sdists.center.align: Align Sequences to a Center

In cba: Clustering for Business Analytics

Align Sequences to a Center

Description

Find a global alignment of a collection of sequences using the center-star-tree heuristic.

Usage

sdists.center.align(x, center, method = "ow", weight = c(1, 1, 0, 2),
                    exclude = c(NA, NaN, Inf, -Inf),
                    break.ties = TRUE, transitive = FALSE,
                    to.data.frame = FALSE)

Arguments

x	a list (of vectors) or a vector of character.
center	a vector
method	argument to sdists.
weight	argument to sdists.
exclude	arguments to sdists.
break.ties	a logical specifying whether random tie-breaking should be performed. Otherwise the first alignment is used.
transitive	a logical specifying whether the sequences in x should be aligned with each other, too.
to.data.frame	a logical specifying whether the result should be converted to data.frame.

Details

Each component of x is aligned with center in turn such that the latter is aligned with all sequences processed so far.

If center is missing isdists.center is used to compute an initial center.

Value

Either a list of sequences with attributes center and ties, or a data.frame with the sequences in the columns.

Note

The global alignment may depend on the order of x.

Author(s)

Christian Buchta

References

D. Gusfield (1997). Algorithms on Strings, Trees, and Sequences. Cambridge University Press, Chapter XX.

See Also

sdists for computation of distances, sdists.center for computation of centroids.

Examples

## continue example
x <- c("ABCD", "AD", "BCD", "ACF", "CDF", "BC")
sdists.center.align(x)
sdists.center.align(x, transitive = TRUE, to.data.frame = TRUE)

cba documentation built on Sept. 11, 2024, 9:32 p.m.