 (2020-03-11) - More S3 methods. - Back-port pyvtreat recommendation code to Rvtreat. Changes in version 1.5.2 (2020-02-08) - Control imputation on design_missingness_treatment. - Share cross-splits in multinomial mode to minimize data leakage. - Earlier argument checking. - Default classification target to TRUE. - Some documentation improvements. - Move wrapr to Depends. Changes in version 1.5.1 (2020-01-16) - Check for same-frame on prepare paths. - Pipe into ft. - Rename multinomial arguments to match other methods. - Move parallel to a suggestion and configure a global option to shut it down ( vtreat.allow_parallel ). Changes in version 1.5.0 (2020-01-08) - Fix multinomial variable restriction. - Fix FT multinomial columns copy. - Work on ft serialization environments. - More tests. - Improve custom coder flexibility. Changes in version 1.4.8 (2019-12-08) - Center/scale improvement from nfultz. - Documentation updates. - fit_tranform interface. Changes in version 1.4.7 (2019-10-01) - fix wrong y-name in multinomial cross frame. Changes in version 1.4.6 (2019-09-23) - Some doc updates. Changes in version 1.4.5 (2019-09-11) - Some doc updates. Changes in version 1.4.4 (2019-07-27) - Adjust license to GPL-2 | GPL-3 - Some doc updates. Changes in version 1.4.3 (2019-07-18) - Fix bug in custom coder NA path and let numeric coder center if wanted. - More tests. Changes in version 1.4.2 (2019-07-01) - Fix eronious Cohen reference in documentation. Changes in version 1.4.0 (2019-05-05) - Fancy level and variable names. - More tests on odd level names (and collisions). Changes in version 1.3.8 (2019-03-31) - Remove spline from default value variables. - Fix ggplot2 vignette dependence issue. - Make treatment plans pipeable targets. Changes in version 1.3.7 (2019-02-21) - Fix design_missingness_treatment() prepare. - Move to wrapr test runner. Changes in version 1.3.6 (2019-02-09) - Add patch_columns_into_frame(). - Fix column name munging. - Start switching to RUnit tests. Changes in version 1.3.5 (2019-01-27) - Make categorical scoring default TRUE. - logit-ize custom coders. - spline custom coder. - Get stricter about row ordering in building custom coders. - neaten up printing a bit. - Collar spline and lower its complexity. Changes in version 1.3.4 (2019-01-02) - Accept pre-built approximation tables from numeric custom coders. - Fix .customCodeNum() extrapolation, down-sampling, and remote numeric ".center" option. - More docs. Changes in version 1.3.3 (2018-12-17) - remove _clean suffix. - Fix non-scalar comparisions (mostly form class vectors). - add segmented variable calculation. - add pre-computed split plan. - bump dependencies. - Example higher order coders. Changes in version 1.3.2 (2018-11-05) - force parent.frame - add a drop columns option to design_missingness_treatment() - Doc fixes Changes in version 1.3.1 (2018-09-10) - Fix variable naming in multi class case. - Some doc fixes. - Start on NaN and Infinity on databases. - More tests. Changes in version 1.3.0 (2018-07-20) - Fix z-split annotation issue. - Change designTreatmentsZ() defaults. - Documentation fixes. - Multiclass treatments. - Simple treatments. - Fix CRAN Note on pre 3.5.0 R parallel usage. Changes in version 1.2.3 (2018-07-11) - Smooth catP novel levels scoring a bit. - Fix check error on parallel::getDefaultCluster() Changes in version 1.2.2 (2018-07-04) - Fix issue 19. - Do not use NULL to signal when parallelism is desired. Changes in version 1.2.1 (2018-06-27) - default data.table merging on (may be a performance regression to not set this). - rqdatatable treatment path. - better formatting. - add extracols argument to prepare(). - Improve regexps. Changes in version 1.2.0 (2018-06-19) - Translate treatment plans to rquery. - Minor documentation improvements. - Improve error messages on argument checking. - Improve name generation (remove dots). - Remove dplyr dependence. Changes in version 1.0.4 (2018-05-05) - Add data.table as an optional row-binder. - Declare an R version. Changes in version 1.0.3 (2018-03-10) - parallel indicator calculation. - add optional warning on encountering novel levels in prepare. Changes in version 1.0.2 (2018-01-20) - bind options. - fix deps. - restore parallel test. - kWayStratifiedY performance fix from @khotilov Vadim Khotilovich. Changes in version 1.0.1 (2017-10-17) - Minor documentation fixes. - rm data.table (possibly related to issues 2413 or 2418). Changes in version 1.0.0 (2017-10-04) - Minor documentation fixes. - More work on novel values for non-centered custom coders. - Numeric custom coders. - Isotone examples. Changes in version 0.6.0 (2017-09-20) - Add codeRestriction option to design steps. - Prepare for custom models. - Prefer data.table::rbindlist() for assembling frames. - Add forceSplit mode. Changes in version 0.5.32 (2017-06-14) - Add codeRestriction option to prepare(). Changes in version 0.5.31 (2017-04-14) - make prueSig an optional argument in prepare, and force by-name access. - Remove left.op=TRUE from findInterval in "vtreat Rare Levels" vignette (seems to be a new addition to findInterval, so fails CRAN check r-oldrel-windows-ix86+x86_64). Changes in version 0.5.30 (2017-01-21) - General improvements in documentation and vignettes. - Document saving/loading treatment plans. Changes in version 0.5.29 - Add 'rsq' column to scoreFrame (rsq- for numeric targets, pseudo-rsq for categorical targets). Changes in version 0.5.28 (2016-10-25) - Fix treatment of constant columns in cross-partitions. - Switch doCollar default to FALSE. - Return indicators on designTreatmentsZ. - Fix extraDegreesOfFreedom calculation. - Allow repeated application rows in cross frames. - Remove lsig and csig from scoreFrame. - Add meanY to treatmentplan. - Documentation fixes. Changes in version 0.5.27 (2016-08-17) Changes: - Change catB variables to delta-logit score. - Fix passing of arguments to parallel prepare, and reduce size of data passed. - Ensure set of variables consistency in mkCross* methods. - More parallelization of level significance calculations, and cheaper chi-square test where appropriate. Changes in version 0.5.26 (2016-07-12) - Facilities for y-stratified and grouped splitting (useful for unbalanced classes). - catScaling=TRUE mode uses logistic regression for y-aware variable scaling. - Fix erroneous bad type warning on date columns. Changes in version 0.5.25 (2016-05-03) - Fix bug that caused catB variables to be scored as "insignificant". - Add test to check for above bug. - Expose cross validation controls. - More guards on significance calculations. Changes in version 0.5.23 (2016-04-29) - Fix issue of non-significant variables not being scaled. - Documentation fixes, document variable types, improve vignettes. - Minor performance fixes on result accumulation. - Add optional use of dplyr for row binding (of score report frames). Changes in version 0.5.22 (2016-01-08) - Calculations of non catX significances are now deterministic - Catch mis-naming or non-varying y earlier - Expose buildEvalSets as a public function - More tests Changes in version 0.5.21 (2015-11-11) - Isolated "cross" or "out of sample" frame generation into mkCrossFrameCExperiment() and mkCrossFrameNExperiment() - Many small bug fixes and corner cases patched Changes in version 0.5.20 (2015-11-05) - Simplified out of sample frame generation - Added "no-Y" treatment option - Minor documentation fixes Changes in version 0.5.18 (2015-10-07) - Fixed bugs in cross-validated mode - Force out of sample calculations in more situations - Fix vignette titles - Fix documentation - Do not allow small or insufficiently varying data frames (exact conditions in documentation) Changes in version 0.5.16 (2015-09-13) - Unified rare level treatment - Separate treatment of insignificant levels - Tests confirming compatibility with 'data.table' - More special case hardening - Over-fit vignette - Minor documentation fixes Changes in version 0.5.14 (2015-09-06) - First CRAN release