kmeansPlus: 'kmeansPlus'

In samrabi1/ada.classification: Classification Methods: K-means and Random Forests

Description

A tool to aid in the implementation of conventional k means clustering, kmeansPlus() provides the normal functionality of stats::kmeans() with some modest additions. In short, it allows the user to quickly plot results from kmeans(), as well as add cluster identifiers to the input dataframe as a new variable.

Usage

kmeansPlus(
  data,
  k,
  exclude = NULL,
  full.output = TRUE,
  plot = TRUE,
  x = NULL,
  y = NULL,
  iter.max = 10,
  nstart = 1,
  algorithm = c("Hartigan-Wong", "Lloyd", "Forgy", "MacQueen"),
  trace = FALSE
)

Arguments

data	A matrix or dataframe containing numeric data in tidy format. This is equivalent to the 'x' argument from kmeans().
k	Either the desired number of clusters, or a set of initial (distinct) cluster centers. This is equivalent to the 'centers' argument from kmeans().
exclude	A vector, either numeric or character, indicating either indices or colnames of variables in 'data' that the user wishes to exclude. The excluded variable will not be removed from the tibble printed in the final output (when full.output and plot are set to FALSE), but it will be excluded from all clustering and vizualisation procedures.
full.output	A logical vector indicating whether the output of kmeansPlus() should include the full output of kmeans().
plot	A logical vector indicating whether the output of kmeansPlus() should include a plot.
x	A string (character vector of length 1) containing the colname of a variable from 'data' to be plotted on the x axis (if plot = TRUE).
y	A string (character vector of length 1) containing the colname of a variable from 'data' to be plotted on the y axis (if plot = TRUE).
iter.max	This is equivalent to the 'iter.max' argument from kmeans(), and is set to the same default.
nstart	This is equivalent to the 'nstart' argument from kmeans(), and is set to the same default.
algorithm	This is equivalent to the 'algorithm' argument from kmeans(), and is set to the same default.
trace	This is equivalent to the 'trace' argument from kmeans(), and is set to the same default.

Examples

kmeansPlus(data = iris, k = 3, exclude = "Species", full.output = TRUE, plot = TRUE,
x = "Sepal.Length", y = "Sepal.Width")

samrabi1/ada.classification documentation built on May 23, 2020, 7:01 a.m.