News for Package rebmix

Changes in version 2.16.0

• Some minor changes and bug fixes in C++ and R codes.

• Improved C++ code for handling warnings and errors.

• Improved C++ functions RoughEstimationKNN(), RoughEstimationKDE() and RoughEstimationH().

• Additional argument Mode enters function REBMIX.

• Improved C++ functions GlobalModeKNN(), GlobalModeKDE() and GlobalModeH().

Changes in version 2.15.0

• Method "labelmoments" is added.

• Method "mergelabels" is added.

• Adjacency matrix A slot is added to "RCLRMIX" class.

• Improved C++ functions CombineComponentsEntropy() and CombineComponentsDemp().

Changes in version 2.14.2

• Valgrind problems have been resolved.

Changes in version 2.14.1

• Class "Histogram" is added.

• Methods "chistogram", "fhistogram" and mapclusters are added.

• Argument y0 is removed from REBMIX, bins, optbins methods and from class "REBMIX".

• The C++ function REBMIXK() is added. It is called by the REBMIX method if the argument Dataset contains objects of type "Histogram".

• Numerous minor changes and debugging in C++ and R codes required due to the above changes.

• Methods "demix", "dfmix", "pemix", "pfmix" and all information criterion methods are modified for class "Histogram".

Changes in version 2.14.0

• The package has been extended to three parametric family types.

• Improved C++ functions REBMIXKNN(), REBMIXKDE() and REBMIXH().

• Method plot is debugged and improved.

• Value "cdf" is added to what argument.

• Class "EMMIX.Theta" is added.

• Method EMMIX is added.

Changes in version 2.13.1

• Reduced size of the vignette.

• Conditional jump or move depends on uninitialised value(s.

Changes in version 2.13.0

• Method plot is debugged and improved.

• Improved C++ functions REBMIXKNN(), REBMIXKDE() and REBMIXH().

• EM algorithm is added to the C++ code for the improved estimation of all mixture model parameters.

• Updated examples.

Changes in version 2.12.0

• Value "density" is replaced by "pdf" in what argument.

• Value "marginal" is replaced by "marginal pdf" in what argument.

• Value "distribution" is replaced by "marginal cdf" in what argument.

• Improved C++ functions regarding memory allocation and efficiency.

• Improved outlier detection.

• "Knuth equal" and "Knuth unequal" binning rules are added to the existing "Sturges", "Log10" and "RootN" rules.

• Method plot is improved.

• Method RCLRMIX is debugged and improved.

• Method REBMIX is debugged and improved.

• Method bins is added.

• Method optbins is added.

• Fixed bugs in C++ and R code.

Changes in version 2.11.0

• Method split is improved.

• Improved C++ functions REBMIXKNN(), REBMIXKDE() and REBMIXH().

• Method RCLSMIX is improved.

• Method plot is improved.

• Continuous parametric family "Gumbel" is added.

• EM algorithm is added to the C++ code for the improved estimation of the Gaussian mixture model parameters.

• Class EM.Control is added for EM algorithm control parameters handling.

Changes in version 2.10.3

• Method Zp is replaced by a.Zp accessor method.

• Method coef is replaced by a.theta1.all and a.theta2.all accessor methods.

• Accessor methods are added for all slots.

• Class "RNGMIX.Theta" is added.

• Method show is added for "RCLS.chunk" class.

• Minimum number of component cmin is added to REBMIX arguments.

• Minimum number of component cmin slot is added to "REBMIX" class.

• Improved C++ functions REBMIXKNN(), REBMIXKDE() and REBMIXH().

• Preprocessing "Parzen window" is renamed to "kernel density estimation".

• Rough parameter estimation for binomial and Poisson parametric families is improved.

• Latent class analysis is added.

Changes in version 2.10.2

• Method split is improved.

• Fixed GCC 8.1 notes and warnings in C++ functions.

Changes in version 2.10.1

• Fixed numerical problems related to high dimensional datasets.

• Fixed bug in REBMIX method.

• Improved C++ functions REBMIXKNN(), REBMIXPW() and REBMIXH().

• Improved C++ functions RoughEstimationKNN(), RoughEstimationPW() and RoughEstimationH().

Changes in version 2.10.0

• Fixed bug in plot method.

• Additional argument rseed enters boot method.

• Maximum number of nonempty bins has been introduced in C++ to avoid histograms with excessive number of nonempty bins.

Changes in version 2.9.3

• Acceleration rate has been improved. It is now progressively increasing.

• The Newton-Raphson root finding in C++ functions has been improved. It affects only "Weibull", "gamma" and "vonMises" parametric families.

Changes in version 2.9.2

• Continuous circular parametric family "vonMises" is added.

• Fixed bug in C++ function REBMIXH.

• Improved C++ functions InformationCriterionKNN(), InformationCriterionPW() and InformationCriterionH().

• Improved C++ functions EnhancedEstimationKNN(), EnhancedEstimationPW() and EnhancedEstimationPW().

Changes in version 2.9.1

• Properly registered native routines and disabled symbol search in C++ code.

Changes in version 2.9.0

• Fixed bugs in RCLRMIX method.

Changes in version 2.8.4

• Method Zp is added.

• Fixed bugs in plot method.

• Fixed bugs in split method.

• Fixed bugs in RCLRMIX method.

• Fixed bugs in RCLSMIX method.

• Improved C++ functions GlobalModeKNN(), GlobalModePW() and GlobalModeH().

• Improved C++ functions REBMIXKNN(), REBMIXPW() and REBMIXH().

Changes in version 2.8.3

• Fixed convergence bug in C++ code.

• Bayes classification is improved by introducing outliers.

• Method plot is improved.

• Fixed bug in C++ functions RoughEstimationKNN(), RoughEstimationPW() and RoughEstimationH().

• Improved C++ functions GlobalModeKNN(), GlobalModePW() and GlobalModeH().

Changes in version 2.8.2

• Fixed information criterion bug in C++ and R code.

• Fixed heap block freed with an inappropriate deallocation function bug in C++ code.

• Method plot is improved.

• Methods demix, dfmix, pemix and pfmix are improved.

• Methods split, chunk and BFSMIX are added.

• Renewed vignette.

Changes in version 2.8.1

• Fixed isnan and isinf bug in C++ code.

• Fixed invalid object bug in vignette.

Changes in version 2.8.0

• Object-oriented C++ code is improved considerably.

• R code is extended and rewritten in S4 class system.

• Multivariate normal parametric family with unrestricted variance-covariance matrices is enabled.

• Classification is improved.

• Clustering is added.

• Datasets iris is added.

• Renewed vignette.

• Fixed bug in C++ functions RoughLognormalParameters(), RoughWeibullParameters() and RoughGammaParameters().

Changes in version 2.7.2

• Switch _TIME_LEFT_SWITCH is eliminated from C code.

• C code is converted into object-oriented C++ code.

• Fixed no visible global function definition bug in NAMESPACE file.

• Renewed vignette.

Changes in version 2.7.1

• Demos rebmix.galaxy, rebmix.univariate.normal, rebmix.mixed.continuous.discrete and rebmix.multivariate.normal are changed.

Changes in version 2.7.0

• Fixed title field in DESCRIPTION file.

• Fixed S3 generic/method consistency bug in NAMESPACE file.

• Fixed line endings in Makevars file.

• Fixed \VignetteKeyword entries bug in vignette.

• Method predict.list is converted to function RCLSMIX.

• Method boot is converted to function boot.REBMIX.

• Method plot is improved.

• Function kseq is improved.

• Function REBMIX is improved.

• Total of positive relative deviations D is eliminated from REBMIX arguments.

• Value "c" is eliminated from what argument.

• Value "K" is added to what argument.

• Fixed bug in C functions InformationCriterionKNN(), InformationCriterionPW() and InformationCriterionH().

• Fixed bug illegal characters found in URL.

• Methods AIC, AIC3, AIC4, AICc, CAIC, BIC, HQC, MDL2, MDL5, AWE, CLC, ICL, ICLBIC, PRD, SSE and PC are converted to functions with the same names.

• Renewed vignette.

Changes in version 2.6.2

• Demos rebmix.galaxy, rebmix.univariate.normal, rebmix.mixed.continuous.discrete, rebmix.multivariate.normal, rebmix.weibullnormal and rebmix.truck are added.

• Datasets weibullnormal and truck are added.

• Method boot.REBMIX for bootstrap is improved.

• Function kseq for sequence of bins or nearest neighbours generation is added.

• Additional argument y0 enters function REBMIX.

• Improved treatment of accuracy Eps in C functions.

• Fixed bug in C functions EnhancedEstimationKNN(), EnhancedEstimationPW() and EnhancedEstimationH().

Changes in version 2.6.1

• Renewed vignette.

• Renewed references in Reference manual.

• Method PD is added.

• Fixed bug in C functions REBMIXKNN(), REBMIXPW() and REBMIXH().

Changes in version 2.6.0

• Switch _TIME_LEFT_SWITCH introduced in C code.

• Simplified treatment of loose restraints in C functions RoughEstimationKNN(), RoughEstimationPW() and RoughEstimationH().

• Fixed bug in C functions REBMIXKNN(), REBMIXPW() and REBMIXH().

• Minimum weight multiplier b is eliminated from REBMIX arguments.

• Fixed source and destination overlap in memcpy bug in C code.

Changes in version 2.5.1

• Fixed checking top-level files.

• Fixed checking for old-style vignette sources.

• Packages mixtools and mclust excluded from vignette.

Changes in version 2.5.0

• Rough parameter estimation is improved by introducing constrained entropy maximization.

• Fixed bug in C functions RoughEstimationKNN(), RoughEstimationPW() and RoughEstimationH().

• Fixed bug in boot.REBMIX method.

Changes in version 2.4.2

• Fixed symbol eating bug for Mac OS X.

Changes in version 2.4.1

• Continuous parametric family "gamma" is added.

Changes in version 2.4.0

• Methods AIC, AIC3, AIC4, AICc and CAIC are added.

• Method AWE is added.

• Method BIC is added.

• Method boot.REBMIX for bootstrap is added.

• Method CLC is added.

• Function demix for empirical density calculation is added.

• Function dfmix for predictive density calculation is added.

• Method HQC is added.

• Method ICL is added.

• Method ICLBIC is added.

• Method logL is added.

• Methods MDL2 and MDL5 are added.

• Function pemix for empirical distribution function calculation is added.

• Function pfmix for predictive distribution function calculation is added.

• Function plot.REBMIX is extended. It enables besides "pdf" plots also "marginal pdf", "c", "IC", "logL", "D" and "marginal cdf" plots.

• Additional arguments what enters method plot.REBMIX.

• Method PRD is added.

• Methods print.boot.REBMIX and summary.boot.REBMIX are added.

• Method SSE is added.

• Dataset weibull is added.

Changes in version 2.3.0

• Discrete parametric families "binomial", "Poisson" and "Dirac" are added.

• Information criteria "D" and "SSE" are added.

• Methods print.RNGMIX, print.REBMIX, coef.REBMIX and summary.REBMIX are added.

• Method predict.list for class membership prediction is added.

• The package does not write to stdout and read from stdout any more.

• The package is protected against wrong input arguments.

• Additional arguments Variables, theta1, theta2, ymin, ymax and b enter function REBMIX.

• Minimum radius RMIN is eliminated.

• Simplified treatment of global modes with equal probabilities in C functions GlobalModeKNN(), GlobalModePW() and GlobalModeH().

• Improved treatment of potentially singular solutions in C functions EnhancedEstimationKNN(), EnhancedEstimationPW() and EnhancedEstimationH().

• Improved convergence criteria in C functions REBMIXKNN(), REBMIXPW() and REBMIXH().

• Fixed bug in C function PreprocessingPW().

• Fixed bug in C functions RoughEstimationKNN(), RoughEstimationPW() and RoughEstimationH().

• Fixed bug in plot.REBMIX method.

• Dataset adult is added.