当前位置： 文江博客话题详情

R 中树状图的轮廓图

发布于 2025-01-14 03:18:33 字数 2150 浏览 2 评论 0原文

我正在对我的数据使用层次聚类。我想绘制不同数量的聚类的轮廓分数。我搜索了很多帖子，发现我需要使用 pam 进行聚类才能绘制 Silhouette 分数。我想知道是否有一种方法可以根据层次聚类结果进行绘图？

这是示例数据：

structure(list(safe = c(1.5, 1.5, 2, 1, 1, 1, 2, 1.5, 1, 1, 1.5, 
1, 2, 1, 3.5, 1, 1, 1.5, 1.5, 1, 1, 1, 1, 2, 1.5, 1, 1.5, 1, 
1, 1.5, 2.5, 1, 2, 1, 1.5, 1, 1.5, 1, 1, 1, 2.5, 2, 1, 1, 1, 
2, 1, 1.5, 1.5, 1.5, 1.5, 3, 3, 1, 1.5, 2, 1, 1.5, 1, 1.5, 1, 
1.5, 1, 1, 1, 1.5, 1, 1, 1, 1.5, 1.5, 1.5, 1, 2, 1, 1, 1, 1, 
1, 1, 1.5, 1, 1, 2, 1, 1, 1, 1.5, 1, 1.5, 1.5, 1, 1, 1, 1, 1.5, 
1, 2, 1.5, 1, 1), nhood.soccapi = c(1.8, 1.6, 2.8, 2.2, 2, 3.6, 
3.2, 1.8, 1.6, 1.8, 1.4, 3.8, 1.6, 1, 2, 2.2, 1, 1, 2, 1, 1, 
2.2, 1, 1.4, 1.8, 2, 2.4, 1.8, 1, 2, 2.2, 1.6, 2.2, 1.2, 2, 2, 
1, 2, 2, 2, 2, 1.8, 1.4, 1.6, 1, 2.2, 1.4, 1.6, 2.4, 1.2, 1.4, 
2.4, 2, 2.4, 2, 1.8, 1.6, 1, 1.2, 1.8, 2, 3.4, 2, 2, 1, 2, 1, 
1.4, 2, 2.8, 2, 1, 2, 1.2, 1.4, 2, 1.6, 1.4, 2.2, 2.4, 1.8, 1.4, 
1.4, 2, 2.2, 1, 2, 2.2, 1, 1.8, 2.2, 1.6, 1.2, 1, 2, 1, 1.2, 
2.6, 1.8, 1.8, 1.8), DISORDER = structure(c(1L, 1L, 1L, 1L, 1L, 
1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, NA, NA, 2L, 1L, 2L, 1L, 1L, 
1L, 1L, 2L, 1L, 1L, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, NA, 2L, 
NA, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, NA, 2L, 1L, 1L, 2L, 1L, NA, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, NA, 1L, 1L, 1L, 
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, NA, NA, 1L, 
1L, 2L, 2L, 2L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 2L, NA, 2L
), .Label = c("0", "1"), class = "factor"), Scho_socialdep1000_3 = structure(c(3L, 
3L, 3L, 3L, 3L, 2L, NA, 3L, 2L, 1L, 2L, 1L, NA, 2L, NA, NA, 1L, 
2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 3L, 2L, NA, NA, 1L, 2L, 2L, 2L, 
1L, 1L, 2L, 3L, NA, 1L, 1L, 2L, NA, 2L, 2L, 1L, 2L, NA, 1L, 3L, 
2L, 1L, 1L, NA, 3L, 2L, 3L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 
2L, 1L, 1L, 2L, 3L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, NA, 1L, 1L, 
1L, NA, NA, 1L, 3L, 3L, 2L, 3L, 2L, 1L, 2L, 1L, 1L, 3L, 2L, 1L, 
NA, 2L, NA, 3L), .Label = c("0", "1", "2"), class = "factor")), row.names = 100:200, class = "data.frame")

以及我的集群代码：

dist <- daisy(dt, metric = "gower")
cls.env <- hclust(dist, method = "average")
原文

I'm using hierarchical clustering for my data. And I'd like to plot the Silhouette score across different number of cluster. I have searched a lot posts, and I found that I need to use pam for the clustering in order to plot the Silhouette score. I'm wodering if there is a way to plot based on hierarchical clustering result?

Here is a sample data:

structure(list(safe = c(1.5, 1.5, 2, 1, 1, 1, 2, 1.5, 1, 1, 1.5, 
1, 2, 1, 3.5, 1, 1, 1.5, 1.5, 1, 1, 1, 1, 2, 1.5, 1, 1.5, 1, 
1, 1.5, 2.5, 1, 2, 1, 1.5, 1, 1.5, 1, 1, 1, 2.5, 2, 1, 1, 1, 
2, 1, 1.5, 1.5, 1.5, 1.5, 3, 3, 1, 1.5, 2, 1, 1.5, 1, 1.5, 1, 
1.5, 1, 1, 1, 1.5, 1, 1, 1, 1.5, 1.5, 1.5, 1, 2, 1, 1, 1, 1, 
1, 1, 1.5, 1, 1, 2, 1, 1, 1, 1.5, 1, 1.5, 1.5, 1, 1, 1, 1, 1.5, 
1, 2, 1.5, 1, 1), nhood.soccapi = c(1.8, 1.6, 2.8, 2.2, 2, 3.6, 
3.2, 1.8, 1.6, 1.8, 1.4, 3.8, 1.6, 1, 2, 2.2, 1, 1, 2, 1, 1, 
2.2, 1, 1.4, 1.8, 2, 2.4, 1.8, 1, 2, 2.2, 1.6, 2.2, 1.2, 2, 2, 
1, 2, 2, 2, 2, 1.8, 1.4, 1.6, 1, 2.2, 1.4, 1.6, 2.4, 1.2, 1.4, 
2.4, 2, 2.4, 2, 1.8, 1.6, 1, 1.2, 1.8, 2, 3.4, 2, 2, 1, 2, 1, 
1.4, 2, 2.8, 2, 1, 2, 1.2, 1.4, 2, 1.6, 1.4, 2.2, 2.4, 1.8, 1.4, 
1.4, 2, 2.2, 1, 2, 2.2, 1, 1.8, 2.2, 1.6, 1.2, 1, 2, 1, 1.2, 
2.6, 1.8, 1.8, 1.8), DISORDER = structure(c(1L, 1L, 1L, 1L, 1L, 
1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, NA, NA, 2L, 1L, 2L, 1L, 1L, 
1L, 1L, 2L, 1L, 1L, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, NA, 2L, 
NA, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, NA, 2L, 1L, 1L, 2L, 1L, NA, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, NA, 1L, 1L, 1L, 
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, NA, NA, 1L, 
1L, 2L, 2L, 2L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 2L, NA, 2L
), .Label = c("0", "1"), class = "factor"), Scho_socialdep1000_3 = structure(c(3L, 
3L, 3L, 3L, 3L, 2L, NA, 3L, 2L, 1L, 2L, 1L, NA, 2L, NA, NA, 1L, 
2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 3L, 2L, NA, NA, 1L, 2L, 2L, 2L, 
1L, 1L, 2L, 3L, NA, 1L, 1L, 2L, NA, 2L, 2L, 1L, 2L, NA, 1L, 3L, 
2L, 1L, 1L, NA, 3L, 2L, 3L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 
2L, 1L, 1L, 2L, 3L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, NA, 1L, 1L, 
1L, NA, NA, 1L, 3L, 3L, 2L, 3L, 2L, 1L, 2L, 1L, 1L, 3L, 2L, 1L, 
NA, 2L, NA, 3L), .Label = c("0", "1", "2"), class = "factor")), row.names = 100:200, class = "data.frame")

And my cluster code:

dist <- daisy(dt, metric = "gower")
cls.env <- hclust(dist, method = "average")

如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论， 你可以免费 注册 一个本站的账号。

评论（1）

无力看清 2025-01-21 03:18:33

hclust 仅返回表示簇内簇的树状图。轮廓分数是在一种特定的聚类上定义的，而不是在所有可能的聚类上定义的。这就是它与 Partitioning Arround Medoids (PAM) 开箱即用的原因。然而，在层次聚类中，首先需要通过切割树状图来决定选择哪个聚类。

这是使用 k=5 聚类绘制分层聚类轮廓的方法：

library(tidyverse)
library(cluster)

data <- structure(list(safe = c(
  1.5, 1.5, 2, 1, 1, 1, 2, 1.5, 1, 1, 1.5,
  1, 2, 1, 3.5, 1, 1, 1.5, 1.5, 1, 1, 1, 1, 2, 1.5, 1, 1.5, 1,
  1, 1.5, 2.5, 1, 2, 1, 1.5, 1, 1.5, 1, 1, 1, 2.5, 2, 1, 1, 1,
  2, 1, 1.5, 1.5, 1.5, 1.5, 3, 3, 1, 1.5, 2, 1, 1.5, 1, 1.5, 1,
  1.5, 1, 1, 1, 1.5, 1, 1, 1, 1.5, 1.5, 1.5, 1, 2, 1, 1, 1, 1,
  1, 1, 1.5, 1, 1, 2, 1, 1, 1, 1.5, 1, 1.5, 1.5, 1, 1, 1, 1, 1.5,
  1, 2, 1.5, 1, 1
), nhood.soccapi = c(
  1.8, 1.6, 2.8, 2.2, 2, 3.6,
  3.2, 1.8, 1.6, 1.8, 1.4, 3.8, 1.6, 1, 2, 2.2, 1, 1, 2, 1, 1,
  2.2, 1, 1.4, 1.8, 2, 2.4, 1.8, 1, 2, 2.2, 1.6, 2.2, 1.2, 2, 2,
  1, 2, 2, 2, 2, 1.8, 1.4, 1.6, 1, 2.2, 1.4, 1.6, 2.4, 1.2, 1.4,
  2.4, 2, 2.4, 2, 1.8, 1.6, 1, 1.2, 1.8, 2, 3.4, 2, 2, 1, 2, 1,
  1.4, 2, 2.8, 2, 1, 2, 1.2, 1.4, 2, 1.6, 1.4, 2.2, 2.4, 1.8, 1.4,
  1.4, 2, 2.2, 1, 2, 2.2, 1, 1.8, 2.2, 1.6, 1.2, 1, 2, 1, 1.2,
  2.6, 1.8, 1.8, 1.8
), DISORDER = structure(c(
  1L, 1L, 1L, 1L, 1L,
  1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, NA, NA, 2L, 1L, 2L, 1L, 1L,
  1L, 1L, 2L, 1L, 1L, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, NA, 2L,
  NA, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, NA, 2L, 1L, 1L, 2L, 1L, NA,
  1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, NA, 1L, 1L, 1L,
  2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, NA, NA, 1L,
  1L, 2L, 2L, 2L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 2L, NA, 2L
), .Label = c("0", "1"), class = "factor"), Scho_socialdep1000_3 = structure(c(
  3L,
  3L, 3L, 3L, 3L, 2L, NA, 3L, 2L, 1L, 2L, 1L, NA, 2L, NA, NA, 1L,
  2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 3L, 2L, NA, NA, 1L, 2L, 2L, 2L,
  1L, 1L, 2L, 3L, NA, 1L, 1L, 2L, NA, 2L, 2L, 1L, 2L, NA, 1L, 3L,
  2L, 1L, 1L, NA, 3L, 2L, 3L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L,
  2L, 1L, 1L, 2L, 3L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, NA, 1L, 1L,
  1L, NA, NA, 1L, 3L, 3L, 2L, 3L, 2L, 1L, 2L, 1L, 1L, 3L, 2L, 1L,
  NA, 2L, NA, 3L
), .Label = c("0", "1", "2"), class = "factor")), row.names = 100:200, class = "data.frame")



dist <- daisy(data, metric = "gover")
#> Warning in daisy(data, metric = "gover"): with mixed variables, metric "gower"
#> is used automatically
dendro <-
  dist %>%
  hclust(method = "average") %>%
  # need to put the elements into mutually exclusive sets of clusters
  cutree(k = 5)

silhouette(dendro, dist) %>%
  plot()

请注意，k 的选择是任意的。选择另一个值您将得到不同的结果。

由 reprex 包 (v2.0.0)

hclust returns just a dendrogram representing clusters inside clusters. The silhouette score is defined on one specific clustering and not on all possible clusterings. This is why it works with Partitioning Arround Medoids (PAM) out of the box. In hierarchical clustering, however, one needs to decide first which clustering to chose by cutting dendrogram tree.

This is how to plot the silhouettes for a hierarchical clustering using k=5 clusters:

library(tidyverse)
library(cluster)

data <- structure(list(safe = c(
  1.5, 1.5, 2, 1, 1, 1, 2, 1.5, 1, 1, 1.5,
  1, 2, 1, 3.5, 1, 1, 1.5, 1.5, 1, 1, 1, 1, 2, 1.5, 1, 1.5, 1,
  1, 1.5, 2.5, 1, 2, 1, 1.5, 1, 1.5, 1, 1, 1, 2.5, 2, 1, 1, 1,
  2, 1, 1.5, 1.5, 1.5, 1.5, 3, 3, 1, 1.5, 2, 1, 1.5, 1, 1.5, 1,
  1.5, 1, 1, 1, 1.5, 1, 1, 1, 1.5, 1.5, 1.5, 1, 2, 1, 1, 1, 1,
  1, 1, 1.5, 1, 1, 2, 1, 1, 1, 1.5, 1, 1.5, 1.5, 1, 1, 1, 1, 1.5,
  1, 2, 1.5, 1, 1
), nhood.soccapi = c(
  1.8, 1.6, 2.8, 2.2, 2, 3.6,
  3.2, 1.8, 1.6, 1.8, 1.4, 3.8, 1.6, 1, 2, 2.2, 1, 1, 2, 1, 1,
  2.2, 1, 1.4, 1.8, 2, 2.4, 1.8, 1, 2, 2.2, 1.6, 2.2, 1.2, 2, 2,
  1, 2, 2, 2, 2, 1.8, 1.4, 1.6, 1, 2.2, 1.4, 1.6, 2.4, 1.2, 1.4,
  2.4, 2, 2.4, 2, 1.8, 1.6, 1, 1.2, 1.8, 2, 3.4, 2, 2, 1, 2, 1,
  1.4, 2, 2.8, 2, 1, 2, 1.2, 1.4, 2, 1.6, 1.4, 2.2, 2.4, 1.8, 1.4,
  1.4, 2, 2.2, 1, 2, 2.2, 1, 1.8, 2.2, 1.6, 1.2, 1, 2, 1, 1.2,
  2.6, 1.8, 1.8, 1.8
), DISORDER = structure(c(
  1L, 1L, 1L, 1L, 1L,
  1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, NA, NA, 2L, 1L, 2L, 1L, 1L,
  1L, 1L, 2L, 1L, 1L, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, NA, 2L,
  NA, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, NA, 2L, 1L, 1L, 2L, 1L, NA,
  1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, NA, 1L, 1L, 1L,
  2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, NA, NA, 1L,
  1L, 2L, 2L, 2L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 2L, NA, 2L
), .Label = c("0", "1"), class = "factor"), Scho_socialdep1000_3 = structure(c(
  3L,
  3L, 3L, 3L, 3L, 2L, NA, 3L, 2L, 1L, 2L, 1L, NA, 2L, NA, NA, 1L,
  2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 3L, 2L, NA, NA, 1L, 2L, 2L, 2L,
  1L, 1L, 2L, 3L, NA, 1L, 1L, 2L, NA, 2L, 2L, 1L, 2L, NA, 1L, 3L,
  2L, 1L, 1L, NA, 3L, 2L, 3L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L,
  2L, 1L, 1L, 2L, 3L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, NA, 1L, 1L,
  1L, NA, NA, 1L, 3L, 3L, 2L, 3L, 2L, 1L, 2L, 1L, 1L, 3L, 2L, 1L,
  NA, 2L, NA, 3L
), .Label = c("0", "1", "2"), class = "factor")), row.names = 100:200, class = "data.frame")



dist <- daisy(data, metric = "gover")
#> Warning in daisy(data, metric = "gover"): with mixed variables, metric "gower"
#> is used automatically
dendro <-
  dist %>%
  hclust(method = "average") %>%
  # need to put the elements into mutually exclusive sets of clusters
  cutree(k = 5)

silhouette(dendro, dist) %>%
  plot()

Please note that the choice of k is arbitrary. You will get different results selecting another value.

Created on 2022-03-15 by the reprex package (v2.0.0)

回复 原文
~没有更多了~

关于作者

爱情眠于流年

暂无简介

文章
评论
30 人气
发私信

相关话题

更多

热门标签

操作系统 程序设计 IT运维 Linux系统管理 JavaScript 服务器应用 solaris C/C++ PHP Shell BSD Vue.js aix Oracle Python HTML 系统管理 HTML5 CSS 前端
更多

推荐作者

李珊平

文章 0 评论 0

Quxin

文章 0 评论 0

范无咎

文章 0 评论 0

github_ZOJ2N8YxBm

文章 0 评论 0

若言

文章 0 评论 0

南…巷孤猫

文章 0 评论 0

更多

友情链接

文江博客
    我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站，即表示您同意使用 Cookies 和您的相关数据。
    原文