[Vegan-commits] r477 - in branches/1.13: R inst man
noreply at r-forge.r-project.org
noreply at r-forge.r-project.org
Tue Aug 19 09:59:54 CEST 2008
Author: jarioksa
Date: 2008-08-19 09:59:54 +0200 (Tue, 19 Aug 2008)
New Revision: 477
Modified:
branches/1.13/R/ordiArgAbsorber.R
branches/1.13/R/plot.procrustes.R
branches/1.13/R/varpart.R
branches/1.13/inst/ChangeLog
branches/1.13/man/cascadeKM.Rd
branches/1.13/man/cca.Rd
branches/1.13/man/varpart.Rd
branches/1.13/man/vegan-internal.Rd
Log:
merges to branches/1.13: r434 (wider formula in varpart), r461
(ordiArgAbsorber knows 'const' arg), r472 (plot.procrustes failed with
identical configs), and doc updates r435 (cca, varpart), r465
(cascadeKM)
Modified: branches/1.13/R/ordiArgAbsorber.R
===================================================================
--- branches/1.13/R/ordiArgAbsorber.R 2008-08-15 00:03:18 UTC (rev 476)
+++ branches/1.13/R/ordiArgAbsorber.R 2008-08-19 07:59:54 UTC (rev 477)
@@ -1,3 +1,3 @@
`ordiArgAbsorber` <- function(..., shrink, origin, scaling, triangular,
- display, choices, FUN)
+ display, choices, const, FUN)
match.fun(FUN)(...)
Modified: branches/1.13/R/plot.procrustes.R
===================================================================
--- branches/1.13/R/plot.procrustes.R 2008-08-15 00:03:18 UTC (rev 476)
+++ branches/1.13/R/plot.procrustes.R 2008-08-19 07:59:54 UTC (rev 477)
@@ -20,10 +20,16 @@
abline(v = 0, lty = 2)
abline(h = 0, lty = 2)
if (ncol(x$rotation) == 2) {
- ## Sometimes rotation[1,1] is 2.2e-16 above one
- x$rotation[1,1] <- min(x$rotation[1,1], 1)
- abline(0, tan(acos(x$rotation[1, 1])), lty = 1)
- abline(0, 1/tan(acos(-x$rotation[1, 1])), lty = 1)
+ ## Draw rotated axes only if they visibly differ from
+ ## unrotated axes
+ b <- abs(x$rotation[1,1])
+ EPS <- 1e-8
+ if (1 - b > EPS && b > EPS) {
+ abline(0, tan(acos(x$rotation[1, 1])), lty = 1)
+ abline(0, 1/tan(acos(-x$rotation[1, 1])), lty = 1)
+ } else {
+ abline(v = 0, h = 0)
+ }
}
else {
Y <- x$Yrot %*% t(x$rotation)
@@ -59,4 +65,3 @@
}
invisible(out)
}
-
Modified: branches/1.13/R/varpart.R
===================================================================
--- branches/1.13/R/varpart.R 2008-08-15 00:03:18 UTC (rev 476)
+++ branches/1.13/R/varpart.R 2008-08-19 07:59:54 UTC (rev 477)
@@ -40,9 +40,8 @@
out$transfo <- transfo
out$call <- match.call()
mx <- rep(" ", length(X))
- for (i in 1:length(X)) mx[i] <- deparse(out$call[[i+2]])
+ for (i in 1:length(X)) mx[i] <- deparse(out$call[[i+2]], width.cutoff = 500)
out$tables <- mx
class(out) <- c("varpart", class(out))
out
}
-
Modified: branches/1.13/inst/ChangeLog
===================================================================
--- branches/1.13/inst/ChangeLog 2008-08-15 00:03:18 UTC (rev 476)
+++ branches/1.13/inst/ChangeLog 2008-08-19 07:59:54 UTC (rev 477)
@@ -1,5 +1,3 @@
-
-
$Date$
VEGAN DEVEL VERSIONS at http://r-forge.r-project.org/
@@ -25,6 +23,19 @@
* merged r453: ordiArgAbsorber knows about 'choices' and 'display'
args of function scores().
+ * merged r434: wider formula cutoff in varpart.
+
+ * merged r435: cca & varpart doc tells that formula accepts
+ matrices.
+
+ * merged r461, 462: ordiArgAbsorber learnt about 'const' arg in
+ scores.rda.
+
+ * merged r465: cascadeKM doc update.
+
+ * merged r472: fix procrustes plot failure with identical
+ configurations.
+
Version 1.13-1 (released June 11, 2008)
* adonis: speed-up and doc updates.
Modified: branches/1.13/man/cascadeKM.Rd
===================================================================
--- branches/1.13/man/cascadeKM.Rd 2008-08-15 00:03:18 UTC (rev 476)
+++ branches/1.13/man/cascadeKM.Rd 2008-08-19 07:59:54 UTC (rev 477)
@@ -68,7 +68,8 @@
The default value is \code{"calinski"}, which refers to the well-known
Calinski-Harabasz (1974) criterion. The other available index is the
- simple structure index \code{"ssi"}. In the case of groups of equal
+ simple structure index \code{"ssi"} (Dolnicar et al. 1999).
+ In the case of groups of equal
sizes, \code{"calinski"} is generally a good criterion to indicate the
correct number of groups. Users should not take its indications
literally when the groups are not equal in size. Type \code{"all"} to
@@ -82,13 +83,10 @@
is simply an \eqn{F} (ANOVA) statistic.
\item \bold{ssi}:
- this "Simple Structure Index"
- combines three elements which influence the interpretability of a
- solution, i.e., the maximum difference of each variable between the
- clusters, the sizes of the most contrasting clusters and the
- deviation of a variable in the cluster centers compared to its
- overall mean. These three elements are multiplicatively combined and
- normalized to give a value between \eqn{0} and \eqn{1}.
+ the \dQuote{Simple Structure Index} multiplicatively combines
+ several elements which influence the interpretability of a
+ partitioning solution. The best partition is indicated by the
+ highest SSI value.
}
In a simulation study, Milligan and Cooper (1985) found
@@ -148,6 +146,12 @@
Calinski, T. and J. Harabasz. 1974. A dendrite method for cluster
analysis. \emph{Commun. Stat.} \strong{3}: 1-27.
+
+ Dolnicar, S., K. Grabler and J. A. Mazanec. 1999. A tale of three
+ cities: perceptual charting for analyzing destination images. Pp.
+ 39-62 in: Woodside, A. et al. [eds.] \emph{Consumer psychology of
+ tourism, hospitality and leisure}. CAB International, New York.
+
Gower, J. C. 1966. Some distance properties of latent root and vector
methods used in multivariate analysis. \emph{Biometrika} \strong{53}:
Modified: branches/1.13/man/cca.Rd
===================================================================
--- branches/1.13/man/cca.Rd 2008-08-15 00:03:18 UTC (rev 476)
+++ branches/1.13/man/cca.Rd 2008-08-19 07:59:54 UTC (rev 477)
@@ -86,7 +86,9 @@
The constraints can contain ordered or unordered factors,
interactions among variables and functions of variables. The defined
\code{\link{contrasts}} are honoured in \code{\link{factor}}
- variables. The formula can include a special term \code{Condition}
+ variables. The constraints can also be matrices (but not data
+ frames).
+ The formula can include a special term \code{Condition}
for conditioning variables (``covariables'') ``partialled out'' before
analysis. So the following commands are equivalent: \code{cca(X, Y,
Z)}, \code{cca(X ~ Y + Condition(Z))}, where \code{Y} and \code{Z}
Modified: branches/1.13/man/varpart.Rd
===================================================================
--- branches/1.13/man/varpart.Rd 2008-08-15 00:03:18 UTC (rev 476)
+++ branches/1.13/man/varpart.Rd 2008-08-19 07:59:54 UTC (rev 477)
@@ -255,7 +255,9 @@
mite.hel <- decostand(mite, "hel")
mod <- varpart(mite.hel, mm1, mm2, mite.pcnm)
# Use RDA to test fraction [a]
-rda.result <- rda(mite.hel, mm1, cbind(mm2, mite.pcnm))
+# Matrix can be an argument in formula
+rda.result <- rda(mite.hel ~ mm1 + Condition(mm2) +
+ Condition(as.matrix(mite.pcnm)))
anova(rda.result, step=200, perm.max=200)
# Four explanatory tables
Modified: branches/1.13/man/vegan-internal.Rd
===================================================================
--- branches/1.13/man/vegan-internal.Rd 2008-08-15 00:03:18 UTC (rev 476)
+++ branches/1.13/man/vegan-internal.Rd 2008-08-19 07:59:54 UTC (rev 477)
@@ -18,7 +18,7 @@
ordiTerminfo(d, data)
ordiArrowMul(x, at = c(0,0), fill = 0.75)
ordiArgAbsorber(..., shrink, origin, scaling, triangular,
- display, choices, FUN)
+ display, choices, const, FUN)
centroids.cca(x, mf, wt)
permuted.index(n, strata)
pasteCall(call, prefix = "Call:")
More information about the Vegan-commits
mailing list