kantorovich: A Function That Computes Kantorovich Distance

In fchuffar/ptlmapper: Useful genetic tool allowing to discriminate individuals by comparing the distribution of their phenotype and to map the genetic loci responsible for specific distributions

A Function That Computes Kantorovich Distance

Description

This function computes Kantorovich distance betwenn two vector of numerics, or two histograms.

Usage

kantorovich(x, y, nbreaks = 100, lims = NULL, h1 = NULL, h2 = NULL)

Arguments

x	A vector of numerics.
y	A vector of numerics.
nbreaks	The number of breaks used to build histograms.
lims	vector of numerics of length 2 that specifies the range on which the histograms need to be built.
h1	An histogram.
h2	An histogram with the same breaks value as h1.

Value

The kantorovich distance between two samples.

Examples

layout(matrix(1:3, 3))
x = rnorm(100000,0,1)
y = rnorm(100000,0,2)
lims = c(min(x, y),max(x, y))
H = hist(lims, plot = FALSE, breaks = 200);
tmp_breaks = H$breaks
h1 <-  hist(x, plot = FALSE, breaks = tmp_breaks);
h2 <-  hist(y, plot = FALSE, breaks = tmp_breaks);
diff = h1$density - h2$density
cumdiff = cumsum(diff)

plot(h1$density, main="Distributions", type="l", col=2, xlab="", ylab="density")
lines(h2$density, type="l", col=4, lwd=3)
legend("topright", col=c(2,4),  legend=c("P", "Q"), lwd=2)
abline(h=0, lty=2)
axis(2, at=0)

plot(diff, type="l", main="Difference", lwd=3, xlab="", ylab="diff")
abline(h=0, lty=2)
axis(2, at=0)

plot(cumdiff, type="l", main="Cumulative Sum", lwd=3, xlab="", ylab="cumsum")
polygon(x= 1:length(cumdiff), y = cumdiff, col = "grey")
lines(cumdiff, type="l", lwd=3)
abline(h=0, lty=2)
axis(2, at=0)

fchuffar/ptlmapper documentation built on March 27, 2024, 3:28 p.m.