- update math/R to 2.15.0, and adjust dependent ports
- minor changes to bsd.cran.mk [2]: rename MASTER_CRAN_SITES to
MASTER_SITE_CRAN, as in bsd.sites.mk; make the install target more
flexible and allow CRAN ports to override it; add a regression-test
target; set USE_FORTRAN to match math/R; remove some of the
redundant checks of USE_R_MOD; honor NOPORTDATA and NOPORTDOCS
Reviewed by: thierry, tota, wen
Approved by: D. Rue (maintainer) [1], wen [2]
to Mk/bsd.cran.mk
PR: ports/162238
Submitted by: tota (myself)
Approved by: wen (maintainer of Mk/bsd.cran.mk and many related ports),
David Naylor <naylor_DOT_b_DOT_david_AT_gmail_DOT_com>
(maintainer of math/R-cran-RSvgDevice and math/R-cran-car),
Dan Rue <drue_AT_therub_DOT_org>
(maintainer of math/R-cran-psych, timeout > 2 weeks)
Feature safe: yes
includes workarounds intended to fix the broken sparc64
build, and fixes to the static libR, which is now in a
separate slave port, math/libR)
PR: 158947 [1]
Submitted by: wen ([1], independently)
- switch to the bundled Rblas and Rlapack by default (this
can be changed by setting BLAS and LAPACK) which favors
correctness in some corner cases over a slight performance
penalty; this will be revisited after the blas and lapack
updates
- replace the STATIC_LIBR option with a LIBR option (on
by default): if on, libR.a and libR.so are installed,
and R is linked to libR.so. Otherwise, R is static, and
no libRs are installed.
- remove the superfluous copy of libR.so in ${LOCALBASE}/lib [1]
- enable the cairo and pango elements in the X11() graphics
device by default, controlled by new PANGOCAIRO option
- add a few small patches to dependent ports, bumping
PORTREVISION where necessary
PR: 153309 [1]
Approved by: thierry (rkward*), wen (rpy*, R-cran-*)
applications. The package includes: Bayes Regression (univariate or
multivariate dep var), Bayes Seemingly Unrelated Regression (SUR), Binary and
Ordinal Probit, Multinomial Logit (MNL) and Multinomial Probit (MNP),
Multivariate Probit, Negative Binomial (Poisson) Regression, Multivariate
Mixtures of Normals (including clustering), Dirichlet Process Prior Density
Estimation with normal base, Hierarchical Linear Models with normal prior and
covariates, Hierarchical Linear Models with a mixture of normals prior and
covariates, Hierarchical Multinomial Logits with a mixture of normals prior
and covariates, Hierarchical Multinomial Logits with a Dirichlet Process
prior and covariates, Hierarchical Negative Binomial Regression Models,
Bayesian analysis of choice-based conjoint data, Bayesian treatment of linear
instrumental variables models, and Analysis of Multivariate Ordinal survey
data with scale usage heterogeneity (as in Rossi et al, JASA (01)).
WWW: http://www.perossi.org/home/bsm-1
