R/matnormlda.R
predict.matrixlda.RdClassify matrix variate observations in conjunction with matrixlda.
# S3 method for class 'matrixlda'
predict(object, newdata, prior = object$prior, ...)object of class matrixlda
array or list of new observations to be classified.
If newdata is missing, an attempt will be made to retrieve the
data used to fit the matrixlda object.
The prior probabilities of the classes, by default the
proportions in the training set or what was set in the call to
matrixlda.
arguments based from or to other methods
Returns a list containing the following components:
classThe MAP classification (a factor)
posteriorposterior probabilities for the classes
This function is a method for the generic function predict() for
class "matrixlda". It can be invoked by calling predict(x) for
an object x of the appropriate class.
set.seed(20180221)
# construct two populations of 3x4 random matrices with different means
A <- rmatrixnorm(30, mean = matrix(0, nrow = 3, ncol = 4))
B <- rmatrixnorm(30, mean = matrix(1, nrow = 3, ncol = 4))
C <- array(c(A, B), dim = c(3, 4, 60)) # combine together
groups <- c(rep(1, 30), rep(2, 30)) # define groups
prior <- c(.5, .5) # set prior
D <- matrixlda(C, groups, prior)
predict(D)$posterior[1:10, ]
#> [,1] [,2]
#> [1,] 0.9999948 5.224846e-06
#> [2,] 0.6942637 3.057363e-01
#> [3,] 0.9999813 1.869044e-05
#> [4,] 0.9999984 1.602533e-06
#> [5,] 0.9993887 6.113309e-04
#> [6,] 0.8503901 1.496099e-01
#> [7,] 0.9999956 4.433919e-06
#> [8,] 0.9999997 2.543128e-07
#> [9,] 0.7600474 2.399526e-01
#> [10,] 0.9535620 4.643805e-02
## S3 method for class 'matrixlda'