Plot Functional Principal Components
Display the types of variation across a sample of functions. Label with the eigenvalues that indicate the relative importance of each mode of variation.
#plot.pca.fd(x, nx = 128, pointplot = TRUE, harm = 0,
# expand = 0, cycle = FALSE, ...)
#NOTE: The following is required by CRAN rules that
# function names like "as.numeric" must follow the documentation
# standards for S3 generics, even when they are not.
# Please ignore the following line:
## S3 method for class 'pca.fd'
plot(x, nx = 128, pointplot = TRUE, harm = 0,
expand = 0, cycle = FALSE, ...)x |
a functional data object. |
nx |
Number of points to plot or vector (if length > 1) to use as
|
pointplot |
logical: If TRUE, the harmonics / principal components are plotted as '+' and '-'. Otherwise lines are used. |
harm |
Harmonics / principal components to plot. If 0, plot all. If length(harm) > sum(par("mfrow")), the user advised, "Waiting to confirm page change..." and / or 'Click or hit ENTER for next page' for each page after the first. |
expand |
nonnegative real: If expand == 0 then effect of +/- 2 standard deviations of each pc are given otherwise the factor expand is used. |
cycle |
logical: If cycle=TRUE and there are 2 variables then a cycle plot will be drawn If the number of variables is anything else, cycle will be ignored. |
... |
other arguments for 'plot'. |
Produces one plot for each principal component / harmonic to be plotted.
invisible(NULL)
# carry out a PCA of temperature
# penalize harmonic acceleration, use varimax rotation
daybasis65 <- create.fourier.basis(c(0, 365), nbasis=65, period=365)
harmaccelLfd <- vec2Lfd(c(0,(2*pi/365)^2,0), c(0, 365))
harmfdPar <- fdPar(daybasis65, harmaccelLfd, lambda=1e5)
daytempfd <- smooth.basis(day.5, CanadianWeather$dailyAv[,,"Temperature.C"],
daybasis65, fdnames=list("Day", "Station", "Deg C"))$fd
daytemppcaobj <- pca.fd(daytempfd, nharm=4, harmfdPar)
# plot harmonics, asking before each new page after the first:
plot.pca.fd(daytemppcaobj)
# plot 4 on 1 page
op <- par(mfrow=c(2,2))
plot.pca.fd(daytemppcaobj, cex.main=0.9)
par(op)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.