plot_spc: Plot Word Frequency Spectra (zipfR)
In zipfR: Statistical Models for Word Frequency Distributions

Description Usage Arguments Details See Also Examples

Plot a word frequency spectrum, or a comparison of several word frequency spectra, either as a side-by-side barplot or as points and lines on various logarithmic scales.

## S3 method for class 'spc'
plot(x, y, ...,
     m.max=if (log=="") 15 else 50, 
     log="", conf.level=.95,
     bw=zipfR.par("bw"), points=TRUE,
     xlim=NULL, ylim=NULL,
     xlab="m", ylab="V_m", legend=NULL,
     main="Frequency Spectrum",
     barcol=NULL, pch=NULL, lty=NULL, lwd=NULL, col=NULL)

`x, y, ...`	one or more objects of class `spc`, representing observed or expected frequency spectra to be plotted. Alternatively, all spectra can be passed as a list in the `x` argument if the method is called explicitly (see ‘Examples’.
`m.max`	number of frequency classes that will be shown in plot. The default is 15 on linear scale and 50 when using any type of logarithmic scale.
`log`	a character string specifying the axis or axes for which logarithmic scale is to be used (`"x"`, `"y"`, or `"xy"`), similar to the `log` argument of `plot.default`. By default, a barplot on linear scale is displayed. Use `log=""` to show non-logarithmic points-and-lines plot (also see "Details" below).
`conf.level`	confidence level for confidence intervals in logarithmic plots (see "Details" below). The default value of .95 produces 95%-confidence intervals. Set to `NA` in order to suppress confidence interval markers.
`bw`	if `TRUE`, draw plot in B/W style (default is the global `zipfR.par` setting)
`points`	if `TRUE`, spectrum plots on any type of logarithmic scale are drawn as overplotted lines and points (default). Otherwise, they are drawn as lines with different styles.
`xlim, ylim`	visible range on x- and y-axis. The default values are automatically determined to fit the selected data in the plot.
`xlab, ylab`	labels for the x-axis and y-axis. The default values nicely typeset mathematical expressions. The y-axis label also distinguishes between observed and expected frequency spectra.
`main`	a character string or expression specifying a main title for the plot
`legend`	optional vector of character strings or expressions, specifying labels for a legend box, which will be drawn in the upper right-hand corner of the screen. If `legend` is given, its length must correspond to the number of frequency spectra in the plot.
`barcol, pch, lty, lwd, col`	style vectors that can be used to override the global styles defined by `zipfR.par`. If these vectors are specified, they must contain at least as many elements as there are frequency spectra in the plot: the values are not automatically recycled.

By default, the frequency spectrum or spectra are represented as a barplot, with both axes using linear scale. If the log parameter is given, the spectra are shown either as lines in different styles (points=FALSE) or as overplotted points and lines (point=TRUE). The value of log specifies which axes should use logarithmic scale (specify log="" for a points-and-lines plot on linear scale).

In y-logarithmic plots, frequency classes with V_m = 0 are drawn outside the plot region (below the bottom margin) rather than skipped.

In all logarithmic plots, confidence intervals are indicated for expected frequency spectra with variance data (by vertical lines with T-shaped hooks at both ends). The size of the confidence intervals is controlled by the conf.level parameter (default: 95%). Set conf.level=NA in order to suppress the confidence interval indicators.

Line and point styles, as well as bar colours in the barplot, can be defined globally with zipfR.par. They can be overridden locally with the optional parameters barcol, pch, lty, lwd and col, but this should only be used when absolutely necessary. In most cases, it is more advisable to change the global settings temporarily for a sequence of plots.

The bw parameter is used to switch between B/W and colour modes. It can also be set globally with zipfR.par.

spc, lnre, lnre.spc, plot.tfl, plot.vgc, zipfR.par, zipfR.plotutils

## load Italian ultra- prefix data
data(ItaUltra.spc)

## plot spectrum
plot(ItaUltra.spc)

## logarithmic scale for m (more elements are plotted)
plot(ItaUltra.spc, log="x")

## just lines
plot(ItaUltra.spc, log="x", points=FALSE)

## just the first five elements, then the first 100
plot(ItaUltra.spc, m.max=5)
plot(ItaUltra.spc, m.max=100, log="x")

## compute zm model and expeccted spectrum
zm <- lnre("zm", ItaUltra.spc)
zm.spc <- lnre.spc(zm, N(ItaUltra.spc))

## compare observed and expected spectra (also
## in black and white to print on papers)
plot(ItaUltra.spc, zm.spc, legend=c("observed", "expected"))
plot(ItaUltra.spc, zm.spc, legend=c("observed", "expected"), bw=TRUE)
plot(ItaUltra.spc, zm.spc, legend=c("observed", "expected"), log="x")
plot(ItaUltra.spc, zm.spc, legend=c("observed", "expected"), log="x", bw=TRUE)

## re-generate expected spectrum with variances
zm.spc <- lnre.spc(zm, N(ItaUltra.spc), variances=TRUE)

## now 95% ci is shown in log plot
plot(zm.spc, log="x")

## different title and labels
plot(zm.spc, log="x", main="Expected Spectrum with Confidence Interval",
     xlab="spectrum elements", ylab="expected type counts")

## can pass list of spectra in first argument with explicit call
plot.spc(Baayen2001[1:7], m.max=6, legend=names(Baayen2001)[1:7])