时间戳

首页 > 解决方案 > 使用 Nbclust() 计算最佳簇数

r - 使用 Nbclust() 计算最佳簇数

问题描述

我想计算大型数据集的最佳聚类数：17 列和 >80.000 行。

这是我的代码：

1.路径的定义

setwd("C:/Users/A/Documents/Master BWL/Masterarbeit")

2.加载需要的包

library(factoextra); library(cluster); library(skmeans); library(mclust); 
library(fpc); library(psda); library(simEd); library (ggpubr);
library(dbscan); library(clustertend); library(MASS); library(devtools);
library(ggbiplot);library(NbClust)

3.导入csv文件

WKA_ohneJB <- read.csv("WKA_ohneJB_PCA.csv", header=TRUE, sep = ";", stringsAsFactors = FALSE)

WKA_ohneJB_scaled <- scale(WKA_ohneJB)

# NbClust ()
nb <- NbClust(WKA_ohneJB_scaled , distance = "manhattan", min.nc = 2, max.nc = 7, method = "kmeans")

dput(rbind(head(WKA_ohneJB, 10), tail(WKA_ohneJB, 10)))
structure(list(X = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 
821039L, 821040L, 821041L, 821042L, 821043L, 821044L, 821045L, 
821046L, 821047L, 821048L), BASKETS_NZ = c(1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), 
    LOGONS = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), PIS = c(71L, 39L, 50L, 4L, 
    13L, 4L, 30L, 65L, 13L, 31L, 111L, 33L, 3L, 46L, 11L, 8L, 
    17L, 68L, 65L, 15L), PIS_AP = c(14L, 2L, 4L, 0L, 0L, 0L, 
    1L, 0L, 2L, 1L, 13L, 0L, 0L, 2L, 1L, 0L, 3L, 8L, 0L, 1L), 
    PIS_DV = c(3L, 19L, 4L, 1L, 0L, 0L, 6L, 2L, 2L, 3L, 38L, 
    8L, 0L, 5L, 2L, 0L, 1L, 0L, 3L, 2L), PIS_PL = c(0L, 5L, 8L, 
    2L, 0L, 0L, 0L, 24L, 0L, 6L, 32L, 8L, 0L, 0L, 4L, 0L, 0L, 
    0L, 0L, 0L), PIS_SDV = c(18L, 0L, 11L, 0L, 0L, 0L, 0L, 0L, 
    0L, 1L, 6L, 0L, 0L, 13L, 0L, 0L, 1L, 15L, 1L, 0L), PIS_SHOPS = c(3L, 
    24L, 13L, 3L, 0L, 0L, 6L, 28L, 2L, 11L, 71L, 16L, 2L, 5L, 
    6L, 0L, 1L, 0L, 3L, 2L), PIS_SR = c(19L, 0L, 14L, 0L, 0L, 
    0L, 2L, 23L, 0L, 3L, 6L, 0L, 0L, 20L, 0L, 0L, 3L, 32L, 1L, 
    0L), QUANTITY = c(13L, 2L, 18L, 1L, 14L, 1L, 4L, 2L, 5L, 
    1L, 5L, 2L, 2L, 4L, 1L, 3L, 2L, 8L, 17L, 8L), WKA = c(1L, 
    1L, 1L, 1L, 1L, 1L, 0L, 0L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 
    0L, 0L, 1L, 1L), NEW_CUST = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 
    0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), EXIST_CUST = c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L), WEB_CUST = c(1L, 0L, 0L, 0L, 1L, 1L, 0L, 
    1L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 1L), MOBILE_CUST = c(0L, 
    1L, 1L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
    1L, 0L, 1L, 0L), TABLET_CUST = c(0L, 0L, 0L, 0L, 0L, 0L, 
    0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 1L, 0L, 1L, 0L, 0L), 
    LOGON_CUST_STEP2 = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
    0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L)), row.names = c(1L, 
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 821039L, 821040L, 821041L, 
821042L, 821043L, 821044L, 821045L, 821046L, 821047L, 821048L
), class = "data.frame")

错误：na.omit(jeu1) 中的错误：找不到对象“多边形”

标签： rcluster-analysisk-means

解决方案

确定集群数量的简单方法是检查组内平方和和/或轮廓平均宽度图中的肘部，代码会生成简单的图来检查这些...

为了进行聚类，需要NaN在缩放后解决s的问题...

WKA_ohneJB_scaled <- as.matrix(scale(data[, c(-1, -2, -18)]))

plot_scree_clusters <- function(x) {
  wss <- 0
  max_i <- 10 # max clusters
  for (i in 1:max_i) {
    km.model <- kmeans(x, centers = i, nstart = 20)
    wss[i] <- km.model$tot.withinss
  }
  plot(1:max_i, wss, type = "b",
       xlab = "Number of Clusters",
       ylab = "Within groups sum of squares")
}

plot_scree_clusters(WKA_ohneJB_scaled)

plot_sil_width <- function(x) {
  sw <- 0
  max_i <- 10 # max clusters
  for (i in 2:max_i) {
    km.model <- cluster::pam(x = pc_comp$x, k = i)
    sw[i] <- km.model$silinfo$avg.width
  }
  sw <- sw[-1]
  plot(2:max_i, sw, type = "b",
       xlab = "Number of Clusters",
       ylab = "Average silhouette width")
}

plot_sil_width(WKA_ohneJB_scaled)

推荐阅读