从集群（叶子）中检索成员

Question

一旦您使用hclust 建立集群，然后cutree 指定下集群； 你如何检索形成不同集群的成员？假设您创建了一个简单的分层集群，什么命令可以检索在集群组的叶子中“单独”计算的元素？

我试过table()，但没办法...

Answer 1

您可以使用split 函数：对于定义数据应如何分组的第二个参数，使用您的树切割。它将返回一个列表，其中每个元素都是一个不同的集群。

hc <- hclust(dist(USArrests), "ave")
ct <- cutree(hc, k=3)

如果您只想要成员名称：

split(names(ct), ct)
# $`1`
#  [1] "Alabama"        "Alaska"         "Arizona"        "California"   
#  [5] "Delaware"       "Florida"        "Illinois"       "Louisiana"     
#  [9] "Maryland"       "Michigan"       "Mississippi"    "Nevada"        
#  [13] "New Mexico"     "New York"       "North Carolina" "South Carolina"

# $`2`
#  [1] "Arkansas"      "Colorado"      "Georgia"       "Massachusetts"
#  [5] "Missouri"      "New Jersey"    "Oklahoma"      "Oregon"       
#  [9] "Rhode Island"  "Tennessee"     "Texas"         "Virginia"     
# [13] "Washington"    "Wyoming"      

# $`3`
#  [1] "Connecticut"   "Hawaii"        "Idaho"         "Indiana"      
#  [5] "Iowa"          "Kansas"        "Kentucky"      "Maine"        
#  [9] "Minnesota"     "Montana"       "Nebraska"      "New Hampshire"
# [13] "North Dakota"  "Ohio"          "Pennsylvania"  "South Dakota" 
# [17] "Utah"          "Vermont"       "West Virginia" "Wisconsin"    

或者如果您希望将原始数据按集群拆分：

split(USArrests, ct)
# $`1`
#                Murder Assault UrbanPop Rape
# Alabama          13.2     236       58 21.2
# Alaska           10.0     263       48 44.5
# Arizona           8.1     294       80 31.0
# [...]

# $`2`
#               Murder Assault UrbanPop Rape
# Arkansas         8.8     190       50 19.5
# Colorado         7.9     204       78 38.7
# Georgia         17.4     211       60 25.8
# [...]

# $`3`
#               Murder Assault UrbanPop Rape
# Connecticut      3.3     110       77 11.1
# Hawaii           5.3      46       83 20.2
# Idaho            2.6     120       54 14.2
# [...]