vlmctree: Compute the tree structure of a "vlmc" object

In VLMC: Variable Length Markov Chains ('VLMC') Models

Description

Compute the tree representation of a "vlmc" object as R list.

Usage

vlmctree(x)

## S3 method for class 'vtree'
str(object, ...)
.vvec2tree(vv, k, chk.lev)

Arguments

x,object	typically the result of vlmc(..).
vv	integer vector encoding the fitted vlmc, typically x$vlmc.vec[-1].
k	integer, the alphabet size.
chk.lev	integer internally used for consistency checking.
...	further arguments passed to or from methods.

Details

.vvec2tree is the internal (recursive) function building up the tree.

str.vtree is a method for the generic str function and typically for the output of vlmctree(). For each node, it gives the “parenting level” in braces and the counts.

Value

A list of class "vtree" representing the tree structure recursively.

Each “node” of the tree is itself a list with components

level	length-2 integer giving the level in {0,1,...}, counted from the root (which is 0) and the parenting level, i.e the longest branch.
count	integer vector of length k where k is the number of “letters” in the alphabet.
total	equals to sum(* $ count).
child	a list (of length k) of child nodes or NULL (i.e. not there).

Author(s)

Martin Maechler

See Also

vlmc.

Examples

data(presidents)
dpres <- cut(presidents, c(0,45,70, 100)) # three values + NA
table(dpres <- factor(dpres, exclude = NULL)) # NA as 4th level

(vlmc.prc1 <- vlmc(dpres, cut = 1, debug = TRUE))
str(vv.prc1 <- vlmctree(vlmc.prc1))

VLMC documentation built on May 1, 2019, 11:32 p.m.