boxatt: Barplots of univariate attribute dispersion within groups

In mkampert/rCOSA: Clustering Objects on Subsets of Attributes (COSA)

Description

This function plots the attribute weights over groups.

Usage

boxatt(
  data,
  imps,
  grps,
  main = "Consider a maintitle here",
  ylab = "Consider a label here",
  xlab = "Consider a label here",
  SCALE = TRUE,
  colors = palette(),
  ...
)

Arguments

data	data matrix with numeric attributes
imps	typically a vector with attribute indices ordered on their importance
grps	list for which each component contains the index numbers (row numbers in the data) of each group in an integer vector.
main	main title of the plot
ylab	label vertical axis
xlab	label horizontal axis
SCALE	logical TRUE/FALSE, whether to scale the data
colors	by default set to palette()
...	named arguments to be passed to the default method.

Value

values of attribute importances in requested order.

See Also

attimp

Examples

# boxatt(data = ApoE3, imps = attWild$att[1:100],
#  #     grps =  list(1:18, 19:38),
#  #     main = "Wildtype (red) vs Transgenic (blue)",
#  #     ylab = 'Scaled attribute values',
#  #     xlab = '100 most important attributes',
#  #     colors = c('red','white','blue'))

mkampert/rCOSA documentation built on Dec. 23, 2019, 8:21 p.m.