PSTr-class: Nested representation of a probabilistic suffix tree

In PST: Probabilistic Suffix Trees and Variable Length Markov Chains

Description

An object of class "PSTr" is a node of a probabilistic suffix tree (PST). The slot prob contains one or several probability distributions (if the PST is segmented) and the slot counts contains the empirical - possibly weighted - counts from which the probabilities are computed. The slot leaf indicates whether the node (segment) is a terminal node (segment). The 'flat' representation of a PST is an object of class "PSTf"), that is a list that contains one element for each level of the tree. Each element of the list is itself a list whose elements are nodes, that is objects of class PSTr. The 'nested' representation of a probabilistic suffix tree (PST) is a nested list whose elements are children nodes of class "PSTr". This representation is used for printing and plotting PST, in which case the flat representation of a PST, i.e., an object of class "PSTf" is turned into an object of class "PSTr" by using the as function.

Objects from the Class

Objects are created when calling the pstree function.

Slots

.Data:

Object of class "list". In the nested representation of a PST, the elements of the list are the children nodes. Otherwise the list is empty.

alphabet:

Object of class "character". Alphabet on which the sequences, and the PST are built. This slot is non-empty only for the root node of the nested representation of a PST.

labels:

Object of class "character" containing the long state labels. This slot is non-empty only for the root node of the nested representation of a PST.

cpal:

Object of class "character". Color palette used to represent each state of the alphabet. This slot is non-empty only for the root node of the nested representation of a PST.

index:

Object of class "matrix". When the PST is segmented, indicates the id of the segment corresponding to each group.

counts:

Object of class "matrix". The counts to which the probability distributions are computed.

n:

Object of class "matrix". The number of occurrences of the context in the learning sample, see cprob.

prob:

Object of class "matrix". The probability distributions computed from the counts.

path:

Object of class "character". The node label, i.e. the context which is the path from the node to the root node of the tree.

order:

Object of class "integer". The depth of the node in the tree, i.e., the order of the probability distribution(s) stored in the node.

leaf:

Object of class "matrix". Indicates whether the node (segment) is a terminal node (segment).

pruned:

Object of class "matrix". If the PST was pruned with the delete=FALSE option, indicates whether the node (segment) is actually pruned. See prune.

Extends

Class "list", from data part. Class "vector", by class "list", distance 2.

Methods

[[

signature(x = "PSTr"): extract sub-branches of a nested representation of a PST.

plot

signature(x = "PSTr", y = "ANY"): plot a PST, see plot,PSTr,ANY-method.

print

signature(x = "PSTr"): print a PST, see print,PSTr-method.

summary

signature(object = "PSTr"): see summary,PSTr-method.

Author(s)

Alexis Gabadinho

See Also

PSTf

Examples

showClass("PSTr")

PST documentation built on Nov. 25, 2020, 3 p.m.