R语言 系统聚类分析1
#聚类分析是一类将数据所研究对象进行分类的统计方法，这一类方法的共同特点是：
#事先不知道类别的个数与结构 据以进行分类的数据是对象之间的相似性 或差异性数据
#将这些相似（相异）性数据看成是对象之间的距离远近的一种度量 将距离近的对象
#归入一类 不同类之间的对象距离较远
#聚类分析根据分类对象不同分为Q型聚类分析(指的是对样本进行聚类) 和R型聚类分析(指的是对变量进行聚类)
#距离和相似系数
#聚类分析是研究对样本或变量的聚类 变量可以分为两类1定量变量 通常指的是连续量
#2 定性变量(有序变量+名义变量) 这些量并非真有数量上的变化 而只有性质上的差异
#1.距离 1绝对值距离 棋盘距离 城市街区距离 2 Euclide1距离 3Minkowski1距离 4切比雪夫距离 5 Mahalanobis距离 6LanceWilliams距离
#2.数据中心化标准化变换 中心化变换 标准化变换 极差标准化变换 极差正规化变换
#3.相似系数
X<-data.frame( x1=c(2959.19, 2459.77, 1495.63, 1046.33, 1303.97, 1730.84, 1561.86, 1410.11, 3712.31, 2207.58, 2629.16, 1844.78, 2709.46, 1563.78, 1675.75, 1427.65, 1783.43, 1942.23, 3055.17, 2033.87, 2057.86, 2303.29, 1974.28, 1673.82, 2194.25, 2646.61, 1472.95, 1525.57, 1654.69, 1375.46, 1608.82), x2=c(730.79, 495.47, 515.90, 477.77, 524.29, 553.90, 492.42, 510.71, 550.74, 449.37, 557.32, 430.29, 428.11, 303.65, 613.32, 431.79, 511.88, 512.27, 353.23, 300.82, 186.44, 589.99, 507.76, 437.75, 537.01, 839.70, 390.89, 472.98, 437.77, 480.99, 536.05), x3=c(749.41, 697.33, 362.37, 290.15, 254.83, 246.91, 200.49, 211.88, 893.37, 572.40, 689.73, 271.28, 334.12, 233.81, 550.71, 288.55, 282.84, 401.39, 564.56, 338.65, 202.72, 516.21, 344.79, 461.61, 369.07, 204.44, 447.95, 328.90, 258.78, 273.84, 432.46), x4=c(513.34, 302.87, 285.32, 208.57, 192.17, 279.81, 218.36, 277.11, 346.93, 211.92, 435.69, 126.33, 160.77, 107.90, 219.79, 208.14, 201.01, 206.06, 356.27, 157.78, 171.79, 236.55, 203.21, 153.32, 249.54, 209.11, 259.51, 219.86, 303.00, 317.32, 235.82), x5=c(467.87, 284.19, 272.95, 201.50, 249.81, 239.18, 220.69, 224.65, 527.00, 302.09, 514.66, 250.56, 405.14, 209.70, 272.59, 217.00, 237.60, 321.29, 811.88, 329.06, 329.65, 403.92, 240.24, 254.66, 290.84, 379.30, 230.61, 206.65, 244.93, 251.08, 250.28), x6=c(1141.82, 735.97, 540.58, 414.72, 463.09, 445.20, 459.62, 376.82, 1034.98, 585.23, 795.87, 513.18, 461.67, 393.99, 599.43, 337.76, 617.74, 697.22, 873.06, 621.74, 477.17, 730.05, 575.10, 445.59, 561.91, 371.04, 490.90, 449.69, 479.53, 424.75, 541.30), x7=c(478.42, 570.84, 364.91, 281.84, 287.87, 330.24, 360.48, 317.61, 720.33, 429.77, 575.76, 314.00, 535.13, 509.39, 371.62, 421.31, 523.52, 492.60, 1082.82, 587.02, 312.93, 438.41, 430.36, 346.11, 407.70, 269.59, 469.10, 249.66, 288.56, 228.73, 344.85), x8=c(457.64, 305.08, 188.63, 212.10, 192.96, 163.86, 147.76, 152.85, 462.03, 252.54, 323.36, 151.39, 232.29, 160.12, 211.84, 165.32, 182.52, 226.45, 420.81, 218.27, 279.19, 225.80, 223.46, 191.48, 330.95, 389.33, 191.34, 228.19, 236.51, 195.93, 214.40), row.names=c("北京","天津","河北","山西","内蒙古", "辽宁","吉林","黑龙江","上海","江苏","浙江", "安徽","福建","江西","山东","河南","湖北", "湖南","广东","广西","海南","重庆","四川", "贵州","云南","西藏","陕西","甘肃","青海" , "宁夏","新疆") ) d=dist(scale(X)) #scale对数据做中心化或者标准化处理 hc1<-hclust(d) #hclust提供系统聚类的计算 最长距离法 plclust(hc1, hang=-1) #hang是表明谱系图中各类所在的位置 当hang取负值时，谱系图中的类从底部画起 re1<-rect.hclust(hc1, k=5, border="red")
