tidyst_kde_boundary: Tidy and geospatial kernel density estimates with boundary...

In eks: Tidy and Geospatial Kernel Smoothing

Tidy and geospatial kernel density estimates with boundary and truncated kernels

Description

Tidy and geospatial versions of kernel density estimates with boundary and truncated kernels for 1- and 2-dimensional data.

Usage

tidy_kde_boundary(data, ...)
tidy_kde_truncate(data, boundary, ...)
st_kde_boundary(x, ...)
st_kde_truncate(x, boundary, ...)

Arguments

data	data frame/tibble of data values
x	sf object with point geometry
boundary	data frame/sf point geometry of boundary
...	other parameters in ks::kde.boundary function

Details

A boundary kernel density estimate is a modification of the standard density estimate for bounded data. There are two main types: beta kernels (boundary.kernel="beta") and linear kernels (boundary.kernel="linear"). For details of the computation of the boundary kernel estimates and of the bandwidth selector procedure, see ks::kde.boundary. Currently only rectangular boundaries are supported, as defined by xmin x xmax.

A truncated kernel density estimate is a modification of the standard density estimate for bounded data. All the probability mass outside of boundary is set to zero and re-assigned over the regions inside in the boundary. The boundary can be any polygon. For further details of the computation of the truncated kernel estimate, see ks::kde.truncate.

For details of the computation of the boundary kernel estimates and the truncated kernel density estimates, and of the bandwidth selector procedure, see ks::kde.boundary, ks::kde.truncate.

Value

The outputs from *_kde_boundary, *_kde_truncate have the same structure as the standard kernel density estimate from *_kde.

Examples

## tidy boundary density estimates
library(ggplot2)
data(worldbank, package="ks")
worldbank <- dplyr::as_tibble(worldbank)
## percentage data is bounded on [0,100] x [0,100]
wb2 <- na.omit(worldbank[,c("internet", "ag.value")])
xmin <- c(0,0); xmax <- c(100,100)
rectb <- data.frame(x=c(0,100,100,0,0), y=c(0,0,100,100,0))

## standard density estimate
t1 <- tidy_kde(wb2)
## beta boundary density estimate
t2 <- tidy_kde_boundary(wb2, boundary.kernel="beta", xmin=xmin, xmax=xmax)
## linear boundary density estimate
t3 <- tidy_kde_boundary(wb2, boundary.kernel="linear", xmin=xmin, xmax=xmax)
## tidy truncated density estimate
t4 <- tidy_kde_truncate(wb2, boundary=rectb)

t5 <- c(t1, t2, t3, t4, labels=c("Standard KDE","Beta bd KDE", "Linear bd KDE",
    "Truncated KDE"))

## standard estimate exceeds boundary but not boundary or truncated estimates
gr <- geom_polygon(data=rectb, inherit.aes=FALSE, aes(x=x,y=y), 
    fill=NA, colour=1, linetype="dashed")
gt <- ggplot(t5, aes(x=internet,y=ag.value)) 
gt + geom_contour_ks(aes(colour=group)) + gr + facet_wrap(~group)

## geospatial boundary density estimates
data(wa)
data(grevilleasf)
hakeoides <- dplyr::filter(grevilleasf, species=="hakeoides")
hakeoides_crop <- sf::st_crop(hakeoides, xmin=4e5, xmax=5.7e5, ymin=6.47e6, ymax=7e6)
hakeoides_bbox <- sf::st_as_sfc(sf::st_bbox(hakeoides_crop))
xminb <- sf::st_bbox(hakeoides_crop)[1:2]
xmaxb <- sf::st_bbox(hakeoides_crop)[3:4]
s1 <- st_kde(hakeoides_crop)
s2 <- st_kde_boundary(hakeoides_crop, boundary.kernel="beta", 
    xmin=xminb, xmax=xmaxb)
s3 <- st_kde_boundary(hakeoides_crop, boundary.kernel="linear", 
    xmin=xminb, xmax=xmaxb)
## geospatial truncated density estimate    
s4 <- st_kde_truncate(x=hakeoides_crop, boundary=hakeoides_bbox)
s5 <- c(s1, s2, s3, s4, labels=c("Standard KDE","Beta bd KDE", "Linear bd KDE",
    "Truncated KDE"))

## base R plots
xlim <- c(1.2e5, 1.1e6); ylim <- c(6.1e6, 7.2e6)
plot(wa, xlim=xlim, ylim=ylim)
plot(hakeoides_bbox, add=TRUE, lty=3, lwd=2)
plot(s1, add=TRUE, border=1, col="transparent", legend=FALSE)
plot(s2, add=TRUE, border=2, col="transparent", legend=FALSE)
mapsf::mf_legend(type="symb", val=c("Standard KDE","Beta bd KDE"), pal=c(1,2), 
    cex=rep(3,2), pch=rep("-",2), title="Density", pos="bottomleft")

plot(wa, xlim=xlim, ylim=ylim)
plot(hakeoides_bbox, add=TRUE, lty=3, lwd=2)
plot(s1, add=TRUE, border=1, col="transparent", legend=FALSE)
plot(s3, add=TRUE, border=3, col="transparent", legend=FALSE)
mapsf::mf_legend(type="symb", val=c("Standard KDE","Linear bd KDE"), pal=c(1,3), 
    cex=rep(3,2), pch=rep("-",2), title="Density", pos="bottomleft")

plot(wa, xlim=xlim, ylim=ylim)
plot(hakeoides_bbox, add=TRUE, lty=3, lwd=2)
plot(s1, add=TRUE, border=1, col="transparent", legend=FALSE)
plot(s4, add=TRUE, border=4, col="transparent", legend=FALSE)
mapsf::mf_legend(type="symb", val=c("Standard KDE","Truncated KDE"), pal=c(1,4), 
    cex=rep(3,2), pch=rep("-",2), title="Density", pos="bottomleft")

## geom_sf plots
gs <- ggplot(s1) + geom_sf(data=wa, fill=NA) + 
    geom_sf(data=hakeoides_bbox, linewidth=1.2, linetype="dotted", fill=NA) + 
    geom_sf(data=dplyr::mutate(st_get_contour(s1), gr="Standard KDE"), 
        aes(colour=gr), fill=NA) + ggthemes::theme_map()
gs + geom_sf(data=st_get_contour(s5), aes(colour=group), fill=NA) +
    coord_sf(xlim=xlim, ylim=ylim) + facet_wrap(~group)

eks documentation built on April 4, 2025, 1:53 a.m.