nnspat (version 0.1.2)

ipd.mat: Interpoint Distance Matrix

Description

This function computes and returns the distance matrix computed by using the specified distance measure to compute the distances between the rows of the set of points x and y using the dist function in the stats package of the standard R distribution. If y is provided (default=NULL) it yields a matrix of distances between the rows of x and rows of y. Otherwise, it provides a square matrix with \(i,j\)-th entry being the distance between row \(i\) and row \(j\) of x. This function is different from the dist function in the stats package. dist returns the distance matrix in a lower triangular form, and ipd.mat returns in a full matrix. ... are for further arguments, such as method and p, passed to the dist function.

Usage

ipd.mat(x, y = NULL, ...)

Value

A distance matrix whose \(i,j\)-th entry is the distance between row \(i\) of x and row \(j\) of y

if y is provided, otherwise \(i,j\)-th entry is the distance between rows \(i\) and \(j\) of x.

Arguments

x

A set of points in matrix or data frame form where points correspond to the rows.

y

A set of points in matrix or data frame form where points correspond to the rows (default=NULL).

...

Additional parameters to be passed on the dist function.

Author

Elvan Ceyhan

See Also

dist, ipd.mat.euc, and dist.std.data

Examples

#3D data points
n<-3
X<-matrix(runif(3*n),ncol=3)
mtd<-"euclidean" #try also "maximum", "manhattan", "canberra", "binary"
ipd.mat(X,method=mtd)
ipd.mat(X,method="minkowski",p=6)

n<-5
Y<-matrix(runif(3*n),ncol=3)
ipd.mat(X,Y,method=mtd)
ipd.mat(X[1,],Y,method=mtd)
ipd.mat(c(.1,.2,.3),Y,method=mtd)
ipd.mat(X[1,],Y[3,],method=mtd)

#1D data points
X<-as.matrix(runif(3)) # need to be entered as a matrix with one column 
#(i.e., a column vector), hence X<-runif(3) would not work
ipd.mat(X)

Y<-as.matrix(runif(5))
ipd.mat(X,Y)
ipd.mat(X[1,],Y)
ipd.mat(X[1,],Y[3,])