goodness.of.fit.runGMCM() for a local instance.classify() function to ease classification after
fitting a general GMCM.EMAlgorithm is now exported to the user
interface with slight tweaks. Better docs and examples are also
provided.as.theta() and fixed issue
incorrect default axis labels in plot.theta.vector2theta and theta2vector) causing the
first anchored component to be scaled slightly incorrectly. Note, fitted
results will be changed compared to earlier versions (although hopefully
not much).S3 object of class
theta and print.theta(),
summary.theta(), and plot.theta() functions
have been made to fit the usually expected generic functions.rtheta has been updated substantially to allow for
finer and more explicit control if needed. Default is the old
behavior.anyNA on R versions older than 3.1.0).EStep has been implemented in Rcpp and
thus GMCM now features a faster pseudo EM algorithm.rmvnormal and dmvnormal are now
exported and visible to the user. These are now both implemented in and
are faster versions of rmvnorm and dmvnorm
from .verbose and
max.ite in fit.meta.GMCM has been swapped to
make it consistent with fit.full.GMCM. Apologies for any
inconveniences.get.idr is no longer exported and visible to the user.
Use get.IDR to get the local (posterior class
probabilities) and adjusted irreproducibility discovery rates
(IDR).pgmm_marginal and other functions in
src/GMCM.cpp have been rewritten to address memory issues.
should now be more stable and faster.
Need a high-speed mirror for your open-source project?
Contact our mirror admin team at info@clientvps.com.
This archive is provided as a free public service to the community.
Proudly supported by infrastructure from VPSPulse , RxServers , BuyNumber , UnitVPS , OffshoreName and secure payment technology by ArionPay.