导出树状图作为表R

Question

我想从R中导出hclust-dendrogram到数据表中，以便随后将其导入到另一个（“自制”）软件中。 str(unclass(fit))为树形图提供了一个文本概述，但是我正在寻找的实际上是一个数字表。我查看了Bioconductor ctc软件包，但它生成的输出看起来有些隐晦。我想有类似于这张表的东西：http://stn.spotfire.com/spotfire_client_help/heat/heat_importing_exporting_dendrograms.htm 有没有办法从R中的hclust对象中获取它？

Answer 1

有包，做完全相反的你想要什么 - Labeltodendro ;-)

但严重的是，你就不能手动提取hclust对象中的元素（如$merge，$height，$order），并创建自定义表中提取的元素？

Answer 2

如果任何人也对树状图导出感兴趣，这是我的解决方案。最有可能的是，它不是最好的，因为我最近才开始使用R，但至少它工作正常。因此，如何改进代码的建议值得欢迎。

所以，如果hr是我hclust对象，df是我的数据，第一列，其中包含从0开始一个简单的索引和行的名称是集群项目的名称：

# Retrieve the leaf order (row name and its position within the leaves) 
leaf.order <- matrix(data=NA, ncol=2, nrow=nrow(df), 
       dimnames=list(c(), c("row.num", "row.name"))) 
leaf.order[,2] <- hr$labels[hr$order] 
for (i in 1:nrow(leaf.order)) { 
    leaf.order[which(leaf.order[,2] %in% rownames(df[i,])),1] <- df[i,1] 
} 
leaf.order <- as.data.frame(leaf.order) 

hr.merge <- hr$merge 
n <- max(df[,1]) 

# Re-index all clustered leaves and nodes. First, all leaves are indexed starting from 0. 
# Next, all nodes are indexed starting from max. index leave + 1. 
for (i in 1:length(hr.merge)) { 
    if (hr.merge[i]<0) {hr.merge[i] <- abs(hr.merge[i])-1} 
    else { hr.merge[i] <- (hr.merge[i]+n) } 
} 
node.id <- c(0:length(hr.merge)) 

# Generate dendrogram matrix with node index in the first column. 
dend <- matrix(data=NA, nrow=length(node.id), ncol=6, 
      dimnames=list(c(0:(length(node.id)-1)), 
       c("node.id", "parent.id", "pruning.level", 
       "height", "leaf.order", "row.name"))) 
dend[,1] <- c(0:((2*nrow(df))-2)) # Insert a leaf/node index 

# Calculate parent ID for each leaf/node: 
# 1) For each leaf/node index, find the corresponding row number within the merge-table. 
# 2) Add the maximum leaf index to the row number as indexing the nodes starts after indexing all the leaves. 
for (i in 1:(nrow(dend)-1)) { 
    dend[i,2] <- row(hr.merge)[which(hr.merge %in% dend[i,1])]+n 
} 

# Generate table with indexing of all leaves (1st column) and inserting the corresponding row names into the 3rd column. 
hr.order <- matrix(data=NA, 
      nrow=length(hr$labels), ncol=3, 
      dimnames=list(c(), c("order.number", "leaf.id", "row.name"))) 
hr.order[,1] <- c(0:(nrow(hr.order)-1)) 
hr.order[,3] <- t(hr$labels[hr$order]) 
hr.order <- data.frame(hr.order) 
hr.order[,1] <- as.numeric(hr.order[,1]) 

# Assign the row name to each leaf. 
dend <- as.data.frame(dend) 
for (i in 1:nrow(df)) { 
     dend[which(dend[,1] %in% df[i,1]),6] <- rownames(df[i,]) 
} 

# Assign the position on the dendrogram (from left to right) to each leaf. 
for (i in 1:nrow(hr.order)) { 
     dend[which(dend[,6] %in% hr.order[i,3]),5] <- hr.order[i,1]-1 
} 

# Insert height for each node. 
dend[c((n+2):nrow(dend)),4] <- hr$height 

# All leaves get the highest possible pruning level 
dend[which(dend[,1] <= n),3] <- nrow(hr.merge) 

# The nodes get a decreasing index starting from the pruning level of the 
# leaves minus 1 and up to 0 

for (i in (n+2):nrow(dend)) { 
    if ((dend[i,4] != dend[(i-1),4]) || is.na(dend[(i-1),4])){ 
     dend[i,3] <- dend[(i-1),3]-1} 
     else { dend[i,3] <- dend[(i-1),3] } 
} 
dend[,3] <- dend[,3]-min(dend[,3]) 

dend <- dend[order(-node.id),] 

# Write results table. 
write.table(dend, file="path", sep=";", row.names=F)