clustra_rand: clustra_rand: Rand Index cluster evaluation

In clustra: Clustering Longitudinal Trajectories

clustra_rand: Rand Index cluster evaluation

Description

Performs trajectories runs for several k and several random start replicates within k. Returns a data frame with a Rand Index comparison between all pairs of clusterings. This data frame is typically input to rand_plot to produce a heat map with the Adjusted Rand Index results.

Usage

clustra_rand(
  data,
  k,
  starts = "random",
  mccores = 1,
  replicates = 10,
  maxdf = 30,
  conv = c(10, 0),
  save = FALSE,
  verbose = FALSE
)

Arguments

data	The data (see clustra description).
k	Vector of k values to try.
starts	See clustra.
mccores	Number of cores for replicate parallelism via mclapply.
replicates	Number of replicates for each k.
maxdf	Fitting parameters. See link{trajectories}.
conv	Fitting parameters. See link{trajectories}.
save	Logical. When TRUE, save all results as file results.Rdata.
verbose	Logical. When TRUE, information about each run of clustra (but not iterations within) is printed.

Value

See allpair_RandIndex.

clustra documentation built on Oct. 14, 2023, 9:15 a.m.