| Line 1... |
Line 1... |
| 1 |
\name{dist}
|
1 |
\name{dist}
|
| 2 |
\title{Distance Matrix Computation}
|
2 |
\title{Distance Matrix Computation}
|
| 3 |
\usage{
|
3 |
\usage{
|
| 4 |
dist(x, method = "euclidean", diag = FALSE, upper = FALSE)
|
4 |
dist(x, method = "euclidean", diag = FALSE, upper = FALSE, p = 2)
|
| 5 |
|
5 |
|
| 6 |
as.dist(m, diag = FALSE, upper = FALSE)
|
6 |
as.dist(m, diag = FALSE, upper = FALSE)
|
| 7 |
|
7 |
|
| 8 |
\method{print}{dist}(x, diag = NULL, upper = NULL,
|
8 |
\method{print}{dist}(x, diag = NULL, upper = NULL,
|
| 9 |
digits = getOption("digits"), justify = "none", right = TRUE, \dots)
|
9 |
digits = getOption("digits"), justify = "none", right = TRUE, \dots)
|
| Line 19... |
Line 19... |
| 19 |
\alias{as.dist}
|
19 |
\alias{as.dist}
|
| 20 |
\arguments{
|
20 |
\arguments{
|
| 21 |
\item{x}{a numeric matrix, data frame or \code{"dist"} object.}
|
21 |
\item{x}{a numeric matrix, data frame or \code{"dist"} object.}
|
| 22 |
\item{method}{the distance measure to be used. This must be one of
|
22 |
\item{method}{the distance measure to be used. This must be one of
|
| 23 |
\code{"euclidean"}, \code{"maximum"}, \code{"manhattan"},
|
23 |
\code{"euclidean"}, \code{"maximum"}, \code{"manhattan"},
|
| 24 |
\code{"canberra"} or \code{"binary"}.
|
24 |
\code{"canberra"}, \code{"binary"} or \code{"minkowski"}.
|
| 25 |
Any unambiguous substring can be given.}
|
25 |
Any unambiguous substring can be given.}
|
| 26 |
\item{diag}{logical value indicating whether the diagonal of the
|
26 |
\item{diag}{logical value indicating whether the diagonal of the
|
| 27 |
distance matrix should be printed by \code{print.dist}.}
|
27 |
distance matrix should be printed by \code{print.dist}.}
|
| 28 |
\item{upper}{logical value indicating whether the upper triangle of the
|
28 |
\item{upper}{logical value indicating whether the upper triangle of the
|
| 29 |
distance matrix should be printed by \code{print.dist}.}
|
29 |
distance matrix should be printed by \code{print.dist}.}
|
| - |
|
30 |
\item{p}{The power of the Minikowski distance.}
|
| 30 |
\item{m}{A matrix of distances to be converted to a \code{"dist"}
|
31 |
\item{m}{A matrix of distances to be converted to a \code{"dist"}
|
| 31 |
object (only the lower triangle is used, the rest is ignored).}
|
32 |
object (only the lower triangle is used, the rest is ignored).}
|
| 32 |
\item{digits, justify}{passed to \code{\link{format}} inside of
|
33 |
\item{digits, justify}{passed to \code{\link{format}} inside of
|
| 33 |
\code{print()}.}
|
34 |
\code{print()}.}
|
| 34 |
\item{right, \dots}{further arguments, passed to the (next)
|
35 |
\item{right, \dots}{further arguments, passed to the (next)
|
| Line 61... |
Line 62... |
| 61 |
\item{\code{binary}:}{(aka \emph{asymmetric binary}): The vectors
|
62 |
\item{\code{binary}:}{(aka \emph{asymmetric binary}): The vectors
|
| 62 |
are regarded as binary bits, so non-zero elements are \sQuote{on}
|
63 |
are regarded as binary bits, so non-zero elements are \sQuote{on}
|
| 63 |
and zero elements are \sQuote{off}. The distance is the
|
64 |
and zero elements are \sQuote{off}. The distance is the
|
| 64 |
\emph{proportion} of bits in which only one is on amongst those in
|
65 |
\emph{proportion} of bits in which only one is on amongst those in
|
| 65 |
which at least one is on.}
|
66 |
which at least one is on.}
|
| - |
|
67 |
|
| - |
|
68 |
\item{\code{minkowki}:}{The \eqn{p} norm, the \eqn{p}th root of the
|
| - |
|
69 |
sum of the \eqn{p}th powers of the differences of the components.}
|
| 66 |
}
|
70 |
}
|
| 67 |
|
71 |
|
| 68 |
Missing values are allowed, and are excluded from all computations
|
72 |
Missing values are allowed, and are excluded from all computations
|
| 69 |
involving the rows within which they occur.
|
73 |
involving the rows within which they occur.
|
| 70 |
Further, when \code{Inf} values are involved, all pairs of values are
|
74 |
Further, when \code{Inf} values are involved, all pairs of values are
|
| 71 |
excluded when their contribution to the distance gave \code{NaN} or
|
75 |
excluded when their contribution to the distance gave \code{NaN} or
|
| 72 |
\code{NA}.\cr
|
76 |
\code{NA}.\cr
|
| 73 |
If some columns are excluded in calculating a Euclidean, Manhattan or
|
77 |
If some columns are excluded in calculating a Euclidean, Manhattan,
|
| 74 |
Canberra distance, the sum is scaled up proportionally to the number
|
78 |
Canberra or Minkowski distance, the sum is scaled up proportionally
|
| 75 |
of columns used. If all pairs are excluded when calculating a
|
79 |
to the number of columns used. If all pairs are excluded when calculating a
|
| 76 |
particular distance, the value is \code{NA}.
|
80 |
particular distance, the value is \code{NA}.
|
| 77 |
|
81 |
|
| 78 |
The functions \code{as.matrix.dist()} and \code{as.dist()} can be used
|
82 |
The functions \code{as.matrix.dist()} and \code{as.dist()} can be used
|
| 79 |
for conversion between objects of class \code{"dist"} and conventional
|
83 |
for conversion between objects of class \code{"dist"} and conventional
|
| 80 |
distance matrices and vice versa.
|
84 |
distance matrices and vice versa.
|
| Line 106... |
Line 110... |
| 106 |
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
110 |
Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
|
| 107 |
\emph{The New S Language}.
|
111 |
\emph{The New S Language}.
|
| 108 |
Wadsworth \& Brooks/Cole.
|
112 |
Wadsworth \& Brooks/Cole.
|
| 109 |
|
113 |
|
| 110 |
Mardia, K. V., Kent, J. T. and Bibby, J. M. (1979)
|
114 |
Mardia, K. V., Kent, J. T. and Bibby, J. M. (1979)
|
| 111 |
\emph{Multivariate Analysis.} London: Academic Press.
|
115 |
\emph{Multivariate Analysis.} Academic Press.
|
| - |
|
116 |
|
| - |
|
117 |
Borg, I. and Groenen, P. (1997)
|
| - |
|
118 |
\emph{Modern Multidimensional Scaling. Theory and Applications.}
|
| - |
|
119 |
Springer.
|
| 112 |
}
|
120 |
}
|
| 113 |
\seealso{
|
121 |
\seealso{
|
| 114 |
\code{\link[cluster]{daisy}} in the \pkg{cluster} package with more
|
122 |
\code{\link[cluster]{daisy}} in the \pkg{cluster} package with more
|
| 115 |
possibilities in the case of \emph{mixed} (contiuous / categorical)
|
123 |
possibilities in the case of \emph{mixed} (contiuous / categorical)
|
| 116 |
variables.
|
124 |
variables.
|
The R Project SVN
R