NEWS

---

mplot 1.1.0

• fixed the "lost braces" NOTE flagged by CRAN in the glmfence.Rd and lmfence.Rd manual pages by using proper \eqn markup for cstar*hat(sigma)_{M,tildeM} (#21)
• af() now uses future::multisession via furrr::future_map() instead of foreach/doParallel/doRNG, and no longer relies on a <<- global assignment inside the parallel worker (#11)
• vis() now uses future::multisession via furrr::future_map() instead of foreach/doParallel/doRNG for all three model-selection branches (bestglm, glmulti, leaps), and no longer relies on <<- global assignments inside the glmulti parallel worker (#12)
• foreach, doParallel and doRNG have been dropped as package dependencies now that af(), vis() and bglmnet() have been migrated to future/furrr (#11, #12)
• bglmnet() is now parallel via furrr::future_map(), honouring the previously-unused cores argument; results are reproducible across different core counts (#13)
• fixed a bglmnet() bug where apply(betaboot, 3, get_unique_mods) silently simplified to an array whenever every bootstrap replication produced the same number of unique selected models, causing a do.call(rbind, x) failure (#14)
• the bglmnet() example now runs sequentially (cores = 1) so it stays well under CRAN's 10 second limit for example run times
• removed the defunct Travis-CI badge from README.md (CRAN flagged the stale URL)
• af() now shuffles the dispatch order of the c-value tasks to avoid load imbalance across workers (the cheap large-c tail is no longer clustered into a single chunk); results remain reproducible via the existing seed argument (#15)
• removed a duplicate cluster closure in af() and vis() that raised 'invalid connection' errors in non-interactive/test environments (#17)
• vis() now suppresses bestglm's 'Morgan-Tatar search' message
• workers now pin BLAS/LAPACK and OpenMP threads to 1 (when RhpcBLASctl is installed) to avoid oversubscription when combined with future::multisession
• added a comprehensive testthat test suite
• source code reformatted with air

mplot 1.0.5

• reduce reliance on bestglm as it appears to be no longer maintained

mplot 1.0.3 (2019-05-14)

• Fix for plot.bglmnet with min.prob in mplot
• Resolve warning messages around exporting objects

mplot 1.0.2 (2019-01-22)

• Compatibility update with a new version of dplyr.

mplot 1.0.0

• Version 1.0.0 release to coincide with appearance of Journal of Statistical Software article.
• Documentation updates.
• Examples simplified so that run time of each is <5 seconds

mplot 0.8.2 (2018-01-05)

• The bglmnet function has been been re-written
• Added boot_size plot option for bglmnet objects
• Vignettes removed, replaced with pkgdown website

mplot 0.8.1 (2017-11-18)

• More sensible nbest parameter behaviour in the vis function. Now nbest = "all" reverts back to nbest = 1 for models with more than 15 parameters. This can be overridden by specifying an integer, rather than specifying "all". For large model sizes, if the number specified is too large, it will lead to memory overruns and failures with dependent packages.
• Fixed vignette/pkgdown issue where there were multiple vignettes created with the same name.

mplot 0.8.0 (2017-11-06)

• Random seed parameter for reproducible results
• New website
• Small fixes for JSS article (e.g. googleVis axis padding)

mplot 0.7.8 (2016-08-16)

• reimplemented classic plots in ggplot2
• classic plots are now default (reviewer feedback)
• improved documentation - more detail about procedures - more detail about plotting methods
• fixed the passing of weights for weighted models
• can now obtain full loss v dimension which="lvk" plots for glms
• vis() default is now nbest="all".
• experimental support for glmulti as a backend instead of bestglm for glms for the vis function. This enables users to enforce marginality constraints.

mplot 0.7.6

• maintenance, larger update coming soon

mplot 0.7.5 (2015-11-16)

• added fev and wallabies dataset

mplot 0.7.4

• added tag option to googleVis plots to facilitate easier plotting in rmarkdown documents.
• citation updated to reference arXiv article
• bootstrapping glmnet (bglmnet) function refined and added to the mplot() shiny interface

mplot 0.7.1 (2015-09-09)

• Fix for undefined globals (CRAN submission)

mplot 0.7.0

• Release to coincide with JSS article
• Implements "all" for vis function
• Improved blmnet plots
• Consistency with interactive plotting methods
• Improved documentation

mplot 0.6.5

• Numerous refinements including consistency of style between the classic plots
• ylim argument for classic boot and lvk plots
• legend.position argument for classic af plots

mplot 0.6.0

• First CRAN release
• Reimplemented vis function to avoid massive memory use for moderate model sizes. Now runs much faster and leaner.

mplot 0.5.5

• mplot interface now uses shinydashboard
• the scatterplot matrix from the mplot shiny interface has now been spun off into its own package: parisD3
• issue with zooming on transparent reported to GoogleCharts - the workaround is to not use backgroundColor = 'transparent' until it is fixed at the source

mplot 0.5.0

• Limited robustness via screening.
• Weights now get passed through in the adaptive fence.

mplot 0.4.9

• Changed parallel backend for af() from doMC to doParallel which should work for both unix-like systems and windows.
• Added redundant variable to vis().
• Fixed issue with deparse(model.formula) when the model.formula was too long for deparse to cope with.

mplot 0.4.7

• New data sets: diabetes and artificial example

mplot 0.4.6

• First public version