gmdepth.fd {bigdatadist} | R Documentation |
This function allows you to compute the Generalized Kernel Mahalanobis depth measure as stated in Hernandez et al (2018, submitted) and the Generalized Mahalanobis distance in Martos et al (2014), for functional data represented in a Reproducing Kernel Hilbert Space.
gmdepth.fd(fdframe, gamma = 1,kerfunc="rbf" ,
kerpar=list(sigma=1,bias=0,degree=2),d=2,resol,k.neighbor)
fdframe |
an |
gamma |
regularization parameter. |
kerfunc |
kernel function to be used. |
kerpar |
a list of kernel parameters where sigma is the scale with both kernels. |
d |
truncation parameter in the Reproducing Kernel Hilbert Space representation. |
resol |
resolution level to estimate the generalized Mahalanobis distance. |
k.neighbor |
number of neighbours to estimate the support of the disitribution. |
depth |
the generalized Mahalanobis depth measure for the curves in the sample. |
distance |
the generalized Mahalanobis distance for the curves in the sample. |
Hernandez and Martos
Hernandez N. et al (2018, submitted). Generalized Mahalanobis depth functions. Martos, G. et al (2014). Generalizing the Mahalanobis distance via density kernels. Inteligent Data Anal.
data(Ausmale); t <- Ausmale[[1]]
t = as.numeric(( t - min(t) ) / length(t))
raw.data = fdframe(t=t, Y=Ausmale[[2]])
gmd.fit.fd = gmdepth.fd(raw.data,gamma=0.001,
kerfunc="rbf",kerpar=list(sigma = 10))
gmd.fit.fd$distance
gmd.fit.fd$depth
rbPal <- colorRampPalette(c('red','black'))
color = rbPal(5)[as.numeric(cut(gmd.fit.fd$depth,breaks = 5))]
plot(rkhs(raw.data,gamma=0.0001,kerfunc="rbf",kerpar=list(sigma = 10)),
col = color, xlab='time',ylab='')