Changes in version 2.1.8.2 (2026-02-05)                 

Misc

    o   Patch ../tests/clara-NAs.R and ../tests/mona.R and their
	*.Rout.save to adapt to R-devel (to be R 4.6.0)'s different
	summary() using "NAs" instead of "NA's".  To get these working
	in both R <= 4.5.x and R >= 4.6.0, also need to adapt the print
	width options(width = *).

                Changes in version 2.1.8.1 (2025-03-12)                 

Misc

    o   use complete argument names in most cases to satisfy lovers of
	options(warnPartialMatch* = TRUE).

    o   using \(.) would need R >= 4.1.0.

                 Changes in version 2.1.8 (2024-12-11)                  

Bug Fixes

    o   C codes underlying agnes() and daisy() under UBSAN and LTO no
	longer show pointer expression overflow (of a length 0 vector a
	with a-- call).

                 Changes in version 2.1.7 (2024-12-08)                  

Misc

    o   man/pam.Rd set.seed() for _data_, hence reproducible example.

    o   src/daisy.c and src/dysta.c produced from their Fortran *.f
	versions by f2c, my perl script f2c-clean and manual pretty
	editing.
	
	C function dysta() now returns the jhalt "flag"; it is no
	longer callable from R, nor is dysta3() which is 'static' now,
	in src/fanny.c.
	
	*Goal*: Use .Call() instead of .C() and hence allow long
	vectors for the length n(n-1)/2 distance vectors.

    o   fanny-ex.R tests: use IGNORE_RDIFF_BEGIN .. and some explicit
	cheks to become less platform dependent.

                 Changes in version 2.1.6 (2023-12-01)                  

Bug Fixes

    o   clara(*, metric="gower") is too buggy, and hence *removed* for
	now, see below (2.1.5).

Misc

    o   tweak tests/fanny-ex.{R,Rout.save} for less "diffs".

                 Changes in version 2.1.5 (2023-11-27)                  

New Features

    o   pam() and clara() also accept a logical matrix as input.

    o   clara() gets new metric = "gower" donated by Kasper
	Fischer-Rasmussen.  - was removed in 2.1.6 because of
	valgrind-detected memory leaks (and problems/bugs found earlier
	in R experiments).

Misc

    o   renamed internal function silhouette.default.R to silhouetteR.

    o   CITATION switched from old citEntry() to bibentry().

    o   clara(*, trace = <pos>) prints slightly better info.

    o   DESCRIPTION gets Enhances: for packages cross-referenced in
	man/*.Rd.

                 Changes in version 2.1.4 (2022-08-22)                  

New Features

    o   New medoids() to compute pam-consistent medoids, given a
	clustering (and data).

Bug Fixes

    o   help(dissimilarity.object) now correctly describes the meaning
	of a method = "gower" result type "T".  Also, help(daisy) now
	extensively documents the different options for type = *,
	notably "ordratio" and "logratio".

    o   pam(x, diss=TRUE) uses inherits(x, "dissimilarity") instead of
	semi-deprecated data.class(x) == "dissimilarity") to check.

    o   Using deparse1() from R version 4.0.0 and newer (even when
	cluster is installed into an older versions of R), e.g., in
	plot default titles.

                 Changes in version 2.1.3 (2022-03-28)                  

New Features

    o   as.data.frame(<silhouette>) now works; suggested by Jonathan
	Marshall (@Massey, NZ).

Translations

    o   Updated German translations (Detlef Steuer)

Tweaks

    o   use explicit cast, quieting -Wconversion.

                 Changes in version 2.1.2 (2021-04-17)                  

New Features

    o   Updated the Italian translations (by Daniele Medri), the French
	(by Philippe Grosjean) and the German (by Detlef Steuer).  New
	Lithuanian translations by Gabriele Stupuriene & Rimantas
	Zakauskas.

                 Changes in version 2.1.1 (2021-02-14)                  

New Features

    o   Added Italian translations from Daniele Medri, and updated the
	French ones from Philippe Grosjean.

    o   clara() gains a cluster.only argument, entirely “in parallel”
	to pam().

    o   the silhouette() method for clara now allows full to be a
	number in [0,1] instead of just a logical and it gains gains
	new optional argument subset to specify the indices of
	observations for which silhouette values shold be computed.

    o   Faster pam() - ‘fasterPAM’ from Erich Schubert.  New optional
	arguments medoids = "random", nstart, and variant, notably
	variant = "faster".

                 Changes in version 2.1.0 (2019-06-19)                  

Bug Fixes

    o   volume(obj) is now correct also for ellipsoids of dimension d >
	2.

    o   --enable-lto compilation revealed missing weights argument in
	src/cluster.h's declaration of cldaisy().

Tweaks

    o   Replaced many “old style” `<word>' quotations.

                 Changes in version 2.0.9 (2019-05-01)                  

Tweaks

    o   src/mona.c now uses correct _void_ F77_NAME and source cleaned.

                 Changes in version 2.0.8 (2019-04-05)                  

New Features

    o   pam() gets new pamonce options, for values 3, 4, or 5, choosing
	versions of fastpam, contributed by Erich Schubert, Univ.
	Dortmund.

    o   update tests/* to work with R >= 3.6.0 (sample.kind)

Bug Fixes

    o   correct thinko in ?clusGap, the help page.

                 Changes in version 2.0.7 (2018-04-01)                  

New Features

    o   clara() gets new option metric = "jaccard", contributed by
	Kamil Kozlowski and Kamil Jadszko.

    o   pam() and clara() use match.arg(metric) and hence metric can be
	abbreviated (and invalid strings give an error instead of being
	interpreted as "euclidean").

Bug Fixes

    o   The bug fix of clara(*, correct.d = TRUE) (from version 2.0.4)
	for the NA-data case now also applies to the internal C
	function selec().

                 Changes in version 2.0.6 (2017-03-16)                  

New Features

    o   mona() now C- instead of Fortran-based (having used f2c etc)
	and now has a trace.lev option which allows progress reporting
	“remembers” if the original data had missing values.

Bug Fixes

    o   mona(<1-column>) no longer loops infinitely but signals an
	error.

                 Changes in version 2.0.5 (2016-10-08)                  

New Features

    o   clusGap() gets a new option scaleH0, and scaleH0 = "original"
	is an alternative to the default PCA rotation.

    o   clusGap() now also stores its call and uses that for print()ing
	and (by default in the main title) for plot()ing "clusGap"
	objects.

    o   
	__ MOSTLY NOT IMPLEMENTED yet __
	
	diana() gets new optional argument stop.at.k.  When a positive
	integer, the DIANA algorithm will stop early, as much desirable
	for large n.

Bug Fixes

    o   daisy() gets 3+1 new options warn* which allow to suppress
	three different kind of warnings, as these are undesirable in
	some cases.  With thanks to Kirill Müller for the convincing
	context.

    o   pam() now signals an error when there are more than 65536
	observational units (whereas it could segfault previously),
	thanks to a patch from Mikko Korpela, Helsinki.

                 Changes in version 2.0.4 (2016-04-18)                  

New Features

    o   clusGap() gets a new option d.power = 1 allowing to choose the
	basic weight statistic as it was originally proposed, namely
	_squared_ distances by setting d.power = 2.

Bug Fixes

    o   fix small glitch in silhouette's help page.

    o   Finally fixed a bug (in the original Fortran code from
	Rousseeuw!) in clara's distance computation when there are NAs
	in the data.  As the fix is not backward compatible, a warning
	is produced (for the time being) if there _are_ NAs and the
	user does not explicitly use clara(*, correct.d = TRUE).

                 Changes in version 2.0.3 (2015-07-21)                  

New Features

    o   This new NEWS.Rd file - going to replace ChangeLog eventually.

Bug Fixes

    o   import all we need (but not more) from the "base" pkgs (stats,
	graphics, ...).

                 Changes in version 2.0.2 (2015-06-19)                  

New Features

    o   using new anyNA() where appropriate.

    o   New Korean translations, thanks to Chel Hee Lee.

    o   plotpart(): cmdscale() tweaks.

Bug Fixes

    o   valgrind detected missing allocation (nisol["1"] for k=1).

    o   typo R/daisy.q (R bug PR#16430).

                 Changes in version 2.0.1 (2015-01-31)                  

Bug Fixes

    o   Fix silhouette( obj ) for obj <- pam(x, k = 1).

                 Changes in version 2.0.0 (2015-01-29)                  

New Features

    o   pam() now using .Call() instead of .C() is potentially
	considerably more efficient.

    o   agnes() has improved trace behaviour; also, some invalid
	par.method = * settings now give an early and understandable
	error message.

    o   lower.to.upper.tri.inds() (etc) now returns integer.

Bug Fixes

    o   .C(..) and .Fortran(..): no longer using DUP=FALSE as that has
	become deprecated.

                 Changes in version 1.15.3 (2014-09-04)                 

New Features

    o   agnes() and diana() finally get, respectively work with a
	trace.lev option.

    o   plot.(agnes|diana)() now deals well with long calls, by using
	multiple title lines.

    o   Message translations now also for C level error messages.

Bug Fixes

    o   agnes(*, method="flexible", par.method = c(a1, a2, b, c)),
	i.e., length(alpha) == 4, finally works _correctly_.

                 Changes in version 1.15.2 (2014-03-31)                 

New Features

    o   Rewrote parts of the R level messages so they are more easily
	translatable, thanks to proposals by Lukasz Daniel.

    o   French translations from Philippe Grosjean.

                 Changes in version 1.15.1 (2014-03-13)                 

Bug Fixes

    o   mona example not working in R < 3.0.x.

                 Changes in version 1.15.0 (2014-03-11)                 

New Features

    o   agnes(*, method = "gaverage") contributed by Pierre Roudier.

    o   documentation improvements;

    o   better translatable messages and translation updates.

                 Changes in version 1.14.4 (2013-03-26)                 

Tweaks

    o   2 de translations; update mona.Rout.save

                 Changes in version 1.14.3 (2012-10-14)                 

New Features

    o   Polnish translations from Lukasz Daniel.

Misc

    o   Tweaks for translations.

    o   Improve clusGap() examples.

                 Changes in version 1.14.2 (2012-02-08)                 

New Features

    o   New clusGap() to compute the “cluster Gap” goodness-of-fit
	statistic.

    o   Export coefHier()

    o   as.dendrogram() now for "twins", not just "agnes".

                 Changes in version 1.14.1 (2011-10-17)                 

New Features

    o   First translations (into German, thanks to Detlef Steuer).

    o   better citation("cluster")

Bug Fixes

    o   plot.silhouette(..., col = <one per cluster>) had ordering bug.

                 Changes in version 1.14.0 (2011-06-08)                 

New Features

    o   Make clara() more pam()-like; provide pamLike = * option.

    o   clusplot.default() re-factored; use new mkCheckX(); new args
	add = FALSE, cex, cex.txt.

Bug Fixes

    o   agnes( <n=1> ): correct error now.

                 Changes in version 1.2-1 (1999-12-05)                  

Many historical releases

    o   60 more CRAN releases of the package cluster from Dec 1999 to
	Feb 2011, see also the ChangeLog file and svn log.

                 Changes in version 1.2-0 (1999-04-12)                  

First CRAN release of the 'cluster' package, by Kurt Hornik

    o   Martin Maechler had its own version independently.

    o   Both closely modeled after clus the tarball off JSS.

R Functions - Fortran Files

    o   agnes() - twins.f for the “twins” agnes and diana.

    o   clara() - clara.f

    o   daisy() - daisy.f (and meet.f)

    o   diana() - (twins.f)

    o   fanny() - fanny.f

    o   mona() - mona.f

    o   pam() - pam.f

Data Sets

    o   agriculture

    o   animals

    o   flower

    o   ruspini

    o   votes.repub

Further Features

    o   all Examples in man/*.Rd hand edited to become executable.

    o   summary(), print() (and print.summary.**() methods) for the six
	basic R functions above.

                        Changes in version 1.1-2                        

Renamed previous 'clus' to 'cluster'

    o   .

                        Changes in version 1.1-1                        

New Features

    o   started ChangeLog