R语言与数据分析练习：K-Means聚类
k-means实现
k-means算法，是一种最广泛使用的聚类算法。k-means以k作为参数，把数据分为k个组，通过迭代计算过程，将各个分组内的所有数据样本的均值作为该类的中心点，使得组内数据具有较高的相似度，而组间的相似度最低。
k-means工作原理
- 初始化数据，选择k个对象作为中心点。
- 遍历整个数据集，计算每个点与每个中心点的距离，将它分配给距离中心最近的组。
- 重新计算每个组的平均值，作为新的聚类中心。
- 上面2-3步，过程不断重复，直到函数收敛，不再新的分组情况出现。
k-means聚类，适用于连续型数据集。在计算数据样本之间的距离时，通常使用欧式距离作为相似性度量。k-means支持多种距离计算，还包括maximum, manhattan, pearson, correlation, spearman, kendall等。各种的距离算法的介绍，请参考文章R语言实现46种距离算法
kmeans()函数实现
在R语言中，我们可以直接调用系统中自带的kmeans()函数，就可以实现k-means的聚类。同时，有很多第三方算法包也提供了k-means的计算函数。当我们需要使用kmeans算法，可以使用第三方扩展的包，比如flexclust, amap等包。
题目：
在篮球运动中，一般情况下，控球后卫与得分后卫的助攻数较多，小前锋的得分数较多，而大前锋与中锋的助攻数与得分数较少。下表为21名篮球运动员每分钟助攻数和每分钟得分数的数据集，请运用K-Means聚类算法将这21名篮球运动员划分为5类，并通过画图判断他们分别属于什么位置。
数据如下：
assists_per_minute为每分钟助攻次数
points_per_minute为每分钟得分数
; 实现代码：
setwd('D:/bigdata/R语言与数据分析/data03')
basketballdata read.csv("data.csv",stringsAsFactors = F)
outfile matrix(data=NA,
nrow = nrow(basketballdata),
ncol = 2,
byrow = TRUE,
dimnames = list(c(1:nrow(basketballdata)),
c("assists_per_minute","points_per_minute")))
outfile[,1] basketballdata[,2]
outfile[,2] basketballdata[,3]
summary(outfile)
write.csv(outfile,'datachange.csv',row.names = FALSE)
basketballdata read.csv('datachange.csv', header = TRUE)
zscoredfile scale(basketballdata)
write.csv(zscoredfile, 'standardizeddata.csv',row.names = FALSE)
inputfile read.csv('standardizeddata.csv', header = TRUE)
result kmeans(inputfile, 5)
type result$cluster
type
table(type)
centervec result$center
centervec
max apply(centervec,2,max)
max
min apply(centervec,2,min)
min
df = data.frame(rbind(max,min,centervec))
df
library(cluster)
library(factoextra)
fviz_cluster(result,basketballdata)
运行结果：
; 对球员的数据进行分析：
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:6dcbfcb1-49dc-4b9a-b359-beda74893c2b
[En]
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:bb2f5b7a-9449-497f-a51c-ac26768daaa3
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:3e942cd7-8987-41c2-9481-66b432d0b887
[En]
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:e94d6743-6974-4d2b-98c2-68316e1115d5
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:50da0cef-843d-492e-93d8-de2759004627
[En]
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:d1b4c7cf-d977-4ab9-8653-5af825d8ddf7
推测出每个球员的位置：
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:ddff36bf-b481-41f4-9f5a-642b18a38883
[En]
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:bb624009-2462-4a45-bdd0-5bc08b22b54d
（第一组：9，11，15，21）
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:f6af1cc7-735c-49de-869e-ae0a22558512
[En]
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:1ae83224-a9d9-41a3-8fb8-e09f9a443b0e
（第二组：6，7，18）
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:61ab354a-e84b-4ecd-8242-84582d6f26c1
[En]
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:534cd65e-055e-446e-adc8-cba97e9a81ad
（第三组：2）
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:91c362af-6114-471e-ab3a-d0149dcc900b
[En]
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:d27e1044-04ae-41f2-af11-8510470204cd
（第四组：10，12，14，17，20）
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:0a0068e7-144d-4b20-b05b-90ef7bc32618
[En]
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:f56bab90-6171-4520-a9ba-0a3b57c05ab4
（第五组：1，3，4，5，8，13，16，19）
Original: https://blog.csdn.net/weixin_47580081/article/details/115018232
Author: John Zhuang
Title: R语言与数据分析练习：K-Means聚类
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/560772/
转载文章受原作者版权保护。转载请注明原作者出处！