R中K-Means、Clara、C-Means三种聚类的评估

R中cluster中包含多种聚类算法，下面通过某个数据集，进行三种聚类算法的评估

# ============================

#     评估聚类               #

# ============================

# 引入fpc包(cluster.stats)

library(fpc)

# 引入包库(clara、fanny)

library(cluster)

#=====调用聚类算法=======================================================

# 确定簇心个数

cluster_num <- 3

# 读取数据

data <- read.csv("data.csv",header = T)

# 调用kmeans算法

km <- kmeans(data,cluster_num)

# 调用(clara)算法

cl <- clara(data,cluster_num)

# 调用模糊C-Means聚类算法

fan <- fanny(data,cluster_num)

#=====调用聚类算法=======================================================

# 聚类评价统计量

km_stats <- cluster.stats(dist(data), km$cluster)

cl_stats <- cluster.stats(dist(data), cl$cluster)

fcm_stats <- cluster.stats(dist(data), fan$clustering)

# 信息数据框表化

info <- data.frame(

  Algorithm = c("KMeans", "Clara", "FCM"),

  Silwidth = c(km_stats$avg.silwidth,cl_stats$avg.silwidth,fcm_stats$avg.silwidth),

  AverageWithin = c(km_stats$average.within, cl_stats$average.within, fcm_stats$average.within),

  averageBetween = c(km_stats$average.between, cl_stats$average.between, fcm_stats$average.between),

  ch = c(km_stats$ch, cl_stats$ch, fcm_stats$ch)

)

# 重命名字段

names(info)[2:5] <- c("轮廓系数","簇内平均距离","簇间平均聚类","Calinski和Harabasz指数")