dendextend (version 0.14.2)

untangle_random_search: Untangle - random search

Description

Searches for two untangled dendrogram by randomlly shuflling them and each time checking if their entanglement was improved.

Usage

untangle_random_search(tree1, tree2, R = 100L, L = 1,
  leaves_matching_method = c("order", "labels"), ...)

Arguments

tree1

a tree object (of class dendrogram/hclust/phylo).

tree2

a tree object (of class dendrogram/hclust/phylo).

R

numeric (default is 100). The number of shuffles to perform.

L

the distance norm to use for measuring the distance between the two trees. It can be any positive number, often one will want to use 0, 1, 1.5, 2 (see 'details' for more). It is passed to entanglement.

leaves_matching_method

a character scalar passed to entanglement. It can be either "order" (default) or "labels". If using "labels", then we use the labels for matching the leaves order value. And if "order" then we use the o

...

not used

Value

• A list with two trees with the best entanglement that was found.

Details

Untangaling two trees is a hard combinatorical problem without a closed form solution. One way for doing it is to run through a random spectrom of options and look for the "best" two trees. This is what this function offers.

See Also

tanglegram, match_order_by_labels, entanglement.

Examples

hc1 <- hclust(dist(iris[,-5]), "com")
hc2 <- hclust(dist(iris[,-5]), "single")
dend1 <- as.dendrogram(hc1)
dend2 <- as.dendrogram(hc2)
tanglegram(dend1,dend2)

set.seed(65168)
dend12 <- untangle_random_search(dend1, dend2)
tanglegram(dend12[[1]],dend12[[2]])

entanglement(dend1,dend2, L = 2) # 0.8894
entanglement(dend12[[1]],dend12[[2]], L = 2) # 0.0998