我希望使用R（https://cran.r-project.org/web/packages/pdc/pdc.pdf）的置换分布聚类包进行多变量时间序列聚类。在使用pdclust方法（url pdf的第11页）进行分层聚类之后，我使用绘图方法绘制了树形图（再次参见第11页）。有60个样本。所以，在情节中（Hierarchical clustering plot ），有60个时间序列，但它们没有标记。当我尝试指定标签向量而不是标签= NULL时，我总是得到这个错误“图形中的错误::: plotHclust（n1，合并，高度，顺序（x $ order），挂起，：无效的树形图输入”）。任何帮助将不胜感激。这是我的代码：
data1 <- read.csv(file="file_PID_1_1Apr_00-03.csv",head=FALSE,sep=",")
data2 <- read.csv(file="file_PID_2_1Apr_00-03.csv",head=FALSE,sep=",")
data3 <- read.csv(file="file_PID_3_1Apr_00-03.csv",head=FALSE,sep=",")
data4 <- read.csv(file="file_PID_4_1Apr_00-03.csv",head=FALSE,sep=",")
data5 <- read.csv(file="file_PID_5_1Apr_00-03.csv",head=FALSE,sep=",")
data6 <- read.csv(file="file_PID_6_1Apr_00-03.csv",head=FALSE,sep=",")
data7 <- read.csv(file="file_PID_7_1Apr_00-03.csv",head=FALSE,sep=",")
data8 <- read.csv(file="file_PID_8_1Apr_00-03.csv",head=FALSE,sep=",")
data9 <- read.csv(file="file_PID_1_1Apr_03-06.csv",head=FALSE,sep=",")
data10 <- read.csv(file="file_PID_2_1Apr_03-06.csv",head=FALSE,sep=",")
data11 <- read.csv(file="file_PID_3_1Apr_03-06.csv",head=FALSE,sep=",")
data12 <- read.csv(file="file_PID_4_1Apr_03-06.csv",head=FALSE,sep=",")
data13 <- read.csv(file="file_PID_5_1Apr_03-06.csv",head=FALSE,sep=",")
data14 <- read.csv(file="file_PID_6_1Apr_03-06.csv",head=FALSE,sep=",")
data15 <- read.csv(file="file_PID_7_1Apr_03-06.csv",head=FALSE,sep=",")
data16 <- read.csv(file="file_PID_8_1Apr_03-06.csv",head=FALSE,sep=",")
data17 <- read.csv(file="file_PID_1_1Apr_06-09.csv",head=FALSE,sep=",")
data18 <- read.csv(file="file_PID_2_1Apr_06-09.csv",head=FALSE,sep=",")
data19 <- read.csv(file="file_PID_3_1Apr_06-09.csv",head=FALSE,sep=",")
data20 <- read.csv(file="file_PID_4_1Apr_06-09.csv",head=FALSE,sep=",")
data21 <- read.csv(file="file_PID_5_1Apr_06-09.csv",head=FALSE,sep=",")
data22 <- read.csv(file="file_PID_6_1Apr_06-09.csv",head=FALSE,sep=",")
data23 <- read.csv(file="file_PID_7_1Apr_06-09.csv",head=FALSE,sep=",")
data24 <- read.csv(file="file_PID_8_1Apr_06-09.csv",head=FALSE,sep=",")
data25 <- read.csv(file="file_PID_1_1Apr_09-12.csv",head=FALSE,sep=",")
data26 <- read.csv(file="file_PID_2_1Apr_09-12.csv",head=FALSE,sep=",")
data27 <- read.csv(file="file_PID_3_1Apr_09-12.csv",head=FALSE,sep=",")
data28 <- read.csv(file="file_PID_4_1Apr_09-12.csv",head=FALSE,sep=",")
data29 <- read.csv(file="file_PID_5_1Apr_09-12.csv",head=FALSE,sep=",")
data30 <- read.csv(file="file_PID_6_1Apr_09-12.csv",head=FALSE,sep=",")
data31 <- read.csv(file="file_PID_7_1Apr_09-12.csv",head=FALSE,sep=",")
data32 <- read.csv(file="file_PID_8_1Apr_09-12.csv",head=FALSE,sep=",")
data33 <- read.csv(file="file_PID_1_1Apr_12-15.csv",head=FALSE,sep=",")
data34 <- read.csv(file="file_PID_2_1Apr_12-15.csv",head=FALSE,sep=",")
data35 <- read.csv(file="file_PID_3_1Apr_12-15.csv",head=FALSE,sep=",")
data36 <- read.csv(file="file_PID_4_1Apr_12-15.csv",head=FALSE,sep=",")
data37 <- read.csv(file="file_PID_5_1Apr_12-15.csv",head=FALSE,sep=",")
data38 <- read.csv(file="file_PID_6_1Apr_12-15.csv",head=FALSE,sep=",")
data39 <- read.csv(file="file_PID_7_1Apr_12-15.csv",head=FALSE,sep=",")
data40 <- read.csv(file="file_PID_8_1Apr_12-15.csv",head=FALSE,sep=",")
data41 <- read.csv(file="file_PID_2_1Apr_15-18.csv",head=FALSE,sep=",")
data42 <- read.csv(file="file_PID_3_1Apr_15-18.csv",head=FALSE,sep=",")
data43 <- read.csv(file="file_PID_4_1Apr_15-18.csv",head=FALSE,sep=",")
data44 <- read.csv(file="file_PID_6_1Apr_15-18.csv",head=FALSE,sep=",")
data45 <- read.csv(file="file_PID_7_1Apr_15-18.csv",head=FALSE,sep=",")
data46 <- read.csv(file="file_PID_8_1Apr_15-18.csv",head=FALSE,sep=",")
data47 <- read.csv(file="file_PID_1_1Apr_18-21.csv",head=FALSE,sep=",")
data48 <- read.csv(file="file_PID_2_1Apr_18-21.csv",head=FALSE,sep=",")
data49 <- read.csv(file="file_PID_3_1Apr_18-21.csv",head=FALSE,sep=",")
data50 <- read.csv(file="file_PID_4_1Apr_18-21.csv",head=FALSE,sep=",")
data51 <- read.csv(file="file_PID_6_1Apr_18-21.csv",head=FALSE,sep=",")
data52 <- read.csv(file="file_PID_7_1Apr_18-21.csv",head=FALSE,sep=",")
data53 <- read.csv(file="file_PID_8_1Apr_18-21.csv",head=FALSE,sep=",")
data54 <- read.csv(file="file_PID_1_1Apr_21-24.csv",head=FALSE,sep=",")
data55 <- read.csv(file="file_PID_2_1Apr_21-24.csv",head=FALSE,sep=",")
data56 <- read.csv(file="file_PID_3_1Apr_21-24.csv",head=FALSE,sep=",")
data57 <- read.csv(file="file_PID_4_1Apr_21-24.csv",head=FALSE,sep=",")
data58 <- read.csv(file="file_PID_6_1Apr_21-24.csv",head=FALSE,sep=",")
data59 <- read.csv(file="file_PID_7_1Apr_21-24.csv",head=FALSE,sep=",")
data60 <- read.csv(file="file_PID_8_1Apr_21-24.csv",head=FALSE,sep=",")
list <- array(0,dim=c(720,60,4))
myfunc <- function(j,i,k){
if (j == 1) return (data1[i,k])
else if (j==2) return (data2[i,k])
else if (j==3) return (data17[i,k])
else if (j==4) return (data9[i,k])
else if (j==5) return (data5[i,k])
else if (j==6) return (data6[i,k])
else if (j==7) return (data7[i,k])
else if (j==8) return (data8[i,k])
else if (j==9) return (data9[i,k])
else if (j==10) return (data10[i,k])
else if (j==11) return (data11[i,k])
else if (j==12) return (data12[i,k])
else if (j==13) return (data13[i,k])
else if (j==14) return (data14[i,k])
else if (j==15) return (data15[i,k])
else if (j==16) return (data16[i,k])
else if (j==17) return (data17[i,k])
else if (j==18) return (data18[i,k])
else if (j==19) return (data19[i,k])
else if (j==20) return (data20[i,k])
else if (j==21) return (data21[i,k])
else if (j==22) return (data22[i,k])
else if (j==23) return (data23[i,k])
else if (j==24) return (data24[i,k])
else if (j==25) return (data25[i,k])
else if (j==26) return (data26[i,k])
else if (j==27) return (data27[i,k])
else if (j==28) return (data28[i,k])
else if (j==29) return (data29[i,k])
else if (j==30) return (data30[i,k])
else if (j==31) return (data31[i,k])
else if (j==32) return (data32[i,k])
else if (j==33) return (data33[i,k])
else if (j==34) return (data34[i,k])
else if (j==35) return (data35[i,k])
else if (j==36) return (data36[i,k])
else if (j==37) return (data37[i,k])
else if (j==38) return (data38[i,k])
else if (j==39) return (data39[i,k])
else if (j==40) return (data40[i,k])
else if (j==41) return (data41[i,k])
else if (j==42) return (data42[i,k])
else if (j==43) return (data43[i,k])
else if (j==44) return (data44[i,k])
else if (j==45) return (data45[i,k])
else if (j==46) return (data46[i,k])
else if (j==47) return (data47[i,k])
else if (j==48) return (data48[i,k])
else if (j==49) return (data49[i,k])
else if (j==50) return (data50[i,k])
else if (j==51) return (data51[i,k])
else if (j==52) return (data52[i,k])
else if (j==53) return (data53[i,k])
else if (j==54) return (data54[i,k])
else if (j==55) return (data55[i,k])
else if (j==56) return (data56[i,k])
else if (j==57) return (data57[i,k])
else if (j==58) return (data58[i,k])
else if (j==59) return (data59[i,k])
else if (j==60) return (data60[i,k])
}
list <- array(0,dim=c(720,60,4))
for(i in 1:720){
for (j in 1:60){
list[i,j,1] <- myfunc(j,i,6)
list[i,j,2] <- myfunc(j,i,7)
list[i,j,3] <- myfunc(j,i,8)
list[i,j,4] <- myfunc(j,i,9)
}
}
library("pdc")
clustering <- pdclust(list)
plot(clustering, labels= NULL, type="rectangle", timeseries.as.labels = T, p.values=T)
答案 0 :(得分：2)
我创建了一个没有数据文件的精简版代码，因此更容易讨论您的问题。在这里，我创建了60个时间序列，包含4个维度和720个时间点（就像你一样）。只有我从一个随机法线模拟一半的试验，而另一半从线性趋势模拟一个叠加的随机法线。因此，对于pdc，它们应该明显可分为两组。这是代码：
require("pdc")
# make this replicable by setting a random seed
set.seed(7823)
# 60 TS each with 4 dimensions and 720 timepoints
# half of them are random uniform other half are a mix of random uniform
# and linear increase
list <- array(0,dim=c(720,60,4))
for (i in 1:30) {
for (j in 1:4) {
list[,i,j] <- rnorm(n = 720)
list[,i+30,j] <- rnorm(n=720)+1:720
}
}
cols <- c(rep("red",30),rep("blue",30))
labels <- c(rep("normal",30),rep("normal+trend",30))
# run clustering and color original groups each in red and blue
clustering <- pdclust(list)
pdf("pdcplot.pdf")
plot(clustering, labels= labels, type="rectangle", cols=cols, cex=0.5)
dev.off()
我没有绘制标签的麻烦。我添加了一个＆＃34; cex = 0.5＆＃34;减少绘图中的字体大小。另外，我删除了＆＃34; timeseries.as.labels = T＆＃34;因为在指定标签时会覆盖它。这是我的情节的样子（带标签）：
Clustering of simulated data with labels
我只能在我指定的标签数量与时间序列数量不匹配时重现您报告的错误。您可能需要再次检查标签向量的大小（例如length(labels)==60）。
