PAM集群-在另一个数据集中使用结果

一般情况下,对k个集群尝试此操作:

k <- 2 # pam with k clusters
res <- pam(x,k)

y <- c(1.5,4.5) # new point

# get the cluster centroid to which the new point is to be assigned to
# break ties by taking the first medoid in case there are multiple ones

# non-vectorized function
get.cluster1 <- function(res, y) which.min(sapply(1:k, function(i) sum((res$medoids[i,]-y)^2)))

# vectorized function, much faster
get.cluster2 <- function(res, y) which.min(colSums((t(res$medoids)-y)^2))

get.cluster1(res, y)
#[1] 2
get.cluster2(res, y)
#[1] 2

# comparing the two implementations (the vectorized function takes much les s time)
library(microbenchmark)
microbenchmark(get.cluster1(res, y), get.cluster2(res, y))

#Unit: microseconds
#                 expr    min     lq     mean median     uq     max neval cld
# get.cluster1(res, y) 31.219 32.075 34.89718 32.930 33.358 135.995   100   b
# get.cluster2(res, y) 17.107 17.962 19.12527 18.817 19.245  41.483   100  a 

任意距离函数的扩展:

# distance function
euclidean.func <- function(x, y) sqrt(sum((x-y)^2))
manhattan.func <- function(x, y) sum(abs(x-y))

get.cluster3 <- function(res, y, dist.func=euclidean.func) which.min(sapply(1:k, function(i) dist.func(res$medoids[i,], y)))
get.cluster3(res, y) # use Euclidean as default
#[1] 2
get.cluster3(res, y, manhattan.func) # use Manhattan distance
#[1] 2