76 lines
2.2 KiB
R
76 lines
2.2 KiB
R
|
#' @title Linkage
|
||
|
|
#' @description Create hierarchical cluster tree.
|
||
|
|
#' @details Z = LINKAGE(Y) creates a hierarchical cluster tree, using the single
|
||
|
|
#' linkage algorithm. The input Y is a distance matrix such as is generated by
|
||
|
|
#' PDIST. Y may also be a more general dissimilarity matrix conforming to the
|
||
|
|
#' output format of PDIST.
|
||
|
|
#' @param Y data
|
||
|
|
#' @param method either 'si', 'av', 'co' 'ce' or 'wa'
|
||
|
|
#' @export
|
||
|
|
linkage <- function(Y, method) {
|
||
|
|
k <- size(Y)[1]
|
||
|
|
n <- size(Y)[2]
|
||
|
|
m <- (1 + sqrt(1 + 8 * n)) / 2
|
||
|
|
if ((k != 1) | (m != trunc(m))) {
|
||
|
|
stop(
|
||
|
|
'The first input has to match the output',
|
||
|
|
'of the PDIST function in size.'
|
||
|
|
)
|
||
|
|
}
|
||
|
|
if (nargin == 1) { # set default switch to be 'co'
|
||
|
|
method <- 'co'
|
||
|
|
}
|
||
|
|
method <- lower(method[1:2]) # simplify the switch string.
|
||
|
|
monotonic <- 1
|
||
|
|
Z <- zeros(m - 1, 3) # allocate the output matrix.
|
||
|
|
N <- zeros(1, 2 * m - 1)
|
||
|
|
N[1:m] <- 1
|
||
|
|
n <- m; # since m is changing, we need to save m in n.
|
||
|
|
R <- 1:n
|
||
|
|
for (s in 1:(n-1)) {
|
||
|
|
X <- Y
|
||
|
|
v <- min(X)[1]
|
||
|
|
k <- min(X)[2]
|
||
|
|
i <- floor(m + 1 / 2 - sqrt(m ^ 2 - m + 1 / 4 - 2 * (k - 1)))
|
||
|
|
j <- k - (i - 1) * (m - i / 2) + i
|
||
|
|
Z[s, ] <- c(R[i], R[j], v) # update one more row to the output matrix A
|
||
|
|
# Temp variables
|
||
|
|
I1 <- 1:(i - 1)
|
||
|
|
I2 <- (i + 1):(j - 1)
|
||
|
|
I3 <- (j + 1):m
|
||
|
|
|
||
|
|
U <- c(I1, I2, I3)
|
||
|
|
I <- c(
|
||
|
|
I1 * (m - (I1 + 1) / 2) - m + i,
|
||
|
|
i * (m - (i + 1) / 2) - m + I2,
|
||
|
|
i * (m - (i + 1) / 2) - m + I3
|
||
|
|
)
|
||
|
|
J <- c(
|
||
|
|
I1 * (m - (I1 + 1) / 2) - m + j,
|
||
|
|
I2 * (m - (I2 + 1) / 2) - m + j,
|
||
|
|
j * (m - (j + 1) / 2) - m + I3
|
||
|
|
)
|
||
|
|
|
||
|
|
switch(method,
|
||
|
|
'si' = Y[I] <- min(Y[I], Y[J]), # single linkage
|
||
|
|
'av' = Y[I] <- Y[I] + Y[J], # average linkage
|
||
|
|
'co' = Y[I] <- max(Y[I], Y[J]), #complete linkage
|
||
|
|
'ce' = {
|
||
|
|
K <- N[R[i]] + N[R[j]] # centroid linkage
|
||
|
|
Y[I] <- (N[R[i]] * Y[I] + N[R[j]] * Y[J] -
|
||
|
|
(N[R[i]] * N[R[j]] * v ^ 2) / K) / K
|
||
|
|
},
|
||
|
|
'wa' = Y[I] <- ((N[R[U]] + N[R[i]]) * Y[I] + (N[R[U]] + N[R[j]]) *
|
||
|
|
Y[J] - N[R[U]] * v) / (N[R[i]] + N[R[j]] + N[R[U]])
|
||
|
|
)
|
||
|
|
J <- c(J, i * (m - (i + 1) / 2) - m + j)
|
||
|
|
Y[J] <- vector() # no need for the cluster information about j
|
||
|
|
|
||
|
|
# update m, N, R
|
||
|
|
m <- m - 1
|
||
|
|
N[n + s] <- N[R[i]] + N[R[j]]
|
||
|
|
R[i] <- n + s
|
||
|
|
R[j:(n - 1)] <- R[(j + 1):n]
|
||
|
|
}
|
||
|
|
return(Z)
|
||
|
|
}
|