Forum – Page 10

New function: plot.valid

New function plot.valid to display the results of the valid function
New code for imgCor function for a nicer representation of the correlation matrices
In predict function the argument 'method' were replaced by method = c("max.dist", "class.dist", "centroids.dist", "mahalanobis.dist")
The arguments dendrogram, ColSideColors and RowSideColors were added to the cim function
valid function can also been performed with missing values
Functions pls, plsda, spls and splsda were modified to identify zero- or near-zero variance predictors
The functions plotVar and plot3dVar were modified to represent only the X variables in the case of PLS-DA and SPLS-DA
The pca function has been improved so that the S3 methods plotIndiv, plot3dIndiv, plotVarand plot3dVar can be used with these new classe

plsda and splsda have been further improved so that all the S3 functions predict, print, plotIndiv, plot3dIndiv can be used with these new classes
Several prediction methods are now available to predict the classes of test data with plsda andsplsda, see argument 'method' (max.dist, class.dist, centroids.dist, mahalanobis.dist) in thepredict function

plsda and splsda functions are implemented to perform PLS Discriminant Analysis (PLS-DA) and sparse PLS-DA respectively
breast.tumors data set is introduced to illustrate the (s)PLS-DA
PCA can also been performed with missing values using the NIPALS algorithm and 3D plots are also available for PCA
Network (updated) to display relevant associations between variables for (r)CCA and (s)PLS, with a new similarity function
A new similarity measure has been included in cim function and the arguments hclusfuncand distfunc to display Clustered image maps (heatmaps)