binostics (version 0.1.2)

scagnostics: Calculate scagnostics for a scatterplot

Description

Scagnostics summarize potentially interesting patterns in 2d scatterplot

Usage

scagnostics(x, ...)
# S3 method for default
scagnostics(x, y, bins = 50, outlierRmv = TRUE, ...)
# S3 method for matrix
scagnostics(x, ...)
# S3 method for data.frame
scagnostics(x, ...)
scagnostics_2d(x, ...)

Arguments

x, y

object to calculate scagnostics on: a vector, a matrix or a data.frame

...

Extra arguments

bins

number of bins, default=50

outlierRmv

logical for trimming data, default=TRUE

Details

Current scagnostics are:

• Outlying

• Skewed

• Clumpy

• Sparse

• Striated

• Convex

• Skinny

• Stringy

• Monotonic

These are described in more detail in: Graph-Theoretic Scagnostics, Leland Wilkinson, Anushka Anand, Robert Grossman. http://papers.rgrossman.com/proc-094.pdf

You can call the function with two 1d vectors to get a single vector of scagnostics, or with a 2d structure (matrix or data frame) to get scagnostics for every combination of the variables.

Examples

# NOT RUN {
scagnostics(1:10, 1:10)
scagnostics(rnorm(100), rnorm(100))
scagnostics(mtcars)
scagnostics(as.matrix(mtcars))
# }