问从R中切割的树状图中提取标签的隶属度/分类(即:树状图的cutree函数)

EN

# Toy data:
hc <- hclust(dist(USArrests), "ave")
dend1 <- as.dendrogram(hc)

# Get the package:
install.packages("dendextend")
library(dendextend)

# Get the package:
cutree(dend1,h=70) # it now works on a dendrogram
# It is like using:
dendextend:::cutree.dendrogram(dend1,h=70)

dend1 <- color_branches(dend1, k = 4)
dend1 <- color_labels(dend1, k = 5)
plot(dend1)

# This would also work with k:
cutree(dend1,k=4)

# and would give identical result as cutree on hclust:
identical(cutree(hc,h=70)  , cutree(dend1,h=70)  )
   # TRUE

# But this is not the case for classify:
identical(classify(dend1,70)   , cutree(dend1,h=70)  )
   # FALSE


install.packages("microbenchmark")
require(microbenchmark)
microbenchmark(classify = classify(dend1,70),
               cutree = cutree(dend1,h=70)  )
#    Unit: milliseconds
#        expr      min       lq   median       uq       max neval
#    classify  9.70135  9.94604 10.25400 10.87552  80.82032   100
#      cutree 37.24264 37.97642 39.23095 43.21233 141.13880   100
# 4 times faster for this tree (it will be more for larger trees)

# Although (if to be exact about it) if I force cutree.dendrogram to not go through hclust (which can happen for "weird" trees), the speed will remain similar:
microbenchmark(classify = classify(dend1,70),
               cutree = cutree(dend1,h=70, try_cutree_hclust = FALSE)  )
# Unit: milliseconds
#        expr       min        lq    median       uq      max neval
#    classify  9.683433  9.819776  9.972077 10.48497 29.73285   100
#      cutree 10.275839 10.419181 10.540126 10.66863 16.54034   100

classify <- function(dendrogram,height){

#mini-function to use with dendrapply to return tip labels
 members <- function(n) {
    labels<-c()
    if (is.leaf(n)) {
        a <- attributes(n)
        labels<-c(labels,a$label)
    }
    labels
 }

 dend2 <- cut(dendrogram,height) #the cut dendrogram object
 branchesvector<-c()
 membersvector<-c()

 for(i in 1:length(dend2$lower)){                             #for each lower tree resulting from the cut
  memlist <- unlist(dendrapply(dend2$lower[[i]],members))     #get the tip lables
  branchesvector <- c(branchesvector,rep(i,length(memlist)))  #add the lower tree identifier to a vector
  membersvector <- c(membersvector,memlist)                   #add the tip labels to a vector
 }
out<-as.integer(branchesvector)                               #make the output a list of named integers, to match cut() output
names(out)<-membersvector
out
}

hc <- hclust(dist(USArrests), "ave")
dend1 <- as.dendrogram(hc)

classify(dend1,70) #Florida 1, North Carolina 1, etc.
cutree(hc,h=70)    #Alabama 1, Arizona 1, Arkansas 1, etc.

library(dendextend)

# set the number of clusters
clust_k <- 8

# make the hierarchical clustering
par(mar = c(2.5, 0.5, 1.0, 7))
d <- dist(mat, method = "euclidean")
hc <- hclust(d)
dend <- d %>% hclust %>% as.dendrogram
labels_cex(dend) <- .65
dend %>% 
  color_branches(k=clust_k) %>%
  color_labels() %>%
  highlight_branches_lwd(3) %>% 
  plot(horiz=TRUE, main = "Branch (Distribution) Clusters by Heloc Attributes", axes = T)

# creates a single item vector of the clusters    
myclusters <- cutree(dend, k=clust_k, h=4)

# make the dataframe of two columns cluster number and label
clusterDF <-  data.frame(Cluster = as.numeric(unlist(myclusters)),
                         Branch = names(myclusters))

# sort by cluster ascending
clusterDFSort <- clusterDF %>% arrange(Cluster)