ellipseplot {elliplot}

Draw Ellipse Summary Plot

Description

Correlation chart of two set (x and y) of data. Using Quantiles. Visualize the effect of factor.

Usage

ellipseplot(x, ...)

## Default S3 method:
ellipseplot(x, y=NULL, SUMMARY=ninenum, SHEER=sheer.color,
            plot=TRUE, verbose=FALSE, ...)

Arguments

x

An x-axis data, such as data frame of factors (1st column) and observations (2nd column). A vector, a matrix or a list is also acceptable. If a vector is given, a single ellipse without factors are drawn. A matrix is as same format as the data frame. A list is formed by factors with observatoin vectors as each item.

y

A y-axis data, such as data frame of factors (1st column) and observations (2nd column). Same types as the x-axis data are also acceptable. It can be a NULL (default), to draw a single axis chart.

SUMMARY

A function generating quantile summaries to write contours of ellipses. The default is ninenum to use nine number summary. The function must return an odd length numerical vector, because a center, such as median, is required.

SHEER

A function adjusting color levels of ellipses. The default is sheer.color function shown below.

sheer.color <- function(col, level) {
  sheer <- level^2 * 0.5
  adjustcolor(col, alpha.f=sheer)
}
    

plot

If FALSE is given, it disable to plot and print a summary. The default is TRUE.

verbose

If TRUE is given, it print verbose debugging information. The default is FALSE.

...

Plot parameters are acceptable.

Details

This function is designed to visualize a correlation between 2 sets of independent observation with common factors. Such as, the plant height v.s. the soil pH by location.

Value

A summary list is explicitly printed when plot=FALSE is given, and is invisibly returned when plot=TRUE.

Author(s)

Shinichiro Tomizono

References

Ellipse Summary Plot https://tomizonor.wordpress.com/2013/04/29/ellipse-plot/

See Also

ninenum, seventeennum, midpoints.

Examples

# iris data: Sepal.Length v.s. Sepal.Width by Species
ellipseplot(iris[c(5,1)], iris[c(5,2)])

# PlantGrowth data: weight by group : single axis
# five number summaries are used.  
# similar to boxplot(weight~group,PlantGrowth)
ellipseplot(PlantGrowth[2:1], SUMMARY=fivenum)

# iris data: Sepal.Length v.s. Sepal.Width without factor
ellipseplot(iris[,1], iris[,2], xlab='Sepal.Length', ylab='Sepal.Width')

# list example
ellipseplot(list(untreated=rnorm(30,3,1), treated=rnorm(30,5,2)), 
            list(untreated=rnorm(20,6,3), treated=rnorm(20,4,2)))

# using cutomized sheer function
my.sheer.color <- function(col, level) adjustcolor(rainbow(100)[runif(1,1,100)], alpha.f=0.4)
ellipseplot(iris[c(5,1)], iris[c(5,2)], SHEER=my.sheer.color)