version 1.3.0

DESCRIPTION

@@ -1,9 +1,9 @@
 Package: IMIFA
 Type: Package
-Date: 2017-05-29
+Date: 2017-06-22
 Title: Fitting, Diagnostics, and Plotting Functions for Infinite
         Mixtures of Infinite Factor Analysers and Related Models
-Version: 1.2.1
+Version: 1.3.0
 Authors@R: c(person("Keefe", "Murphy", email = "keefe.murphy@ucd.ie", role = c("aut", "cre")),
              person("Isobel Claire", "Gormley", role = "ctb"),
              person("Cinzia", "Viroli", role = "ctb"))
@@ -19,10 +19,10 @@ Suggests: Rmpfr, gmp, knitr, methods, rmarkdown
 RoxygenNote: 6.0.1
 VignetteBuilder: knitr
 NeedsCompilation: no
-Packaged: 2017-05-29 18:06:27 UTC; Keefe
+Packaged: 2017-06-21 23:05:49 UTC; Keefe
 Author: Keefe Murphy [aut, cre],
   Isobel Claire Gormley [ctb],
   Cinzia Viroli [ctb]
 Maintainer: Keefe Murphy <keefe.murphy@ucd.ie>
 Repository: CRAN
-Date/Publication: 2017-05-29 21:27:51 UTC
+Date/Publication: 2017-06-21 23:21:39 UTC

MD5

@@ -1,47 +1,51 @@
-8fbef014b257ab9a86b71d689c541ee1 *DESCRIPTION
-95b024647b60e3f9c11b1f5cddb7bb17 *NAMESPACE
-391f8dda881be954ca8da43ae7c7a5ea *NEWS.md
-be0384a926c98b040e176084bb088478 *R/Diagnostics.R
-3ea94817414d18c67901c9849ab91d62 *R/FullConditionals.R
-655d03b12cbf713a2a097bb973de74ed *R/Gibbs_FA.R
-38026b02c0bdb8a2c40f194d8f125734 *R/Gibbs_IFA.R
-c970958719b976dd9e6de080aec22c32 *R/Gibbs_IMFA.R
-ec3f3d6624b65257a634a288b8eef0f2 *R/Gibbs_IMIFA.R
-d5043fd053925e875f390f7aac7be5ae *R/Gibbs_MFA.R
-ebb07e5e8eacdf4ad8a0759b33990073 *R/Gibbs_MIFA.R
-117b7b6cca7149d6b75f22f6b0d9dc10 *R/Gibbs_OMFA.R
-c85f11bca841e53a725cb0aaea6a226c *R/Gibbs_OMIFA.R
-ebd02fe24220a83120fabdeafd357579 *R/IMIFA.R
-f0eda2478bc4bfb52f7d7e66c133d02d *R/MainFunction.R
-19a73413ced425c3685e7eb9a4958939 *R/PlottingFunctions.R
-0cb8c8cd01e93c694eeede23e44434b7 *R/SimulateData.R
+518280fc5fdedb5c6f448a0d18b152b3 *DESCRIPTION
+0047fac4b5c2453d9b0afd9ee250b973 *NAMESPACE
+80a41879a45e16dfd227d30a4079311b *NEWS.md
+fbd82d61f472e4a76c051f9c50175ef4 *R/Diagnostics.R
+4b89229356df76717f2ff700f15dbf68 *R/FullConditionals.R
+63376a72809ceb0baa3990d44a8edafd *R/Gibbs_FA.R
+c1fc1959cf8c67d4e796d8bfd2f1cb33 *R/Gibbs_IFA.R
+e0b97b062fa6fe05f72bd3eeab63b89c *R/Gibbs_IMFA.R
+4f1aaa458c28c50a741e7801e875510e *R/Gibbs_IMIFA.R
+5f46204afe1252d9f387ee927e83193c *R/Gibbs_MFA.R
+adff3bb80797bcd86416a54c45bda19a *R/Gibbs_MIFA.R
+dabfc9c8ff6cac826b5ecea8463412f4 *R/Gibbs_OMFA.R
+4ffa37dedbdc7b82b213b405025fa66a *R/Gibbs_OMIFA.R
+f677e31c954826a66d464e59ad58ddfb *R/IMIFA.R
+c757631ab7576b8c6d25b2435a61ba87 *R/MainFunction.R
+d79824fa029795fc325c8f368ed6b5ec *R/PlottingFunctions.R
+5070d58144279fe7ed1d188382a77188 *R/SimulateData.R
 4e1464abd196123142e032a066f9628c *R/data.R
 67451aae22ea6399aa7705ac5d0432c1 *README.md
 1888491b0f83f4166b5d387d781d75e0 *build/vignette.rds
 6deddc586bb3532833f3ffa6652327c3 *data/coffee.rda
 34fbecb96149bd96a12e9bdd0dc94f98 *data/olive.rda
 906fec5f08c1de15c0dca6ab045a32e1 *inst/doc/IMIFA.R
-c1641bafdad997671ab7c2ddd4778804 *inst/doc/IMIFA.Rmd
-29255a5d4d5142805aa2d4a2dc59ff9d *inst/doc/IMIFA.html
-07473dd71acd068b7a5309b80e066974 *man/G_expected.Rd
-cdc3492cb586de9e9289f0da6b13179d *man/G_priorDensity.Rd
-e96e63e5bd631174a4f467eab91dadab *man/G_variance.Rd
-c3c87f2bc1320d1d273a4c3dd26408e2 *man/IMIFA.Rd
+9089df39fde860c767672118c90cfe91 *inst/doc/IMIFA.Rmd
+3a28c75df6f3e19cee280b9ca26bf100 *inst/doc/IMIFA.html
+67cfaf32d098bf18936c64e60c05e844 *man/G_expected.Rd
+a0cb77dec5c8c94d2df661fb6d928c69 *man/G_priorDensity.Rd
+67d1aea332b1ce55492ac0eb4cf95ee7 *man/G_variance.Rd
+a47919032b7c9433bf6fc7973d9e76c4 *man/IMIFA.Rd
+38a51bb77be43b62466cfda64336dee0 *man/Ledermann.Rd
 ea98d66316220f2c2c956f9cd24fd632 *man/MGP_check.Rd
-3cd8e8dd2131c30fc675a3dfff90c43b *man/PGMM_dfree.Rd
-4ccccdc0421273d74d56e172ed301483 *man/Zsimilarity.Rd
+8adb98e4697504a5937f19451d08419f *man/PGMM_dfree.Rd
+7151ecfc3c5ec73d80f22bc99bdd3201 *man/Procrustes.Rd
+76fc1b7fdad59738ffca8cdfe269aa8e *man/Zsimilarity.Rd
 0a414a386768243e488b2cc37644e4da *man/coffee.Rd
-aa4a739849ca14b52183ec7b5a823d2e *man/get_IMIFA_results.Rd
-a54f5eec1b0d2cda89e4f834acda0c4e *man/gumbel_max.Rd
-35010a68b88a53f50983dec770c30260 *man/heat_legend.Rd
-274e09ab4f05e234c4afd8b29bc4b415 *man/is.posi_def.Rd
-a5262c1f6f648adbd5f47c4e48abf26e *man/mat2cols.Rd
-9090634ec37d5d035ffde49f221d060b *man/mcmc_IMIFA.Rd
+4233f1cda9d481905b21665e04f35d32 *man/get_IMIFA_results.Rd
+731d02c05edfdd82be03166026ea499c *man/gumbel_max.Rd
+b15dccf7816d92b9beaa3849fcb6ce76 *man/heat_legend.Rd
+a27d2b64f0ea460502f9ae3d1345d35a *man/is.cols.Rd
+351a5b7f3c125591e38dc579e7fc1972 *man/is.posi_def.Rd
+207be28b7553de68c184d61486a1429f *man/mat2cols.Rd
+15daf805dfcc1efbf6f99f587f7a57ce *man/mcmc_IMIFA.Rd
 66f2ceddb66664646e63803a468d74ca *man/olive.Rd
 a6ef83c11ea344659931d42ac3d15c59 *man/plot.Results_IMIFA.Rd
-983d339b088d04942786e831742d2b51 *man/plot_cols.Rd
+6c430cd112a8df01123f85c98a63ba06 *man/plot_cols.Rd
 bfe7d96a2294c66843ca30f9071b97e6 *man/psi_hyper.Rd
-c8e01465312349f111bd7d490330b805 *man/rDirichlet.Rd
-470011ea7014881b12674be3889d3222 *man/sim_IMIFA_data.Rd
-c1641bafdad997671ab7c2ddd4778804 *vignettes/IMIFA.Rmd
+27dba6f5d8f11fcbc03698d50c84279d *man/rDirichlet.Rd
+91df66c816df4c382a428180b77c49a2 *man/shift_GA.Rd
+2b9ea02f5604e35850975e387a8eefa0 *man/sim_IMIFA_data.Rd
+9089df39fde860c767672118c90cfe91 *vignettes/IMIFA.Rmd
 c52793291f0e0f057c961e4b45f446f2 *vignettes/res_olive_IMIFA__Edited-Vignette-only-Version.rda

NAMESPACE

@@ -9,18 +9,22 @@ S3method(summary,Results_IMIFA)
 export(G_expected)
 export(G_priorDensity)
 export(G_variance)
+export(Ledermann)
 export(MGP_check)
 export(PGMM_dfree)
+export(Procrustes)
 export(Zsimilarity)
 export(get_IMIFA_results)
 export(gumbel_max)
 export(heat_legend)
+export(is.cols)
 export(is.posi_def)
 export(mat2cols)
 export(mcmc_IMIFA)
 export(plot_cols)
 export(psi_hyper)
 export(rDirichlet)
+export(shift_GA)
 export(sim_IMIFA_data)
 import(graphics)
 import(stats)

NEWS.md

@@ -1,6 +1,39 @@
 __Infinite Mixtures of Infinite Factor Analysers__
 ==================================================  
 
+# IMIFA v1.3.0 - (_4th release [minor update]: 2017-06-22_)
+## New Features
+* Added options `"constrained"` & `"single"` to `mcmc_IMIFA`'s `uni.type` argument:  
+  as well as being either diagonal or isotropic (UUU / UUC), uniquenesses can now further be  
+  constrained across clusters (UCU / UCC), with appropriate warnings, defaults, checks,  
+  initialisations, computation of model choice penalties, and plotting behaviour in all 4 cases.
+* `mcmc_IMIFA` gains the `tune.zeta` argument, a list of `heat`, `lambda` & `target` parameters, to invoke  
+  diminishing adaptation for tuning the uniform proposal to achieve a target acceptance rate when `alpha`  
+  is learned via  Metropolis-Hastings when the Pitman-Yor Process prior is employed for the IM(I)FA models.
+
+## Improvements
+* (I)FA models sped up by considering uniquenesses under 1-cluster models as `"constrained"` or `"single"`,  
+  rather than previously `"unconstrained"` or `"isotropic"`, utilising pre-computation and empty assignment.
+* Previously hidden functions improved, exported and documented with examples:  
+  `is.cols`, `Ledermann`, `Procrustes` & `shift_GA`.
+* `is.posi_def` gains `make` argument, merging it with previously hidden function `.make_posdef`:  
+  Thus the 'nearest' positive-(semi)definite matrix and the usual check can be returned in a single call.
+* Sped-up sampling IM(I)FA labels, esp. when 'active' G falls to 1, or the _dependent_ slice-sampler is used:  
+  `log.like` arg. removed from `gumbel_max`; function stands alone, now only stored log-likelihoods computed.
+* `psi` argument added to `sim_IMIFA_data` to allow supplying true uniqueness parameter values directly.
+
+## Bug Fixes
+* Used `bw="SJ"` everywhere `density` is invoked for plotting (`bw="nrd0"` is invoked if this fails).
+* Fixed initialisation of uniquenesses for `isotropic` (I)FA models.
+* Fixed parallel coordinates plot axes and labels for all `isotropic` uniquenesses plots.
+* Fixed adaptation for MIFA/OMIFA/IMIFA models when all clusters simultaneously have zero factors.
+* Fixed storage bug in IM(I)FA models when `learn.d` is `TRUE` but `learn.alpha` is `FALSE`.
+* Fixed density plot for `discount` when mutation rate is too low (i.e. too many zeros).
+* Fixed simulation of loadings matrices for empty MIFA/OMIFA/IMIFA clusters using `byrow=TRUE`:  
+  loop to simulate loadings matrices now generally faster also for all models.
+* Fixed silly error re: way in which (I)FA models are treated as 1-cluster models to ensure they run:  
+  Related bug fixed for OM(I)FA/IM(I)FA models when starting number of clusters is actually supplied.
+
 # IMIFA v1.2.1 - (_3rd release [patch update]: 2017-05-29_)
 ## Improvements
 * Posterior mean scores can now also be plotted in the form of a heat map (previously loadings only).  
@@ -23,46 +56,46 @@ __Infinite Mixtures of Infinite Factor Analysers__
 * Learning the Pitman-Yor `discount` & `alpha` parameters via Metropolis-Hastings now implemented.  
   Plotting function's `param` argument gains the option `discount` for posterior inference.
 * Sped up simulating cluster labels from unnormalised log probabilities using the Gumbel-Max trick (Yellott, 1977):  
-  `gumbel_max` replaces earlier function to sample cluster labels & is now unhidden/exported/documented.
-* Added new plot when `plot.meth=GQ` for OM(I)FA/IM(I)FA methods depicting trace(s) of #s of active/non-empty groups.
+  `gumbel_max` replaces earlier function to sample cluster labels and is now unhidden/exported/documented.
+* Added new plot when `plot.meth=GQ` for OM(I)FA/IM(I)FA models depicting trace of #s of active/non-empty clusters.
 * Added function `Zsimilarity` to summarise posterior clustering by the sampled labels with minimum  
-  squared distance to a sparse similarity matrix constructed by averaging the adjacency matrices.  
-  When optionally called inside `get_IMIFA_results`, the similarity matrix can be plotted via `plot.meth="zlabels"`.
+  squared distance to a sparse similarity matrix constructed by averaging the adjacency matrices:  
+  when optionally called inside `get_IMIFA_results`, the similarity matrix can be plotted via `plot.meth="zlabels"`.
 
 ## Improvements
 * Metropolis-Hastings updates implemented for `alpha` when `discount` is non-zero, rather than usual Gibbs.  
   Mutation rate monitored rather than acceptance rate for Metropolis-Hastings updates of `discount` parameter.
-* Fixed calculation of # 'free' parameters for `aic.mcmc` & `bic.mcmc` criteria when uniquenesses are isotropic:    
+* Fixed calculation of # '_free_' parameters for `aic.mcmc` & `bic.mcmc` criteria when uniquenesses are isotropic:    
   `PGMM_dfree`, which calculates # 'free' parameters for _finite_ factor analytic mixture models is exported/documented.  
   This function is also used to add checks on the Dirichlet hyperparameter for OM(I)FA methods.
 * DIC model selection criterion now also available for infinite factor models (previously finite only).
 * `G_priorDensity` now better reflects discrete nature of the density, and plots for non-zero PY discount values.
 * Posterior mean loadings heatmaps now also display a colour key legend via new function `heat_legend`.
 * Avoided redundant simulation of stick-breaking/mixing proportions under both types of IM(I)FA slice sampler.
 * Simulated (finite) mixing proportions w/ _Gamma(alpha, 1)_ trick (Devroye 1986, p.594) instead of `MCMCpack:rdirichlet`:  
-  `rDirichlet` replaces earlier function to sample mixing proportions & is now unhidden/exported/documented.
+  `rDirichlet` replaces earlier function to sample mixing proportions and is now unhidden/exported/documented.
 * Deferred setting `dimnames` attributes in `mcmc_IMIFA` to `get_IMIFA_results`: lower memory burden/faster simulations.
 * Jettisoned superfluous duplicate material in object outputted from `get_IMIFA_results` to reduce size/simplify access.
-* IMFA/IMIFA `trunc.G` arg, the max allowable # active groups, defaults to `range.G` & # active groups now stored.
-* Code sped up when G=1 by not simulating labels for OM(I)FA/IM(I)FA & not simulating mixing proportions for OM(I)FA.
+* IMFA/IMIFA `trunc.G` arg, the max allowable # active clusters, defaults to `range.G` and # active clusters now stored.
+* Code sped up when `active` G=1 by not simulating labels for IM(I)FA models.
 * Reduced chance of crash by exceeding memory capacity; `score.switch` defaults to `FALSE` if # models ran is large.
 
 ## Bug Fixes 
 * 2<sup>nd</sup> IM(I)FA label switching move sped up/properly weighted to ensure uniform sampling of neighbouring cluster pairs.
 * Offline label switching square assignment correction now permutes properly.
-* Fixed factor score trace plots by extracting indices of stored samples using `Rfast::sort_unique` & rotating properly. 
+* Fixed factor score trace plots by extracting indices of stored samples using `Rfast::sort_unique` and rotating properly. 
 * Fixed adding of `rnorm` columns to scores matrix during adaptation, esp. when widest loadings matrix grows/shrinks.
-* Fixed initialisation (& upper limit) of number of clusters for OM(I)FA/IM(I)FA, esp. when `N < P`.
-* Updates of DP/PY `alpha` parameter now correctly depend on current # non-empty rather than active groups.
+* Fixed initialisation (and upper limit) of number of clusters for OM(I)FA/IM(I)FA, esp. when `N < P`.
+* Updates of DP/PY `alpha` parameter now correctly depend on current # non-empty rather than active clusters.
 * Fixed density plots for parameters with bounded support, accounting for spike at zero for `discount`.
 * Slightly rearranged order Gibbs updates take place, esp. to ensure means enter simulation of uniquenesses properly.
 * Edited/robustified subsetting of large objects when storing `mcmc_IMIFA` output.
 * Tightened controls for when certain parameters are not stored for posterior inference.
 * Edited Ledermann upper bound `stop(...)` for finite factor models to `warning(...)`.
-* Geometric rather than arithmetic mean used in derivation of single rate hyperparameter for PPCA's isotropic uniquenesses.
+* Geometric rather than arithmetic mean used to derive single rate hyperparameter for PPCA's isotropic uniquenesses.
 * Uniquenesses now stored correctly for all clustering methods.
 * Indices of uncertain obs. returned (`get_IMIFA_results`)/printed (`plot.Results_IMIFA`) even when `zlabels` not supplied.
 * Fixed behaviour of progress bar when `verbose=FALSE`.
-* Fixed typos & expanded/clarified help documentation/vignette.
+* Fixed typos and expanded/clarified help documentation/vignette.
 
 # IMIFA v1.1.0 - (_1st release: 2017-02-02_)