标准化是将一个值转换为另一个值，以便从中获取原始值的一组值的平均值变为零，而标准偏差变为1的过程。要标准化矩阵元素，我们可以使用data.clusterSim包的归一化函数，但是我们需要确保将类型参数设置为n1，因为它对应于均值为零且标准偏差为1的标准化。
加载clusterSim包-
library("clusterSim")M1<-matrix(rnorm(25,5,1),ncol=5) M1
[,1] [,2] [,3] [,4] [,5] [1,] 5.556224 2.934854 6.239076 4.501244 5.697287 [2,] 5.663404 4.404059 4.458465 2.875686 2.939572 [3,] 4.254188 4.168798 5.716965 5.003396 5.501523 [4,] 4.720976 5.032672 5.511445 4.678973 5.289942 [5,] 2.882521 5.694891 4.996887 4.825759 3.951424
data.Normalization(M1,type="n1")
[,1] [,2] [,3] [,4] [,5] [1,] -0.84326235 -1.4331856 0.03959949 0.006214853 -0.6799208 [2,] 0.93062056 0.5714407 -0.31945831 0.065871281 -0.7808809 [3,] -1.18376086 -0.6408459 0.33301120 -0.026702496 -0.6877277 [4,] 1.00673967 0.5514687 -1.40208868 -1.435823004 1.3452576 [5,] 0.08966297 0.9511221 1.34893630 1.390439366 0.8032717
attr(,"normalized:shift")
1 2 3 4 5 5.473020 4.598571 5.143872 4.673848 4.880121
attr(,"normalized:scale")
1 2 3 4 5 1.0620129 0.9269254 0.9739280 1.2254604 0.9488868
M2<-matrix(rpois(100,10),ncol=10) M2
[,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [1,] 15 10 14 15 5 3 11 11 11 7 [2,] 10 8 6 13 4 15 8 6 13 14 [3,] 2 10 5 15 4 10 9 7 6 13 [4,] 12 5 14 11 7 13 8 12 8 7 [5,] 11 11 12 15 10 9 9 12 19 8 [6,] 10 12 8 9 6 12 10 15 11 10 [7,] 13 12 11 9 7 8 17 17 18 13 [8,] 11 8 8 6 10 6 9 8 13 12 [9,] 9 8 10 13 12 14 8 7 4 13 [10,] 7 10 4 7 14 8 10 13 11 11
data.Normalization(M2,type="n1")
data.Normalization(M2,type="n1") [,1] [,2] [,3] [,4] [,5] [,6] [1,] -1.9409899 -0.8923761 1.86543426 -1.67507682 -1.1484061 -1.4356319 [2,] 0.9704950 1.5101749 -0.64037295 -0.09481567 -1.6477131 -0.8114441 [3,] 0.3234983 0.1372886 1.03016519 -0.09481567 1.8474359 -0.4993502 [4,] 0.3234983 0.8237318 -0.64037295 -1.04297236 0.3495149 2.3094948 [5,] 0.9704950 0.1372886 0.75174216 0.53728879 -0.1497921 -0.1872563 [6,] -0.3234983 1.5101749 0.19489612 -0.09481567 0.8488219 0.4369314 [7,] -0.6469966 -0.5491545 -1.47564202 -0.41086790 -0.6490991 -0.4993502 [8,] -0.9704950 -1.2355977 -0.08352691 -0.09481567 -0.1497921 0.4369314 [9,] 0.0000000 -0.8923761 -0.91879598 1.80149771 0.3495149 0.1248376 [10,] 1.2939933 -0.5491545 -0.08352691 1.16939325 0.3495149 0.1248376 [,7] [,8] [,9] [,10] [1,] -0.9091373 2.07152663 0.76931647 1.4367622 [2,] 0.6060915 0.74362494 -0.62944075 -0.2535463 [3,] 1.2121831 -1.11543742 0.06993786 0.1690309 [4,] -1.5152288 0.21246427 0.06993786 -0.6761234 [5,] -0.6060915 -0.84985708 -0.27975144 -1.5212777 [6,] -0.3030458 0.47804461 -1.67850865 -0.6761234 [7,] -0.9091373 -0.05311607 0.06993786 0.5916080 [8,] 1.5152288 -0.05311607 0.06993786 1.0141851 [9,] 0.3030458 -0.05311607 2.16807368 1.0141851 [10,] 0.6060915 -1.38101775 -0.62944075 -1.0987005
attr(,"normalized:shift")
1 2 3 4 5 6 7 8 9 10 12.0 10.6 10.3 9.3 10.3 10.6 10.0 9.2 8.8 8.6
attr(,"normalized:scale")
1 2 3 4 5 6 7 8 3.091206 2.913570 3.591657 3.164034 2.002776 3.204164 3.299832 3.765339 9 10 2.859681 2.366432
M3<-matrix(round(runif(36,2,10),0),ncol=6) M3
[,1] [,2] [,3] [,4] [,5] [,6] [1,] 4 9 4 8 7 5 [2,] 8 3 9 7 9 3 [3,] 9 3 8 4 9 4 [4,] 6 10 4 7 3 3 [5,] 7 8 10 9 4 6 [6,] 7 9 6 9 3 7
data.Normalization(M3,type="n1")
[,1] [,2] [,3] [,4] [,5] [,6] [1,] 0.8017837 1.4647150 1.5430335 -0.6358384 0.1331559 0.8017837 [2,] -1.3363062 -1.3315591 -0.7715167 -1.1808427 0.9320914 -0.2672612 [3,] -0.8017837 -0.5326236 0.1543033 1.5441789 -0.2663118 -0.8017837 [4,] -0.2672612 -0.5326236 -0.3086067 0.4541703 -1.0652473 -1.3363062 [5,] 0.2672612 0.6657796 -1.2344268 -0.6358384 -1.0652473 0.2672612 [6,] 1.3363062 0.2663118 0.6172134 0.4541703 1.3315591 1.3363062
attr(,"normalized:shift")
1 2 3 4 5 6 5.500000 5.333333 4.666667 5.166667 6.666667 6.500000
attr(,"normalized:scale")
1 2 3 4 5 6 1.870829 2.503331 2.160247 1.834848 2.503331 1.870829
M4<-matrix(rexp(16,0.50),nrow=4) M4
[,1] [,2] [,3] [,4] [1,] 1.8392684 0.1260047 1.8536475 0.3727895 [2,] 2.3926115 2.9282159 0.5356917 0.6675259 [3,] 0.6198705 5.3994087 0.7795360 1.6238094 [4,] 3.9293381 0.6119497 0.8212652 0.6498672
data.Normalization(M4,type="n1")
[,1] [,2] [,3] [,4] [1,] -0.76247841 0.6334982 0.2251928 1.2625561 [2,] -0.08745082 -1.0914747 -0.8013569 -0.6296948 [3,] 1.43733539 -0.5780098 -0.7465997 -0.9525044 [4,] -0.58740616 1.0359864 1.3227638 0.3196432
attr(,"normalized:shift")
1 2 3 4 1.587821 1.762592 2.272075 3.611091
attr(,"normalized:scale")
1 2 3 4 0.4923935 1.5823407 2.2370054 1.3130271