Learn R Programming

⚠️There's a newer version (0.94.1) of this package.Take me there.

PST (version 0.81)

Probabilistic Suffix Trees

Description

This package provides functions to analyse state sequences with probabilistic suffix trees (PST), the construction that stores variable length Markov chains (VLMC). The PST library allows to learn VLMC models and includes many additional tools and features to analyse sequence data with these models: visualization tools, functions for model optimization, for sequence prediction and artificial sequences generation, context and pattern mining. The package is specifically adapted to the field of social sciences by allowing to learn VLMC models from sets of individual sequences possibly containing missing values and to account for case weights. The library also allows to fit segmented VLMC, where conditional transition probabilities are estimated and stored for each value of a covariate. This software results from research work executed within the framework of the Swiss National Centre of Competence in Research LIVES, which is financed by the Swiss National Science Foundation. The authors are grateful to the Swiss National Science Foundation for its financial support.

Copy Link

Version

Install

install.packages('PST')

Monthly Downloads

215

Version

0.81

License

GPL (>= 2)

Maintainer

Alexis Gabadinho

Last Published

December 10th, 2012

Functions in PST (0.81)

pqplot

Prediction quality plot
prune

Prune a probabilistic suffix tree
s1

Example sequence data set
cmine

Mining contexts
PSTr-class

Nested representation of a probabilistic suffix tree
impute

Impute missing values using a probabilistic suffix tree
ppplot

Plotting a branch of a probabilistic suffix tree
subtree

Extract a subtree from a segmented PST
pstree

Build a probabilistic suffix tree
summary-methods

Summary of variable length Markov chain model
tune

AIC, AICc or BIC based model selection
plot-PSTr

Plot a PST
cplot

Plot single nodes of a probabilistic suffix tree
pdist

Compute probabilistic divergence between two PST
PSTf-class

Flat representation of a probabilistic suffix tree
nodenames

Retrieve the node labels of a PST
generate

Generate sequences using a probabilistic suffix tree
print

Print method for objects of class PSTf and PSTr
logLik

Log-Likelihood of a variable length Markov chain model
predict

Compute the probability of categorical sequences using a probabilistic suffix tree
nobs

Extract the number of observations to which a VLMC model is fitted
query

Retrieve counts or next symbol probability distribution
SRH

Longitudinal data on self rated health
pmine

PST based pattern mining
cprob

Empirical conditional probability distributions of order L