(September 2026)
ggplot2 is now the default plotting engine. plot() gains an engine argument, which takes "ggplot2" or "base".gg_biplot() builds a biplot as a ggplot object.autoplot() method for biplot objects, plus print(), plot() and + methods for the resulting gg_biplot objects. The + method lets you add your own ggplot2 layers.MCA() function for multiple correspondence analysis biplots. The indicator matrix variant is available in this release.fit.measures() now reports overall quality for MCA biplots.CatPCA() function for categorical PCA biplots, with nom.axes() and ord.axes() to format nominal and ordinal axes.plot() gains an add argument, so a biplot can be drawn on top of an existing plot.axes(), newaxes(), nom.axes() and ord.axes() gain label.dir = "Along", which places each axis title alongside its axis line, rotated to the slope of the axis. The default label.dir is now NULL, meaning "Along" with the ggplot2 engine and "Orthog" with base graphics.biplot object now stores p2, the number of categorical variables.PCA() and CA() documentation.CATPCA() has been renamed to CatPCA().axes_coordinates() is no longer exported.biplot() now stops with an error if a numeric variable has zero standard deviation.ggplot2. Some features are not supported by the ggplot2 engine yet and fall back to base graphics with a warning. These are zooming, 1D and 3D biplots, CatPCA() nominal and ordinal axes, and spline axes.ggplot2 engine.legend.type(new = TRUE) is a base graphics feature only. The ggplot2 engine always places the legend next to the biplot.newsamples() for CA biplots in base graphics.legend.type() for the ggplot2 engine.ggrepel is no longer used in base graphics plotting.Princ and Stand.PCA() when group.aes is specified in biplot() or PCA().alpha.bags() colours inherited from samples().Rcpp. The call to optim() was replaced by a Nelder-Mead routine written in C++.Depends: R (>= 3.6.0) added.Rcpp added to Imports and LinkingTo.RColorBrewer added to Suggests. grid, R.devices and testthat removed.(November 2024)
axes_coordinates() and CLRs() (format aesthetics for category level regions).which in samples().AoD() and spline axes.biplot.spline.axis() and plot3D() are no longer exported.print.CA() S3 method removed.(September 2024)
CLPs() (format aesthetics for category level points) and biplot.spline.axis() for nonlinear (spline) biplot axes, added as compiled Fortran code.which/exp.factor fixes for CA().(July 2024)
CA() for correspondence analysis biplots.CATPCA() for categorical PCA biplots.PCO() for principal coordinate analysis biplots and regress() for regression biplots, plus AoD() for biplots based on the Analysis of Distance method.classification()/classify() for classification regions, and prediction() for CVA and PCA biplots.density1D() and density2D() for density clouds.newaxes(), translate_axes(), rotate() and reflect() for constructing and transforming biplot axes.extended.matching.coefficient() and sqrtManhattan() distance measures, and plot3D() for 3D biplots.group.aes.ggrepel error when group 1 is not plotted.which eliminated axes.fit.measures().useDynLib().ggplot2/ggrepel/grid-based plotting groundwork from 1.2.0 was removed; plotting remained base-graphics only.(December 2023)
newsamples(), interpolate(), means(), fit.measures() and a summary() method for biplot objects.concentration.ellipse() renamed to ellipses().prcomp and princomp support as input to PCA().samples() gains a which argument and label.col.(October 2023)
inherits() for class checks.Initial CRAN submission. (August 2023)