get_semirandom function

Generate initial semi-random start

Generate an initial semi-random start for the (low dimensional) Additive Profile Clustering algorithm (see adproclus and adproclus_low_dim).

get_semirandom(data, nclusters, seed = NULL)

Arguments

• data: Object-by-variable data matrix of class matrix or data.frame.
• nclusters: Number of clusters to be used. Must be a positive integer.
• seed: Integer. Seed for the random number generator. Default: NULL

Returns

get_semirandom returns a list with the following components:

• type: A character string denoting the type of start ('Semi-random Start')
• A: An initial Membership matrix

Details

An initial cluster membership matrix $A$ is generated by finding the best $A$ conditional on an initial profile matrix $P$ generated by drawing k randomly chosen, distinct, rows from data (for details, see Depril et al., 2012).

Warning: This function does not obtain an ADPRCOLUS model. To perform aditive profile clustering, see adproclus.

Examples

# Obtain data from data set "Stackloss" and generate start allocation
start_allocation <- get_semirandom(stackloss, 3)$A

References

Wilderjans, T. F., Ceulemans, E., Van Mechelen, I., & Depril, D. (2010). ADPROCLUS: a graphical user interface for fitting additive profile clustering models to object by variable data matrices. Behavior Research Methods, 43(1), 56-65.

Depril, D., Van Mechelen, I., & Mirkin, B. (2008). Algorithms for additive clustering of rectangular data tables. Computational Statistics and Data Analysis, 52, 4923-4938.

#' Depril, D., Van Mechelen, I., & Wilderjans, T. F. (2012). Lowdimensional additive overlapping clustering. Journal of classification, 29, 297-320.

See Also

• adproclus, adproclus_low_dim: for details about membership and profile matrices
• get_random: for generating random starts
• get_rational: for generating rational starts