mfpcaPlot {Funclustering}R Documentation

Plot multivariate functional pca

Description

This function plots the functional pca.

Usage

mfpcaPlot(pca, grid = c())

Arguments

pca

is the result of mfpca. In the univariate case, mfpcaPlot uses the fda package and is similar to its plot.pca.fd function. In the multivariate case, we will make a graphic window for each dimension.

grid

specify how to divide the graphics window. grid=c(n,m) divided the widow in to n lines and m columns. If user don't specify grid then he must enter <Enter> to pass to the next graphic.

Examples

# Multivariate
# ---------  CanadianWeather (data from the package fda) --------
CWtime <- 1:365
CWrange <- c(1, 365)
CWbasis <- create.fourier.basis(CWrange, nbasis = 65)
harmaccelLfd <- vec2Lfd(c(0, (2 * pi / 365)^2, 0), rangeval = CWrange)

# -- Build the curves ---
temp = CanadianWeather$dailyAv[, , "Temperature.C"]
CWfd1 <- smooth.basisPar(
CWtime, CanadianWeather$dailyAv[, , "Temperature.C"], CWbasis,
Lfdobj = harmaccelLfd, lambda = 1e-2)$fd
precip = CanadianWeather$dailyAv[, , "Precipitation.mm"]
CWfd2 <- smooth.basisPar(
CWtime, CanadianWeather$dailyAv[, , "Precipitation.mm"], CWbasis,
Lfdobj = harmaccelLfd, lambda = 1e-2)$fd

CWfd = list(CWfd1, CWfd2)

pca = mfpca(CWfd, nharm = 4)
mfpcaPlot(pca, grid = c(2, 2))

[Package Funclustering version 1.0.3 Index]