Add a column with named cluster assignments to a data frame — add_named

This function is tailored for three clusters. After checking the results of the clustering procedure with summarise_clustering() and a graphical examination, we can choose names for the three clusters manually and input them into this function to get a meaningful variable to analyse.

Usage

add_named_clusters(
  df,
  clustering,
  method = "CSPA",
  names = c("cluster_1", "cluster_2", "cluster_3"),
  levels = names,
  contrasts = paste0("_", levels),
  base = 1,
  ...
)

Arguments

df: A data frame with the OSIVQ scores, typically obtained from get_clean_data().
clustering: A clustering object obtained from cluster_osivq().
method: A character string specifying the consensus clustering method to use. Must be "kmodes", "majority", or "CSPA". Default is "CSPA".
names: A character vector of names for the clusters. Default is c("cluster_1", "cluster_2", "cluster_3").
levels: A character vector of levels for the factor. Default is the same as names.
contrasts: A character vector of contrasts for the factor levels.
base: An integer indicating the base level for the contrasts. Default is 1, which corresponds to the first cluster in names.
...: Additional arguments passed to add_factor_contrasts().

Value

A data frame with an additional column cluster that contains the named cluster assignments.